River flow prediction is a pivotal task in the field of water resource management during the era of rapid climate change. The highly dynamic and evolving nature of the climatic variables e.g., precipitation has a significant impact on the temporal distribution of the river discharge in recent days making the discharge forecasting even more complicated for diversified water-related issues e.g., flood prediction and irrigation planning. To predict the discharge, various physics-based numerical models are used using numerous hydrologic parameters. Extensive lab-based investigation and calibration are required to reduce the uncertainty involved in those parameters. However, in the age of data-driven predictions, several deep learning algorithms showed satisfactory performance in dealing with sequential data. In this research, Long Short-term Memory (LSTM) neural network regression model is trained using over 80 years of daily data to forecast the discharge time series up to 3 days ahead of time. The performance of the model is found satisfactory through the comparison of the predicted data with the observed data, visualization of the distribution of the errors and Root Mean Squared Error (RMSE) value of 0.09. Higher performance is achieved through the increase in the number of epochs and hyper parameter tuning. This model can be transferred to other locations with proper feature engineering and optimization to perform univariate predictive analysis and potentially be used to perform real-time river discharge prediction.

Modeling brain dynamics to better understand and control complex behaviors underlying various cognitive brain functions are of interests to engineers, mathematicians, and physicists from the last several decades. With a motivation of developing computationally efficient models of brain dynamics to use in designing control-theoretic neurostimulation strategies, we have developed a novel data-driven approach in a long short-term memory (LSTM) neural network architecture to predict the temporal dynamics of complex systems over an extended long time-horizon in future. In contrast to recent LSTM-based dynamical modeling approaches that make use of multi-layer perceptrons or linear combination layers as output layers, our architecture uses a single fully connected output layer and reversed-order sequence-to-sequence mapping to improve short time-horizon prediction accuracy and to make multi-timestep predictions of dynamical behaviors. We demonstrate the efficacy of our approach in reconstructing the regular spiking to bursting dynamics exhibited by an experimentally-validated 9-dimensional Hodgkin-Huxley model of hippocampal CA1 pyramidal neurons. Through simulations, we show that our LSTM neural network can predict the multi-time scale temporal dynamics underlying various spiking patterns with reasonable accuracy. Moreover, our results show that the predictions improve with increasing predictive time-horizon in the multi-timestep deep LSTM neural network.

Measure While Drilling (MWD) refers to a comprehensive array of sensors employed to gather performance data throughout the process of rock drilling in mining blast holes. Multiple MWD metrics are collected by researchers depending on the setup of MWD sensors. Trends in MWD data can be correlated with pre-excavation subsurface conditions. The low-cost, extensive MWD data acquisition resolution of blast holes compared to expensive and sparsely collected exploration drill holes make the former one a desirable method for characterizing pre-excavation subsurface conditions. Nevertheless, the application of MWD technology in open pit mining is constrained by a substantial amount of data that requiring manual analysis within a short time. To address this limitation, computerized data acquisition and interpretation of MWD variables has been used to broadly determine open pit mining lithological boundaries. The results of artificial intelligence algorithms, such as Neural Networks, and Gaussian Processes, to recognize subsurface conditions, such as rock type, from MWD data have consistently returned >90% prediction accuracy. However, methods of evaluating the importance of each MWD feature, such as Principal Component Analysis, has not been optimally used. This review focuses on the progression of intelligent MWD analysis using Machine Learning methods in open-pit mining, to determine the geotechnical, geological, and geochemical subsurface characteristics before open-pit mining excavation.

Cities are undergoing huge shifts in technology and operations in recent days, and `data science' is driving the change in the current age of the Fourth Industrial Revolution (Industry 4.0 or 4IR). Extracting insights or actionable knowledge from city data and building a corresponding data-driven model is the key to making a city system automated and intelligent. Data science is typically the study and analysis of actual happenings with historical data using a variety of scientific methodology, machine learning techniques, processes, and systems. In this paper, we concentrate on and explore ``Smart City Data Science", where city data collected from various sources like sensors and Internet-connected devices, is being mined for insights and hidden correlations to enhance decision-making processes and deliver better and more intelligent services to citizens. To achieve this goal, various machine learning analytical modeling can be employed to provide deeper knowledge about city data, which makes the computing process more actionable and intelligent in various real-world services of today's cities. Finally, we identify and highlight ten open research issues for future development and research in the context of data-driven smart cities. Overall, we aim to provide an insight into smart city data science conceptualization on a broad scale, which can be used as a reference guide for the researchers, professionals, as well as policy-makers of a country, particularly, from the technological point of view.

The nature of contemporary Spatial Data Infrastructures lies in the provision of geospatial information in an on-demand fashion. Though recent applications identified the need to react to real-time information in a time-critical way. In particular, research efforts in the field of geospatial Internet of Things have identified substantial gaps in this context, ranging from a lack of standardization for event-based architectures to the meaningful handling of real-time information as ''events''. This manuscript presents work in the field of Event-driven Spatial Data Infrastructures with a particular focus on sensor networks and the devices capturing in-situ measurements. The current landscape of Spatial Data Infrastructures is outlined and used as the basis for identifying existing gaps that retain certain geospatial applications from using real-time information. We present a selection of approaches - developed in different research projects - to overcome these gaps. Being designed for specific application domains, these approaches share commonalities as well as orthogonal solutions and can build the foundation of an overall Event-driven Spatial Data Infrastructure.

The Genji firefly is a key symbol of the conservation and management of rural environments. The species lives underwater as larvae, in the soil when they pupate, and emerges on the ground as adults. Because of the large differences in habitat conditions between larvae and adults, the habitat requirements of the Genji firefly must be clarified over a wide range, from the instream to the surrounding riparian environment. In this study, we built a habitat suitability model for the Genji firefly by relating local landscape features to the number of individuals surveyed in a small river in an agricultural watershed. For habitat suitability modelling, tree-based machine learning methods, namely Random Forests (RF) and classification and regression trees (CART), are used to model species distributions and extract quantitative information on their ecological characteristics. Because the model performance on the test dataset was poor, we removed noisy absences using model outputs from the RF computation using the entire dataset. As a result, we observed improved model performance, in which there seems to be an optimal level for removing noisy absences. Variable importance and partial dependence plots were then used to visualize the relationship between the local landscape features and habitat suitability of the adult firefly. Detailed information on landscape features extracted using RF and CART is useful for a deeper understanding of the ecology of the Genji fireflies.

This paper argues that popular misrepresentation of the nature of AI has important consequences concerning how it should be regulated. Viewing AI as something that exists in itself, rather than as a set of cognitive technologies whose characteristics – physical, cognitive, and systemic – are quite different from ours (and at times from each other) leads to inefficient approaches to regulation. It limits our ability to anticipate the consequences of its foreseeable developments and social diffusion. It undermines attempts to protect ourselves from the social and political dangers it presents. After a short introduction, section 2 retraces rapidly the history of the idea that intelligence is essentially a quality, one that AI shares with human intelligence and that this resemblance trumps the differences that exist between artificial and natural cognitive systems. Section 3 reviews two approaches to the dangers of AI that reflect the illusion that AI exists in itself. Section 4 turns to the proper understanding of regulations and what is their main goal and purpose. Section 5 analyses three central characteristics of artificial cognitive systems which section six compares with corresponding characteristics of natural cognitive systems. Finally, section 7 draws some conclusions regarding how we should regulate artificial intelligence.

Performing predictive maintenance (PdM) is challenging for many reasons. Dealing with large datasets which may not contain run-to-failure data (R2F) complicates PdM even more. When no R2F data are available, identifying condition indicators (CIs), estimating the health index (HI), and thereafter, calculating a degradation model for predicting the remaining useful lifetime (RUL) are merely impossible using supervised learning. In this paper, a 3 dof delta robot used for pick and place task is studied. In the proposed method, autoencoders (AEs) are used to predict when maintenance is required based on the signal sequence distribution and anomaly detection, which is vital when no R2F data is available. Due to the sequential nature of the data, non-linearity of the system, and correlations between parameter time series, convolutional layers are used for feature extraction. Thereafter, a sigmoid function is used to predict the probability of having an anomaly given CIs acquired from AEs. This function can be manually tuned given the sensitivity of the system or optimized by solving a minimax problem. Moreover, the proposed architecture can be used for fault localization for the specified system. Additionally, the proposed method is capable of calculating RUL using Gaussian process (GP), as a degradation model, given HI values as its input.

The segmentation and de-noising are basic operations, required in every signal processing and classification system. The classical segmentation and de-noising approaches are time-invariant. Consequently, it results in the post processing of an unnecessary information and causes an increase in the system processing activity and power consumption. In this context, an efficient event-driven segmentation and de-noising technique is proposed. It is founded on the principles of level crossing and activity selection. Therefore, it can adapt its sampling frequency, segmentation window length and position along with the filter order by analyzing the input signal local characteristics. As a result, the computational complexity and the power consumption of the proposed system is reduced compared to the counter ones. The suggested system performance is compared with the classical one. It is done for the case of a multi-channel Electroencephalogram (EEG) signals. Results show a noticeable compression gain with an effective adaptation of the de-noising filters order. It aptitudes a significant computational gain, transmission data rate reduction and power consumption reduction of the proposed technique, compared to the counter ones. It shows that the proposed solution is an attractive candidate to embed in the new generation EEG wearables.

The importance of antibodies in health care and the biotechnology research and development demands not only knowledge of their experimental structures at high resolution, but also practical implementation of this knowledge for both effective and efficient design and production of antibody for its use in both medical and research applications. While the experimental wet-lab approach is usually costly, laborious and time-consuming, computational (dry-lab) approaches, in spite of their intrinsic limitations in comparison with its experimental (wet-lab) counterpart, provide a cheaper and faster alternative option. For the first time, this article reports a comprehensive set of structural electrostatic features extracted from experimentally determined antigen-antibody-related structures, including especially those structural electrostatic features at the interfaces of all experimentally determined antigen-antibody complex structures as of February 29, 2020, to facilitate effective and efficient machine learning-based computational antibody design using currently available experimental structures inside Protein Data Bank.

In this paper, we address the following research question: Is feasibility to use an artificial intelligence system to predict the risk of student failure in a course based solely on their performance in prerequisite courses? Adopting a machine learning-based quantitative approach, we implement Course Prophet, the prototype of a predictive system that maps the input variables representing student performance to the target variable, i.e., the risk of course failure. We evaluate multiple machine learning methods and find that the Gaussian process with Matern kernel outperforms other methods, achieving the highest accuracy and a favorable trade-off between precision and recall. We conduct this research in the context of the students pursuing a Bachelor’s degree in Systems Engineering at the University of Córdoba, Colombia. In this context, we focus on predicting the risk of failing the Numerical Methods course. In conclusion, the main contribution of this research is the development of Course Prophet, providing an efficient and accurate tool for predicting student failure in the Numerical Methods course based on their academic history in prerequisite courses.

The variety of risks due to climate change with a potential impact on Cultural Heritage CH requires a multidisciplinary approach and a preliminary overview of the existing methods for risk analysis and assessment in different fields. Thus, the starting point of the research conducted by the Sapienza PNRR working group consists in a systematic literature review of risk assessment approaches, methods and indicators. As a first outcome, the research has designed a multidisciplinary comprehensive framework consisting of the definition of risk categorization, the framework represented by a measurable index and the main target, according to the classification of Cultural Heritage based on the harmonization of European vocabularies definitions and protocols. The risk assessment framework sets the methodological core of a future multi criteria matrix and digital platform for decision focused on the historic built environment and it is functional to the definition of specific operational guidelines connected to each risk for elaborating descriptive/predictive Architectural Heritage’s transformation scenarios to support the development of mitigation and adaptation strategies.

This paper proposes an optimal trading algorithm based on a novel application of the conventional Control Engineering (CE). We consider a fundamental CE concept, namely, the feedback control and apply it to the Algorithmic Trading (AT). The concrete feedback control strategy is designed in a form of the celebrated Proportional-Integral-Derivative (PID) model. The highly fluctuating nature of the modern financial markets has led to the adoption of a model-free realisation of the generic PID framework. The control theoretical methodology we propose is combined with the advanced statistics for the historical market data. We obtain a specific log-normal probability distribution function (pdf) associated with the specific quantities associated with the available stock data. The empirical log-normal pdf mentioned above makes it possible the necessary PID gains optimization. For this aim, we apply the data-driven optimization approaches and consider the corresponding Monte Carlo solution procedure. The optimized PID trading algorithm we propose is also studied in the Fourier analysis framework. This equivalent frequency domain representation involves a new concept in the financial engineering, namely, the "stock market energy" concept. For the evaluation, we implement the proposed PID optimal trading algorithm and develop a Python based prototype software. We finally apply the corresponding prototype software to a dataset from the Binance BTC / USDT stock market. The experimental result illustrates the implementability of the proposed optimal PID trading scheme and also shows the effectiveness of the proposed CE methods in the modern AT.

: Cybersecurity has become a critical area in the digital field in recent years. The expansion of networks has revolutionised the way network structures are organised and managed. However, with increased connectivity and the growing complexity of modern networks, the threat of cyber-attacks has become more intense. As technology continues to advance, it brings both opportunities and challenges. One of the major challenges is the need to secure networks and sensitive data from various malicious activities. Traditional networks have evolved to include Software Defined Network (SDN), which offers a more flexible and programmable framework. Researchers should focus on detecting attacks in SDN because SDN networks are becoming more popular and attractive targets for clients due to their programmability and dynamic nature. The centralised controller, known as the backbone of an SDN, becomes a single point of failure and a potential target for attackers if not properly secured. Researchers need to emphasise the detection of attacks in SDN in order to mitigate these risks. By understanding the potential vulnerabilities and attack methods specific to SDN, researchers can develop effective detection approaches and propose countermeasures. This methodology helps protect the network from potential threats and minimises the impact of successful attacks. Therefore, this survey paper provides a review of Intrusion Detection Systems (IDSs) in Software-Defined Networks (SDN) to provide a thorough understanding of SDN security issues.

The combination of artificial intelligence algorithms and numerical methods has recently become popular in the prediction of macroscopic and microscopic hydrodynamics parameters of bubble column reactors. The multi inputs and outputs machine learning can cover small phase interactions or large fluid behavior in industrial domains. This numerical combination can develop the smart multiphase bubble column reactor with the ability of low-cost computational time. It can also decrease case studies for the optimization process when big data is appropriately used during learning. There are still many model parameters that need to be optimized for a very accurate artificial algorithm, including data processing and initialization, the combination of inputs and outputs, number of inputs and model tuning parameters. For this study, we aim to train four inputs big data during learning process by an adaptive neuro-fuzzy inference system or adaptive-network-based fuzzy inference system (ANFIS) method, and we consider the superficial gas velocity as one of the input variables, while for the first time, one of the computational fluid dynamics (CFD) outputs named gas velocity is used as an output of the artificial algorithm. The results show that the increasing number of input variables improves the intelligence of the ANFIS method up to , and the number of rules during learning process has a significant effect on the accuracy of this type of modeling. The results also show that propper selection of model parameters results in more accuracy in prediction of the flow characteristics in the column structure.

Scanning underwater areas, using magnetometers, in search of unexploded ordnance is a difficult challenge, where machine learning methods can find a significant application. However, this requires the creation of a set enabling the training of prediction models. Such a task is difficult and costly due to the limited availability of relevant data. To meet this challenge in the article, we propose the use of numerical modeling to solve this task. The conducted experiments allow us to conclude that it is possible to obtain high compliance of the numerical model with the results of physical tests. In addition, the paper discusses the methodology of simplifying the computational model, allowing for almost three times reduction of the calculation time. In addition, in the work we present the methodology of creating an appropriate data set, enabling the generation of any number of training samples.

Deep Neutral Networks (DNNs) were initially proposed towards the midst of the 20th century, motivated by the neural structure and mechanism of the human brain. Thanks to major ad-vancements in computational resources, during the past decade DNN-based systems have demonstrated unprecedented performance in terms of accuracy and speed. However, recent work has shown that such models may not be sufficiently robust during the inference process. Furthermore, due to the data-driven learning nature of DNNs, designing interpretable and gen-eralizable networks is a major challenge, especially in critical applications, such as medical Computer Aided Diagnostics (CAD) and other medical imaging tasks, including classification, regression and reconstruction. Within this context, a line of physics-driven approaches for deep learning has recently emerged, aimed at improving the stability and generalization capacity of DNNs for medical imaging applications. In this paper, we review recent work focused on phys-ics-driven or prior-information learning for a variety of imaging modalities and medical applica-tions. We discuss how the inclusion of domain-related knowledge into the learning process and networks’ design supports their stability and generalization capability. In addition, we highlight current and future challenges within this scope.

Dyadic data which is also called co-occurrence data (COD) contains co-occurrences of objects. Searching for statistical models to represent dyadic data is necessary. Fortunately, finite mixture model is a solid statistical model to learn and make inference on dyadic data because mixture model is built smoothly and reliably by expectation maximization (EM) algorithm which is suitable to inherent spareness of dyadic data. This research summarizes mixture models for dyadic data. When each co-occurrence in dyadic data is associated with a value, there are many unaccomplished values because a lot of co-occurrences are inexistent. In this research, these unaccomplished values are estimated as mean (expectation) of random variable given partial probabilistic distributions inside dyadic mixture model.

The work presented in this paper makes multiple scientific contributions related to the investigation of the global fear associated with COVID-19 by performing a comprehensive analysis of a dataset comprising survey responses of participants from 40 countries. First, the results of subjectivity analysis of responses where participants indicated their biggest concern related to COVID-19 showed that the average subjectivity in responses by the age group of 41-50 decreased from April 2020 to June 2020, the average subjectivity in responses by the age group of 71-80 drastically increased from May 2020, and the age group of 11-20 indicated the least level of subjectivity in their responses between June 2020 to August 2020. Second, subjectivity analysis also revealed the percentage of highly opinionated, neutral opinionated, and least opinionated responses per age-group where the analyzed age groups were 11-20, 21-30, 31-40, 41-50, 51-60, 61-70, 71-80, and 81-90. For instance, the percentage of highly opinionated, neutral opinionated, and least opinionated responses by the age group of 11-20 were 17.92%, 16.24%, and 65.84%, respectively. Third, data analysis of responses from different age groups showed that the highest percentage of responses indicating that they were very worried about COVID-19 came from individuals in the age group of 21-30. Fourth, data analysis of the survey responses also revealed that in the context of taking precautions to prevent contracting COVID-19, the percentage of individuals in the age group of 31-40 taking precautions was higher as compared to the percentages of individuals from the age groups of 41-50, 51-60, 61-70, 71-80, and 81-90. Finally, a deep learning model was developed to detect if the survey respondents were seeing or planning to see a psychologist or psychiatrist for any mental health issues related to COVID-19. The deep learning model used the responses to multiple questions in the context of fear, preparedness, and response related to COVID-19 from the dataset and achieved an overall performance accuracy of 91.62% after 500 epochs.

Responding to changing value creation processes in the sheet metal working sec-tor, where the complexity and interchangeability of products challenge traditional dif-ferentiation strategies, this empirical analysis explores integrating service-oriented and data-driven business models as new paths to ensure competitiveness, especially for small and medium-sized enterprises (SMEs). This study aims to capture the current state and challenges associated with the implementation of these business models in this sector. The research was conducted through semi-structured interviews with SMEs in the industry. The findings indicate that service-oriented and data-driven business models are not yet widely adopted and that manufacturing companies re-quire support in their implementation. Fields of action were identified for the industry. These are "Creating awareness and understanding", "Recognizing added value", "In-creasing company maturity" and "Understanding the change process". Cooperation between science and industry is essential in tackling these fields of action to ensure the successful integration of such business models in manufacturing companies. This pa-per identifies challenges in the fields of action that companies must address through a structured approach promoting awareness, recognizing value, improving organiza-tional maturity, and understanding the change process to successfully implement ser-vice-oriented and data-driven business models.

Eutrophication is a major environmental issue with many negative consequences, such as hypoxia and harmful cyanotoxins production. Monitoring coastal eutrophication is a crucial, especially for island countries like the Republic of Cyprus, which are economically dependent on the touristic sector. Additionally, the open-sea aquaculture industry in Cyprus has been exhibiting an increase in the last decades and environmental monitoring to identify possible signs of eutrophication is mandatory according to the legislation. Therefore, in this modelling study, two different types of Artificial Neural Networks (ANNs) are developed based on in situ-data collected from stations located in the coastal waters of Cyprus. Theses ANNs aim to model the eutrophication phenomenon based on two different data-driven modelling procedures. Firstly, the self-organizing map (SOM) ANN examines several water quality parameters (specifically water temperature, salinity, nitrogen species, ortho-phosphates, dissolved oxygen and electrical conductivity) interactions with the Chlorophyll-a parameter. The SOM model enables us to visualize the monitored parameters relationships and to comprehend complex biological mechanisms related to Chlorophyll-a production. A second feed-forward ANN model is also developed for predicting the Chlorophyll-a levels. Based on this ANN model, several scenarios associated to the eutrophication-related water quality parameters can be extracted. The combination of these two ANNs models is considered a holistic modelling approximation for the identification of eutrophication scenarios, since it enables not only the prediction of the Chlorophyll-a parameter levels, but also the “capturing” of hidden biological mechanisms associated with algal production.

The fault diagnosis of safety critical systems such as wind turbine installations includes extremely challenging aspects that motivate the research issues considered in this paper. In fact, the prompt detection and the reliable diagnosis of faults in their earlier occurrence represent the key point especially for offshore installations. For these plants, operation and maintenance procedures in harsh environments would inevitably increase the cost of the energy production. Therefore, this work investigates fault diagnosis solutions that are considered in a viable way and used as advanced techniques for condition monitoring of dynamic processes. To this end, the work proposes the design of fault diagnosis strategies that exploit the estimation of the fault by means of data--driven approaches. This solution leads to the development of effective methods allowing the management of partially unknown information of the system dynamics, while coping with measurement errors, the model--reality mismatch and other disturbance effects. In mode detail, the proposed data--driven methodologies exploit fuzzy systems and neural networks in order to estimate the nonlinear dynamic relations between the input and output measurements of the considered process and the faults. To this end, the fuzzy and neural network structures are integrated with auto--regressive with exogenous input descriptions, thus making them able to approximate unknown nonlinear dynamic functions with arbitrary degree of accuracy. Once these models are estimated from the input and output data measurement acquired from the considered dynamic process, the capabilities of their fault diagnosis capabilities are validated by using a high--fidelity benchmark that simulates the healthy and the faulty behaviour of a wind turbine system. Moreover, at this stage the benchmark is also useful to analyse the robustness and the reliability characteristics of the developed tools in the presence of model--reality mismatch and modelling error effects featured by the wind turbine simulator. On the other hand, a hardware--in--the--loop tool is finally implemented for testing and comparing the performance of the developed fault diagnosis strategies in a more realistic environment and with respect to different fault diagnosis approaches.

Mathematical modelling of bioprocesses has a long and notable history, with eminent contributions from fields including microbiology, ecology, biophysics, chemistry, statistics, control theory and mathematical theory. This richness of ideas and breadth of concepts provide great motivation for inquisitive engineers and intrepid scientists to try their hand at modelling, and this collaboration of disciplines has also delivered significant milestones in the quality and application of models for both theoretical and practical interrogation of engineered biological systems. The focus of this review is the anaerobic digestion process, which, as a technology that has come in and out of fashion, still remains a fundamental process for addressing the global climate emergency. Whether with conventional anaerobic digestion systems, biorefineries, or other anaerobic technologies, mathematical models are important tools that are used to design, monitor, control and optimise the process. Both highly structured, mechanistic models and data-driven approaches have been used extensively over half a decade, but recent advances in computational capacity, scientific understanding and diversity and quality of process data, presents an opportunity for the development of new modelling paradigms, augmentation of existing methods, or even incorporation of tools from other disciplines, to ensure that anaerobic digestion research can remain resilient and relevant in the face of emerging and future challenges.

The paper investigates into the intricacies of semiconductor manufacturing, a highly complex process entailing a wide array of subprocesses and diverse equipment. Semiconductors are miniaturized integrated circuits comprising numerous components. The semiconductor manufacturing process begins with the thin disc-shaped silicon wafers. On each wafer, up to thousands of identical chips can be prepared depending upon the diameter of the wafer to build up the circuits layer by layer in a wafer fab. The size of the semiconductors requires a high number of units to be produced, thus necessitating a large amount of data to control for improving the semiconductor manufacturing process. Therefore, the collection and analysis of the equipment data, process data, and machine history data throughout the manufacturing process are required to diagnose faults, monitor the process, and manage the manufacturing process effectively. This research is focused on improving the semiconductor manufacturing process through a rigorous analysis of collected manufacturing process data, employing statistical process control (SPC), data mining techniques, and data-driven decision models. The project's primary objective is to increase the manufacturing process stability and productivity by utilizing the latest data-driven technologies in the scientific community. A structured review was undertaken, exploring contemporary data-driven methodologies in semiconductor manufacturing process improvement, specifically pertaining to process capability, product yield rate, and process stability. This review accentuates a comprehensive evaluation of data-driven methodologies applicable to conventional semiconductor manufacturing facilities, aiming to drive substantial process improvements. It features a detailed demonstration facilitating the selection of optimal semiconductor manufacturing processes to enhance overall operational performance. This study of process improvement in the semiconductor manufacturing steps through the application of data-driven methodologies will be effective in delivering advanced, real-time, and proactive control decisions throughout the manufacturing facilities. This endeavor is expected to promptly provide critical insights for enterprise manufacturing decision-makers to reduce manufacturing cycle time, improve the product yield rate, and increase the overall efficiency of the manufacturing process.

A heterogeneous disease like cancer is activated through multiple pathways and different perturbations. Depending upon the activated pathway(s), patients’ survival vary significantly and show different efficacy to various drugs. Therefore, cancer subtype detection using genomics level data is a significant research problem. Subtype detection is often a complex problem, and in most cases, needs multi-omics data fusion to achieve accurate subtyping. Different data fusion and subtyping approaches have been proposed, such as kernel-based fusion, matrix factorization, and deep learning autoencoders. In this paper, we compared the performance of different deep learning autoencoders for cancer subtype detection. We performed cancer subtype detection on four different cancer types from The Cancer Genome Atlas (TCGA) datasets using four autoencoder implementations. We also predicted the optimal number of subtypes in a cancer type using the silhouette score. We observed that the detected subtypes exhibit significant differences in survival profiles. Furthermore, we also compared the effect of feature selection and similarity measures for subtype detection. To evaluate the results obtained, we selected the Glioblastoma multiforme (GBM) dataset and identified the differentially expressed genes in each of the subtypes identified by the autoencoders; the obtained results coincide well with other genomic studies and can be corroborated with the involved pathways and biological functions. Thus, it shows that the results from the autoencoders, obtained through the interaction of different datatypes of cancer, can be used for the prediction and characterization of patient subgroups and survival profiles.

Prediction of protein-ligand binding affinities is crucial for computational drug discovery. A number of deep learning approaches have been developed in recent years to improve the accuracy of such affinity prediction. While the predicting power of these systems have advanced to some degrees depending on the dataset used for model training and testing, the effects of the quality and quantity of the underlying data have not been thoroughly examined. In this study, we employed erroneous datasets and data subsets of different sizes, created from one of the largest databases of experimental binding affinities, to train and evaluate a deep learning system based on convolutional neural networks. Our results show that data quality and quantity do have significant impacts on the prediction performance of trained models. Depending on the variations in data quality and quantity, the performance discrepancies could be comparable to or even larger than those observed among different deep learning approaches. In particular, the presence of proteins during model training leads to a dramatic increase in prediction accuracy. This implies that continued accumulation of high-quality affinity data, especially for new protein targets, is indispensable for improving deep learning models to better predict protein-ligand binding affinities.

Data mining techniques have garnered significant attention within the realm of education. However, the procurement of ample student data poses a formidable challenge. In response to this challenge, we present a student dataset characterized by its size and distinctive attributes. This dataset encompasses various task-related topics interconnected through a learning pathway, thereby enabling researchers to delve into the data from novel perspectives. Moreover, it encompasses extensive longitudinal student behavioral data, a rarity that adds substantial value. Spanning the years from 2010 to 2021, our dataset comprises a cohort of 7,933 students, 64,344 test scores, and 183,390 behavior records, solidifying its status as a valuable resource for educational research. In our experiments, we achieved successful predictions of students' test outcomes based on behavioral learning data. The strengths of our dataset render it apt for analyzing the nexus between student conduct and academic performance, crafting personalized learning recommendations, and pursuing various other research pursuits.

Variations in groundwater levels that are noticed in different parts of the world are typically the primary focus of research carried out in hydrology. The fluctuating levels of groundwater can be ascribed to several different factors, some of which include an increase in the demand for water, inappropriate irrigation practices, improper management of soil, and unregulated extraction from aquifers. It is necessary to effectively manage groundwater resources to have a trustworthy method of measuring and forecasting groundwater levels. The dynamics of groundwater are inherently uneven and difficult to understand. As a result, applying methods driven by data could potentially yield significant gains in hydrology. In this study, two data-driven models were utilized to estimate groundwater levels at a total of 4 monitoring wells located in Colorado state, USA. These models included ARIMA and ANN. The comparative analysis of the algorithms made use of a data set that had one month's worth of information from each of the years 1980 to 2019. The models were put through their paces, and the results of those tests were statistically and visually assessed. To evaluate the relative accuracy and precision of the models, the mean absolute error (MAE), mean square error (MSE), and root-mean-square error (RMSE) were used. When compared to ARIMA, the analysis demonstrates that ANN can produce the most accurate forecasts of groundwater levels in Colorado state USA.

In this paper, we present a framework that automatically labels Latent Dirichlet Allocation (LDA) generated topics using sentiment and aspect terms from COVID-19 tweets to help the end-users by minimizing the cognitive overhead of identifying key topics labels. Social media platforms especially Twitter are considered as one of the most influential sources of information for providing public opinion related to a critical situation like the COVID-19 pandemic. LDA is a popular topic modelling algorithm that extracts hidden themes of documents without assigning a specific label. Thus automatic labelling of LDA-generated topics from COVID-19 tweets is a great challenge instead of following the manual labelling approach to get an overview of wider public opinion. To overcome this problem, in this paper, we propose a framework named \texttt{SATLabel} that effectively identifies significant topic labels using \textit{top unigrams features of sentiment terms and aspect terms clusters from LDA generated topics} of COVID-19 related tweets to uncover various issues related to the COVID-19 pandemic. The experimental results show that our methodology is more effective, simpler, and traces better topic labels compare to the manual topic labelling approach.

Total cloud cover (TCC) retrieval from ground-based optical imagery is a problem being tackled by a few generations of researchers. The number of human-designed algorithms for the estimation of TCC grows every year. However, there is not very much progress in terms of quality, mostly due to the lack of systematic approach to the design of the algorithms, to the assessment of their generalization ability, and to the assessment of the TCC retrieval quality. In this study, we discuss the optimization nature of data-driven schemes for TCC retrieval. In order to compare the algorithms, we propose the framework for the assessment of the algorithms characteristics. We present several new algorithms that are based on deep learning techniques: a model for outliers filtering, and a few models for TCC retrieval from all-sky imagery. For training and assessment of data-driven algorithms of this study, we present the Dataset of All-Sky Imagery over the Ocean (DASIO) containing over one million of all-sky optical images of visible sky dome taken in various regions of the World Ocean. The research campaigns contributed to DASIO collection took place in the Atlantic ocean, the Indian ocean the Red and Mediterranean seas, and also in the Arctic ocean. Optical imagery collected during these missions are accompanied by standard meteorological observations of cloudiness characteristics made by experienced observers. We assess the generalization ability of the presented models in several scenarios that differ in terms of the regions selected for the train and validation subsets. As a result, we demonstrate that our models based on convolutional neural networks deliver superior quality compared to all previously published schemes. As a key result, we demonstrate considerable drop of the ability to generalize the training data in case of strong covariate shift between training and validation subsets of imagery which may take place in case of region-aware subsampling.

In Model-Driven Development (MDD), the models, their generation, and imposing changes on them (model transformation) are used for the development of software. Models provide a framework to start from the imagination and abstraction to create and accomplish the final system. Models create a slow and steady transition from whatness to howness, i.e. from the natural path of the generation of software. For supporting this path, the Logic and Functionality of software must be changeable during its evolution. Here we provide a brief introduction to the concept of Model Driven Development.

Artificial intelligence (AI) techniques have grown rapidly in recent years in the context of computing with smart mobile phones that typically allows the devices to function in an intelligent manner. Popular AI techniques include machine learning and deep learning methods, natural language processing, as well as knowledge representation and expert systems, can be used to make the target mobile applications intelligent and more effective. In this paper, we present a comprehensive view on mobile data science and intelligent apps in terms of concepts and AI-based modeling that can be used to design and develop intelligent mobile applications for the betterment of human life in their diverse day-to-day situation. This study also includes the concepts and insights of various AI-powered intelligent apps in several application domains, ranging from personalized recommendation to healthcare services, including COVID-19 pandemic management in recent days. Finally, we highlight several research issues and future directions relevant to our analysis in the area of mobile data science and intelligent apps. Overall, this paper aims to serve as a reference point and guidelines for the mobile application developers as well as the researchers in this domain, particularly from the technical point of view.

This paper presents a study on the thermal efficiency improvement of the user equipment room in the district heating system based on reinforcement learning [1], and suggests a general method of constructing a learning network(DQN)[2] using deep Q learning[3], which is a reinforcement learning algorithm that does not specify a model. In addition, we introduce the big data platform system and the integrated heat management system for the energy field in the massive data processing from the IoT sensor installed in large number of thermal energy control facilities.

Ultrasonic-guided lamb wave approach is an effective non-destructive testing (NDT) method used for detecting localized mechanical damage, corrosion, and welding defects experienced in metallic pipelines. Signal processing of the guided waves is often challenged due to the complexity of operational conditions and environments in the pipelines. Machine learning approaches in recent years, including convolutional neural networks (CNN) and long short-term memory (LSTM), have exhibited their advantages to overcome these challenges for signal process and data classification of complex systems, thus great potential for damage detection of critical oil/gas pipeline structures. In this study, a CNN-LSTM hybrid model is utilized for decoding ultrasonic guided waves for damage detection of metallic pipelines, and twenty-nine features are extracted as input to classify different types of defects from metallic pipes. The prediction capacity of the CNN-LSTM model is assessed by comparing it to the CNN and LSTM. The results demonstrate that the CNN-LSTM hybrid model exhibits much higher accuracy, with 94.8%, as compared to those of CNN and LSTM. Interestingly, the results also reveal that predetermined features, including time-, frequency-, and time-frequency domains, could significantly improve the robustness of the deep learning approaches, even though the deep learning approaches are often believed they include automated feature extraction, without the hand-crafted steps as the shallow learning do. Furthermore, the CNN-LSTM model displays higher performance when the noise level is relatively low (e.g., SNR=9 or higher), as compared to the other two models, but its prediction drops gradually with the increase of the noise.

Object classification is a crucial task in deep learning, which involves the identification and categorization of objects in images or videos. Although humans can easily recognize common objects, such as cars, animals, or plants, performing this task on a large scale can be time-consuming and error-prone. Therefore, automating this process using neural networks can save time and effort while achieving higher accuracy. Our study focuses on the classification step of human chromosome karyotyping, an important medical procedure that helps diagnose genetic disorders. Traditionally, this task is performed manually by expert cytologists, which is a time-consuming process that requires specialized medical skills. Therefore, automating it through deep learning can be immensely useful. To accomplish this, we implemented and adapted existing preprocessing and data augmentation techniques to prepare the chromosome images for classification. We used ResNet-50 convolutional neural networks and an ensemble approach to classify the chromosomes, obtaining state-of-the-art performance in the tested dataset.

Scientists and astronomers have attached Scientists and astronomers have attached great importance to the task of discovering new exoplanets, even more so if they are in the habitable zone. To date, more than 4300 exoplanets have been confirmed by NASA, using various discovery techniques, including planetary transits, in addition to the use of various databases provided by space and ground-based telescopes. This article proposes the development of a deep learning system for detecting planetary transits in Kepler Telescope lightcurves. The approach is based on related work from the literature and enhanced to validation with real lightcurves. A CNN classification model is trained from a mixture of real and synthetic data, and validated only with real data and different from those used in the training stage. The best ratio of synthetic data is determined by the perform of an optimisation technique and a sensitivity analysis. The precision, accuracy and true positive rate of the best model obtained are determined and compared with other similar works. The results demonstrate that the use of synthetic data on the training stage can improve the transit detection performance on real light curves.

Artificial Intelligence (AI) models are expected to have a great impact in the manufacturing industry, optimizing time and resource cost by enabling applications such as predictive maintenance (PM) of production machines. A necessary condition for this is the availability of high quality data collected as close as possible to the process in question. With the advent of 5G equipped multi sensor platforms (MSPs), high sampling rate data can be collected and transmitted for processing in real time. This poses a data security challenge, since this data may give valuable insight into confidential business information of companies. Federated learning (FL) enables the training of AI models with data from multiple sources without it leaving the shop floor, by utilizing distributed computing resources available on premise. This paper introduces an architecture of FL based on data collected from 5G MSPs for enabling PM in industrial environments and discusses its potential benefits and challenges.

Although learning analytics (LA) holds great potential to improve teaching and learning, LA research and practice are currently riddled with limitations that impact every stage of the LA life cycle. The present paper offers an overview of these challenges before proposing strategies to overcome them and exploring how the recent innovations brought forth by language models can improve LA research and practice. In particular, we encourage the empowerment of teachers during LA development, as this would strengthen the theoretical foundation of LA solutions and increase their interpretability and usability. Furthermore, we provide examples of how process data can be used to understand learning processes and generate more interpretable LA insights. Furthermore, we explore how LLMs could come into play in LA to generate interpretable insights, timely and actionable feedback, increase personalization, and support teachers’ tasks more broadly.

Sparse reward long horizon task is a major challenge for deep reinforcement learning algorithm. One of the key barriers is data-inefficiency. Even in the simulation environment, it usually takes weeks to training the agent. In this study, a data-efficiency training framework is proposed, where a curriculum learning is design for the agent in the simulation scenario. Different distributions of the initial state are set for the agent to get more informative reward during the whole training process. A fine-tuning of the parameters in the output layer of the neural network for value function is conduct to bridge the gap between sim-to-real. An experiment of UAV maneuver control is conducted in the proposed training framework to verify the method more efficient. We demonstrate that data-efficiency is different for the same data in different training stages.

This paper proposes a Grouped Contrastive Learning of self-supervised Sentence Representation (GCLSR), which can learn an effective and meaningful representation of sentences. Previous works maximize the similarity between two vectors to be the objective of contrastive learning, suffering from the high-dimensionality of the vectors. In addition, most previous works have adopted discrete data augmentation to obtain positive samples and directly employed contrastive framework of computer vision to perform contrastive training, which could hamper contrastive training because text data is discrete and sparse compared with image data. To address those issues, we propose a grouped contrastive learning framework, i.e., GCLSR, which divides the high-dimensional feature vector into several groups and respectively computes the groups’ contrastive losses to make use of more local information, eventually obtaining a more fine-grained sentence representation. In addition, in GCLSR, we design a new self-attention mechanism and a continuous as well as partial word vector augmentation (PWVA). For the discrete and sparse text data, the usage of self-attention could help model focus the informative words by measuring the importance of every word in a sentence. By using the PWVA, GCLSR can obtain high-quality positive samples used for contrastive learning. Experimental results demonstrate that our proposed GCLSR achieves an encouraging result on the challenging datasets of the standard semantic textual similarity (STS) task and transfer task.

As the development of high-throughput technologies, more and more high-dimensional or ultra high-dimensional genomic data are generated. Therefore, how to make effective analysis of such data becomes a challenge. Machine learning (ML) algorithms have been widely applied for modelling nonlinear and complicated interactions in a variety of practical fields such as high-dimensional survival data. Recently, the multilayer deep neural network (DNN) models have made remarkable achievements. Thus, a Cox-based DNN prediction survival model (DNNSurv model) , which was built with Keras and Tensorflow, was developed. However, its results were only evaluated to the survival datasets with high-dimensional or large sample sizes. In this paper, we evaluate the prediction performance of the DNNSurv model using ultra high-dimensional and high-dimensional survival datasets, and compare it with three popular ML survival prediction models (i.e., random survival forest and Cox-based LASSO and Ridge models). For this purpose we also present the optimal setting of several hyper-parameters including selection of tuning parameter. The proposed method demonstrates via data analysis that the DNNSurv model performs overall well as compared with the ML models, in terms of three main evaluation measures (i.e., concordance index, time-dependent Brier score and time-dependent AUC) for survival prediction performance.

The COVID-19 led to changes modifying the role of digital transformation and unleashing unparalleled opportunities to improve business production processes in all three dimensions of sustainability - economic, social, and environmental through data-driven innovative service implications that significantly impact restaurant business, resulting in an increased competitive advantage. This paper identifies the innovative service implications and summarizes sustainable social systems measures in the context of strategic management in the restaurant industry triggered by COVID-19. Based on in-depth interviews with sixteen key experts in the restaurant industry, the paper clarifies and concretizes the rapidly transforming problem of identifying the main changes in the restaurant business, using three dimensions: consumer demand, corporate strategy optimization, and the use of the company's innovative potential. The findings reveal how companies need to expand their digital strategies and adapt their management approach to all stakeholders bringing sustainable business development in the post-pandemic period into focus. This paper serves as a framework for understanding the digital transformation role in resilient business management within restaurant social systems, with friction occurring along the workflow from kitchen to customer.

This paper focuses on quantifying the economic and financial viability of NB-IoT and LoRaWAN technologies, two low-power wide-area network (LPWAN) technologies with unique characteristics that make them suitable for IoT applications. The purpose of the study is to propose an artefact for performing life cycle cost analysis and demonstrate its application to these technologies. The methodology uses pragmatic computational tools to facilitate the analysis and considers all relevant economic and financial factors, such as operating costs, equipment costs, and revenue potential. The main finding of the study is that NB-IoT and LoRaWAN technologies have different cost structures and revenue potentials, which may affect their economic and financial viability for different IoT applications. Ultimately, the study concludes that a comprehensive life cycle cost analysis is critical to making informed decisions about technology adoption, and that the proposed methodology can be applied to other IoT technologies to gain insight into their economic and financial viability.

Wind turbine plants are complex dynamic and uncertain processes driven by stochastic inputs and disturbances, as well as different loads represented by gyroscopic, centrifugal, and gravitational forces. Moreover, as their aerodynamic models are nonlinear, both modelling and control become challenging problems. On one hand, high-fidelity simulators should contain different parameters and variables in order to accurately describe the main dynamic system behaviour. Therefore, the development of modelling and control for wind turbine systems should consider these complexity aspects. On the other hand, these control solutions have to include the main wind turbine dynamic characteristics without becoming too complicated. The main point of this paper is thus to provide two practical examples of development of robust control strategies when applied to a simulated wind turbine plant. Experiments with the wind turbine simulator and the Monte–Carlo tools represent the instruments for assessing the robustness and reliability aspects of the developed control methodologies when the model-reality mismatch and measurement errors are also considered. Advantages and drawbacks of these regulation methods are also highlighted with respect to different control strategies via proper performance metrics.

Increasingly, there is a focus on utilising renewable energy resources in a bid to fulfil increasing energy requirements and mitigate the climate change impacts of fossil fuels. While most renewable resources are free, the technology used to usefully convert such resources is not and there is an increasing focus on improving the conversion economy and efficiency. To this end, advanced control technologies can have a significant impact and is already a relatively mature technology for wind turbines. Though hydroelectric plants can use simple regulation systems, significant benefits have been shown to accrue from the appropriate use of the same control methods designed for wind turbine plants. This represents the key point of the paper. In fact, to date, the application communities connected with wind and hydraulic energies have had little communication, resulting in little cross fertilisation of control ideas and experience, particularly from the more mature wind area to hydrodynamic systems. Therefore, this paper examines the models and the application of control technology across both domains, both from a comparative and contrasting point of view, with the aim of identifying commonalities in models and control objectives, as well as potential solutions. Key comparative reference points include the articulation of the exployed models, specification of control objectives, development of high--fidelity simulators, and development of solution concepts. Not least, in terms of realistic system requirements are the set of physical and constraints under which such renewable energy systems must operate, and the need to provide reliable and robust control solutions, which respect the often remote and relatively inaccessible location of many onshore and offshore deployments.

Digital Twin Cities (DTCs) play a fundamental role in city planning and management. They allow three-dimensional modeling and simulation of cities. 3D semantic segmentation is the foundation for automatically creating enriched DTCs, as well as their updates. Past studies indicate that prior level fusion approaches demonstrate more promising precisions in 3D semantic segmentation compared to point level fusion, features level fusion, and decision level fusion families. In order to improve point cloud enriched semantic segmentation outcomes, this article proposes a new approach for 3D point cloud semantic segmentation through developing and benchmarking three prior level fusion scenarios. A reference approach based on point clouds and aerial images was proposed to compare it with the different developed scenarios. In each scenario, we inject a specific prior knowledge (geometric features,classified images ,etc) and aerial images as attributes of point clouds into the neural network’s learning pipeline. The objective is to find the one that integrates the most significant prior knowledge and enhances neural network knowledge more profoundly, which we have named the "smart fusion approach". The advanced Deep Learning algorithm "RandLaNet" was adopted to implement the different proposed scenarios and the reference approach, due to its excellent performance demonstrated in the literature. The introduction of some significant features associated with the label classes facilitated the learning process and improved the semantic segmentation results that can be achievable with the same neural network alone. Overall, our contribution provides a promising solution for addressing some challenges, in particular more accurate extraction of semantically rich objects from the urban fabric. An assessment of the semantic segmentation results obtained by the different scenarios is performed based on metrics computation and visual investigations. Finally,the smart fusion approach was derived based on the obtained qualitative and quantitative results.

Deep learning (DL) models have been recently widely used to extract task-oriented patterns from large scale of datasets, and to improve the data image understanding and analysis accuracy in many different decision-making processes for tasks such as image classification, segmentation, detection, and so on. However, in practice, the performances of DL models are easily affected by environmental illumination conditions. Conversely, DL models can also be utilized for extracting the illumination hints from the images, and these hints are critically useful for improving the model robustness, classifying the environmental scenes, estimating scene depth information, and rendering 3D objects. In this study, an extensive and exhaustive review is carried out for DL based color constancy, indoor and outdoor illumination estimation, and image depth estimations with the considerations of strengths and weaknesses of DL models. This study also explores the different network designs and the paradoxes in parameter optimization during the model training. Current technology barriers involved in implementing these models and recommendations to overcome these barriers are also suggested in the review.

In the field of computer vision, large-scale image classification tasks are both important and highly challenging. With the ongoing advances in deep learning and optical character recognition (OCR) technologies, neural networks designed to perform large-scale classification play an essential role in facilitating OCR systems. In this study, we developed an automatic OCR system designed to identify up to 13,070 large-scale printed Chinese characters by using deep learning neural networks and fine-tuning techniques. The proposed framework comprises four components, including training dataset synthesis and background simulation, image preprocessing and data augmentation, the process of training the model, and transfer learning. The training data synthesis procedure is composed of a character font generation step and a background simulation process. Three background models are proposed to simulate the factors of the background noise and anti-counterfeiting patterns on ID cards. To expand the diversity of the synthesized training dataset, rotation and zooming data augmentation are applied. A massive dataset comprising more than 19.6 million images was thus created to accommodate the variations in the input images and improve the learning capacity of the CNN model. Subsequently, we modified the GoogLeNet neural architecture by replacing the FC layer with a global average pooling layer to avoid overfitting caused by a massive amount of training data. Consequently, the number of model parameters was reduced. Finally, we employed the transfer learning technique to further refine the CNN model using a small number of real data samples. Experimental results show that the overall recognition performance of the proposed approach is significantly better than that of prior methods and thus demonstrate the effectiveness of proposed framework, which exhibited a recognition accuracy as high as 99.39% on the constructed real ID card dataset.

Measurements of systems taken along a continuous functional dimension, such as time or space, are ubiquitous in many fields, from the physical and biological sciences to economics and engineering. Such measurements can be viewed as realisations of an underlying smooth process sampled over the continuum. However, traditional methods for independence testing and causal learning are not directly applicable to such data, as they do not take into account the dependence along the functional dimension. By using specifically designed kernels, we introduce statistical tests for bivariate, joint, and conditional independence for functional variables. Our method not only extends the applicability to functional data of the Hilbert-Schmidt independence criterion (HSIC) and its d-variate version (d-HSIC), but also allows us to introduce a test for conditional independence by defining a novel statistic for the conditional permutation test (CPT) based on the Hilbert-Schmidt conditional independence criterion (HSCIC), with optimised regularisation strength estimated through an evaluation rejection rate. Our empirical results of the size and power of these tests on synthetic functional data show good performance, and we then exemplify their application to several constraint- and regression-based causal structure learning problems, including both synthetic examples and real socio-economic data.

Multimodal remote sensing data classification can enhance the model’s ability to distinguish land features through multimodal data fusion. In this context, how to help models understand the relationship between multimodal data and target tasks is the focus of researchers. Inspired by human feedback learning mechanisms, causal reasoning mechanisms, and knowledge induction mechanisms, this paper integrates causal learning, reinforcement learning, and meta learning into a unified remote sensing data classification framework and proposed the causal meta-reinforcement learning (CMRL). First, based on feedback learning mechanisms, we have overcome the limitations of traditional implicit optimization of fusion features and customized a reinforcement learning environment for multimodal remote sensing data classification tasks. Through feedback interactive learning between agents and the environment, we help them understand the complex relationships between multimodal data and labels, thereby achieving full mining of multimodal complementary information. Second, based on the causal inference mechanism we designed causal distribution prediction action, classification reward, and causal intervention reward, capturing pure causal factors in multimodal data and cutting off false statistical associations between non-causal factors and class labels. Finally, based on the knowledge induction mechanism, we designed a bi-layer optimization mechanism based on meta-learning. By constructing a meta training task and meta validation task simulation model in the generalization scenario of unseen data, we helped the model induce cross-task shared knowledge, thereby improving its generalization ability for unseen multimodal data. The experimental results on multiple sets of multimodal datasets show that the proposed method achieved state-of-the-art performance in multimodal remote sensing data classification tasks.

Physical inactivity increases the risk of many adverse health conditions, including the world’s major non-communicable diseases, such as coronary heart disease, type 2 diabetes, and breast and colon cancers, shortening life expectancy. There are minimal medical care and personal trainers’ methods to monitor a patient’s actual physical activity types. To improve activity monitoring, we propose an artificial-intelligence-based approach to classify the physical movement activity patterns. In more detail, we employ two deep learning (DL) methods, namely a deep feed-forward neural network (DNN) and a deep recurrent neural network (RNN) for this purpose. We evaluate the proposed models on two physical movement datasets collected from several volunteers who carried tri-axial accelerometer sensors. The first dataset is from the UCI machine learning repository, which contains 14 different activities-of-daily-life (ADL) and is collected from 16 volunteers who carried a single wrist-worn tri-axial accelerometer. The second dataset includes ten other ADLs and is gathered from 8 volunteers who placed the sensors on their hips. Our experiment results show that the RNN model provides the accuracy performance compared to the state-of-the-art methods in classifying the fundamental movement patterns with an overall accuracy of 84.89% and an overall F1-score of 82.56%. Our results indicate that the proposed method will provide the medical doctors and trainers a promising way to precisely track and understand a patient’s physical activities for better treatment.

In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal information for training. Secondly, deep neural networks need a very large amount of labelled training data to achieve good quality performance, yet in practice it is difficult to collect enough samples for most classes of interest. In this paper, we propose factorising the final task of audio transcription into multiple intermediate tasks in order to improve the training performance when dealing with this kind of low-resource datasets. We evaluate three data-efficient approaches of training a stacked convolutional and recurrent neural network for the intermediate tasks. Our results show that different methods of training have different advantages and disadvantages.

Validation and verification are the critical requirements in the knowledge acquisition method for the clinical decision support system (CDSS). After acquiring the medical knowledge from diverse sources, the rigorous validation and formal verification process are required before creating the final knowledge model. Previously, we have proposed a hybrid knowledge acquisition method for acquiring medical knowledge from clinical practice guidelines (CPGs) and patient data in the Smart CDSS for treatment of oral cavity cancer. The final knowledge model was created by combining knowledge models obtained from CPGs and patient data after passing through a rigorous validation process. However, detailed analysis shows that due to lack of formal verification process, it involves various inconsistencies in knowledge relevant to the formalism of knowledge, conformance to CPGs, quality of knowledge, and complexities of knowledge acquisition artifacts. Therefore, it is required to enhance a hybrid knowledge acquisition method that thwarts the inconsistencies using formal verification. This paper presents the verification process using the Z formal method and its outcome as an enhanced acquisition method – known as the refined knowledge acquisition (ReKA) method. The ReKA method adopted verification method and explored the mechanism of theorem proving using the Z notation. It enables to identify inconsistencies in the validation process used for hybrid knowledge acquisition. Additionally, it refines the hybrid knowledge acquisition method by discovering the missing steps in the current validation process at the acquisition stage. Consequently, ReKA adds a set of nine additional criteria to be used to have a final valid refined clinical knowledge model. The criteria ensure the validity of final knowledge model concerning formalism of knowledge, conformance to GPGs, quality of the knowledge, usage of stringent conditions and treatment plans, and inconsistencies possibly resulting from the complexities. Evaluation, using four medical knowledge acquisition scenarios, shows that newly added knowledge in CDSS due to the addition of criteria by ReKA method always produces a valid knowledge model. The final knowledge model was also evaluated with 1229 oral cavity patient cases, which outperformed with an accuracy of 72.57\% compared to a similar approach with an accuracy of 69.7\%. Furthermore, ReKA method identified a set of decision paths (about 47.8%) in the existing approach, which results in a final knowledge model with low quality, non-conformed from standard CPGs. In conclusion, ReKA is formally proved method which always yields valid knowledge model having high quality, supporting local practices, and influenced from standard guidelines.

The interest on the use of renewable energy resources is increasing, especially towards wind and hydro powers, which should be efficiently converted into electric energy via suitable technology tools. To this aim, data--driven control techniques represent viable strategies that can be employed for this purpose, due to the features of these nonlinear dynamic processes working over a wide range of operating conditions, driven by stochastic inputs, excitations and disturbances. Some of the considered methods, such as fuzzy and adaptive self--tuning controllers, were already verified on wind turbine systems, and similar advantages may thus derive from their appropriate implementation and application to hydroelectric plants. These issues represent the key features of the work, which provides some guidelines on the design and the application of these control strategies to these energy conversion systems. The working conditions of these systems will be also taken into account in order to highlight the reliability and robustness characteristics of the developed control strategies, especially interesting for remote and relatively inaccessible location of many installations.

The interest on the use of renewable energy resources is increasing, especially towards wind and hydro powers, which should be efficiently converted into electric energy via suitable technology tools. To this aim, self--tuning control techniques represent viable strategies that can be employed for this purpose, due to the features of these nonlinear dynamic processes working over a wide range of operating conditions, driven by stochastic inputs, excitations and disturbances. Some of the considered methods were already verified on wind turbine systems, and important advantages may thus derive from the appropriate implementation of the same control schemes for hydroelectric plants. This represents the key point of the work, which provides some guidelines on the design and the application of these control strategies to these energy conversion systems. In fact, it seems that investigations related with both wind and hydraulic energies present a reduced number of common aspects, thus leading to little exchange and share of possible common points. This consideration is particularly valid with reference to the more established wind area when compared to hydroelectric systems. In this way, this work recalls the models of wind turbine and hydroelectric system, and investigates the application of different control solutions. The scope is to analyse common points in the control objectives and the achievable results from the application of different solutions. Another important point of this investigation regards the analysis of the exploited benchmark models, their control objectives, and the development of the control solutions. The working conditions of these energy conversion systems will be also taken into account in order to highlight the reliability and robustness characteristics of the developed control strategies, especially interesting for remote and relatively inaccessible location of many installations.

The fault diagnosis of wind farms has been proven to be a challenging task and motivates the research activities carried out through this work. Therefore, this paper deals with the fault diagnosis of a wind park benchmark model, and it considers viable solutions to the problem of earlier fault detection and isolation. The design of the fault indicator involves data-driven approaches, as they can represent effective tools for coping with poor analytical knowledge of the system dynamics, noise, uncertainty and disturbances. In particular, the proposed data-driven solutions rely on fuzzy models and neural networks that are used to describe the strongly nonlinear relationships between measurement and faults. The chosen architectures rely on nonlinear autoregressive with exogenous input models, as they can represent the dynamic evolution of the system along time. The developed fault diagnosis schemes are tested by means of a high-fidelity benchmark model, that simulates the normal and the faulty behaviour of a wind farm installation. The achieved performances are also compared with those of a model-based approach relying on nonlinear differential geometry tools. Finally, a Monte-Carlo analysis validates the robustness and the reliability of the proposed solutions against typical parameter uncertainties and disturbances.

The fossil record is notorious for being incomplete and distorted, frequently conditioning the type of knowledge that can be extracted from it. In many cases, this often leads to issues when performing complex statistical analyses, such as classification tasks, predictive modelling, and variance analyses, such as those used in Geometric Morphometrics. Here different Generative Adversarial Network architectures are experimented with, testing the effects of sample size and domain dimensionality on model performance. For model evaluation, robust statistical methods were used. Each of the algorithms were observed to produce realistic data. Generative Adversarial Networks using different loss functions produced multidimensional synthetic data significantly equivalent to the original training data. Conditional Generative Adversarial Networks were not as successful. The methods proposed are likely to reduce the impact of sample size and bias on a number of statistical learning applications. While Generative Adversarial Networks are not the solution to all sample-size related issues, combined with other pre-processing steps these limitations may be overcome. This presents a valuable means of augmenting geometric morphometric datasets for greater predictive visualization.

This paper presents a new framework to classify floor plan elements and represent them in a vector format. Unlike existing approaches using image-based learning frameworks as the first step to segment the image pixels, we first convert the input floor plan image into vector data and utilize graph neural network. Our framework consists of three steps. (1) image pre-processing and vectorization of the floor plan image. (2) region adjacency graph conversion. (3) graph neural network on converted floor plan graphs. Our approach is able to capture different types of indoor elements including basic elements such as walls, doors, and symbols as well as spatial elements such as rooms and corridors. In addition, the proposed method can also detect element shapes. Experimental results show that our framework can classify indoor elements with an F1 score of 95%, with scale and rotation invariance. Furthermore, we propose a new graph neural network model that takes the distance between nodes into account, which is a valuable feature of spatial network data.

Recently, deep learning-based image quality enhancement models have been proposed to improve the perceptual quality of distorted synthesized views impaired by compression and Depth Image Based Rendering (DIBR) process in multiview video systems. However, due to the lack of multi-view video plus depth data, the training data for quality enhancement models is small, which limits the performance and progress of these models. Augmenting the training data to enhance the Synthesized View Quality Enhancement (SVQE) models is a feasible solution. In this paper, we suggest a deep learning-based SVQE model using more synthetic Synthesized View Images (SVIs). To simulate the irregular geometric displacement of DIBR distortion, a random irregular polygon-based SVI synthesis method is proposed based on existing massive RGB/RGBD data, and a synthetic synthesized view database is constructed, which includes synthetic SVIs and DIBR distortion masks. Moreover, to further guide the SVQE models to focus more precisely on DIBR distortion, the DIBR distortion mask prediction network which could predict the position and variance of DIBR distortion is embedded into the SVQE models. The experimental results demonstrate that by pretraining on the synthetic SVI database, the performance of the existing SVQE models could be greatly promoted. In addition, by introducing the DIBR distortion mask prediction network, the SVI quality could be further enhanced.

Data collection and analysis are becoming more and more important in a variety of application domains as long as the novel technologies advance. At the same time, we are experiencing a growing need for human-machine interaction with expert systems pushing research through new knowledge representation models and interaction paradigms. In particular, in the last years eHealth - that indicates all the health-care practices supported by electronic elaboration and remote communications - calls for the availability of smart environment and big computational resources. The aim of this paper is to introduce the HOLMeS (Health On-Line Medical Suggestions) framework. The introduced system proposes to change the eHealth paradigm where a trained machine learning algorithm, deployed on a cluster-computing environment, provides medical suggestion via both chat-bot and web-app modules. The chat-bot, based on deep learning approaches, is able to overcome the limitation of biased interaction between users and software, exhibiting a human-like behavior. Results demonstrate the effectiveness of the machine learning algorithms showing 74.65% of Area Under ROC Curve (AUC) when first-level features are used to assess the occurrence of different prevention pathways. When disease-specific features are added, HOLMeS shows 86.78% of AUC achieving a more specific prevention pathway evaluation.

It is not easy to dynamically analyze thermal bridges that require multidimensional analysis in building energy simulations, which are mostly one-dimensional platforms. To solve this problem, many studies have been conducted and, recently, a study was conducted to model the thermal bridge based on the data by approaching this in a similar way to steady-state analysis, showing high accuracy. This was an early-stage study, which is only applicable when the indoor temperature is constant. By extending this study, a thermal bridge model that can be applied even when the indoor temperature changes over time is proposed and validated. Since the governing equation, the heat diffusion equation, is linear, the key idea is to create and apply two thermal bridge transfer function models by expressing the heat flow entering the room as a linear combination of the transfer function for indoor temperature and the transfer function for outdoor temperature. For the proposed thermal bridge model, the NRMSE of the model itself showed a high accuracy of 99.9%, and in the verification through annual simulation using the model, the NRMSE showed an accuracy of 88.8%.

The comprehensibility of good predictive models learned from high-dimensional gene expression data is attractive because it can lead to biomarker discovery. Several good classifiers provide comparable predictive performance but differ in their abilities to summarize the observed data. We extend a Bayesian Rule Learning (BRL-GSS) algorithm, previously shown to be a significantly better predictor than other classical approaches in this domain. It searches a space of Bayesian networks using a decision tree representation of its parameters with global constraints, and infers a set of IF-THEN rules. The number of parameters and therefore the number of rules are combinatorial to the number of predictor variables in the model. We relax these global constraints to a more generalizable local structure (BRL-LSS). BRL-LSS entails more parsimonious set of rules because it does not have to generate all combinatorial rules. The search space of local structures is much richer than the space of global structures. We design the BRL-LSS with the same worst-case time-complexity as BRL-GSS while exploring a richer and more complex model space. We measure predictive performance using Area Under the ROC curve (AUC) and Accuracy. We measure model parsimony performance by noting the average number of rules and variables needed to describe the observed data. We evaluate the predictive and parsimony performance of BRL-GSS, BRL-LSS and the state-of-the-art C4.5 decision tree algorithm, across 10-fold cross-validation using ten microarray gene-expression diagnostic datasets. In these experiments, we observe that BRL-LSS is similar to BRL-GSS in terms of predictive performance, while generating a much more parsimonious set of rules to explain the same observed data. BRL-LSS also needs fewer variables than C4.5 to explain the data with similar predictive performance. We also conduct a feasibility study to demonstrate the general applicability of our BRL methods on the newer RNA sequencing gene-expression data.

Background: Learning arrangements in health care profession education are increasingly taking place in digital environments. VR in nursing education, as one of the digital elements, is the subject of controversial debate. On the one hand it supports the authenticity of case studies by adding realistic perspectives and information. On the other hand, the costs of developing and maintaining software and hardware hinder long-term implementation. Methods: In this paper, we describe our findings and insights from two different research projects focused on the incorporation of digital tools, particularly virtual reality (VR), into nursing education. Based on the German context, our aim is to promote the adoption of innovative digital methods in nursing education and to offer invaluable experiences from the field. Results: Starting with a brief recapitulation of the projects, we then elucidate the pedagogical strategies for embedding VR-driven scenarios in nursing education. Based on our experiences during the projects we identify various positive aspects, such as change of perspective and simulating acute situations. Key findings: Although potential drawbacks remain, we advocate long-term implementation and specific use of VR at the interface between theory and practice. Nevertheless it is crucial to establish regular evaluation observing the value of digitalisation, especially VR; for nursing education.

Chronic venous disease (CVD) occurs in a substantial proportion of the world's population. If the onset of CVD looks like a cosmetic defect, then over time, it can develop into serious problems that require surgical intervention. The aim of the work is to use deep learning (DL) methods for automatic classification of the stage of CVD for self-diagnosis of a patient by using the image of the patient’s legs. The required for DL algorithms images of legs with CVD were obtained by using Internet Data Mining. For images preprocessing, the binary classification problem “legs - no legs” was solved based on Resnet50 with accuracy 0.998. The application of this filter made it possible to collect a data set of 11,118 good quality leg images with various stages of CVD. For classification of various stages of CVD according to CEAP classification, the multi classification problem was set and resolved by using two neural networks with completely different architecture - Resnet50 and DeiT. The model based on DeiT without any tuning shows better results than the model based on Resnet50 (precision = 0.770 (DeiT) and 0.615 (Resnet50)). To demonstrate the results of the work, a telegram bot was developed, in which fully functioning DL algorithms are implemented. This bot allows evaluating the condition of the patient's legs with a fairly good accuracy for the CVD classification.

The necessity for effective intrusion detection systems (IDS) in big data environments has grown critical due to the rising prevalence of big data systems and the rising amount of security threats. Applying conventional intrusion detection methods to the enormous and intricate data produced by big data ecosystems presents difficulties. Deep learning, has proven to be exceptionally adept at deciphering complex, large-scale data. This study proposes a Deep Learning-based Intrusion Detection System (IDS) created specifically for the Big Data environment. Traditional intrusion detection systems struggle to efficiently identify and prevent cyber threats due to the ever-increasing volume and complexity of data in current networks. We suggest an IDS that makes use of Deep Learning (CNN, LSTM, GAN, etc.), to address this problem. These cutting-edge neural network topologies give the system the ability to process and analyze massive amounts of data for precise intrusion detection. Data collection, data preprocessing, feature engineering, DL model training, intrusion detection, warning generation, and reaction are some of the crucial parts of the suggested IDS. The data collection module mines the Big Data environment for network traffic, system logs, and security event information. To make sure the data is suitable for analysis, it is preprocessed. To improve the detection abilities of the DL models, important features are extracted from the data using feature engineering approaches.

Machine learning has become an increasingly ubiquitous technology, as big data continues to inform and influence everyday life and decision-making. Currently in healthcare, as well as in most other industries, the two most prevalent machine learning paradigms are supervised learning and transfer learning. Both practices rely on large-scale, manually annotated datasets to train increasingly complex models. However, the requirement of data to be manually labeled leaves an excess of unused, unlabeled data available in both public and private data repositories. Self-supervised learning (SSL) is a growing area of machine learning that has the ability to take advantage of unlabeled data. Contrary to other machine learning paradigms, SSL algorithms create artificial supervisory signals from unlabeled data and pretrain algorithms on these signals. The aim of this review is two-fold: firstly, we provide a formal definition of SSL, divide SSL algorithms into their four unique subsets, and review the state-of-the-art published in each of those subsets between the years of 2014-2020. Second, this work surveys recent SSL algorithms published in healthcare, in order to provide medical experts with a clearer picture of how they can integrate SSL into their research, with the objective of leveraging unlabeled data.

Antennas are crucial elements for wireless technologies, communications and power transfer across the entire spectrum of electromagnetic waves, including radio, microwaves, THz and optics. In this paper, we review our recent achievements in two promising areas: coherently enhanced wireless power transfer (WPT) and superdirective dielectric antennas. We show that the concept of coherently enhanced WPT allows improvement of the antenna receiving efficiency by coherent excitation of the outcoupling waveguide with a backward propagating guided mode with a specific amplitude and phase. Antennas with the superdirectivity effect can increase the WPT systems performance in another way, through tailoring of radiation diagram via engineering antenna multipoles excitation and interference of their radiation. We demonstrate a way to achieving the superdirectivity effect via higher-order multipoles excitation in a subwavelength high-index spherical dielectric resonator supporting electric and magnetic Mie multipoles. Thus, both types of antenna discussed here possess a coherent nature and can be used in modern intelligent antenna systems.

The case for demand-driven research and development has received important considerations among governments, donors and programme implementing partners in development planning and implementation. Addressing demand is believed to be a bottom-top approach for designing and responding to development priorities and is good for achieving development outcomes. In this paper, we discuss the concept and application of demand driven research for development (DDRD) in Africa. We use evidence of six projects implemented under the BiomassWeb Project in Africa. We focus on parameters on level of engagement of stakeholders - whose demand is being articulated, the processes for demand articulation, capacity building and implementation processes, innovativeness of the project, reporting and sustainability of the project. We find that the nature of the institutions involved in articulation and implementation of demand-driven research and development projects and their partnerships influence the impact and reporting of demand-driven projects.

Background: Ongoing molecular profiling studies enabled by advances in biomedical technologies are producing vast amounts of ‘omic’ data for early detection, monitoring, and prognosis of diverse diseases. A major common limitation is the scarcity of biological samples, necessitating integrative modeling frameworks that can make optimal use of available data for disease classification tasks. Related data sets are often available from different studies, but may have been generated using different technology platforms. Thus, there is a critical need for flexible modeling methods that can handle data from diverse sources to facilitate the discovery of robust biomarkers that underlie disease regulatory processes. Results: In this paper, we introduce a novel framework called Knowledge Augmented Rule Learning (KARL), which incorporates two sources of knowledge, domain, and data, for pattern discovery from small and high-dimensional datasets, such as transcriptomic data. We propose KARL as a transfer rule learning framework in which knowledge of the domain is transferred to the learning process on data in order to 1) improve the reliability of the discovered patterns, and 2) study the knowledge of the domain when used along with data for modeling. In this work, we generated KARL models on gene expression datasets for five types of cancer, including brain, breast, colon, lung, and prostate. As our knowledge of the domain, we used the Ingenuity Knowledge Base (IKB) to extract genes related to hallmarks of cancer and annotated these prior relationships before learning classifiers from these datasets. Conclusions: Our results show that KARL produces, on average, rule models that are more robust classifiers than the baseline without such background knowledge, for our tasks of cancer prediction using 25 publicly available gene expression datasets. Moreover, KARL helped us learn insights about previously known relationships in these gene expression datasets, along with new relationships not input as known, to enable informed biomarker discovery for cancer prediction tasks. KARL can be applied to modeling similar data from any other domain and classification task. Future work would involve extensions to KARL to handle hierarchical knowledge to derive more general hypotheses to drive biomedicine.

The purpose of this study was to detect mind-wandering experienced by pre-service teachers while learning video lecture on physics. The lecture was videotaped and consisted of a live lecture in a classroom. The lecture was about Gauss's law on physics. We investigated whether oculomotor data and eye movements could be used as a marker to indicate the learner’s mind-wandering. Each data was collected in a study in which 24 pre-service teachers (16 females and 8 males) reported self-caught mind-wandering while learning physics video lecture during30 minutes. A Tobii Pro Spectrum (sampling rate: 300Hz) was used to capture their eye-gaze during learning Gauss's law course video. After watching video lecture, we interviewed pre-service teachers about their mind-wandering experience. We first used the self-caught method to capture the mind-wandering timing of pre-service teachers while learning from video lectures. We detected more accurate mind-wandering segments by comparing fixation duration and saccade count. We investigated two types of oculomotor data (blink count, pupil size) and nine eye movements (average peak velocity of saccades; maximum peak velocity of saccades; standard deviation of peak velocity of saccades; average amplitude of saccades; maximum amplitude of saccades; total amplitude of saccades; saccade count/s; fixation duration; fixation dispersion). The result was that the blink count could not be used as a marker for mind-wandering during learning video lectures among them (oculomotor data and eye movements), unlike previous literatures. Based on the results of this study, we identified elements that can be used as mind-wandering markers while learning from video lectures that are similar to real classes, among the oculomotor data and eye movement mentioned in previous literatures. Also, we found that most participants focused on past thoughts and felt unpleasant after experiencing mind-wandering through interview analysis.

Automated spectrum analysis serves as a troubleshooting tool that helps to diagnose faults in wireless networks like difficult signal propagation conditions and coexisting wireless networks. It provides a higher monitoring coverage while requiring less expertise compared to manual spectrum analysis. In this paper, we introduce a data set that can be used to train and evaluate deep learning models, capable of detecting frames from different wireless standards as well as interference between single frames. Since manually labelling a high variety of frames in different environments is too challenging, an artificial data generation pipeline has been developed. The data set consists of 20 000 augmented signal segments, each containing a random number of different Wi-Fi and Bluetooth frames, their spectral image representations and labels that describe the position and type of frame within the spectrogram. The data set contains results of intermediate processing steps that enables the research or teaching community to create new data sets for specific requirements or to provide new interesting examination examples.

In this work, a hybrid component Fault Detection and Diagnosis (FDD) approach for industrial sensor systems is established and analyzed, to provide a hybrid schema that combines the advantages and eliminates the drawbacks of both model-based and data-driven methods of diagnosis. Moreover, it shines the light on a new utilization of Random Forest (RF) together with model-based diagnosis, beyond its ordinary data-driven application. RF is trained and hyperparameter tuned using three-fold cross validation over a random grid of parameters using random search, to finally generate diagnostic graphs as the dynamic, data-driven part of this system. This is followed by translating those graphs into model-based rules in the form of if-else statements, SQL queries or semantic queries such as SPARQL, in order to feed the dynamic rules into a structured model essential for further diagnosis. The RF hyperparameters are consistently updated online using the newly generated sensor data to maintain the dynamicity and accuracy of the generated graphs and rules thereafter. The architecture of the proposed method is demonstrated in a comprehensive manner, and the dynamic rules extraction phase is applied using a case study on condition monitoring of a hydraulic test rig using time-series multivariate sensor readings.

In this work, A hybrid component Fault Detection and Diagnosis (FDD) approach for industrial sensor systems is established and analyzed, to provide a hybrid schema that combines the advantages and eliminates the drawbacks of both model-based and data-driven methods of diagnosis. Moreover, spotting the light on a new utilization of Random Forest (RF) together with model-based diagnosis, beyond its ordinary data-driven application. RF is trained and hyperparameter tuned using 3-fold cross-validation over a random grid of parameters using random search, to finally generate diagnostic graphs as the dynamic, data-driven part of this system. Followed by translating those graphs into model-based rules in the form of if-else statements, SQL queries or semantic queries such as SPARQL, in order to feed the dynamic rules into a structured model essential for further diagnosis. The RF hyperparameters are consistently updated online using the newly generated sensor data, in order to maintain the dynamicity and accuracy of the generated graphs and rules thereafter. The architecture of the proposed method is demonstrated in a comprehensive manner, as well as the dynamic rules extraction phase is applied using a case study on condition monitoring of a hydraulic test rig using time series multivariate sensor readings.

The paper presents the design and the implementation of different advanced control strategies that are applied to a nonlinear model of a thermal unit. A data–driven grey–box identification approach provided the physically meaningful nonlinear continuous–time model, which represents the benchmark exploited in this work. The control problem of this thermal unit is important since it constitutes the key element of passive air conditioning systems. The advanced control schemes analysed in this paper are used to regulate the outflow air temperature of the thermal unit by exploiting the inflow air speed, whilst the inflow air temperature is considered as an external disturbance. The reliability and robustness issues of the suggested control methodologies are verified with a Monte–Carlo analysis for simulating modelling uncertainty, disturbance and measurement errors. The achieved results serve to demonstrate the effectiveness and the viable application the suggested control solutions to air conditioning systems. The benchmark model represents one of the key issues of this study, which is exploited for benchmarking different model–based and data–driven advanced control methodologies through extensive simulations. Moreover, this work highlights the main features of the proposed control schemes, while providing practitioners and heating, ventilating and air conditioning engineers with tools to design robust control strategies for air conditioning systems.

Deep learning dominates automated animal activity recognition (AAR) tasks due to the high performance on large-scale datasets. However, constructing centralised data across diverse farms raises data privacy issues. Federated learning (FL) provides a distributed learning solution to train a shared model by coordinating multiple farms (clients) without sharing their private data. Whereas directly applying FL to AAR tasks often faces two challenges: client-drift during local training and gradient conflicts during global aggregation. In this study, we develop a novel FL framework called FedAAR to achieve AAR with sensor data. Specifically, we devise a prototype-guided local update module to alleviate the client-drift issue, which introduces global prototypes as shared knowledge to force clients to learn consistent features. To reduce gradient conflicts between clients, we design a gradient refinement-based aggregation module to eliminate conflicting components between client gradients during global aggregation, thereby improving the agreement between clients. Experiments are conducted on a public dataset to verify FedAAR’s effectiveness, which consists of 87,621 2-s motion data. The results demonstrate that FedAAR outperforms state-of-the-arts, with precision (75.23%), recall (75.17%), F1-score (74.70%), and accuracy (88.88%), respectively. The ablation experiments also show FedAAR’s robustness against various factors (i.e., different data sizes, communication frequency, and client numbers).

This research aims to explore factors that influence sustainable music learning system from psychological perspective, and innovatively constructs a combination of qualitative and quantitative approaches. For first time, combines nonlinear system and identifies relevant factors affecting music learning by establishing data system for questionnaire answering and a quantitative model for actual academic performance. Existing research mainly looks at several factors that affect fragmented music learning system from perspective of teachers' teaching rules, emphasizing phased teaching state and learning goals of teachers as main body, thus ignoring music learning students, who are a large group of music learning objects. The research fills gap in this type of research object, focusing on sustainable music learning system from emotional perspective and students who occupy a dominant position in music learning, so as to more accurately explore impact of their emotional influencing factors on music learning system. The most prominent innovation of this study lies in construction of stochastic nonlinear system for psychological influencing factors of student music learning and a quantitative model for actual learning effect. Through analysis of nonlinear system, weight values of several negative emotions on music learning system are obtained. The comprehensive impact of emotional factors and practical learning on music learning system can be obtained by weighting them together.

Despite the importance of few-shot learning, the lack of labeled training data in the real world, makes it extremely challenging for existing machine learning methods as this limited data set does not represent the data variance well. In this research, we suggest employing a generative approach using variational autoencoders (VAEs), which can be used specifically to optimize few-shot learning tasks by generating new samples with more intra-class variations. The purpose of our research is to increase the size of the training data set using various methods to improve the accuracy and robustness of the few-shot face recognition. Specifically, we employ the VAE generator to increase the size of the training data set, including the basic and the novel sets while utilizing transfer learning as the backend. Based on extensive experimental research, we analyze various data augmentation methods to observe how each method affects the accuracy of face recognition. We conclude that the face generation method we proposed can effectively improve the recognition accuracy rate to 96.47% using both the base and the novel sets.

In a dynamic and rapidly changing world, customers’ often conflicting demands plus fluid economic requirements, often driven by geo-politics, have continued to evolve, out-striping the capability of existing production systems. With its inherent shortcomings, the traditional factory has proven to be incapable of addressing these modern-day manufacturing challenges. Recent advancements in Industry 4.0 have catalyzed the development of new manufacturing paradigms (or smart factory visions) under different monikers (e.g., Smart factory, Intelligent factory, Digital factory, Cloud-based factory etc.) would help fix these challenges. Due to a lack of consensus on a general nomenclature for these manufacturing paradigms, the term Future Factory (or Factory of the Future) is here used as a collective euphemism, without prejudice. The Future Factory constitutes a creative convergence of multiple technologies, techniques and capabilities that represent a significant change in current production capabilities, models, and practices. It is a data-driven manufacturing approach and system that harnesses intelligence from multiple information streams i.e., assets (including people), processes, and subsystems to help create new forms of production efficiency and flexibility. Serving both as a review monograph and reference companion, this paper details the meanings, characteristics, and technological underpinnings of the Future Factory. It also elucidates on the architectural models that guide the structured deployment of these modern factories with particular emphasis on three advanced communication technologies capable of speeding up advancements in the field. It not only highlights the relevance of communication between assets but also lays out mechanisms to achieve these interactions using the Administration shell. Finally, the paper also discusses the key enabling technologies that are typically embedded into bare bone factories to help improve their visibility, resilience, intelligence, and capacity, in addition to how these technologies are being deployed and to what effect. At the onset of the study, we were interested in developing a monograph which would serve as a comprehensive but concise review of general principles, fundamental concepts, major characteristics, key building blocks and implementation guidelines for the Future Factory within the overall context of the manufacturing ecosystem, in the age of Industry 4.0. Our hope is that this paper would enrich the extant literature on advanced manufacturing, help shape policy and research, and provide insights on how some of the identified pathways can be diffused into industry.

Genomics involving tens of thousands of genes is a complex system determining phenotype. An interesting and vital issue is that how to integrate highly sparse genetic genomics data with a mass of minor effects into prediction model for improving prediction power. We find that deep learning method can work well to extract features by transforming highly sparse dichotomous data to lower dimensional continuous data in a non-linear way. This idea may provide benefits in risk prediction based on genome-wide data associated e.g. integrating most of the information in the genotype data. Hence, we developed a multi-stage strategy to extract information from highly sparse binary genotype data and applied it for risk prediction. Specifically, we first reduced the number of biomarkers via a univariable regression model to a moderate size. Then a trainable auto-encoder was used to extract compact representations from the reduced data. Next, we performed a LASSO problem process over a grid of tuning parameter values to select the optimal combination of extracted features. Finally, we applied such feature combination to two prognostic models, and evaluated predictive effect of the models. The results of simulation studies and real data applying indicated that these highly compressed transformation features could better improve predictive performance and did not easily lead to over-fitting.

This study addressed the need for efficient data collection in micro-mobility using low-end hardware, focusing on developing a system capable of handling large real-time data streams. We proposed a novel data collection system that leverages incremental learning techniques, enabling AI-based services for micro-mobility passengers through smartphones. Our approach utilizes 3-axis acceleration sensors integrated into micro-mobility devices, collecting motion data in real-time. This data is processed through an incremental learning pre-processing server, employing the Broad Learning System algorithm, to ensure robust performance in noisy, real-world environments. The use of incremental learning is pivotal, allowing our system to adapt continuously to new data, enhancing the accuracy and relevance of the AI services provided to passengers. This research not only advances the technical capabilities in micro-mobility data handling but also has the potential to enhance the overall passenger experience through improved AI-based services.

Cable-Driven Parallel Robots (CDPRs) are a special kind of parallel manipulator which use cables to control the position and orientation of the mobile platform or end-effector. The usage of cables instead of rigid links offer some advantages over their conventional rigid counterparts. As cables can only pull, but not push, the number of cables (n) required to command the end-effector is always n+1. This configuration is known as fully-constrained and it is the most extended configuration for CDPRs. Although CDPRs have many advantages, such as their ability to cover large working areas, one of their main problems is that their working area (workspace) is limited in comparison to its frame area (planar case), or frame volume (spatial case), due to the minimum and maximum allowed tensions. Depending of these tensions values the workspace can be notoriously decreased. In order to tackle this problem, lots of works focus on solving kinematics or dynamics problems for cable sagging, i.e., they take into account sagging when modelling the robot kinematic and include these poses inside the usable robot workspace. Taking into account phenomenons like this increases the mathematical complexity of the problem, and much more complex techniques are required. On the other hand, the lack of workspace problem can be tackled by adding active or passive elements to the robot design. In this sense, this paper proposes two mechanical modifications: to add passive carriages to the robot frame and to use a single cable loop to command the end-effector position and orientation. This work presents the kinematic, static and dynamic models of the novel design and shows the gain of workspace for a planar case while taking into account different parameters of the robot.

This paper uses the spatial analysis software GeoDa as a tool, takes GRP (Gross regional product) of Sichuan Province in 2012 and 2018 as the dependent variable, and takes the city (autonomous prefecture) factor-driven, investment-driven and innovation-driven indicators as the dependent variable to explore the impact of innovation activities on regional economic development and the spatial distribution characteristics of regional economy. Through the comparison of the global correlation and local correlation, this paper explores the crux of the regional economic polarization and unbalanced development, and puts forward some measures to solve the existing economic development problems, such as cultivating and improving the regional industrial dependence, accelerating the regional transportation accessibility and convenience, and constructing the regional collaborative innovation system, So as to achieve the strategic goal of the construction of innovative Province in Sichuan Province.

While machine learning (ML) has been quite successful in the field of structural health monitoring (SHM), its practical implementation has been limited. This is because ML model training requires data containing a variety of distinct damaged instances captured from a real structure and the experimental generation of such data is challenging. One way to tackle this issue is by generating training data through numerical simulations. However, simulated data cannot capture the bias and variance of experimental uncertainty. To overcome this problem, this work proposes a deep learning-based domain transformation method for transforming simulated data to the experimental domain. Use of this technique has been demonstrated for debonding location and size prediction of stiffened panels using a vibration-based method. The results are satisfactory for both, debonding location and size prediction. This domain transformation method can be used in any field where experimental data for training machine learning models is scarce.

The novel coronavirus disease (COVID-19) pandemic is provoking a prevalent consequence on mental health because of less interaction among people, economic collapse, negativity, fear of losing jobs, and death of the near and dear ones. To express their mental state, people often are using social media as one of the preferred means. Due to reduced outdoor activities, people are spending more time on social media than usual and expressing their emotion of anxiety, fear, and depression. On a daily basis, about 2.5 quintillion bytes of data are generated on social media, analyzing this big data can become an excellent means to evaluate the effect of COVID-19 on mental health. In this work, we have analyzed data from Twitter microblog (tweets) to find out the effect of COVID-19 on peoples mental health with a special focus on depression. We propose a novel pipeline, based on recurrent neural network (in the form of long-short term memory or LSTM) and convolutional neural network, capable of identifying depressive tweets with an accuracy of 99.42%. Preprocessed using various natural language processing techniques, the aim was to find out depressive emotion from these tweets. Analyzing over 571 thousand tweets posted between October 2019 and May 2020 by 482 users, a significant rise in depressing tweets was observed between February and May of 2020, which indicates as an impact of the long ongoing COVID-19 pandemic situation.

In the extensive monitoring of maritime traffic, maritime management frequently encounters incomplete automatic identification system (AIS) data, particularly in critical static fields like vessel types. This shortfall presents substantial challenges in safety management, necessitating robust methods for data completion. Distinct from road traffic, where road width imposes constraints, maritime vessels of identical classifications often choose significantly divergent routes, deviating by several nautical miles. Sole dependence on trajectory clustering is insufficient. Addressing this issue, we segments the maritime area into spatiotemporal grids, transforming vessel paths into sequences of grid encodings. Utilizing natural language processing techniques, we integrate the Word2vec word embedding approach with our novel biLSTM self-attention chunk-max pooling net (biSAMNet) model, enhancing the classification of vessel trajectories. This method is crucial for determining static details like vessel types. Employing the Taiwan Strait as a case study and benchmarking against CNN, RNN, and methods based on the attention mechanism, our findings underscore our model’s superiority. The biSAMNet achieves an impressive vessel classification F1 score of 0.94, using only 5-dimensional word embeddings, highlighting the effectiveness of Word2vec pre-trained embedding layers. This research introduces a novel paradigm for processing vessel trajectory data, greatly enhancing the accuracy of filling in incomplete vessel type details.

The research proposes a self-directed paradigm with self-design using the existing technology with LMS modules, discussions, and self-tests. The research establishes its criteria for assurance of teaching and learning known as 7x2C for the compliance of content, and appearance along with other criteria for the analysis. The above technology of web and LMS is tested for a business course that is technology-oriented in creating an experiential learning system for Covid-19 awareness. Similarly, among other ideas, an environment for educating learners about diabetes and obesity has been designed. The project is known as Sunchoke with its theme of Grow, Eat, and Heal. The educators can use their technology and apply self-directed pedagogy to transform this approach to their customized ways by using their content and rubrics.

Electricity demand forecasting plays a significant role in energy markets. Accurate prediction of electricity demand is the key factor to optimize power generation, consumption, saving energy resources, and determining the energy prices. However, integrating energy mix scenarios, including solar and wind power which are highly non-linear and seasonal, into an existing grid increases uncertainty in generation, adds the challenges for precise forecast. To tackle these challenges, state-of-the-art methods and algorithms have been implemented in literature. We have developed Artificial Intelligence (AI) based deep learning models that can effectively handle the information of long time-series data. Based on the pattern of dataset, four different scenarios were developed and two best scenarios were selected for prediction. Dozens of models were developed and tested in deep AI networks. In the first scenario (Scenario1), data for weekdays excluding holidays was taken and in the second scenario (Scenario2) all the data in the basket was taken. Remaining two scenarios, weekends and holidays were tested and neglected because of their high prediction error. To find the optimal configuration, models were trained and tested within a large space of alternatives called hyper-parameters. In this study, an Aritificial Neural Network (ANN) based Feed-forward Neural Network (FNN) showed the minimum prediction error for Scenario1 while a Recurrent Neural Network (RNN) based Gated Recurrent Network (GRU) showed the minimum prediction error for Scenario2. While comparing the accuracy, the lowest MAPE of 2.47% was obtained from FNN for Scenario1. When evaluating the same testing dataset (non-holidays) of Scenario2, the RNN-GRU model achieved the lowest MAPE of 2.71%. Therefore, we can conclude that grouping of weekdays as Senario1 prepared by excluding the holidays provides better forecasting accuracy compared to the single group approach used in Scenario2, where all the dataset is considered together. However, Scenario2 is equally important to predict the demand for weekends and holidays.

This paper establishes methods that quantify the structure of statistical interactions within a given data set using the characterization of information theory in cohomology by finite methods, and provides their expression in terms of statistical physic and machine learning. Following [1–3], we show directly that k multivariate mutual-informations (I_k) are k-coboundaries. The k-cocycles are given by I_k = 0, which generalize statistical independence to arbitrary dimension k. The topological approach allows to investigate Shannon’s information in the multivariate case without the assumptions of independent identically distributed variables. We develop the computationally tractable subcase of simplicial information cohomology represented by entropy H_k and information I_k landscapes. The I₁ component defines a self-internal energy functional U_k, and (−1)^k I_k,k≥2 components define the contribution to a free energy functional G_k of the k-body interactions. The set of information paths in simplicial structures is in bijection with the symmetric group and random processes, provides a topological expression of the 2nd law and points toward a discrete Noether theorem (1st law). The local minima of free-energy, related to conditional information negativity and the non-Shannonian cone of Yeung [4], characterize a minimum free energy complex. This complex formalizes the minimum free-energy principle in topology, provides a definition of a complex system, and characterizes a multiplicity of local minima that quantifies the diversity observed in biology. Finite data size effects and estimation bias severely constrain the effective computation of the information topology on data, and we provide simple statistical tests for the undersampling bias and for the k-dependences following [5]. We give an example of application of these methods to genetic expression and cell-type classification. The maximal positive I_k identifies the variables that co-vary the most in the population, whereas the minimal negative I_k identifies clusters and the variables that differentiate-segregate the most. The methods unravel biologically relevant I₁₀ with a sample size of 41. It establishes generic methods to quantify the epigenetic information storage and a unified epigenetic unsupervised learning formalism.

Fabry-Pérto (FP) cavity is the essential component of ultra-stable laser (USL) for gravitational wave detection, which couples multi-physic (Optical/Thermal/Mechanics) fields and requires ultra-high precision. To satisfy the requirements of precise and efficient design, a multi-physic coupling optimization method for fixing cubic FP cavity based on data learning is proposed. A multi-physic model for the cubic FP cavity is established and the performance is obtained by finite element analysis. The key performance indices (V, wF, wF) and key design variables (d, l, F) are determined considering the features of the FP cavity. The 49 sets of data by orthogonal experiment are acquired for the establishment and comparison of different data learning models (NN, RSF, KRG). The result turns out that the neural network has the best performance. Based on NSGA-II, the Pareto optimal front is obtained and the optimal combination of design variables is finally determined as {5,32,250}. The performance after optimization has proven to be a great improvement, of which the displacement under the fixing force and vibration test are decreased by more than 60%. The optimization strategy can not only help the design of the FP cavity but also enlighten other optimization fields.

Development of supervised AI algorithms requires a large amount of labeled images. Image labelling is both time-consuming and expensive. Therefore, we explored the value of e-learning derived annotations for AI algorithm development in medical imaging. Methods We have developed an e-learning platform that involves image-based single click labelling as part of the educational learning process. Ten radiology residents, as part of their residency training, trained the recognition of pneumothorax on 1161 chest X-rays in posterior-anterior projection. Using this data, multiple AI algorithms for detecting pneumothorax were developed. Classification and localization performance of the models was tested on an independent internal testing dataset and on the public NIH ChestX-ray14 dataset. Results The AI models F1 scores on the internal and the NIH dataset were 0.87 and 0.44, respectively. Sensitivity was 0.85 and 0.80 for classification and specificity 0.96 and 0.48 for classification. F1 scores were 0.72 and 0.66, sensitivity 0.72 and 0.72. False positive rate was 0.36 and 0.32 for localisation. Conclusion Our results demonstrated that e-learning derived annotations are a valuable data source for algorithm development. Further work is needed to include additional parameters such as user performance, consensus of diagnosis, and quality control in the development pipeline.

Polarimetric features extracted from polarimetric synthetic aperture radar (PolSAR) images contain abundant scattering information of objects. Utilizing this information for PolSAR image classification can improve accuracy and enhance object monitoring. Although significant progress has been achieved in related research, there are still issues such as insufficient utilization of polarimetric information and features. In this paper, a deep learning classification method based on polarimetric channel power features for PolSAR is proposed. The distinctive characteristic of this method is that the polarimetric features inputted into the deep learning network are the power values of polarimetric channels, where these channels are treated equivalently and contain complete polarimetric information. In terms of experimental comparative study, besides polarimetric power combinations, three different data input schemes were employed as data for the input end of the convolutional neural network (CNN), taking into account existing research. The neural networks utilizes the extracted polarimetric features to classify images, and the classification accuracy analysis is employed to compare the strengths and weaknesses of different input schemes. It is worth mentioning that the polarized characteristics of the data input scheme mentioned in this article have been derived through rigorous mathematical deduction, and each polarimetric feature has clear physical meaning. By testing different data input schemes on the Gaofen-3 (GF-3) PolSAR image, the experimental results show that the method proposed in this article outperforms existing methods and can improve the accuracy of classification to a certain extent, validating the effectiveness of this method in large-scale area classification.

The separation of Li+ and [Bmim]+(1-Butyl-3-methylimidazolium) by electrically driven membrane technology was studied. The effects of the types and modification processes of cation exchange membranes, current density, total cation concentration, temperature, and anion types on separation efficiency were investigated. The results indicated that it is feasible to achieve efficient separation of Li+ and [Bmim]+ using the selectivity of cation exchange membranes under electric field. Membrane CMX and the modified membrane A and B which obtained from the CMX showed obvious selective of Li+ from [Bmim]+. When the current density is 5 mA/cm2 and the feed concentrations of Li+ and [Bmim]+ are 0.3 mol/L and 0.2 mol/L, the selective transport coefficient of the modified membrane B can reach 6.2 in the first 120 minutes of the process. Reducing current density and increasing total cation concentration can improve separation efficiency. Lowering the temperature can improve the separation effect, but improvement is not obviously. Changing the anion of the feed from chloride ion to acetate has no effect on the separation.

Digital filtering is a fundamental technique in digital signal processing, which operates on a digital sequence without any information on how the sequence was generated. This paper proposes a methodology for designing the equivalent of digital filtering for neuromorphic samples, which are a low power alternative to conventional digital samples. In the literature, filtering using neuromorphic samples is done by filtering the reconstructed analog signal, which is required to belong to a predefined input space. We show that this requirement is not necessary, and introduce a new method for computing the neuromorphic samples of the filter output directly from the input samples, backed by theoretical guarantees. We show numerically we can achieve a similar accuracy compared to the conventional method. However, given that we bypass the analog signal reconstruction step, our results show significantly reduced computation time for the proposed method and good performance even when signal recovery is not possible.

Cable interference in cable-driven mechanisms (CDM) is a major challenge in their applications. The wrench closure workspace (WCW) in a fully constrained mechanism may not be realized unless cable interference is considered. This paper classifies all possible types of cable interferences for planar cable-driven mechanisms and presents an analytical solution to find the boundaries of the constant-orientation interference region. It is shown that interference between cables starts and ends when one end of a cable coincides with another cable which can be thought as lying a point on a line segment. This geometrical view is developed and applied to provide a framework for the analysis of cable interference. By subtracting the interference space form WCW, the interference-free workspace is obtained in which the robot is able to operate.

To assist Java programming learning of novice students, we have developed the web-based Java programming learning assistant system (JPLAS). JPLAS provides several types of exercise problems to cultivate code reading/writing skills at various levels. In JPLAS, the code writing problem (CWP) asks a student to write a source code that will pass the test code given in the assignment where the correctness is verified by running them on JUnit. In this paper, to reduce the teacher load at marking process, we present the answer code validation program that verifies all the source codes from a lot of students for each assignment at a time and reports the number of passing tests for each source code in the CSV file. Besides, to test a source code with various input data, we implement the test data generation algorithm that identifies the data type, generates a new data, and replaces it for each test data in the test code. Furthermore, to verify the correctness of the implemented procedure in the source code, we introduce the intermediate state testing in the test code. For evaluations, we applied the proposal to source codes and test codes in a Java programming course in Okayama university, Japan, and confirmed the validity and effectiveness.

Age estimation in dental radiographs Orthopantomography (OPG) is a medical imaging technique that physicians and pathologists utilise for disease identification and legal matters. For example, for estimating post-mortem interval, detecting child abuse, drug trafficking, and identifying an unknown body. Recent development in automated image processing models improved the age estimation's limited precision to an approximate range of +/- one year. While this estimation is often accepted as accurate measurement, age estimation should be as precise as possible in most serious matters, such as homicide. Current age estimation techniques are highly dependent on manual and time-consuming image processing. Age estimation is often a time-sensitive matter in which the image processing time is vital. Recent development in Machine learning-based data processing methods has decreased the imaging time processing; however, the accuracy of these techniques remains to be further improved. We proposed an ensemble method of image classifiers and transfer learning techniques to enhance the accuracy of age estimation using OPGs from one year to a couple of months (1-3-6). This hybrid model is based on convolutional neural networks (CNN) and K nearest neighbours (KNN). The hybrid (HCNN-KNN) model was used to investigate 1,922 panoramic dental radiographs of patients aged 15 to 23. These OPGs were obtained from the various teaching institutes and private dental clinics in Malaysia. To minimise the chance of overfitting in our model, we used the principal component analysis (PCA) algorithm and eliminated the features with high correlation. To further enhance the performance of our hybrid model, we performed systematic image pre-processing. We applied a series of classifications to train our model. We have successfully demonstrated that combining these innovative approaches has improved the classification and segmentation and thus the age-estimation outcome of the model. Our findings suggest that our innovative model, for the first time, to the best of our knowledge, successfully estimated the age in classified studies of one year old, six months, three months and one-month-old cases with accuracies of 99.98, 99.96, 99.87, and 98.78 respectively.

Deep learning has been applied in many areas that have had a significant impact on applications that improves real-life challenges. The success of deep learning in a wide range of areas is due in part to the use of activation functions, which are particularly effective at solving non-linear problems. Activation functions are a key focus for researchers in artificial intelligence who aim to improve the performance of neural networks. This article provides a comprehensive explanation and comparison of different activation functions, with a focus on the arc tangent and its variations specifically. The paper presents experimental results that show that variations of the arc tangent using irrational numbers such as pi, the golden ratio, and Euler’s number, as well as a self-arctan function, produce promising results. Since we experimented with promising activation functions on two different problems, and datasets, we reached a result that different irrationals work well for different problems. In other words, arctan ϕ gives the best results mostly for multiclass classification and arctan e gives the best results for time series prediction problems. The paper focuses on a multiclass classification problem applied to the Reuters Newswire dataset and a time-series prediction problem on Türkiye energy trade value to show the impacts of activation functions.

Addressing the urgent sustainability challenges in the wine industry, this study explores the efficacy of sustainability-oriented innovations (SOIs) and smart farming technologies (SFTs) across wine value chains in Cyprus and Italy. Employing KPIs for a rigorous assessment, the research delves into the environmental, economic, and social impacts of these technologies. In Cyprus (SIP7), the integration of digital labelling and smart farming solutions led to a substantial reduction in pesticide usage by up to 75% and enhanced the perceived quality of wine by an average of 8%. Italy's SIP10 witnessed a 33.4% decrease in greenhouse gas emissions, with an additional benefit of a 5.3% improvement in intrinsic product quality. Notably, SIP10 also introduced a carbon credit system, potentially generating an average annual revenue of €4,140 per farm. These findings highlight the transformative potential of SOIs and SFTs in promoting sustainable practices within the wine industry, demonstrating significant advancements in reducing environmental impact, improving product quality, and enhancing economic viability. The study underscores the critical role of innovative technologies in achieving sustainability goals and provides a compelling case for wider adoption within the agricultural sector.

Deep learning has been applied in many areas that have had a significant impact on applications that improves real-life challenges. The success of deep learning in a wide range of areas is due in part to the use of activation functions, which are particularly effective at solving non-linear problems. Activation functions are a key focus for researchers in artificial intelligence who aim to improve the performance of neural networks. This article provides a comprehensive explanation and comparison of different activation functions, with a focus on the arc tangent and its variations specifically. The paper presents experimental results that show that variations of the arc tangent using irrational numbers such as pi, the golden ratio, and Euler’s number, as well as a self-arctan function, produce promising results. Since we experimented with promising activation functions on two different problems, and datasets, we reached a result that different irrationals work well for different problems. In other words, arctan ϕ gives the best results mostly for multiclass classification and arctan e gives the best results for time series prediction problems. The paper focuses on a multi-class classification problem applied to the Reuters Newswire dataset and a time-series prediction problem on Türkiye energy trade value to show the impacts of activation functions.

To make wind power more competitive, it is necessary to reduce turbine downtime and reduce costs associated with wind turbine Operation and Maintenance (O&M). Incorporating machine learning in developing condition-based predictive maintenance methodologies for wind turbines can enhance their efficiency and reliability. This paper presents a monitoring method that utilizes Base Density for the Support Vector Machine (BDSVM) and the evolutionary Fourier spectra of vibrations. This method allows smart monitoring of the function evolution of the turbine. A complex optimal function (FO) for 5-degree order has been developed that will be the boundary function of the BDSVM to timely determine the magnitude, frequency, and place of the failure occurring in wind turbine drive.