In Ultra-wideband (UWB)-based wireless ranging or distance measurement, differentiation between line-of-sight~(LOS), non-line-of-sight~(NLOS), and multi-path (MP) conditions are important for precise indoor localization. This is because the accuracy of the reported measured distance in UWB ranging systems is directly affected by the measurement conditions (LOS, NLOS or MP). However, the major contributions in literature only address the binary classification between LOS and NLOS in UWB ranging systems. The MP condition is usually ignored. In fact, the MP condition also has a significant impact on the ranging errors of the UWB compared to the direct LOS measurement results. Though, the magnitudes of the error contained in MP conditions are generally lower than completely blocked NLOS scenarios. This paper addresses machine learning techniques for identification of the mentioned three classes (LOS, NLOS, and MP) in the UWB indoor localization system using an experimental data-set. The data-set was collected in different conditions at different scenarios in indoor environments. Using the collected real measurement data, we compare three machine learning (ML) classifiers, i.e., support vector machine (SVM), random forest (RF) based on an ensemble learning method, and multilayer perceptron (MLP) based on a deep artificial neural network, in terms of their performance. The results show that applying ML methods in UWB ranging systems are effective in identification of the above-mentioned three classes. In specific, the overall accuracy reaches up to 91.9% in the best-case scenario and 72.9% in the worst-case scenario. Regarding the F1-score, it is 0.92 in the best-case and 0.69 in the worst-case scenario. For reproducible results and further exploration, we (will) provide the publicly accessible experimental research data discussed in this paper at PUB - Publications at Bielefeld University. The evaluations of the three classifiers are conducted using the open-source python machine learning library scikit-learn.

The real estate market is exposed to many fluctuations in prices, because of existing correlations with many variables, some of which cannot be controlled or might even be unknown. Housing prices can increase rapidly (or in some cases, also drop very fast), yet the numerous listings available online where houses are sold or rented are not likely to be updated that often. In some cases, individuals interested in selling a house (or apartment) might include it in some online listing, and forget about updating the price. In other cases, some individuals might be interested in deliberately setting a price below the market price in order to sell the home faster, for various reasons. In this paper we aim at developing a machine learning application that identifies opportunities in the real estate market in real time, i.e., houses that are listed with a price substantially below the market price. This program can be useful for investors interested in the housing market. We have focused in a use case considering real estate assets located in the Salamanca district in Madrid (Spain) and listed in the most relevant Spanish online site for home sales and rentals. The application is formally implemented as a regression problem, that tries to estimate the market price of a house given features retrieved from public online listings. For building this application, we have performed a feature engineering stage in order to discover relevant features that allows attaining a high predictive performance. Several machine learning algorithms have been tested, including regression trees, $k$-nearest neighbors, support vector machines and neural networks, identifying advantages and handicaps of each of them.

Artificial Intelligence (AI) has the power to generate scenarios and make predictions through the use of advanced algorithms and machine learning techniques. OpenAI’s GPT-3 AI is a state-of-the-art language model that has been trained on a large dataset of text, which allows it to generate hu-man-like text, and it can generate scenarios for different fields. However, GPT-3 was trained on data available up until June 2021, had no access to more recent data nor was connected to the internet. In this study, we investigated the capability of OpenAI’s GPT-3 AI to predict the Ukrainian war es-calation, which started in 2022 and had massive geopolitical effects. We used GPT-3´s capability to generate future scenarios, to check those scenarios for internal consistency, and to create a proba-bility estimate. The results showed that although GPT-3 described an open war as one of the low probability scenarios, its capability on predicting the future was limited. Furthermore, it became evident that checking internal consistency of the generated scenarios could be improved. We ap-preciated GPT-3 as very useful and powerful for generating future scenarios, but also concluded that its prediction capabilities of real-world events are limited, should be used with caution, and require further development.

Skin image analysis using artificial intelligence (AI) has recently attracted significant research interest, particularly for analyzing skin images captured by mobile devices. Acne is one of the most common skin conditions with profound effects in severe cases. In this study, we developed an AI system called AcneDet for automatic acne object detection and acne severity grading using facial images captured by smartphones. AcneDet includes two models for conducting two tasks: (1) a Faster R-CNN-based deep learning model for the detection of acne lesion objects of four types including blackheads/whiteheads, papules/pustules, nodules/cysts, and acne scars; and (2) a LightGBM machine learning model for grading acne severity using the Investigator’s Global Assessment (IGA) scale. The output of the Faster R-CNN model, i.e., the counts of each acne type, were used as input for the LightGBM model for acne severity grading. A dataset consisting of 1,572 labeled facial images captured by both iOS and Android smartphones was used for training. The results show that the Faster R-CNN model achieves a mAP of 0.54 for acne object detection. The mean accuracy of acne severity grading by the LightGBM model is 0.85. With this study, we hope to contribute to the development of artificial intelligent systems that are able to help acne patients understand more about their conditions and support doctors in acne diagnosis.

Document deskewing is a fundamental problem in document image processing. While existing methods have limitations, such as Hough Line Transformation that can deskew images upside down, and Deep Learning models that require huge amounts of human labour and computational resources and still fail to deskew while taking care of orientation, OCR-based methods also struggle to read text when it is tilted. In this paper, we propose a novel, simple, cost-effective deep learning method for fixing the skew and orientation of documents. Our approach reduces the search space for the machine learning model to predict whether an image is upside down or not, avoiding the huge search space of predicting an angle between 0 and 360. We finetuned a MobileNetV2 model, which was pre-trained on imagenet, using only 200 images and achieve good results. This method is useful for automation-based tasks, such as data extraction using OCR technology, and can greatly reduce manual labour.

Classification of human actions from uni-modal and multi-modal datasets is an ongoing research problem in computer vision. This review is aimed to scope current literature on data-fusion and action-recognition techniques and to identify gaps and future research direction. Success in producing cost-effective and portable vision-based sensors has dramatically increased the number and size of datasets. The rise in number of action recognition datasets intersects with advances in deep-learning architectures and computational support, both of which offer significant research opportunities. Naturally, each action-data modality - such as RGB, depth, skeleton, and infrared - has distinct characteristics; therefore, it is important to exploit the value of each modality for better action recognition. In this article we will focus solely on areas such as data fusion and recognition techniques in the context of vision with a uni-modal and multi-modal perspective. We conclude by discussing research challenges, emerging trends, and possible future research directions.

Vibration measurement serves as the basis for various engineering practices such as natural frequency or resonant frequency estimation. As image acquisition devices become cheaper and faster, vibration measurement and frequency estimation through image sequence analysis continue to receive increasing attention. In the conventional photogrammetry and optical methods of frequency measurement, vibration signals are first extracted before implementing the vibration frequency analysis algorithm. In this work, we demonstrated that frequency prediction can be achieved using a single feed-forward convolutional neural network. The proposed method is verified using a vibration signal generator and excitation system, and the result obtained was compared with that of an industrial contact vibrometer in a real application. Our experimental results demonstrate that the proposed method can achieve acceptable prediction accuracy even in unfavorable field conditions.

This paper examines the potential of Artificial Intelligence (AI) to address societal megatrends, with a specific focus on OpenAI’s Generative Pre-Trained Transformer 3 (GPT-3). To do this, we con-ducted an analysis using GPT-3 in order to explore the benefits of AI for digitalization, urbanization, globalization, climate change, automation and mobility, global health issues and aging population. We also looked at emerging markets as well as sustainability in this study. Interaction with GPT-3 was done solely through prompt questions and generated responses were analyzed. Our results indicate that AI can significantly improve our understanding of these trends by providing insights into how they develop over time and what solutions could be implemented. Further research is needed to determine how effective AI will be in addressing them successfully but initial findings are encouraging. Our discussion focuses on the implications of our findings for society going forward and suggests that further investigation should be done into how best to utilize new technologies like GPT-3 when tackling these challenges. Lastly, we conclude that while there is still much work left to do before any tangible effects can be seen from utilizing AI tools such as GPT-3 on societal mega-trends; early indications suggest it may have a positive impact if used correctly.

The world has been evolving with new technologies and advances day-by-day. With the advent of various learning technologies in every field, the research community is able to provide solution in every aspect of life with the applications of Artificial Intelligence, Machine Learning, Deep Learning, Computer Vision, etc. However, with such high achievements, it is found to lag behind the ability to provide explanation against its prediction. The current situation is such that these modern technologies are able to predict and decide upon various cases more accurately and speedily than a human, but failed to provide an answer when the question of why to trust its prediction is put forward. In order to attain a deeper understanding into this rising trend, we explore a very recent and talked-about novel contribution which provides rich insight on a prediction being made -- ``Explainability.'' The main premise of this survey is to provide an overview for researches explored in the domain and obtain an idea of the current scenario along with the advancements published to-date in this field. This survey is intended to provide a comprehensive background of the broad spectrum of Explainability.

Portable Document Format (PDF) is one of the most widely used files types worldwide in data exchange, this has encourage hackers to utilize such files to spread any malicious content through PDF, utilizing different methods and techniques to accomplish that, on the other hand, security researches kept trying to improve detection methods to cope up to the rapidly increasing number of malwares daily, one of the commonly used detection technique nowadays is by utilizing artificial intelligence and Machine learning classificat; thision to help detecting PDF Malwares, in this paper, we utilize machine learning classifier Random Forest on a newly released PDF Malware dataset CIC-Evasive-PDFMal2022 to achieve the main goal of detecting malicious PDF documents, results showing a detection accuracy of around 99.5%

The recent public release of the generative AI language model ChatGPT has captured the public imagination and has resulted a rapid uptake and widespread experimentation by the general public and academia alike. The number of academic publications focusing on the capabilities as well as practical and ethical implications of generative AI has been growing exponentially. One of the concerns with this unprecedented growth in scholarship related to generative AI, in particular ChatGPT, is that in most cases the raw data, that is the text of the original ‘conversations,’ have not been made available to the audience of the papers and thus cannot be drawn on to assess the veracity of the arguments made and the conclusions drawn therefrom. This paper provides a protocol for the documentation and archiving of these raw data.

One of the most common and important destructive attacks on the victim system is Advanced Persistent Threats (APT)-attack. The APT attacker can achieve his hostile goals by obtaining information and gaining financial benefits regarding the infrastructure of a network. One of the solutions to detect a secret APT attack is using network traffic. Due to the nature of the APT attack in terms of being on the network for a long time and the fact that the network may crash because of high traffic, it is difficult to detect this type of attack. Hence, in this study, machine learning methods such as C5.0 decision tree, Bayesian network and deep neural network are used for timely detection and classification of APT-attacks on the NSL-KDD data set. Moreover, 10-fold cross validation method is used to experiment these models. As a result, the accuracy (ACC) of the C5.0 decision tree, Bayesian network and 6-layer deep learning models is obtained as 95.64%, 88.37% and 98.85%, respectively, and also, in terms of the important criterion of the false positive rate (FPR), the FPR value for the C5.0 decision tree, Bayesian network and 6-layer deep learning models is obtained as 2.56, 10.47 and 1.13, respectively. Other criterions such as sensitivity, specificity, accuracy, false negative rate and F-measure are also investigated for the models, and the experimental results show that the deep learning model with automatic multi-layered extraction of features has the best performance for timely detection of an APT-attack comparing to other classification models.

Most popular machine learning algorithms like k-nearest neighbour, k-means, SVM uses a metric to identify the distance(or similarity) between data instances. It is clear that performances of these algorithm heavily depends on the metric being used. In absence of prior knowledge about data we can only use general purpose metrics like Euclidean distance, Cosine similarity or Manhattan distance etc, but these metric often fail to capture the correct behaviour of data which directly affects the performance of the learning algorithm. Solution to this problem is to tune the metric according to the data and the problem, manually deriving the metric for high dimensional data which is often difficult to even visualize is not only tedious but is extremely difficult. Which leads to put effort on \textit{metric learning} which satisfies the data geometry.Goal of metric learning algorithm is to learn a metric which assigns small distance to similar points and relatively large distance to dissimilar points.

Oil and gas pipeline vandalism is a recurrent problem in oil rich zones of Nigeria and its West African neighbors and remains a challenge for multinationals to set ahead control measures to avert possible damages to operations both in infrastructure and business profit margins. In this paper, an integrative systems model comprising of a machine intelligence technique called Hierarchical Temporal Memory (HTM) and a sequence learning neural network called the Online-Sequential Extreme Learning Machine (OS-ELM) is proposed for monitoring and prediction of pipeline pressure data. The system models the continual prediction of pipeline oil/gas pressure signals useful for secure monitoring and control to avert acts of vandalism in oil and gas installations. The HTM uses a spatial pooler operated in temporal aggregated fashion and is defined as HTM-SP. The OS-ELM technique uses an explicit hierarchical training scheme so that the best cost estimates may be found after a stipulated number of trial runs. We study the performance of three OS-ELM neural activations: the sigmoid (sig), sinusoidal (sin) and radial basis function (rbf) activations. The results indicate improvement factors of 1.297, 1.297 and 1.300 of the HTM-SP over the OS-ELM sigmoid, sinusoidal and radial basis activations respectively.

The upsurge of Generative Adversarial Networks (GANs) in the previous five years has led to advancements in unsupervised data manipulation, sourced feature translation, and precise input-output synthesis through a competitive optimization of the discriminator and generator networks. More specifically, the recent rise of cycle-consistent GANs enables style transfers from a discrete source (input A) to target domain (input B) by preprocessing object features for a multi-discriminative adversarial network. Traditionally, cyclical adversarial networks have been exploited for unpaired image-to-image translation and domain adaptation by determining mapped relationships between an input A graphic and an input B graphic. However, this integral mechanism of domain adaptation can be applied to the complex acoustical features of human speech. Although well-established datasets, such as the 2018 Voice Conversion Challenge repository, paved way for female-male voice transformation, cycle-GANs have rarely been re-engineered for voices outside the datasets. More critically, cycle-GANs have massive potential to extract surface-level and hidden feature to distort an input A source into a texturally unrelated target voice. By preprocessing, compressing, and packaging unique acoustical voice properties, CycleGANs can learn to decompose speech signals and implement new translation models while preserving emotion, the intent of words, rhythm, and accents. Due to the potential of CycleGAN’s autoencoder in realistic unsupervised voice-voice conversion/feature adaptation, the researchers raise the ethical implications of controlling source input A to manipulate target voice B, particularly in cases of defamation and sabotage of target B’s words. This paper analyzes the potential of cycle-consistent GANs in deceptive voice-voice conversion by manipulating interview excerpts of political candidates.

Numerous goods and services are now offered through online platforms due to the recent growth of online transactions like e-commerce. Users have trouble locating the product that best suits them from the numerous products available in online shopping. Many studies in deep learning-based recommender systems (RSs) have focused on the intricate relationships between the attributes of users and items. Deep learning techniques have used consumer or item-related traits to improve the quality of personalized recommender systems in many areas, such as tourism, news, and e-commerce. Various companies, primarily e-commerce, utilize sentiment analysis to enhance product quality and effectively navigate today's business environment. Customer feedback regarding a product is gathered through sentiment analysis, which uses contextual data to split it into separate polarities. The explosive rise of the e-commerce industry has resulted in a large body of literature on e-commerce from different perspectives. Researchers have made an effort to categorize the recommended future possibilities for e-commerce study as the field has grown. There are several challenges in e-commerce, such as fake reviews, frequency of user reviews, advertisement click fraud, and code-mixing. In this review, we introduce an overview of the preliminary design for e-commerce. Second, the concept of deep learning, e-commerce, and sentiment analysis are discussed. Third, we represent different versions of the commercial dataset. Finally, we explain various difficulties facing RS and future research directions.

Structural system design is the process of giving form to a set of interconnected components subjected to loads and design constraints while navigating a complex design space. While safe designs are relatively easy to develop, optimal designs are not. Modern computational optimization approaches employ population based metaheuristic algorithms to overcome challenges with the system design optimization landscape. However, the choice of the initial population, or ground structure, can have an outsized impact on the resulting optimization. This paper presents a new method of generating such ground structures, using a combination of topology optimization (TO) and a novel system extraction algorithm. Since TO generates monolithic structures, rather than systems, its use for structural system design and optimization has been limited. In this paper, truss systems are extracted from topologies through morphological analysis and artificial intelligence techniques. This algorithm, and its assessment, constitutes the key contributions of this paper. The structural systems obtained are compared with ground truth solutions to evaluate the performance of the algorithms. The generated structures are also compared against benchmark designs from the literature. The results indicate that the presented truss generation algorithm produces structures comparable to those generated through metaheuristic optimization, while mitigating the need for assumptions about initial ground structures.

Dictionary Learning (DL) and Sparse Representation (SR) based Classifier have impacted greatly on the classification performance and has had good recognition rate on image data. In Video Semantic Analysis (VSA), the local structure of video data contains more vital discriminative information needed for classification. However, this has not been fully exploited by the current DL based approaches. Besides, similar coding findings are not being realized from video features with the same video category. Based on the issues stated afore, a novel learning algorithm, called Sparsity based Locality-Sensitive Discriminative Dictionary Learning(SLSDDL) for VSA is proposed in this paper. In the proposed algorithm, a discriminant loss function for the category based on sparse coding of the sparse coefficients is introduced into structure of Locality-Sensitive Dictionary Learning (LSDL) algorithm. Finally, the sparse coefficients for the testing video feature sample are solved by the optimized method of SLSDDL and the classification result for video semantic is obtained by minimizing the error between the original and reconstructed samples. The experiment results show that, the proposed SLSDDL significantly improves the performance of video semantic detection compared with the comparative state-of-the-art approaches. Moreover, the robustness to various diverse environments in video is also demonstrated, which proves the universality of the novel approach.

Object detection is one of the most critical tasks in the field of Computer vision. This task comprises identifying and localizing an object in the image. Architectural floor plans represent the layout of buildings and apartments. The floor plans consist of walls, windows, stairs, and other furniture objects. While recognizing floor plan objects is straightforward for humans, automatically processing floor plans and recognizing objects is a challenging problem. In this work, we investigate the performance of the recently introduced Cascade Mask R-CNN network to solve object detection in floor plan images. Furthermore, we experimentally establish that deformable convolution works better than conventional convolutions in the proposed framework. Identifying objects in floor plan images is also challenging due to the variety of floor plans and different objects. We faced a problem in training our network because of the lack of publicly available datasets. Currently, available public datasets do not have enough images to train deep neural networks efficiently. We introduce SFPI, a novel synthetic floor plan dataset consisting of 10000 images to address this issue. Our proposed method conveniently surpasses the previous state-of-the-art results on the SESYD dataset and sets impressive baseline results on the proposed SFPI dataset. The dataset can be downloaded from SFPI Dataset Link. We believe that the novel dataset enables the researcher to enhance the research in this domain further.

This paper compares a series of traditional and deep learning methodologies for the segmentation of textures. Six well-known texture composites first published by Randen and Hus{\o}y were used to compare traditional segmentation techniques (co-occurrence, filtering, local binary patterns, watershed, multiresolution sub-band filtering) against a deep-learning approach based on the U-Net architecture. For the latter, the effects of depth of the network, number of epochs and different optimisation algorithms were investigated. Overall, the best results were provided by the deep-learning approach. However, the best results were distributed within the parameters, and many configurations provided results well below the traditional techniques.

A significant attention has been made to the accurate detection of diabetes which is a big challenge for the research community to develop a diagnosis system to detect diabetes in a successful way in the IoT e-healthcare environment. Internet of Things (IOT) has emerging role in healthcare services which delivers a system to analyze the medical data for diagnosis of diseases applied data mining methods. The existing diagnosis systems have some drawbacks, such as high computation time, and low prediction accuracy. To handle these issues, we have proposed a IOT based diagnosis system using machine learning methods, such as preprocessing of data, feature selection, and classification for the detection of diabetes disease in e- healthcare environment. Model validation and performance evaluation metrics have been used to check the validity of the proposed system. We have proposed a filter method based on the Decision Tree (Iterative Dichotomiser 3) algorithm for highly important feature selection. Two ensemble learning Decision Tree algorithms, such as Ada Boost and Random Forest are also used for feature selection and compared the classifier performance with wrapper based feature selection algorithms also. Machine learning classifier Decision Tree has been used for the classification of healthy and diabetic subjects. The experimental results show that the Decision Tree algorithm based on selected features improves the classification performance of the predictive model and achieved optimal accuracy. Additionally, the proposed system performance is high as compared to the previous state-of-the-art methods. High performance of the proposed method is due to the different combinations of selected features set and GL, DPF, and BMI are more significantly important features in the dataset for prediction of diabetes disease. Furthermore, the experimental results statistical analysis demonstrated that the proposed method would be effectively detected diabetes disease and can easily be deployed in IOT wireless sensor technologies based e-healthcare environment.

Restricted Boltzmann machines (RBMs) are the building blocks of some deep learning networks. However, despite their importance, it is our perception that some very important derivations about the RBM are missing in the literature, and a beginner may feel RBM very hard to understand. We provide here these missing derivations. We cover the classic Bernoulli-Bernoulli RBM and the Gaussian-Bernoulli RBM, but leave out the ``continuous'' RBM as it is believed not as mature as the former two. This tutorial can be used as a companion or complement to the famous RBM paper ``Training restricted Boltzmann machines: An introduction'' by Fisher and Igel.

In this paper, our goal is to perform a virtual restoration of an ancient coin from its image. The present work is the first one to propose this problem, and it is motivated by two key promising applications. The first of these emerges from the recently recognised dependence of automatic image based coin type matching on the condition of the imaged coins; the algorithm introduced herein could be used as a pre-processing step, aimed at overcoming the aforementioned weakness. The second application concerns the utility both to professional and hobby numismatists of being able to visualise and study an ancient coin in a state closer to its original (minted) appearance. To address the conceptual problem at hand, we introduce a framework which comprises a deep learning based method using Generative Adversarial Networks, capable of learning the range of appearance variation of different semantic elements artistically depicted on coins, and a complementary algorithm used to collect, correctly label, and prepare for processing a large numbers of images (here 100,000) of ancient coins needed to facilitate the training of the aforementioned learning method. Empirical evaluation performed on a withheld subset of the data demonstrates extremely promising performance of the proposed methodology and shows that our algorithm correctly learns the spectra of appearance variation across different semantic elements, and despite the enormous variability present reconstructs the missing (damaged) detail while matching the surrounding semantic content and artistic style.

Introduction: Social media platforms such as Facebook, LinkedIn, Twitter, among others have been used as a tool for staging protests, opinion polls, campaign strategy, medium of agitation and a place of interest expression especially during elections. Past studies have established people’s opinion elections using social media posts. The advent of state-of-the-art algorithms for unstructured text processing implies tremendous progress in natural language processing and understanding. Aim: In this work, a Natural Language framework is designed to understand Nigeria 2023 presidential election based on public opinion using Twitter dataset. Methods: Raw datasets concerning discourse around Nigeria 2023 elections from Twitter of 2,059,113 18 dimensions were collected. Sentiment analysis was performed on the preprocessed dataset using three different machine learning models namely: Long Short-Term Memory (LSTM) Recurrent Neural Network, Bidirectional Encoder Representations from Transformers (BERT) and Linear Support Vector Classifier (LSVC) models. Personal tweet analysis of the three candidates provided insight on their campaign strategies and personalities while public tweet analysis established the public’s opinion about them. The performance of the models was also compared using accuracy, recall, false positive rate, precision and F-measure. Results: LSTM model gave an accuracy, precision, recall, AUC and f-measure of 88%, 82.7%, 87.2% , 87.6% and 82.9% respectively; the BERT model gave an accuracy, precision, recall, AUC and f-measure of 94%, 88.5%, 92.5%, 94.7% and 91.7% respectively while the LSVC model gave an accuracy, precision, recall, AUC and f-measure of 73%, 81.4%, 76.4%, 81.2% and 79.2% respectively. Conclusion: The experimental results show that sentiment analysis and other Natural Language Processing tasks can aid in the understanding of the social media space. Results also revealed the leverage of each aspirant towards winning the election. We conclude that sentiment analysis can form a general basis for generating insights for election and modeling election outcomes.

Ancient numismatics, that is, the study of ancient currencies (predominantly coins), is an interesting domain for the application of computer vision and machine learning, and has been receiving an increasing amount of attention in recent years. Notwithstanding the number of articles published on the topic, the variety of different methodological approaches described, and the mounting realisation that the relevant problems in the field are most challenging indeed, all research to date has entirely ignored one specific, readily accessible modality: colour. Invariably, colour is discarded and images of coins treated as being greyscale. The present article is the first one to question this decision (and indeed, it is a decision). We discuss the reasons behind the said choice, present a case why it ought to be reexamined, and in turn investigate the issue for the first time in the published literature. Specifically, we propose two new colour-based representations specifically designed with the aim of being applied to ancient coin analysis, and argue why it is sensible to employ them in the first stages of the classification process as a means of drastically reducing the initially enormous number of classes involved in type matching ancient coins (tens of thousands, just for Ancient Roman Imperial coins). Furthermore, we introduce a new data set collected with the specific aim of denomination-based categorisation of ancient coins, where we hypothesised colour could be of potential use, and evaluate the proposed representations. Lastly, we report surprisingly successful performances which goes further than confirming our hypothesis—rather, they convincingly demonstrate a much higher relevant information content carried by colour than even we expected. Thus we trust that our findings will be noted by others in the field and that more attention and further research will be devoted to the use of colour in automatic ancient coin analysis.

Emotion detection from the text is an important and challenging problem in text analytics. The opinion-mining experts are focusing on the development of emotion detection applications as they have received considerable attention of online community including users and business organization for collecting and interpreting public emotions. However, most of the existing works on emotion detection used less efficient machine learning classifiers with limited datasets, resulting in performance degradation. To overcome this issue, this work aims at the evaluation of the performance of different machine learning classifiers on a benchmark emotion dataset. The experimental results show the performance of different machine learning classifiers in terms of different evaluation metrics like precision, recall ad f-measure. Finally, a classifier with the best performance is recommended for the emotion classification.

Clients are increasingly looking for fast and effective means to quickly and frequently survey and communicate the condition of their buildings so that essential repairs and maintenance work can be done in a proactive and timely manner before it becomes too dangerous and expensive. Traditional methods for this type of work commonly comprise of engaging building surveyors to undertake a condition assessment which involves a lengthy site inspection to produce a systematic recording of the physical condition of the building elements, including cost estimates of immediate and projected long-term costs of renewal, repair and maintenance of the building. Current asset condition assessment procedures are extensively time consuming, laborious, and expensive and pose health and safety threats to surveyors, particularly at height and roof levels which are difficult to access. We propose a method for automated detection and localisation of key building defects from images using deep learning and convolution neural networks. The proposed model is based on a pre-trained VGG-16 classifier with Class Activation Mapping (CAM) for object localisation. The model has proven to be robust and able to accurately detect and localise mould growth, stains, and paint deterioration defects arising from dampness in buildings. The approach is being developed with potentials to scale-up to support automated detection of defects and deterioration of buildings in real-time using mobile devices and drones.

Decentralized Finance (DeFi) is an emerging and revolutionizing field with notable uncertainties of reliability to be used on a mass scale. On the other hand, Artificial Intelligence (AI) has proved to be a crucial helping tool in numerous domains. In this study, we present a systematic review of the utility of AI in Defi in terms of impact, reliability, and security and conduct exhaustive analysis. We further conclude from our extensive literature review that we can identify possible new research opportunities in AI to bridge the gap of trust between peers and make the integration of DeFi more agile in the near future.

The coronavirus disease 2019 (COVID-19) is the fastest transmittable virus caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The detection of COVID-19 using artificial intelligence techniques and especially deep learning will help to detect this virus in early stages which will reflect in increasing the opportunities of fast recovery of patients worldwide. This will lead to release the pressure off the healthcare system around the world. In this research, classical data augmentation techniques along with CGAN based on a deep transfer learning model for COVID-19 detection in chest CT scan images will be presented. The limited benchmark datasets for covid-19 especially in chest CT images is the main motivation of this research. The main idea is to collect all the possible images for covid-19 that exists until the very writing of this research and use the classical data augmentations along with CGAN to generate more images to help in the detection of the COVID-19. In this study, five different deep convolutional neural network-based models (AlexNet, VGGNet16, VGGNet19, GoogleNet, and ResNet50) have been selected for the investigation to detect the coronavirus infected patient using chest CT radiographs digital images. The classical data augmentations along with CGAN improve the performance of classification in all selected deep transfer models. The Outcomes show that ResNet50 is the most appropriate deep learning model to detect the COVID-19 from limited chest CT dataset using the classical data augmentation with testing accuracy of 82.91%.

When computers start to become a dominant part of technology around the 1950s, fundamental questions about reliable designs and robustness were of great relevance. Their development gave rise to the exploration of new questions such as what made brains reliable (since neurons can die) and how computers could get inspiration from neural systems. In parallel, the first Artificial Neural Networks came to life. Since then, the comparative view between brains and computers has been developed in new, sometimes unsuspected directions. With the rise of deep learning and the development of connectomics, an evolutionary look at how both hardware and neural complexity have evolved or designed is required. In this paper, we argue that important similarities have resulted both from convergent evolution (the inevitable outcome of architectural constraints) and inspiration of hardware and software principles guided by toy pictures of neurobiology. Moreover, dissimilarities and gaps originate from the lack of major innovations that have paved the way to biological computing (including brains) that are completely absent within the artificial domain. As it occurs within synthetic biocomputation, we can also ask whether alternative minds can emerge from A.I.\ designs. Here we take an evolutionary view of the problem and discuss the remarkable convergences between living and artificial designs and what are the pre-conditions to achieve artificial intelligence.

This paper serves a survey and empirical evaluation of the state-of-the-art in activity recognition methods using accelerometers. We examine research that has focused on the selection of activities, the features that are extracted from the accelerometer data, the segmentation of the time-series data, the locations of accelerometers, the selection and configuration trade-offs, the test/retest reliability, and the generalisation performance. Furthermore, we study these questions from an experimental platform and show, somewhat surprisingly, that many disparate experimental configurations yield comparable predictive performance on testing data. Our understanding of these results is that the experimental setup directly and indirectly defines a pathway for context to be delivered to the classifier, and that, in some settings, certain configurations are more optimal than alternatives. We conclude by identifying how the main results of this work can be used in practice, specifically in experimental configurations in challenging experimental conditions.

. Identifying students who might have difficulty in their course of studies ahead of time is crucial. There can be many reasons for performance issues, such as personality, family, social, and/or economic. We advocate that educational systems should use machine learning to predict students’ performance based on performance factors. This would allow educational professionals and institutions to put in place a preventive plan to help students towards achievements of their educational goals and success. In this chapter, we propose a student performance prediction method and evaluate its performance. We provide a taxonomy of performance factors that help to gauge students performance from different perspectives and give insights on the categories and features that have more significant impact on students’ performance. The results of this work can be used by education institutions to put in place a student-centric approach to tackle performance issues before they create long-term effects on student’s life. In addition, it will help education policymakers to introduce a tailored approach for the population in specific areas.

Online Social Networks (OSNs), such as Facebook and Twitter, have become a very important part of many people’s daily lives. Unfortunately, the high popularity of these platforms makes them very attractive to spammers. Machine-learning (ML) techniques have been widely used as a tool to address many cybersecurity application problems (such as spam and malware detection). However, most of the proposed approaches do not consider the presence of adversaries that target the defense mechanism itself. Adversaries can launch sophisticated attacks to undermine deployed spam detectors either during training or the prediction (test) phase. Not considering these adversarial activities at the design stage makes OSNs’ spam detectors prone to a range of adversarial attacks. This paper thus surveys the attacks against Twitter spam detectors in an adversarial environment. In addition, a general taxonomy of potential adversarial attacks is proposed by applying common frameworks from the literature. Examples of adversarial activities on Twitter were provided after observing Arabic trending hashtags. A new type of spam tweet (Adversarial spam tweet), which can be used to undermine deployed classifier, were found. In addition, possible countermeasures that could increase the robustness of Twitter spam detectors against such attacks are investigated.

The fact is quite transparent that almost everybody around the world is using android apps. Half of the population of this planet is associated with messaging, social media, gaming, and browsers. This online marketplace provides free and paid access to users. On the Google Play store, users are encouraged to download countless of applications belonging to predefined categories. In this research paper, we have scrapped thousands of users reviews and app ratings. We have scrapped 148 apps’ reviews from 14 categories. We have collected 506259 reviews from Google play store and subsequently checked the semantics of reviews about some applications form users to determine whether reviews are positive, negative, or neutral. We have evaluated the results by using different machine learning algorithms like Naïve Bayes, Random Forest, and Logistic Regression algorithm. we have calculated Term Frequency (TF) and Inverse Document Frequency (IDF) with different parameters like accuracy, precision, recall, and F1 and compared the statistical result of these algorithms. We have visualized these statistical results in the form of a bar chart. In this paper, the analysis of each algorithm is performed one by one, and the results have been compared. Eventually, We've discovered that Logistic Regression is the best algorithm for a review-analysis of all Google play store. We have proved that Logistic Regression gets the speed of precision, accuracy, recall, and F1 in both after preprocessing and data collection of this dataset.

Due to the substantial growth of internet users and its spontaneous access via electronic devices, the amount of electronic contents is growing enormously in recent years through instant messaging, social networking posts, blogs, online portals, and other digital platforms. Unfortunately, the misapplication of technologies has boosted with this rapid growth of online content which leads to the rise in suspicious activities. People misuse the web media to disseminate malicious activity, perform the illegal movement, abuse other people, and publicize suspicious contents on the web. The suspicious contents usually available in the form of text, audio or video, whereas text contents have been used in most of the cases to perform suspicious activities. Thus, one of the most challenging issues for NLP researchers is to develop a system that can identify suspicious text efficiently from the specific contents. In this paper, a Machine Learning (ML)-based classification model is proposed (hereafter called STD) to classify Bengali text into non-suspicious and suspicious categories based on its original contents. A set of ML classifiers with various features has been used on our developed corpus, consisting of 7000 Bengali text documents where 5600 documents used for training and 1400 documents used for testing. The performance of the proposed system is compared with the human baseline and existing ML techniques. The SGD classifier `tf-idf’ with the combination of unigram and bigram features are used to achieve the highest accuracy of 84.57%.

The speech entailed in human voice comprises essentially para-linguistic information used in many voice-recognition applications. Gender voice-recognition is considered one of the pivotal parts to be detected from a given voice, a task that involves certain complications. In order to distinguish gender from a voice signal, a set of techniques have been employed to determine relevant features to be utilized for building a model from a training set. This model is useful for determining the gender (i.e, male or female) from a voice signal. The contributions are involved in two folds: (i) providing analysis information about well-known voice signal features using a prominent dataset, (ii) studying various machine learning models of different theoretical families to classify the voice gender, and (iii) using three prominent feature selection algorithms to find promisingly optimal features for improving classification models. Experimental results show the importance of sub-features over others, which are vital for enhancing the efficiency of classification models performance. Experimentation reveals that the best recall value is equal to 99.97%; 99.7% of two models of Deep Learning (DL) and Support Vector Machine (SVM) and with feature selection the best recall value is 100% for SVM techniques.

Nutrient regulation in aquaponic environments has been the topic of research for many years. Most have focused on appropriate control of nutrients in an aquaponic set-up, but very little research has been done on commercial scale applications. In our model, the input data was sourced on a weekly basis from three commercial aquaponic farms in South-East Texas over the course of a year. Due to limited number of data points, dimensionality reduction techniques like pair-wise correlation matrix was used to remove the highly correlated predictors. Feature selection techniques like the XGBoost classifier and Recursive Feature Elimination with ExtraTreesClassifier were used to rank the features in order of their relative importance. Ammonium and calcium were found to be the top two nutrient predictors and based on the months in which lettuce was cultivated, the median of these nutrient values from the historical dataset served as the optimal concentrations to be maintained in the aquaponic solution. To accomplish this, Vernier sensors were used to measure the nutrient values and actuator systems were built to dispense the appropriate nutrient into the ecosystem via a closed loop.

A huge number of applications available for Android-based smartphone devices have emerged over the past years. Due to which a huge number of malicious applications has been growing explosively. Many approaches have been proposed to ensure the security and quality of application in the markets. Usually, Machine Learning approaches are utilized in the classification process of malicious application detection. Calculating accurate results of characterizing applications behaviors, or other features, has a direct effect on the results with Machine Learning calculations. Android applications emerge so quickly. The behavior of current applications has gotten progressively malicious. The extraction of malware-infected features from applications is thus become a difficult task. According to our knowledge, a ton of features have been extricated in existing work however no survey has overviewed the features built for identifying malicious applications efficiently. In this paper, we will in general give an extensive review of such sort of work that identifies feature applications by describing various practices of uses with various kinds of features. In this survey we have discussed the following dimensions: extraction and selection of feature methods if any, methods of detection and evaluation performed. In light of our review, we notice the issues of investigating malware-affected features from applications, give the scientific categorization and demonstrate the future headings.

Generative large language models (LLMs), e.g., ChatGPT, have demonstrated remarkable proficiency across several NLP tasks such as machine translation, question answering, text summarization, and natural language understanding. Recent research has shown that utilizing ChatGPT for assessing the quality of machine translation (MT) achieves state-of-the-art performance at the system level but performs poorly at the segment level. To further improve the performance of LLMs on MT quality assessment, we conducted an investigation into several prompting methods. Our results indicate that by combining Chain-of-Thoughts and Error Analysis, a new prompting method called Error Analysis Prompting, LLMs like ChatGPT can \textit{generate human-like MT evaluations at both the system and segment level}. Additionally, we discovered some limitations of ChatGPT as an MT evaluator, such as unstable scoring and biases when provided with multiple translations in a single query. Our findings aim to provide a preliminary experience for appropriately evaluating translation quality on ChatGPT while offering a variety of tricks in designing prompts for in-context learning. We anticipate that this report will shed new light on advancing the field of translation evaluation with LLMs by enhancing both the accuracy and reliability of metrics. The project can be found at https://github.com/Coldmist-Lu/ErrorAnalysis_Prompt.

A pixel-based segmentation method was demonstrated to be confounded by developmental stage in estimation of flowering of mango. Categorization of panicles into three developmental stages was undertaken with a single and a two-stage deep learning framework (YOLO and R2CNN), using either upright or rotated bounding boxes. For a validation image set and for total panicle count, the models MangoYOLO(-upright), MangoYOLO-rotated, YOLOv3-rotated, R2CNN(-rotated) and R2CNN-upright achieved: (i) RMSEs of 25.6, 16.0, 15.4, 25.8 and 32.3 panicles per tree image, (ii) Mean average precision (mAP) scores of 72.2, 69.1, 65.0, 62.5 and 70.9% and (iii) weighted F1-scores of 76.5, 76.1, 74.9, 74.0 and 82.0, respectively. For a test set of images involving a different orchard and cultivar and use of a different camera, the R2 for machine vision to human count of panicles per tree was 0.86, 0.80, 0.83, 0.81 and 0.76 for the same models, respectively. Thus, models generalised well, but with no consistent benefit from use of rotated over upright bounding boxes. While the YOLOv3-rotated model was superior in terms of total panicle count, the R2CNN-upright model was more accurate for panicle stage classification. To demonstrate practical application, panicle counts were made weekly for an orchard of 994 trees, with a peak detection routine applied to document multiple flowering events.

With the rapid development of artificial intelligence, machine learning is gradually becoming popular in predictions in all walks of life. In meteorology, It is gradually competing with traditional climate predictions dominated by physical models. This survey aims to consolidate the current understanding of Machine Learning (ML) applications in weather and climate prediction—a field of growing importance across multiple sectors including agriculture and disaster management. Building upon an exhaustive review of more than 20 methods highlighted in existing literature, this survey pinpointed eight techniques that show particular promise for improving the accuracy of both short-term weather and medium-to-long-term climate forecasts. According to the survey, while ML demonstrates significant capabilities in short-term weather prediction, its application in medium-to-long-term climate forecasting remains limited, constrained by factors such as intricate climate variables and data limitations. Current literature tends to focus narrowly on either short-term weather or medium-to-long-term climate forecasting, often neglecting the relationship between the two, as well as general neglect of modelling structure and recent advances. By providing an integrated analysis of models spanning different time scales, this survey aims to bridge these gaps, thereby serving as a meaningful guide for future interdisciplinary research in this rapidly evolving field.

Reemergence of deep Neural Networks (CNNs) has lead to high-performance supervised learning algorithms for the Electro-Optical (EO) domain classification and detection problems. This success is possible because generating huge labeled datasets has become possible using modern crowdsourcing labeling platforms such as Amazon Mechanical Turk that recruit ordinary people to label data. Unlike the EO domain, labeling the Synthetic Aperture Radar (SAR) domain data can be a lot more challenging and for various reasons using crowdsourcing platforms is not feasible for labeling the SAR domain data. As a result, training deep networks using supervised learning is more challenging in the SAR domain. In the paper,we present a new framework to train a deep neural network for classifying Synthetic Aperture Radar (SAR) images by eliminating the need for huge labeled dataset. Our idea is based on transferring knowledge from a related EO domain problem, where labeled data is easy to obtain. We transfer knowledge from the EO domain through learning a shared invariant cross-domain embedding space that is also discriminative for classification. To this end, we train two deep encoders that are coupled through their last year to map data points from the EO and the SAR domains to the shared embedding space such that the distance between the distributions of the two domains is minimized in the latent embedding space. We use the Sliced Wasserstein Distance (SWD) to measure and minimize the distance between these two distributions and use a limited number of SAR label data points to match the distributions class-conditionally. As a result of this training procedure, a classifier trained from the embedding space to the label space using mostly the EO data would generalize well on the SAR domain. We provide theoretical analysis to demonstrate why our approach is effective and validate our algorithm on the problem of ship classification in the SAR domain by comparing against several other learning competing approaches.

This paper presents a comprehensive analysis of the scholarly footprint of ChatGPT, an AI language model, using bibliometric and scientometric methods. The study aims to understand the evolution of research output, citation patterns, collaborative networks, application domains, and future research directions related to ChatGPT. By analyzing data from the Scopus database, 533 relevant articles were identified for analysis. The findings reveal the prominent publication venues, influential authors, and countries contributing to ChatGPT research. Collaborative networks among researchers and institutions are visualized, highlighting patterns of co-authorship. The application domains of ChatGPT, such as customer support and content generation, are examined. Moreover, the study identifies emerging keywords and potential research areas for future exploration. The methodology employed includes data extraction, bibliometric analysis using various indicators, and visualization techniques such as Sankey diagrams. The analysis provides valuable insights into ChatGPT's influence in academia and offers researchers guidance for further advancements. This study stimulates discussions, collaborations and innovations to enhance ChatGPT's capabilities and impact across domains.

The scope of a lucrative career promoted by Google through its video distribution platform YouTube 1 has attracted a large number of users to become content creators. An important aspect of this line of work is the feedback received in the form of comments which show how well the content is being received by the audience. However, volume of comments coupled with spam and limited tools for comment classification makes it virtually impossible for a creator to go through each and every comment and gather constructive feedback. Automatic classification of comments is a challenge even for established classification models, since comments are often of variable lengths riddled with slang, symbols and abbreviations. This is a greater challenge where comments are multilingual as the messages are often rife with the respective vernacular. In this work, we have evaluated top-performing classification models and four different vectorizers, for classifying comments which are a mix of different combinations of English and Malayalam (only English, only Malayalam and Mix of English and Malayalam). The statistical analysis of results indicates that Multinomial Naïve Bayes, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Random Forest and Decision Trees offer similar level of accuracy in comment classification. Further, we have also evaluated 3 multilingual sub-types of the novel NLP language model, BERT and compared its’ performance to the conventional machine learning classification techniques. XLM was the top-performing BERT model with an accuracy of 67.31%. Random Forest with Term Frequency Vectorizer was the best the top-performing model out of all the traditional classification models with an accuracy of 63.59%.

A Twi-English parallel corpus is certainly an important resource for Machine Translation of Twi (ISO 639-3), a Low-Resource African Language (LRAL) which is mainly spoken in Ghana and Ivory Coast. Currently large-scale multi-domain Twi-English parallel corpus is still unavailable partly due to the difficulties and the arduous efforts required in its design. In this paper, we present TWIENG: a large-scale multi-domain Twi-English parallel corpus. We crawled the sentences from the web using web crawlers, translated, aligned, tokenized and compiled to create the corpus. We crawled English sentences from Ghanaian indigenous electronic news portals, Ghanaian Parliamentary Hansards, Twi Bible and crowdsourcing via google forms. The sentences were translated by professional translators and linguists, they were then aligned, tokenized and compiled. The corpus was curated using the sketch engine, a corpus manager and analysis software developed by Lexical Computing Limited. The corpus was manually evaluated by Twi professional linguists. The Corpus has 5,419 parallel sentences.

Scoring targets in shooting sports is a crucial and time-consuming task that relies on manually counting bullet holes. This paper introduced an automatic score detection model using object detection techniques. The performance of seven models belonging to two different architectural setups was compared. Models like YOLOv8n, YOLOv8s, YOLOv8m, RetinaNet-50, and RetinaNet-101 are single-shot detectors, while Faster RCNN-50 and Faster RCNN-101 belong to the two-shot detectors category. The dataset was manually captured from the shooting range and expanded by generating more versatile data using Python code. Before the dataset was trained to develop models, it was resized (640x640) and augmented using Roboflow API. The trained models were then assessed on the test dataset, and their performance was compared using matrices like mAP50, mAP50-90, precision, and recall. The results showed that YOLOv8 models can detect multiple objects with good confidence scores. Among all, YOLOv8m performed the best with the highest mAP50 value of 96.7%, followed by the performance of YOLOv8s with the mAP50 value of 96.5%. It is suggested that if the system is to be implemented in a real-time environment, YOLOv8s is a better choice since it took significantly less inference time (2.3ms) than YOLOv8m (5.7ms) and yet generated the competitive mAP50.

Tables in the document image are one of the most important entities since they contain crucial information. Therefore, accurate table detection can significantly improve information extraction from tables. In this work, we present a novel end-to-end trainable pipeline, HybridTabNet, for table detection in scanned document images. Our two-stage table detector uses the ResNeXt-101 backbone for feature extraction and Hybrid Task Cascade (HTC) to localize the tables in scanned document images. Moreover, we replace conventional convolutions with deformable convolutions in the backbone network. This enables our network to detect tables of arbitrary layouts precisely. We evaluate our approach comprehensively on ICDAR-13, ICDAR-17 POD, ICDAR-19, TableBank, Marmot, and UNLV. Apart from the ICDAR-17 POD dataset, our proposed HybridTabNet outperforms earlier state-of-the-art results without depending on pre and post-processing steps. Furthermore, to investigate how the proposed method generalizes unseen data, we conduct an exhaustive leave-one-out-evaluation. In comparison to prior state-of-the-art results, our method reduces the relative error by 27.57% on ICDAR-2019-TrackA-Modern, 42.64% on TableBank (Latex), 41.33% on TableBank (Word), 55.73% on TableBank (Latex + Word), 10% on Marmot, and 9.67% on UNLV dataset. The achieved results reflect the superior performance of the proposed method.

In recent times, with the increase of Artificial Neural Network (ANN), deep learning has brought a dramatic twist in the field of machine learning by making it more Artificial Intelligence (AI). Deep learning is used remarkably used in vast ranges of fields because of its diverse range of applications such as surveillance, health, medicine, sports, robotics, drones etc. In deep learning, Convolutional Neural Network (CNN) is at the center of spectacular advances that mixes Artificial Neural Network (ANN) and up to date deep learning strategies. It has been used broadly in pattern recognition, sentence classification, speech recognition, face recognition, text categorization, document analysis, scene, and handwritten digit recognition. The goal of this paper is to observe the variation of accuracies of CNN to classify handwritten digits using various numbers of hidden layer and epochs and to make the comparison between the accuracies. For this performance evaluation of CNN, we performed our experiment using Modified National Institute of Standards and Technology (MNIST) dataset. Further, the network is trained using stochastic gradient descent and the backpropagation algorithm.

Electromyographic (EMG) signals provide information about a person's muscle activity. For hand movements, in particular, the execution of each gesture involves the activation of different combinations of the forearm muscles, which generate distinct electrical patterns. Conversely, the analysis of these muscle activation patterns, represented by EMG signals, allows recognizing which gesture is being performed. In this study, we aimed to implement an automatic identification system of hand or wrist gestures based on supervised Machine Learning (ML) techniques. We trained different computational models and determined which of these showed the best capacity to identify six hand or wrist gestures and generalize between different subjects. We used an open access database containing recordings of EMG signals from 36 subjects. Among the results obtained, we highlight the performance of the Random Forest model, with an accuracy of 95.39%, and the performance of a convolutional neural network with an accuracy of 94.77%.

We propose a novel transfer learning method for speech emotion recognition allowing us to obtain promising results when only few training data is available. With as low as 125 examples per emotion class, we were able to reach a higher accuracy than a strong baseline trained on 8 times more data. Our method leverages knowledge contained in pre-trained speech representations extracted from models trained on a more general self-supervised task which doesn’t require human annotations, such as the wav2vec model. We provide detailed insights on the benefits of our approach by varying the training data size, which can help labeling teams to work more efficiently. We compare performance with other popular methods on the IEMOCAP dataset, a well-benchmarked dataset among the Speech Emotion Recognition (SER) research community. Furthermore, we demonstrate that results can be greatly improved by combining acoustic and linguistic knowledge from transfer learning. We align acoustic pre-trained representations with semantic representations from the BERT model through an attention-based recurrent neural network. Performance improves significantly when combining both modalities and scales with the amount of data. When trained on the full IEMOCAP dataset, we reach a new state-of-the-art of 73.9% unweighted accuracy (UA).

Indoor localization (IL) is a significant topic of study with several practical applications. The area of IL has evolved greatly in recent years due to the introduction of numerous technologies such as WiFi, Bluetooth, cameras, and other sensors. Despite the growing interest in this field, there are numerous challenges and drawbacks that must be addressed to develop more accurate and sustainable systems for IL and its real-life applications. This review study gives an in-depth look into IL, covering the most promising artificial intelligence-based and hybrid strategies that have shown excellent potential in overcoming some of the limitations of classic methods. In addition, the paper investigates the significance of high-quality datasets and evaluation metrics in the design and assessment of IL algorithms. Furthermore, this overview study emphasizes the crucial role that machine learning techniques, such as deep learning and transfer learning, play in the advancement of IL. A focus on the importance of IL and the various technologies, methods, and techniques that are being used to improve it. Finally, The survey highlights the need for continued research and development to create more accurate and scalable techniques that can be applied across a range of industries, such as evacuation-egress routes, hazard-crime detection, smart occupancy-driven energy reduction and asset tracking and management.

In this paper, we propose methods for brain tumor detection in MRI images based on ensemble learning. We build upon prior research on ensemble methods by testing the concatenation of pre-trained models: features extracted via transfer learning are merged and segmented by classification algorithms or a stacked ensemble of those algorithms. The proposed approach achieved accuracy scores of 0.98 , outperforming a benchmark VGG-16 model. Considerations to granular computing are given in the paper as well.

The main restriction of the Semantic Web is the difficult of the SPARQL language, that is necessary to extract information from the Knowledge Representation also known as ontology. Making the Semantic Web accessible for people who do not know SPARQL, is essential the use of friendlier interfaces and a good alternative is Natural Language. This paper shows the implementation of a friendly prototype interface to query and retrieve, by voice, information from website building with the Semantic Web tools. In that way, the end users avoid the complicated SPARQL language. To achieve this, the interface recognizes a speech query and converts it into text, it processes the text through a java program and identifies keywords, generates a SPARQL query, extracts the information from the website and read it in voice, for the user. In our work Google Cloud Speech API makes Speech-to-Text conversions and Text-to Speech conversions are made with SVOX Pico. As results, we have measured three variables: The success rate in queries, the response time of query and a usability survey. The values of the variables allows the evaluation of our prototype. Finally the interface proposed provides us a new approach in the problem, using the Cloud like a Service, reducing barriers of access to the Semantic Web for people without technical knowledge of Semantic Web technologies.

Activation Functions are crucial parts of the Deep Learning Artificial Neural Networks. From the Biological point of view, a neuron is just a node with many inputs and one output. A neural network consists of many interconnected neurons. It is a “simple” device that receives data at the input and provides a response. The function of neurons is to process and transmit information; the neuron is the basic unit in the nervous system. Carly Vandergriendt (2018) stated the human brain at birth consists of an estimated 100 billion Neurons. The ability of a machine to mimic human intelligence is called Machine Learning. Deep Learning Artificial Neural Networks was designed to work like a human brain with the aid of arbitrary choice of Non-linear Activation Functions. Currently, there is no rule of thumb on the choice of Activation Functions, “Try out different things and see what combinations lead to the best performance”, however, sincerely; the choice of Activation Functions should not be Trial and error. Jamilu (2019) proposed that Activation Functions shall be emanated from AI-ML-Purified Data Set and its choice shall satisfy Jameel’s ANNAF Stochastic and or Deterministic Criterion. The objectives of this paper are to propose instances where Deep Learning Artificial Neural Networks are SUPERINTELLIGENT. Using Jameel’s ANNAF Stochastic and or Deterministic Criterion, the paper proposed four classes where Deep Learning Artificial Neural Networks are Superintelligent namely; Stochastic Superintelligent, Deterministic Superintelligent, and Stochastic-Deterministic 1^st and 2^nd Levels Superintelligence. Also, a Normal Probabilistic-Deterministic case was proposed.

Machine learning research has been able to solve problems in multiple aspects. An open area of research is machine learning for solving optimisation problems. An optimisation problem can be solved using a metaheuristic algorithm, which is able to find a solution in a reasonable amount of time. However, there is a problem, the time required to find an appropriate metaheuristic algorithm, that would have the convenient configurations to solve a set of optimisation problems properly. A solution approach is shown here, using a proposal that automatically creates metaheuristic algorithms aided by a reinforced learning approach. Based on the experiments performed, the approach succeeded in creating a metaheuristic algorithm that managed to solve a large number of different continuous domain optimisation problems. This work's implications are immediate because they describe a basis for the generation of metaheuristic algorithms in real-time.

Aiming at the problem of model error and tracking dependence in the process of intelligent vehicle motion planning, an intelligent vehicle model transfer trajectory planning method based on deep reinforcement learning is proposed, which obtain an effective control action sequence directly. Firstly, an abstract model of the real environment is extracted. On this basis, Deep Deterministic Policy Gradient (DDPG) and vehicle dynamic model are adopted to jointly train a reinforcement learning model, and to decide the optimal intelligent driving maneuver. Secondly, the actual scene is transferred to equivalent virtual abstract scene by transfer model, furthermore, the control action and trajectory sequences are calculated according to trained deep reinforcement learning model. Thirdly, the optimal trajectory sequence is selected according to evaluation function in the real environment. Finally, the results demonstrate that the proposed method can deal with the problem of intelligent vehicle trajectory planning for continuous input and continuous output. The model transfer method improves the model generalization performance. Compared with the traditional trajectory planning, the proposed method output continuous rotation angle control sequence, meanwhile, the lateral control error is also reduced.

Recent advancements in Software Defined Networking (SDN) makes it possible to overcome the management challenges of traditional network by logically centralizing control plane and decoupling it from forwarding plane. Through centralized controllers, SDN can prevent security breach, but it also brings in new threats and vulnerabilities. Central controller can be a single point of failure. Hence, flow-based anomaly detection system in OpenFlow Controller can secure SDN to a great extent. In this paper, we investigated two different approaches of flow-based intrusion detection system in OpenFlow Controller. The first of which is based on machine-learning algorithm where NSL-KDD dataset with feature selection ensures the accuracy of 82% with Random Forest classifier using Gain Ratio feature selection evaluator. In the later phase, the second approach is combined with Gated Recurrent Unit Long Short-Term Memory based intrusion detection model based on Deep Neural Network (DNN) where we applied an appropriate ANOVA F-Test and Recursive Feature Elimination feature selection method to improve the classifier performance and achieved an accuracy of 88%. Substantial experiments with comparative analysis clearly show that, deep learning would be a better choice for intrusion detection in OpenFlow Controller.

Generic object detection is one of the most important and flourishing branches of computer vision and has real-life applications in our day to day life. With the exponential development of deep learning-based techniques for object detection, the performance has enhanced considerably over the last 2 decades. However, due to the data-hungry nature of deep models, they don't perform well on tasks which have very limited labeled dataset available. To handle this problem, we proposed a transfer learning-based deep learning approach for detecting multiple pigs in the indoor farm setting. The approach is based on YOLO-v2 and the initial parameters are used as the optimal starting values for train-ing the network. Compared to the original YOLO-v2, we transformed the detector to detect only one class of objects i.e. pigs and the back-ground. For training the network, the farm-specific data is annotated with the bounding boxes enclosing pigs in the top view. Experiments are performed on a different configuration of the pen in the farm and convincing results have been achieved while using a few hundred annotated frames for fine-tuning the network.

Deep neural networks are hegemonic approaches to many machine learning areas, including natural language processing (NLP). Thanks to the availability of large corpora collections and the capability of deep architectures to shape internal language mechanisms in self-supervised learning processes (also known as "pre-training"), versatile and performing models are released continuously for every new network design. But these networks, somehow, learn a probability distribution of words and relations across the training collection used, inheriting the potential flaws, inconsistencies and biases contained in such a collection. As pre-trained models have found to be very useful approaches to transfer learning, dealing with bias has become a relevant issue in this new scenario. We introduce bias in a formal way and explore how it has been treated in several networks, in terms of detection and correction. Also, available resources are identified and a strategy to deal with bias in deep NLP is proposed.

An article's tone and framing not only influence an audience's perception of a story but may also reveal attributes of author identity and bias. Building upon prior media, psychological, and machine learning research, this neural network-based system detects those writing characteristics in ten news agencies' reporting, discovering patterns that, intentional or not, may reveal an agency's topical perspectives or common contextualization patterns. Specifically, learning linguistic markers of different organizations through a newly released open database, this probabilistic classifier predicts an article's publishing agency with 74% hidden test set accuracy given only a short snippet of text. The resulting model demonstrates how unintentional 'filter bubbles' can emerge in machine learning systems and, by comparing agencies' patterns and highlighting outlets' prototypical articles through an open source exemplar search engine, this paper offers new insight into news media bias.

In this paper, we introduce deboost, a Python library devoted to weighted distance ensembling of predictions for regression and classification tasks. Its backbone resides on the scikit-learn library for default models and data preprocessing functions. It offers flexible choices of models for the ensemble as long as they contain the predict method, like the models available from scikit-learn. deboost is released under the MIT open-source license and can be downloaded from the Python Package Index (PyPI) at https://pypi.org/project/deboost. The source scripts are also available on a GitHub repository at https://github.com/weihao94/DEBoost.

Intracranial hemorrhage is a serious medical problem that requires rapid and often intensive medical care. Identifying the location and type of any hemorrhage present is a critical step in the treatment of the patient. Diagnosis requires an urgent procedure, and the detection of hemorrhage is a difficult and time-consuming process for human experts. In this paper, we propose methods based on EfficientDet’s deep-learning technology that can be applied to the diagnosis of hemorrhages and thus become a decision-support system. Our proposal is two-fold. On the one hand, the proposed technique classifies slices of computed tomography scans for the presence hemorrhage or its lack, achieving 92.7% accuracy and 0.978 ROC-AUC. On the other hand, our methodology provides visual explanations of the classification chosen using the Grad-CAM methodology.

Smartphones are prone to SMS phishing due to the rapid growth in the availability of smart mobile technologies driven by Internet connections. Also, detecting phishing SMS is a challenging task due to the unstructured nature of SMS text data with non-linear complex correlations. In this concern, considering the recent advancements in the domain of cybersecurity, we have proposed a hybrid deep learning framework that extracts robust features from SMS texts followed by an automatic detection of Phishing SMS. Due to combining the potential capability of individual models into one hybrid framework, it has outperformed various other individual machine learning and deep learning models. The proposed Phishing Detection framework is an effective hybrid combination of pretrained transformer model, MPNet (Masked and Permuted Language Modeling), with supervised ConvNets (CNN) and Bi-directional Gated Recurrent Units (GRU). It is intended to successfully detect unstructured short phishing text messages that contain complex patterns.

Background: The potential of Artificial intelligent (AI) models to process and interpret large health datasets at scale could revolutionize public health and epidemiology, providing a foundation for public health. Ethics has been recognized as a priority concern in the development and deployment of AI. Because AI technology can jeopardize patient safety, privacy, and posing a new set of ethical problems that must be addressed. Objectives: We aim to provide a holistic view on what are the different ethical and legal principles that was addressed in the included studies regarding the use of AI in public health and what are the ethical challenges that can arise.Methods: Following PRISMA guideline, five bibliographic databases were used in our search: PubMed, Scopus, JSTOR, IEEE Xplore, and Google Scholar from 2015 to February 2022. Four reviewers carried out study selection and data extraction, and the data extracted was synthesized by a narrative approach. Results: This review included 23 unique publications out of a total of 1123 items that were initially identified. Different ethical principles regarding the uses of AI in public health and community health were identified and discussed distinctly in the current review. The common ethical and legal themes that this review focused on are equity, bias, privacy and security, safety, transparency, confidentiality, accountability, social justice, and autonomy. In addition, five ethical challenges were mentioned. Conclusion: Research regarding ethical and legal principles and challenges about using AI in public health specifically consider a new filed, because all previous themes are concerning the physical and patients’ area where it focuses only on the clinical settings.

The construction of different roads, such as freeways, highways, major roads or minor roads must be accompanied by constant monitoring and evaluation of service delivery. Pavements are generally assessed by engineers in terms of the smoothness, surface condition, structural condition and surface safety. Pavement assessment is often conducted using the qualitative indices such as international roughness index (IRI), pavement condition index (PCI), structural condition index (SCI) and skid resistance value (SRV), which are used for smoothness assessment, surface condition assessment, structural condition assessment, and surface safety assessment, respectively. In this paper, Tehran-Qom Freeway in Iran has been selected as the case study and its smoothness and pavement surface conditions are assessed. At 2-km intervals, a 100-meter sample unit is selected in the slow-speed lane (totally, 118 sample units). In these sample units, the PCI is calculated after a visual inspection of the pavement and the recording of distresses. Then, in each sample unit, the average IRI is computed. The purpose of this study is to provide a method for estimating PCI based on IRI. The proposed theory was developed by Random Forest (RF), and Random Forest optimized by Genetic Algorithm (RF-GA) methods and these methods were validated using correlation coefficient (CC), scattered index (SI), and Willmott’s index of agreement (WI) criteria. The proposed method reduces costs, saves time and eliminates the safety risks.

Accurate and stable cost forecasting of substation projects is of great significance to ensure the economic construction and sustainable operation of power engineering projects. In this paper, a forecasting model based on the improved least squares support vector machine (ILSSVM) optimized by wolf pack algorithm(WPA) is proposed to improve the accuracy and stability of the cost forecasting of substation projects. Firstly, the optimal features are selected through the data inconsistency rate (DIR), which helps reduce redundant input vectors. Secondly, the wolf pack algorithm is used to optimize the parameters of the improved least square support vector machine. Lastly, the cost forecasting method of WPA-DIR-ILSSVM is established. In this paper, 88 substation projects in different regions from 2015 to 2017 are chosen to conduct the training tests to verify the validity of the model. The results indicate that the new hybrid WPA-DIR-ILSSVM model presents better accuracy, robustness and generality in cost forecasting of substation projects.

The introduction of the AI-powered chatbot ChatGPT by OpenAI has sparked much interest and debate among academic researchers. Commentators from different scientific disciplines have raised many concerns and issues, especially related to the ethics of using these tools in scientific writing and publications. In addition, there has been discussions about whether ChatGPT is trustworthy, effective, and useful in increasing researchers’ productivity. Therefore, in this paper, we evaluate ChatGPT’s performance on tasks related to bibliometric analysis, by comparing the output provided by the chatbot with a recently conducted bibliometric study on the same topic. The findings show that there are large discrepancies and ChatGPT’s trustworthiness is low in this particular area. Therefore, researchers should exercise caution when using ChatGPT as a tool in bibliometric studies.

Although Support Vector Machines (SVM) are widely used for classifying human motion patterns, their application in the automatic recognition of dynamic and static activities of daily life in the healthy older adults is limited. Using a body mounted wireless inertial measurement unit (IMU), this paper explores the use of SVM approach for classifying dynamic (walking) and static (sitting, standing and lying) activities of the older adults. Specifically, data formatting and feature extraction methods associated with IMU signals are discussed. To evaluate the performance of the SVM algorithm, the effects of two parameters involved in SVM algorithm—the soft margin constant C and the kernel function parameter $\mathsf{\gamma }$—are investigated. The changes associated with adding white-noise and pink-noise on these two parameters along with adding different sources of movement variations (i.e., localized muscle fatigue and mixed activities) are further discussed. The results indicate that the SVM algorithm is capable of keeping high overall accuracy by adjusting the two parameters for dynamic as well as static activities, and may be applied as a tool for automatically identifying dynamic and static activities of daily life in the older adults.

The log data generated during the operation of a software system contains information about the system, and using logs for anomaly detection can detect system failures in a timely manner. Most of the existing log anomaly detection methods are specific to a particular system, have cold start problems, and are sensitive to updates in log format. In this paper, we propose a log anomaly detection method LogBD based on pre-training model and domain adaptation, which uses the pre-training model BERT to learn the semantic information of logs, and can solve the problems caused by multiple meaning words and log statement updates. An anomaly detection method LogBD based on distance to determine anomalies is constructed based on domain adaptation, using TCN networks to extract common features of different system logs and map them to the same hypersphere space. Finally, experiments are conducted on two publicly available datasets to evaluate the method, and the experimental results show that the method can better solve the log instability problem and has some improvement in the cross-system log anomaly detection effect.

In this experiment, an efficient and accurate network of detecting automatically disseminated (bot) content on social platforms is devised. Through the utilisation of parallel convolutional neural network (CNN) which processes variable n-grams of text 15, 20, and 25 tokens in length encoded by Byte Pair Encoding (BPE), the complexities of linguistic content on social platforms are effectively captured and analysed. With validation on two sets of previously unexposed data, the model was able to achieve an accuracy of around 96.6% and 97.4% respectively — meeting or exceeding the performance of other comparable supervised ML solutions to this problem. Through testing, it is concluded that this method of text processing and analysis proves to be an effective way of classifying potentially artificially synthesized user data — aiding the security and integrity of social platforms.

Artificial Intelligence (AI) has many advantages over humans in that it can detect incredibly subtle patterns within large quantities of data. This study suggests using AI algorithms in user research tasks for mining variables ranging from the tone of voice, image banks, historical records, and product use to determine where brands sit and where there could be competitive advantages. This study reviews the current design processes of User Experience (UX) designers and the advancements in Deep Learning (DL). It identifies potential areas of automation in the Preparation, Incubation and Illumination stages of the design process. It recognises the possibility of using Long Short-Term Memory (LSTM) models to automate design feedback and the creation of alternate designs with Generative Adversarial Networks (GANs).

Automation is at the core of modern industry. It aims to increase production rates, decrease production costs, and reduce human intervention in order to avoid human mistakes and time delays during manufacturing. On the other hand, human assistance is usually required to customize products and reconfigure control systems through a special process interface called Human Machine Interface (HMI). Machine Learning (ML) algorithms can effectively be used to resolve this tradeoff between full automation and human assistance. This paper provides an example of the industrial application of ML algorithms to help human operators save their mental effort and avoid time delays and unintended mistakes for the sake of high production rates. Based on real-time sensor measurements, several ML algorithms have been tried to classify paper rolls according to paper grammage in a white paper mill. The performance evaluation shows that the AdaBoost algorithm is the best ML algorithm for this application with classification accuracy (CA), precision, and recall of 97.1%. The generalization of the proposed approach for achieving a cost-effective mill construction by reducing the total number of the required physical sensors will be the subject of our future research.

In this paper, we address the problem of car detection from aerial images using Convolutional Neural Networks (CNN). This problem presents additional challenges as compared to car (or any object) detection from ground images because features of vehicles from aerial images are more difficult to discern. To investigate this issue, we assess the performance of two state-of-the-art CNN algorithms, namely Faster R-CNN, which is the most popular region-based algorithm, and YOLOv3, which is known to be the fastest detection algorithm. We analyze two datasets with different characteristics to check the impact of various factors, such as UAV's altitude, camera resolution, and object size. The objective of this work is to conduct a robust comparison between these two cutting-edge algorithms. By using a variety of metrics, we show that YOLOv3 yields better performance in most configurations, except that it exhibits a lower recall and less confident detections when object sizes and scales in the testing dataset differ largely from those in the training dataset.

Building energy consumption plays an essential role in urban sustainability. The prediction of the energy demand is also of particular importance for developing smart cities and urban planning. Machine learning has recently contributed to the advancement of methods and technologies to predict demand and consumption for building energy systems. This paper presents a state of the art of machine learning models and evaluates the performance of these models. Through a systematic review and a comprehensive taxonomy, the advances of machine learning are carefully investigated and promising models are introduced.

Formally specifying hedonic well-being is difficult, but relevant to utilitarian theories of morality. In this paper we describe a starting point based on attitudinal hedonism, which posits that hedonic well-being is determined by the extent to which a moral patient believes her preferences to be fulfilled. While this assumption probably does not capture the sought-out notion of well-being fully, our formalization seems to be relevant first step towards more satisfactory definition of hedonic well-being.

Introduction: Academic success is primary goal of every student. It is described as the extent to which a student has successfully achieved his or her short and long-term educational goals. Several factors have been established to predict academic performance of students. Machine learning techniques have been employed in predicting students’ performance, but it has not been prevalent in developing countries like Nigeria and most studies did not consider class teachers’ end-of-the-year rating. Aim: The aim of this work is to develop a Radial Basis Function Neural Network (RBFNN) for prediction of secondary school students’ performance. Materials and Methods: We obtained data from school repository containing students’ raw score and classteachers’ rating from year one to year six. The data was labelled into pass or fail given the actual outcome of their examinations. Subjects were categorized into Mathematics, English and major, depending on the student’s specialization. Class-teachers’ ratings were also included in the dataset. The preprocessed dataset was used to train the RBFNN model. The impact of Principal Component Analysis (PCA) was also measured. Results: We set up four experiments in order to achieve our aim. The best result gave the sensitivity of 93.49%, specificity of 75%, accuracy of 86.59% and an AUC score of 94%. Other experiments gave a relatively low performance. Conclusion: This study helps students to get a projection of academic success even before sitting for the examination. This will also help parents and counsellors in knowing the direction of their counseling to each student. Teachers and parents should pay attention to class teacher ratings of the students as this is discovered to affect the prediction accuracy of their examination success.

This study aimed to ascertain the applicability of a machine learning approach to the description of residential mobility patterns of households in the Seoul metropolitan region (SMR). The spatial range and temporal scope of the empirical study were set to 2015 to review the most recent residential mobility patterns in the SMR. The analysis data used in this study involve the microdata of Internal Migration Statistics provided by the Microdata Integrated Service of Statistics Korea. We analysed the residential relocation distance of households in the SMR by using machine learning techniques such as ordinary least squares regression and decision tree regression. The results of this study showed that a decision tree model can be more advantageous than ordinary least squares regression in terms of the explanatory power and estimation of moving distance. A large number of residential movements are mainly related to the accessibility to employment markets and some household characteristics. The shortest movements occur when households with two or more members move into densely populated districts. In contrast, job-based residential movements have relatively longer distance. Furthermore, we derived knowledge on residential relocation distance, which can provide significant information on the urban management of metropolitan residential districts and the construction of reasonable housing policies.

Crop breeding is as ancient as the invention of cultivation. In essence, the objective of crop breeding is to improve plant fitness under human cultivation conditions, making crops more productive while maintaining consistency in life cycle and quality. The applications of predictive breeding has been gaining momentum in agricultural industry and public breeding programs for the last decade, in the aftermath of genomic selection being recognized and widely applied for accelerating genetic gain in breeding programs. The massive amounts of data that has been generated by industry and farmers year after year through several decades has finally been recognized as an asset. A wide range of analytical methods such as machine learning, deep learning and artificial intelligence that were initially developed for diverse quantitative disciplines are now being adopted to crop breeding decision making processes. New technologies are currently being developed that would enable integration of data from various domains such as geospatial variables and a multitude of phenotypic responses as well as genetic information, in order to identify, develop and improve crop faster via partial or full automation of the decisions that pertain to variety development. Here we will discuss and summarize efforts from public and private domains for predictive analytics, and its applications to crop breeding and agricultural product development, and provide suggestions for future research.

Creating self-learning algorithms, developing deep neural networks and improving other methods that "learn" for various areas of human activity is the main goal of the theory of machine learning. It helps to replace the human with a machine, aiming to increase the quality of production. The theory of artificial neural networks, which already have replaced the humans in problems of detection of moving objects, recognition of images or sounds, time series prediction, big data analysis and numerical methods remains the most dispersed branch of the theory of machine learning. Certainly, for each area of human activity it is necessary to select appropriate neural network architectures, methods of data processing and some novel tools from applied mathematics. But the universal problem for all these neural networks with specific data is the achieving the highest accuracy in short time. Such problem can be resolved by increasing sizes of architectures and improving data preprocessing, where the accuracy rises with the training time. But there is a possibility to increase the accuracy without time growing, applying optimization methods. In this survey we demonstrate existing optimization algorithms of all types, which can be used in neural networks. There are presented modifications of basic optimization algorithms, such as stochastic gradient descent, adaptive moment estimation, Newton and quasi-Newton optimization methods. But the most recent optimization algorithms are related to information geometry, for Fisher-Rao and Bregman metrics. This approach in optimization extended the theory of classic neural networks to quantum and complex-valued neural networks, due to geometric and probabilistic tools. There are provided applications of all introduced optimization algorithms, what delighted many kinds of neural networks, which can be improved by including any advanced approaches in minimization of the loss function. Afterwards, we demonstrated ways of developing optimization algorithms in further researches, engaging neural networks with progressive architectures. Classical gradient based optimizers can be replaced by fractional order, bilevel and, even, gradient free optimization methods. There is a possibility to add such analogues in graph, spiking, complex-valued, quantum and wavelet neural networks. Besides the usual problems of image recognition, time series prediction, object detection, there are many are other tasks for modern theory of machine learning, such as solving problem of quantum computations, partial differential and integro-differential equations, stochastic processes and Brownian motion, making decisions and computer algebra.

In 1969, Jean-Marie Souriau introduced a “Lie Groups Thermodynamics” in Statistical Mechanics in the framework of Geometric Mechanics. This Souriau’s model considers the statistical mechanics of dynamic systems in their "space of evolution" associated to a homogeneous symplectic manifold by a Lagrange 2-form, and defines in case of non null cohomology (non equivariance of the coadjoint action on the moment map with appearance of an additional cocyle) a Gibbs density (of maximum entropy) that is covariant under the action of dynamic groups of physics (eg, Galileo's group in classical physics). Souriau Lie Group Thermodynamics was also addressed 30 years after Souriau by R. F. Streater in the framework of Quantum Physics by Information Geometry for some Lie algebras, but only in the case of null cohomology. Souriau method could then be applied on Lie Groups to define a covariant maximum entropy density by Kirillov representation theory. We will illustrate this method for homogeneous Siegel domains and more especially for Poincaré unit disk by considering SU(1,1) group coadjoint orbit and by using its Souriau’s moment map. For this case, the coadjoint action on moment map is equivariant. For non-null cohomology, we give the case of Lie group SE(2). Finally, we will propose a new geometric definition of Entropy that could be built as a generalized Casimir invariant function in coadjoint representation, and Massieu characteristic function, dual of Entropy by Legendre transform, as a generalized Casimir invariant function in adjoint representation, where Souriau cocycle is a measure of the lack of equivariance of the moment mapping.

The disruptive application of ChatGPT (GPT-3.5, GPT-4) to a variety of domains has become a topic of much discussion in the scientific community and society at large. Large Language Models (LLMs), e.g., BERT, Bard, Generative Pre-trained Transformers (GPTs), LLaMA, etc., have the ability to take instructions, or prompts, from users and generate answers and solutions based on very large volumes of text-based training data. This paper assesses the impact and potential impact of ChatGPT on the field of digital forensics, specifically looking at its latest pre-trained LLM, GPT-4. A series of experiments are conducted to assess its capability across several digital forensic use cases including artefact understanding, evidence searching, code generation, anomaly detection, incident response, and education. Across these topics, its strengths and risks are outlined and a number of general conclusions are drawn. Overall this paper concludes that while there are some potential low-risk applications of ChatGPT within digital forensics, many are either unsuitable at present, since the evidence would need to be uploaded to the service, or they require sufficient knowledge of the topic being asked of the tool to identify incorrect assumptions, inaccuracies, and mistakes. However, to an appropriately knowledgeable user, it could act as a useful supporting tool in some circumstances.

This paper presents a quantitative approach to poetry, based on the use of several statistical measures (entropy, information energy, N-gram, etc.) applied to a few characteristic English writings. We found that English language changes its entropy as time passes, and that entropy depends on the language used and on the author. In order to compare two similar texts, we were able to introduce a statistical method to asses the information entropy between two texts. We also introduced a method of computing the average information conveyed by a group of letters about the next letter in the text. We found a formula for computing the Shannon language entropy and we introduced the concept of N-gram informational energy of a poetry. We also constructed a neural network, which is able to generate Byron-type poetry and to analyze the information proximity to the genuine Byron poetry.

The dominance of social media has added to the channels of bullying to perpetrators. Unfortunately, cyberbullying (CB) is the most prevalent phenomenon in today’s cyber world and is a severe threat to the mental and physical health of citizens. This opens the need to develop a robust system to prevent bullying content from online forums, blogs, and social media platforms to manage the impact in our society. Several machine learning (ML) algorithms have been proposed for this purpose. However, their performances are not consistent due to high class imbalance issue and generalisation. In recent years, large language models (LLM) like BERT and RoBERTa have achieved state of the art (SOTA) results in several natural language processing (NLP) tasks. Unfortunately, the LLMs have not been applied extensively. In our paper, we explored the use of these models for cyberbullying (CB) detection. We have prepared a new dataset (D2) from existing studies (Formspring and Twitter). Our experimental results for dataset D1 and D2 showed RoBERTa outperformed other models.

The use of drones for various applications has become increasingly popular in recent years, and machine learning has played a significant role in this trend. In this paper, we provide a comprehensive survey of the classification and application of machine learning in drones. The paper begins with an overview of the different types of machine learning algorithms and their applications in drones, including supervised learning, unsupervised learning, and reinforcement learning. Next, we present a detailed analysis of various real-world applications of machine learning in drones, such as object recognition, route planning, obstacle avoidance, search area optimization, and autonomous search. The paper also discusses the challenges and limitations of using machine learning in drones, such as data privacy, data quality, and computational requirements. Finally, the paper concludes with a discussion of the future directions of machine learning in drones and its potential impact on various industries and fields. This paper provides a valuable resource for researchers, practitioners, and students interested in the intersection of machine learning and drones.

Many works have recently identified the need to combine deep learning with extreme learning to strike a performance balance with accuracy especially in the domain of multimedia applications. Considering this new paradigm, namely convolutional extreme learning machine (CELM), we present a systematic review that investigates alternative deep learning architectures that use extreme learning machine (ELM) for a faster training to solve problems based on image analysis. We detail each of the architectures found in the literature, application scenarios, benchmark datasets, main results, advantages, and present the open challenges for CELM. We follow a well structured methodology and establish relevant research questions that guide our findings. We hope that the observation and classification of such works can leverage the CELM research area providing a good starting point to cope with some of the current problems in the image-based computer vision analysis.

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.

Automated skin lesion analysis is one of the trending fields that has gained attention among the dermatologists and healthcare practitioners. Skin lesion restoration is an essential preprocessing step for lesion enhancements for accurate automated analysis and diagnosis. Digital hair removal is a non-invasive method for image enhancement by solving the hair-occlusion artefact in previously captured images. Several hair removal methods were proposed for skin delineation and removal. However, manual annotation is one of the main challenges that hinder the validation of these proposed methods on a large number of images or using benchmarking datasets for comparison purposes. In the presented work, we propose a realistic hair simulator based on context-aware image synthesis using image-to-image translation techniques via conditional adversarial generative networks for generation of different hair occlusions in skin images, along with the ground-truth mask for hair location. Besides, we explored using three loss functions including L1-norm, L2-norm and structural similarity index (SSIM) to maximise the synthesis quality. For quantitatively evaluate the realism of image synthesis, the t-SNE feature mapping and Bland-Altman test are employed as objective metrics. Experimental results show the superior performance of our proposed method compared to previous methods for hair synthesis with plausible colours and preserving the integrity of the lesion texture.

We present and benchmark FilterNet, a flexible deep learning architecture for time series classification tasks, such as activity recognition via multichannel sensor data. It adapts popular CNN and CNN-LSTM motifs which have excelled in activity recognition benchmarks, implementing them in a many-to-many architecture to markedly improve frame-by-frame accuracy, event segmentation accuracy, model size, and computational efficiency. We propose several model variants, evaluate them alongside other published models using the Opportunity benchmark dataset, demonstrate the effect of model ensembling and of altering key parameters, and quantify the quality of the models’ segmentation of discrete events. We also offer recommendations for use and suggest potential model extensions. FilterNet advances the state of the art in all measured accuracy and speed metrics on the benchmarked dataset, and it can be extensively customized for other applications.

Face recognition is a valuable forensic tool for criminal investigators since it certainly helps in identifying individuals in scenarios of criminal activity like fugitives or child sexual abuse. It is, however, a very challenging task as it must be able to handle low-quality images of real world settings and fulfill real time requirements. Deep learning approaches for face detection have proven to be very successful but they require a large computation power and processing time. In this work, we evaluate the speed-accuracy tradeoff of three popular deep-learning-based face detectors on the WIDER Face and UFDD data sets in several CPUs and GPUs. We also develop a regression model capable to estimate the performance, both in terms of processing time and accuracy. We expect this to become a very useful tool for the end user in forensic laboratories in order to estimate the performance for different face detection options. Experimental results showed that the best speed-accuracy tradeoff is achieved with images resized to 50% of the original size in GPUs and images resized to 25% of the original size in CPUs. Moreover, performance can be estimated using multiple linear regression models with a Mean Absolute Error (MAE) of 0.113 what is very promising for the forensic field.

Hateful and abusive speech presents a major challenge for all online social media platforms. Recent advances in Natural Language Processing and Natural Language Understanding allow more accurate detection of hate speech in textual streams. This study presents a multimodal approach to hate speech detection by combining Computer Vision and Natural Language processing models for abusive context detection. Our study focuses on Twitter messages and, more specifically, on hateful, xenophobic and racist speech in Greek aimed at refugees and migrants. In our approach we combine transfer learning and fine-tuning of Bidirectional Encoder Representations from Transformers (BERT) and Residual Neural Networks (Resnet). Our contribution includes the development of a new dataset for hate speech classification, consisting of tweet ids, along with the code to obtain their visual appearance, as they would have been rendered in a web browser. We have also released a pre-trained Language Model trained on Greek tweets, which has been used in our experiments. We report a consistently high level of accuracy (accuracy score=0.970, f1-score=0.947 in our best model) in racist and xenophobic speech detection.

With the advent of modern technologies, the healthcare industry is moving towards a more Personalised smart care model. The enablers of such care models are the Internet of Things (IoT) and Artificial Intelligence. These technologies collect and analyse data from persons in care to alert relevant parties if any anomaly is detected in a patient’s regular pattern. However, such reliance on IoT devices to capture continuous data extends the attack surfaces and demands high-security measures. Both patients and devices need to be authenticated to mitigate a large number of attack vectors. The biometric authentication method has been seen as a promising technique in these scenarios. To this end, this paper proposes an AI-based multimodal biometric authentication model for single and group-based users’ device-level authentication that increases protection against the traditional single modal approach. To test the efficacy of the proposed model, a series of AI models are trained and tested using physiological biometric features such as ECG (Electrocardiogram) and PPG (Photoplethysmography) signals from five publicly available datasets from Physionet and Mendeley data repositories. The multimodal fusion authentication model shows promising results with 99.8% accuracy and an Equal Error Rate (EER) of 0.16.

Current neural network models can demonstrate reasonable-looking behavior, considered by some developers and researchers human-like. For example, a large language model GPT-3 is susceptible to human-like cognitive biases. Yet there is no data of such models solving emotional intelligence (EI) tasks. They are connected to the abilities that has been previously considered as specifically human EI is an important aspect of human communication. The ability to understand and respond to emotional cues is essential for effective communication. Therefore, it is crucial to determine the ways AI models such as ChatGPT demonstrate EI. The present research aims to measure the EI of GPT-4, a large language model trained by OpenAI. Russian version of the Mayer–Salovey–Caruzo Emotional Intelligence Test sections B, C, D, F, G and H were used in this research. High points were obtained in Understanding emotions scale and Strategic EI. Mean points are obtained in Managing emotions scale. Low and less reliable values are obtained in Using emotions to facilitate thought scale. Thus, GPT-4 seems already capable of identifying emotions in text and describing techniques for managing them. However, complex cases and irregular situations requiring emotions qualitative analysis would be a hard task for GPT-4.

(1) Background: Artificial intelligence (AI) has existed in some form for decades, but recent rapid advances in a subset called machine learning (ML) — and more specifically deep learning (DL), a neural network-based approach — have made headlines for the potential to revolutionize and automate multiple large sectors of society, including scientific research and the healthcare field. Furthermore, large language models (LLMs) — which are built on DL — could lead to a more seamless, natural interaction between humans and computers. (2) Methods: We reviewed numerous publications on this subject from recent years. (3) Results: We found these studies collectively show that AI is positively disrupting both biomedical research and medical practice, such as optical imaging in surgery guidance. (4) Conclusions: However, we recommend caution in over-reliance on AI in the laboratory or the clinic due to anticipated risks and current limitations.

Multiple governmental agencies and private organisations have made commitments for the colonisation of Mars. Such colonisation requires complex systems and infrastructure that could be very costly to repair or replace in cases of cyber-attacks. This paper surveys deep learning algorithms, IoT cyber security and risk models, and established mathematical formulas to identify the best approach for developing a dynamic and self-adapting system for predictive cyber risk analytics supported with Artificial Intelligence and Machine Learning and real-time intelligence in edge computing. The paper presents a new mathematical approach for integrating concepts for cognition engine design, edge computing and Artificial Intelligence and Machine Learning to automate anomaly detection. This engine instigates a step change by applying Artificial Intelligence and Machine Learning embedded at the edge of IoT networks, to deliver safe and functional real- time intelligence for predictive cyber risk analytics. This will enhance capacities for risk analytics and assists in the creation of a comprehensive and systematic understanding of the opportunities and threats that arise when edge computing nodes are deployed, and when Artificial Intelligence and Machine Learning technologies are migrated to the periphery of the internet and into local IoT networks.

Deep learning has shown remarkable results in every field, especially in the biomedical field, due to its ability to exploit large-scale datasets. A convolutional neural network (CNN) is a widely used deep learning approach to solve medical imaging problems. Over the past few years, many studies have focused on CNN-based techniques for brain tumor diagnosis. There are, however, still some critical challenges that CNNs face towards clinic application. This study presents a comprehensive review of current literature that involves CNN architectures for brain tumor classification. We compare the key achievements in the performance evaluation metrics of the applied classification algorithms. In addition, this review assesses the clinical effectiveness of the included studies to elaborate on the limitations and directions of this area for future work. No review focusing on the clinical effectiveness of previous works in this field has been published. We believe that this study has the potential to elevate the application of CNN-based deep learning methods in clinical practice and also can be a quick reference for biomedical researchers who are interested in this field.

Social media platforms have been entirely an undeniable part of the lifestyle for the past decade. Analyzing the information being shared is a crucial step to understanding human behavior. Social media analysis aims to guarantee a better experience for the user and risen user satisfaction. However, first, it is necessary to know how and from which aspects to compare users. In this paper, an intelligent system has been proposed to measure the similarity of Twitter profiles. For this, firstly, the timeline of each profile has been extracted using the official TwitterAPI. Then, all information is given to the proposed system. Next, in parallel, three aspects of a profile are derived. Behavioral ratios are time-series-related information showing the consistency and habits of the user. Dynamic time warping has been utilized for the comparison of the behavioral ratios of two profiles. Next, the audience network is extracted for each user, and for estimating the similarity of two sets, Jaccard similarity is used. Finally, for the Content similarity measurement, the tweets are preprocessed respecting the feature extraction method; TF-IDF and DistilBERT for feature extraction are employed and then compared using the cosine similarity method. Results have shown that TF-IDF has slightly better performance; therefore, the more straightforward solution is selected for the model. Similarity level of different profiles. As in the case study, a Random Forest classification model was trained on almost 20000 users revealed a 97.24% accuracy. This comparison enables us to find duplicate profiles with nearly the same behavior and content.

In Thailand, parking time violation is a major problem, especially for mini-marts. At present the task of detecting parking time violation is mainly conducted manually using Closed-Circuit Television (CCTV). This method requires additional human labour to track incoming and outgoing vehicles. Therefore, low cost time violation tracking is needed. To the best of our knowledge, there has not been any research for parking violation detection and tracking conducted for parking time limits. This paper introduces a novel parking time violation detection algorithm using the Yolov8 and DeepSORT tracking algorithms to track vehicles in consecutive frames. The presented parking violation tracking algorithm can provide a guideline for research in parking time violation detection.

Exploiting the linguistic knowledge of the source language for neural machine translation (NMT) has recently achieved impressive performance on many large-scale language pairs. However, since the Turkish→English machine translation task is low-resource and the source-side Turkish is morphologically-rich, there are limited resources of bilingual corpora and linguistic information available to further improve the NMT performance. Focusing on the above issues, we propose a multi-source NMT approach that models the word feature in parallel to external linguistic features by using two separate encoders to explicitly incorporate linguistic knowledge into the NMT model. We extend the word embedding layer of the knowledge-based encoder to accommodate for each word’s linguistic annotations in the context. Moreover, we share all parameters across encoders to enhance the representation ability of the NMT model on the source language. Experimental results show that our proposed approach achieves substantial improvements of up to 2.4 and 1.1 BLEU scores in Turkish→English and English→Turkish machine translation tasks, respectively, which points to a promising way to utilize the source-side linguistic knowledge for the low-resource NMT.

To minimise environmental impact, avoid regulatory penalties, and improve competitiveness, energy-intensive manufacturing firms require accurate forecasts of their energy consumption so that precautionary and mitigation measures can be taken. Deep learning is widely touted as a superior analytical technique to traditional artificial neural networks, machine learning, and other classical time series models due to its high dimensionality and problem solving capabilities. Despite this, research on its application in demand-side energy forecasting is limited. We compare two benchmarks (Autoregressive Integrated Moving Average (ARIMA), and an existing manual technique used at the case site) against three deep learning models (simple Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU)) and three machine learning models (Support Vector Regression (SVM), Random Forest, and K-Nearest Neighbors (KNN)) for short term load forecasting (STLF) using data from a Brazilian thermoplastic resin manufacturing plant. We use the grid search method to identify the best configurations for each model, and then use Diebold-Mariano testing to confirm the results. Results suggests that the legacy approach used at the case site is the worst performing, and that the GRU model outperformed all other models tested.

In recent years, applying deep learning to solve physics problems has attracted much attention. Data-driven deep learning methods produce operators that can learn solutions to the whole system of partial differential equations. However, the existing methods are only evaluated on simple flow equations (e.g., Burger's equation), and only consider the generalization ability on different initial conditions. In this paper, we construct CFDBench, a benchmark with four classic problems in computational fluid dynamics (CFD): lid-driven cavity flow, laminar boundary layer flow in circular tubes, dam flows through the steps, and periodic Karman vortex street. Each flow problem includes data with various boundary conditions, fluid physical properties, and domain geometries. Compared to existing datasets, the advantages of CFDBench are (1) comprehensive. It contains common physical parameters such as velocity, pressure, and cavity fraction. (2) realistic. It is very suitable for deep learning solutions of fluid mechanics equations. (3) challenging. It has a certain learning difficulty, prompting to find models with strong learning ability. (4) standardized. CFDBench facilitates a comprehensive and fair comparison of different deep learning methods for CFD. We make appropriate modifications to popular deep neural networks to apply them to CFDBench and enable the accommodation of more changing inputs. The evaluation on CFDBench reveals some new shortcomings of existing works and we propose possible directions for solving such problems.