U.S. Navy Surface Ship depot-level maintenance periods of performance were studied to develop a method for predicting maintenance durations. The need for the method has been highlighted by Navy leadership in recent media posts describing unacceptable maintenance delays and this research provides practitioners and decisionmakers with a reliable estimating tool. This study helps by putting forth a method that defines the rate of work accomplishment based on relevant variables. Using ordinary least squares models, this research revealed that the size of the contract obligation and the amount of shipyard work occurring simultaneously in the market are key variables in determining depot maintenance durations. With the knowledge found here, the next logical step is an optimization model for each U.S. Navy surface ship homeport.

Using data-driven models to solve predictive maintenance problems has been prevalent for original equipment manufacturers (OEMs). However, such models fail to solve two tasks that OEMs are interested in: (1) Making the well-built failure prediction models working on existing scenarios (vehicles, working conditions) adaptive to target scenarios. (2) Finding out the failure causes, furthermore, determining whether a model generates failure predictions based on reasonable causes. This paper investigates a comprehensive architecture towards making the predictive maintenance system adaptive and interpretable by proposing (1) an ensemble model dealing with time-series data consisting of a long short-term memory (LSTM) neural network and Gaussian threshold to achieve failure prediction one week in advance and (2) an online transfer learning algorithm and a meta learning algorithm, which render existing models adaptive to new vehicles with limited data volumes. (3) Furthermore, the Local Interpretable Model-agnostic Explanations (LIME) interpretation tool and super-feature methods are applied to interpret individual and general failure causes. Vehicle data from Isuzu Motors, Ltd., are adopted to validate our method, which include time-series data and histogram data. The proposed ensemble model yields predictions with 100% accuracy for our test data on engine stalling problem and is more rapidly adaptive to new vehicles with smaller error following application of either online transfer learning or the meta learning method. The interpretation methods help elucidate the global and individual failure causes, confirming the model credibility.

Predictive maintenance (PM) algorithms are widely applied for detecting operational anomalies on industrial processes to trigger maintenance before a possible breakdown; however, much less focus has been devoted to the use of such PM predictions as feedback in automated process control mechanisms. They usually integrate preventive solutions to protect the machines, usually causing downtimes. The premise of this study is to develop a holistic adaptive process scheduling mechanism that incorporates PM analysis as a safety component to optimize the operation mode of an industrial process toward preventing breakdowns while maintaining its availability and operational state, thereby reducing downtimes. As PM is largely a data-driven approach; hence, relies on the setup, we first compare different PM approaches and identify a one-class support vector machine (OCSVM) as the best performing option for the anomaly detection on our setup. Then, we propose a novel pipeline to integrate maintenance predictions into a real-time adaptive process scheduling mechanism. It schedules for the most suitable operation, i.e., optimizing for machine health and process efficiency, according to the abnormal readings. To demonstrate the pipeline on action, we implement our approach on a small-scale conveyor belt system utilizing our Internet of Things (IoT) framework. The results show that our PM-based adaptive process control provides an efficient process with less or no downtime. We also conclude that a PM approach does not provide sufficient efficiency without its integration into an autonomous planning process.

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

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

Over the last 20 years, begomoviruses have emerged as devastating pathogens, limiting the production of different crops worldwide. Weather conditions increase vector populations, with negative effects on crop production. In this work we evaluated the relationship between the in-cidence of begomovirus and climatic conditions before and during the crop cycle. Soybean and bean fields from the northwest (NW) of Argentina were monitored for 14 years and classified as moderate (≤50%) and severe (> 50%) according to the relative incidence. Two hundred bio-meteorological variables were constructed, summarizing meteorological data in 10-day peri-ods from June to March of each crop year. The studied variables included temperature, precipi-tation, relative humidity, wind (speed and direction), pressure, cloudiness and visibility. For bean, high maximum winter temperatures, low spring humidity and precipitation 10 days before planting correlated with severe incidence. In soybeans, high late winter and pre-planting tem-peratures, and low spring precipitations were found to be good predictors of high incidence of begomovirus presence. The results suggest that temperature and pre-sowing precipitations can be used to predict incidence status [predictive accuracy: 82% (bean) and 75% (soybean)]. Thus, these variables can be incorporated in early warning systems for crop management deci-sion-making to reduce the virus impact on bean and soybean crops.

With the disruption of digital technologies, customers have emerged as co-producers in order to reduce costs and enhance productivity. Customer-driven business logic recognizes customer capabilities and sustainable innovation as key factors in the performance of customized manufacturing enterprises. The potential relationship between customers and producers has become a new area of inquiry. Existing research rarely delves into the impact of customer predictive ability on the process of customized production activities, particularly in relation to sustainable innovation, which remains inadequately characterized. Ships serve as a typical representation of customized enterprises. This study explores the underlying drivers of sustainable innovation through customer demand orientation by examining 20-year historical patterns in the global shipping and shipbuilding markets, considering the environmental dependency and temporal correlation characteristics of the shipbuilding market (producers) and the shipping market (consumers). By employing time series and panel data in a machine learning algorithm, specifically the random forest model, the study reveals a strong and statistically significant correlation between new ship deliveries and the Baltic Dry Index (BDI), with larger value ships having a more pronounced impact on the consumer market. The correlation analysis confirms that these two variables, in combination, can comprehensively reflect customer predictive ability and serve as crucial decision criteria for customer investment in new ship production. Furthermore, based on principal component analysis of customer predictive ability and ship innovation levels, as well as Granger causality tests, the study demonstrates that customer predictive ability is a Granger cause of sustainable innovation in customized production. Customer predictive ability influences sustainable innovation in customized enterprises to varying degrees. This research provides valuable insights for shipbuilding companies in terms of engaging in sustainable innovation in international markets and understanding the value of international market customers.

The purpose of this paper is to develop a theoretical predictive model for LNG shipping routes selection process. Strategic decisions about shipping costs could be improved if a deeper knowledge about products economic value is provided. Developments made on the extraction and industrial processes related to this fossil fuel are driving the natural gas sector towards a unique globalised market. Moreover, data analytics applications as well as machine learning are topics presented as perfect catalysers for achieving an unprecedented natural gas globalised market. Additionally, this paper aims at showing the state of the art of new techniques used in transportation engineering that might have synergies with other industries (eg. commodities cost reduction, energy supply…). Finally, this paper aims to provide foundation for further research and development using more sophisticated data and algorithms that will help to close the gap between theoretical and practical scope of this techniques.

A series of experiments were conducted to measure and quantify the yield, dry matter content, sugars content and nitrates content of grass intended for ensilement. These experiments took place in the East Midlands of Ireland during the Spring, Summer and Autumn of 2019. A bespoke sensor rig was constructed; included in this rig was a hyperspectral radiometer that measured a broad spectrum of reflected natural light from a circular spot approximately 1.2 metres in area. Grass inside a 50cm square quadrat was manually collected from the centre of the circular spot for ground truth estimation of the grass qualities. Up to 25 spots were recorded and sampled each day. The radiometer readings for each spot were automatically recorded onto a laptop that controlled the sensor rig, and ground truth measurements were made either on site or within 24 hours in a wet chemistry laboratory. The collected data was used to build Partial Least Squares Regression (PLSR) predictive models of grass qualities from the hyperspectral dataset and it was found that substantial relationships exist between the spectral reflectance from the grass and yield (r2 = 0.62), dry matter % (r2 = 0.54), sugar content (r2 = 0.54) and nitrates (r2 = 0.50). This shows that hyperspectral reflectance data contains substantial information about key grass qualities and can form part of a broader holistic data driven approach to provide accurate and rapid predictions to farmers, agronomists and agricultural contractors.

Pancreatic ductal adenocarcinoma (PDAC) is expected to be the second cause of cancer death by 2022. For nearly 80% of patients, diagnosis occurs at an advanced, non-surgical stage, making such patients incurable. Gemcitabine is still an important component in PDAC treatment and is most often used as a backbone to test new targeted therapies and there is, to date, no routine biomarker to predict its efficacy. Samples from a phase III randomized trial were used to develop trough a large approach based on blood-based liquid biopsy, transcriptome profiling, and machine learning, a 9 gene predictive signature for gemcitabine sensitivity. Patients with a positive test (41.6%) had a significantly longer progression free survival (PFS) (3.8 months vs. 1.9 months p=0.03) and a longer overall survival (OS) (14.5 months vs. 5.1 p<0.0001). In multivariate analyses, this signature was independently associated with PFS (HR=0.5 (0.28-0.9) p=0.025) and OS (HR=0.39 (0.21-0.7) p=0.002).

Machine learning (ML) has emerged as a critical tool for making sense of the growing amount of genetic and genomic data available because of its ability to find complex patterns in high dimensional and heterogeneous data. While the complexity of ML models is what makes them powerful, it also makes them difficult to interpret. Fortunately, recent efforts to develop approaches that make the inner workings of ML models understandable to humans have improved our ability to make novel biological insights using ML. Here we discuss the importance of interpretable ML, different strategies for interpreting ML models, and examples of how these strategies have been applied. Finally, we identify challenges and promising future directions for interpretable ML in genetics and genomics.

The goal of this contribution is an application of the Linear General Model Predictive Control (LGMPC). In this paper, stability of the LGMPC is proven by means of a demonstration of a Theorem stating a sufficient and constructive condition. This condition can be applied for calculating the weight matrices of the cost function in the optimisation problem in LGMPC. Lower bounds conditions are found for one of these matrices and then a system with saturation is taken into consideration. The conditions could be interpreted and discussions through physical aspects. The obtained results were tested by means of computer simulations and an example with a recover water process is considered.

GNSS receivers are nowadays commonly used in monitoring applications, e.g., in estimating crustal and infrastructure deformations. This is basically due to the recent improvements in GNSS instruments and methodologies that allow high precision positioning, 24 h availability and semiautomatic data processing. In this paper, GNSS estimated deformations on a dam structure have been analyzed and compared with pendulum data. This study has been carried out for the Eleonora D’Arborea (Cantoniera) dam, which is in the Sardinia Island. Time series of pendulum and GNSS over a time span of 2.5 years have been aligned so to be comparable. Analytical models fitting these time series have been estimated and compared. Those models were able to properly fit pendulum data and GNSS data, with standard deviation of residuals smaller than one millimeter. This encouraging results led to the conclusion that GNSS technique can be profitably applied to dam monitoring allowing a denser description, both in space and time, of the dam displacements than the one based on pendulum observations.

The present study aimed to develop a mathematical model to estimate the performance of an indoor rowing event of 6000m through an 500 m all out test in junior athletes. We selected141 subjects from the Brazilian rowing confederation database (15.9 ± 1.0 years), subsequently randomised the sample to the development (~70%) and cross-validation (~30%) groups of the mathematical model. Performance data for 500m and 6000m were collected (there was a 48h washout between one test and anoth-er).Subsequently, the mathematical model: Time(min) 6000m = { [( Time(s) 500-m * 6) * 2] / 60} + 1.3, was developed by arithmetic modeling using machine learning and Regression analysis, being tested by intraclass correlation coefficient (ICC), Concordance correlation coefficient (CCC), Validity (Cb ), preci-sion (ρ) and bland-Altman plotting. The prediction of the result of 6000m through the mathematical model utilizando apenas o desempenho de 500m “all-out” test showed a significant reliability in de-velopment group (r2 = 0.730, ICC = 0.753; CCC = 0.895, Cb = 0.879, ρ: 0.957, pure error: 0.2 secounds (1.0% estimative error)); and in cross-validation group (r2 = 0.710, ICC = 0.747; CCC = 0.888, Cb = 0.875, ρ: 0.903, pure error: 0.3 secounds (1.4% estimative error)). When comparing the estimated re-sults of the 6000m performance by the mathematical model with the real performance of 6000m per-formed in indoor rowing, no statistical differences were observed. In addition, the mathematical model did not present a significant proportion bias in relation to the 6000 m performance in both groups. The mathematical model for predicting 6000m performance through a 500m fast test was significant for national level junior rowing athletes.

The territory of Serbia is vulnerable to various types of natural and man-made disasters. The risk is not equal across the entire territory, depending on the type of hazard and the expected potential for damage. So far, the level of community disaster resilience has not been determined in Serbia. There are no scientific preconditions for its improvement to reduce the future material and intangible consequences of disasters. Regarding that, the project’s main objective is to develop and validate a predictive model of community disaster resilience based on social identity influences through an investigation impact of social identity indicators on the level of community disaster resilience in Serbia. The project is based on the upcoming research on whether the level of community disaster resilience can be predicted based on social identity indicators, how social identity indicators affect different dimensions of community disaster resilience, and how disasters shape social identity. The project is based on multimethod research in which quantitative (face-to-face interviews in 40 of the 191 municipalities), and qualitative (semi-structured interviews) research methodology will be applied. A developed predictive model with an index of community disaster resilience in Serbia will empower the creation of preconditions for designing public policies, strategies and procedures for improving resilience and reducing the consequences of disasters on people and their property and enhancing citizens’ security. The project will encourage the prediction of community disaster resilience based on social identity indicators, improving disaster foresight and preparing to limit disaster losses. Based on the development of analytical frameworks for understanding community disaster resilience and social identity in disasters, essential preconditions for designing innovative information systems will be created to enable local communities to increase their level of resilience.

Fuel consumption, subsequent emissions and safe operation of class 8 vehicles are of prime importance in recent days. It is imperative that the vehicle operates in its true optimal operating region given a variety of constraints such as road grade, load, gear shifts, Battery State of charge (for hybrid vehicles), etc. In this paper a research study is conducted to evaluate the fuel economy and subsequent emission benefits when applying predictive control to a mild hybrid line haul truck. The problem is solved using a combination of dynamic programming with back tracking and model predictive control. The specific fuel saving features that are studied in this work are dynamic cruise control, gear shifts, vehicle coasting and torque management. These features are evaluated predictively as compared to a reactive behavior. The predictive behavior of these features are a function of road grade. The result and analysis shows significant improvement in fuel savings along with NOx benefits. Out of the control features dynamic cruise (predictive) control and dynamic coasting showed the most benefits while predictive gear shifts and torque management (by power splitting between battery and engine) for this architecture did not show fuel benefits but provided other benefits in terms of powertrain efficiency.

One of the most dangerous diseases that threaten people is Cancer. Cancer if diagnosed in earlier stages can be eradicated with its life threatening consequences. In addition, accuracy in prediction plays a major role. Hence, developing a reliable model that contributes much towards the medical community in early diagnosis of Biopsy images with perfect accuracy come to the scenario. The article aims towards development of better predictive models using multi-variate data and high-resolution diagnostic tools in clinical cancer research. This paper proposes the social spider optimization (SSO) algorithm tuned neural network to classify microscopic biopsy images of cancer. The significance of the proposed model relies on the effective tuning of the weights of the NN classifier by the SSO algorithm. The performance of the proposed strategy is analysed with the performance metrics, such as accuracy, sensitivity, specificity, and MCC measures, and are attained to be 95.9181%, 94.2515%, 97.125%, and 97.68% respectively, which shows the effectiveness of the proposed method in effective cancer disease diagnosis.

Significant challenges exist globally regarding literacy teaching and learning, particularly in poor socio-economic settings in countries of the Global South. In this paper we argue that to address these challenges, major features of how the brain works that are currently ignored in the educational literature should be taken into account. First, perception is an active process based in detection of errors in hierarchical predictions of sensory data and action outcomes. Reading is a particular case. Second, emotions play a key role in underlying cognitive functioning. Innate affective systems underlie and shape all brain functioning, including oral and written forms of language and sign. Third, there is not the fundamental difference between listening/speaking and reading/writing often alleged on the basis of evolutionary arguments. Both are socio-cultural practices driven and learnt by the communication imperative of the social brain. Fourth, like listening, reading is not a linear, bottom-up process. Both are non-linear contextually shaped psycho-social processes of understanding, shaped by current knowledge and cultural contexts and practices. Reductionist neuroscience studies which focus on decontextualized parts of reading cannot access all the relevant processes. An integrated view of brain function reflecting this non-linear nature implies that an ongoing focus on personal meaning and understanding provides positive conditions for all aspects of literacy learning. Assessment of literacy teaching at all its stages should include indicators that take into account these foundational features relating reading and writing to neuroscience.

Globally, there is massive uptake and explosion of data and challenge is to address issues like scale, pace, velocity, variety, volume and complexity of this big data. Considering the recent epidemic in China, modeling of COVID-19 epidemic for cumulative number of infected cases using data available in early phase was big challenge. Being COVID-19 pandemic during very short time span, it is very important to analyze the trend of these spread and infected cases. This chapter presents medical perspective of COVID-19 towards epidemiological triad and the study of state-of-the-art. The main aim this chapter is to present different predictive analytics techniques available for trend analysis, different models and algorithms and their comparison. Finally, this chapter concludes with the prediction of COVID-19 using Prophet algorithm indicating more faster spread in short term. These predictions will be useful to government and healthcare communities to initiate appropriate measures to control this outbreak in time.

Background: Malignant pleural mesothelioma (MPM) is an atypical, belligerent tumor that matures into cancer in the pleura, a stratum of tissue bordering the lungs. Pleural mesothelioma is a common type of mesothelioma that accounts for about 75 percent of all mesothelioma diagnosed yearly in the United States. Diagnosis of mesothelioma takes several months and is expensive. Given the difficulty of diagnosing MPM, early identification is crucial for patient survival. Our study implements artificial intelligence and recommends the best fit model for early diagnosis and prognosis of MPM. Method: We retrospectively retrieved patient’s medical reports generated by Dicle University, Turkey and implemented multi-layered perceptron (MLP), voted perceptron (VP), Clojure classifier (CC), kernel logistic regression (KLR), stochastic gradient decent SGD), adaptive boosting (AdaBoost), Hoeffding tree (VFDT), and primal estimated sub-gradient solver for support vector machine (s-Pegasos). We evaluated the models, compared and tested using paired T-test (corrected) at 0.05 significance based on their respective classification accuracy, f-measure, precision, recall, root mean squared error, receivers characteristic curve (ROC), and precision-recall curve (PRC). Results: In phase-1 SGD, AdaBoost.M1, KLR, MLP, VFDT generates optimal results with the highest possible performance measures. In phase-2, AdaBoost with a classification accuracy of 71.29% outperformed all other algorithms. C-reactive protein, platelet count, duration of symptoms, gender, and pleural protein were found to be the most relevant predictors that can prognosticate mesothelioma. Conclusion: This study confirms that data obtained from biopsy and imagining tests are strong predictors of mesothelioma but are associated with high cost, however, can identify mesothelioma with optimal accuracy. Predictive analytics without using biopsy results can diagnose mesothelioma with acceptable accuracy. Implementation of phase-2 followed by phase-1 can address diagnosis expenses and maximize disease prognosis. Additionally, results indicate improved MPM diagnosis using AI methods dependent upon the specific application.

Imatinib 400 mg is the standard of care for medical treatment of advanced GISTs. In the majority of cases, however, GISTs eventually develop resistance to imatinib. The optimal second line treatment has not been established yet and imatinib dose escalation (800 mg) or sunitinib represent two feasible options. The objective of this retrospective, multi-institutional, study is to analyze the validity of several parameters as possible predictive factors of response to sunitinib after imatinib failure. We reviewed 128 metastatic GISTs treated with sunitinib between January 2007 to June 2017. Primary tumour site, metastatic site, c-KIT/PDGFR-α mutational status, PET-FDG status and type of disease progression to sunitinib were assessed as possible predictive factors of response. This study identifies the gastric site of primary tumor as a predictive factor to sunitinib efficacy in second line setting. The mutational status (GIST WT), the site of metastasis (peritoneum) and the FDG-PET status (negative), although not statistically significant, seem to be elements of increased activity for sunitinib treatment. These results provide the rationale to drive physician for sunitinib choice in second line setting for metastatic GISTs, to improve patients selection and to maximize the benefit from the treatment, on the basis of possible predictive factors of response.

The paper presents a case study and a model for condition monitoring of Diesel engines’ oil of urban buses, through the accompaniment of the evolution of its degradation, with the objective to implement a predictive maintenance policy. Along time, because the usage, there is some decay in the lubricant properties. However, in normal functioning conditions, the lubricants properties, at the time the manufacturers recommend its changing, regardless of they are within the safety limits. Then, based on the accompaniment of the lubricants’ oil condition, the intervals of oil replacement can be enlarged what implies the availability increasing and the corresponding production increasing of the equipment. The model presented in this paper shows its potential to be spread to other types of equipment and organisations that want can implement similar maintenance policies, to achieve the best availability based on the real equipment health conditioning conditions

The objective of this study is to design an optimal model predictive control (MPC) strategy using manipulated variables to control the production of a sufficient amount of hydrogen through low temperature autothermal reforming of dimethyl ether (DME), a reforming reaction performed using PdO/ZnO/γ-Al2O3 catalysts coated on honeycomb cordierite ceramics. Experiments and simulation have verified that the optimal activity temperature of the catalyst is 400 °C, and the hydrogen volume fraction in syngas is over 43%. In the implementation of the hydrogen production system, the MPC controller can precisely determine the feed rates of DME, high-purity air, and water based on the space state equation of the reformer, to achieve the anti-disturbance of the reformer temperature. Thus, the reduction of hydrogen yield and sintering of the catalyst as a result of overheating are prevented. As the static and dynamic performance of hydrogen production exhibits excellent tracking of the setpoints, an autonomous, automated, and reliable continuous system was designed to meet the desired hydrogen demand situation. This study shows that an autonomous, automated, and reliable continuous hydrogen production reforming system can be designed to actively respond to the on-board hydrogen usage situation.

(1) Background: Ventilator-associated pneumonia (VAP) causes high mortality among patients with respiratory disease and imposes major burdens on healthcare infrastructure. Models that use electronic health record data to predict the onset of VAP may spur earlier treatment and improve patient outcomes. We developed and studied the performance of interpretable machine learning (ML) models that predict the onset of VAP from electronic health records (EHRs); (2) Methods: We trained Logistic Regression (LR), full feature Explainable Boosting Machine (fEBM), and eXtreme Gradient Boosting (XGBoost) ML models on data from the MIMIC- III (v1.3) database. Model performance was measured by area under the receiver operating characteristic curves (AUCs). We trained a minimal-feature EBM model (mEBM) with features derived from white blood cell (WBC) counts, duration of ventilation, and Glasgow Coma Scale (GCS). Finally, model robustness was evaluated on randomly sparsified EHR datasets; (3) Results: The fEBM model outperformed the XGBoost and LR models at 24 hours post-intubation. The mEBM model maintained an AUC of 0.893. The fEBM model performance remained robust on sparsified datasets; (4) Conclusions: Our novel interpretable ML algorithm reliably predicts the onset of VAP in intubated patients. Integration of this EBM-based model into clinical practice may enable clinicians to better anticipate and prevent VAP.

Purpose: To investigate trabeculopuncture (TP) for predicting the outcome of ab interno trabeculectomy (AIT). AIT is an effective, low-risk procedure for open angle glaucoma. Despite widespread utilization, it fails in patients with an unidentified distal outflow resistance. Methods: We bisected 81 enucleated porcine eyes and perfused them for 72 hours. They were assigned to two groups: trial (n=42) and control (n=39). Intraocular pressure (IOP) was measured continuously. At 24 hours, four YAG-laser trabeculopunctures on the nasal trabecular meshwork were performed, followed by a 180° AIT at the same site at 48 hours. Eyes were divided into TP and AIT responders and non-responders; the proportion of TP responders between both AIT groups was compared. Results: Both post-TP and post-AIT IOPs were lower than baseline IOP (p=0.015 and p<0.01, respectively). The success rates of TP and AIT were 69% and 85.7%, respectively. The proportion of TP responders among AIT responders was greater than that of AIT non-responders (p<0.01). Sensitivity and specificity values of TP as predictive test for AIT success were 77.7% and 83.3%, respectively. The positive and negative predictive values were 96.6% and 38.5%, respectively. Conclusion: A 10% reduction in IOP after TP can be used as predictor for the success (>20% IOP decrease) of 180° AIT in porcine eyes.

This paper presents the results of quantitative research regarding the predictive model of citizens' attitudes about the risks of introducing the death penalty in the Republic of Serbia legal system. The research was conducted with the use of a questionnaire that was requested and then collected online from 427 people in June 2021. A multivariate regression analysis was used, identifying the extent to total scores of the main dependent variables (introducing the death penalty; trust in the legal system; advantages of introduction; disadvantages of introduction scores) were associated with five demographic and socio-economic variables: gender, marital, education, income, and age. We tested the central hypothesis of which gender is predicting variables citizens' attitudes about the risks of introducing the death penalty in the legal system of Serbia. The findings revealed that gender and educational level were the most effective predictors of the research variables under question. The majority of respondents support the introduction of the death penalty and the most important predictor of disadvantages of introducing the death penalty in the legal system is age. Based on the findings that there are major differences in the citizens' attitudes about the risks of introducing the death penalty in the legal system, policies, strategies, and regulations must take into account these very important findings.

XGBoost is recognized as an algorithm with exceptional predictive capacity. Models for a binary response indicating the existence of accident claims vs. no claims can be used to identify the determinants of traffic accidents. We compare the relative performances of logistic regression and XGBoost approaches for predicting the existence of accident claims using telematics data. The dataset contains information from an insurance company about individuals’ driving patterns – including total annual distance driven and percentage of total distance driven in urban areas. Our findings show that logistic regression is a suitable model given its interpretability and good predictive capacity. XGBoost requires numerous model-tuning procedures to match the predictive performance of the logistic regression model and greater effort as regards interpretation.

The following paper describes an economical, multiple model predictive control (EMMPC) for an air conditioning system of a confectionery manufacturer in Germany. The application consists of a packaging hall for chocolate bars, in which a new local conveyor belt air conditioning system is used and thus the temperature and humidity limits in the hall can be significantly extended. The EMMPC calculates the optimum energy or cost humidity and temperature set points in the hall. For this purpose, time-discrete state space models and an economic objective function with which it is possible to react to flexible electricity prices in a cost-optimised manner are created. A possible future electricity price model for Germany with a flexible EEG levy was used as a flexible electricity price. The flexibility potential is determined by variable temperature and humidity limits in the hall, which are oriented towards the comfort field for easily working persons, and the building mass. The building mass of the created room model is used as a thermal energy store. Considering electricity price and weather forecasts as well as internal, production plan-dependent load forecasts, the model predictive controller directly controls the heating and cooling register and the humidifier of the air conditioning system.

In recent years, metabolomics has been used as a powerful tool to better understand the physiology of neurodegenerative diseases and identify potential biomarkers for progression. We used targeted and untargeted aqueous, and lipidomic profiles of the metabolome from human cerebrospinal fluid to build multivariate predictive models distinguishing patients with Alzheimer’s disease (AD), Parkinson’s disease (PD), and healthy age-matched controls. We emphasize several statistical challenges associated with metabolomic studies where the number of measured metabolites far exceeds sample size. We found strong separation in the metabolome between PD and controls, as well as between PD and AD, with weaker separation between AD and controls. Consistent with existing literature, we found alanine, kynurenine, tryptophan, and serine to be associated with PD classification against controls, while alanine, creatine, and long chain ceramides were associated with AD classification against controls. We conducted a univariate pathway analysis of untargeted and targeted metabolite profiles and find that vitamin E and urea cycle metabolism pathways are associated with PD, while the aspartate/asparagine and c21-steroid hormone biosynthesis pathways are associated with AD. We also found that the amount of metabolite missingness varied by phenotype, highlighting the importance of examining missing data in future metabolomic studies.

Background: CoronaVirus Disease 2019 (COVID-19) is the main discussed topic world-wide in 2020 and at the beginning of the Italian epidemic, scientists tried to understand the virus diffusion and the epidemic curve of positive cases with controversial findings and numbers. Objectives: In this paper, a data analytics study on the diffusion of COVID-19 in Lombardy Region and Campania Region is developed in order to identify the driver that sparked the second wave in Italy Methods: Starting from all the available official data collected about the diffusion of COVID-19, we analyzed google mobility data, school data and infection data for two big regions in Italy: Lombardy Region and Campania Region, which adopted two different approaches in opening and closing schools. To reinforce our findings, we also extended the analysis to the Emilia Romagna Region. Results: The paper aims at showing how different policies adopted in school opening / closing may have on the impact on the COVID-19 spread. Conclusions: The paper shows that a clear correlation exists between the school contagion and the subsequent temporal overall contagion in a geographical area.

Abstract:Global ship demolition is mostly concentrated in south Asian countries, namely Bangladesh, India, Pakistan and China, since 1990’s, having competitive advantage for their high natural tide, and low environmental and social costs. Due to high social and environmental externalities, stakeholders increase monitoring of the externalities and continue to prescribe improvement towards sustainability, which put pressures on profitability and competitiveness. As a consequence, also seen in the past, a leakage effect may emerge, leading to shift of this activity to a region, with relatively less monitored and less stricter on social and environmental impacts. Unfortunately, the leakage effect is never predicted in shipbreaking in order to understand the level of push compatible in the given socio-economic contexts. In this study, we have attempted to predict the future ship demolition landscape, applying machine learning technique to 34,531 in-service vessels worldwide, larger than 500 gross tonnage (GT), which is run against a learning model based on 3500 demolished vessels from 2014. This study shows that redistribution may occur among the top recycling nations: India may emerge out to be a dominant player in shipbreaking, surpassing Bangladesh by a margin of two-fold, while Pakistan and China are in decreasing trend. In addition, the leakage effect is observed, in that Vietnam is predicted to be the fourth largest ship demolition country, while China and Pakistan recede from the third and fourth place to 6th and 8th. Turkey is predicted to advance from fifth position to third position by vessel count but stays same in term of total GT dismantled. Although it is not clear if any leakage is to be observed in the near future, this study may be a model for future predictive analytics and help stakeholders take evidence-based business decisions.

In this paper, a capacitor microphone system is presented to improve the conversion of mechanical energy to electrical energy using a nonlinear auto regressive moving average-L2 (NARMA-L2) and model predictive control (MPC) controllers for the analysis of the open loop and closed loop system. The open loop system response shows that the output voltage signal need to be improved. The comparison of the closed loop system with the proposed controllers have been analyzed and a promising result have been obtained using Matlab/Simulink.

Modularity is arguably one of the most influential theses guiding research on brain and cognitive function since phrenology. This paper considers the following question: is modularity entailed by recent Bayesian models of brain and cognitive function, especially the predictive processing framework? It starts by considering three of the most well-articulated arguments for the view that modularity and predictive processing work well together. It argues that all three kinds of arguments for modularity come up short, albeit for different reasons. The analysis in this paper, although formulated in the context of predictive processing, speaks to broader issues with how to understand the relationship between functional segregation and integration and the reciprocal architecture of the predictive brain. These conclusions have implications for how to study brain and cognitive function. Specifically, when cognitive neuroscience works within an acyclic Markov decision scheme, adopted by most Bayesian models of brain and cognitive function, it may very well be methodologically misguided. This speaks to an increasing tendency within the cognitive neurosciences to emphasise recurrent and reciprocal neuronal processing captured within newly emerging dynamical causal modelling frameworks. The conclusions also suggest that functional integration is an organising principle of brain and cognitive function.

Multiobjective optimization plays an increasingly important role in modern applications, where several criteria are often of equal importance. The task in multiobjective optimization and multiobjective optimal control is therefore to compute the set of optimal compromises (the Pareto set) between the conflicting objectives. The advances in algorithms and the increasing interest in Pareto optimal solutions have led to a wide range of new applications related to optimal and feedback control which results in new challenges such as expensive models or real-time applicability. Since the Pareto set generally consists of an infinite number of solutions, the computational effort can quickly become challenging which is particularly problematic when the objectives are costly to evaluate or when a solution has to be presented very quickly. This article gives an overview over recent developments in accelerating multiobjective optimal control for complex problems where either PDE constraints are present or where a feedback behavior has to be achieved. In the first case, surrogate models yield significant speed-ups. Besides classical meta-modeling techniques for multiobjective optimization, a promising alternative for control problems is to introduce a surrogate model for the system dynamics. In the case of real-time requirements, various promising model predictive control approaches have been proposed, using either fast online solvers or offline-online decomposition. We also briefly comment on dimension reduction in many-objective optimization problems as another technique for reducing the numerical effort.

Precision Agriculture is the ability to handle variations in productivity within a field and maximize financial return, optimize resource utilization and minimize impact of the environment. It is also the process of automated data collection, cloud storage and utilization to build robust decision support system. In case of Ethiopia, due to poor communication infrastructure coverage and absence of the state-of-the-art technology in the agriculture sector, implementing precision farming system is a challenging tasks in the domain area. In this work, we proposed a fusion of multiple sensors using IOT and IIOT infrastructure to collect critical data from farming fields to develop precision farming facility for decision makers. The main purpose was to monitor weather variability, automate irrigation process, extract critical soil properties. In addition, we have used time series data collected from sensor devices to build forecasting model. Fusion of multiple IoT device provide a mechanism in the agriculture area to deal with real-time monitoring of crops. It is cost-effective technology and required low-energy with edge computing sensor device. We employed the Message Queuing Telemetry Transport (MQTT) protocol to connect the Industrial/Internet of Things (I/IoT) to the cloud server. The communication between system user and sensor device has been done via cloud using Node-RED platform, web android APIs. The cloud-based Eco-system allows us to aggregate, visualize, and analyze live streams output from each sensor in real-time manner. Finally, we have built time series forecasting model using records collected by each sensor device. Using the multi-variate time series data-set, we have obtained about 99 forecasting accuracy on some important variables. Finally, we have developed mobile and web-based application for the end-user to monitor the proposed system remotely.

There is immense variability in the postharvest quality of Hass avocados. However, there is a lack of knowledge to guaranteeing the robustness of fruit with consistent quality. The aims of this work were to develop a multivariate methodology for evaluating the postharvest quality of avocado and to determine predictive quality markers to manage fruit quality. Fruit samples produced under different nutrient management, elevation, date-to-harvest, and growing-cycle conditions were analyzed. The results highlighted soil and weather differences among orchards. Nutrient management practices based on index balancing in some samples increased both productivity and the fruit size. High variability was observed in the dry matter related to the age of the fruit at harvest. Ripening heterogeneity was very large in low-elevation orchards where the fruit was picked relatively early. High flesh mineral contents delayed fruit ripening. At low growing temperatures, more oleic and linoleic acids were present in fruits. The sensory texture and taste descriptors were affected by the fruit age and related to the flesh composition. Logistic, PLS-DA, and biplot models effectively represented the variabilities in the ripening pattern, composition, and sensory profile of avocado fruits and allowed the samples to be grouped according to the internal fruit quality.

Immune checkpoint inhibitors (ICI) are currently use in a wide range of tumors, but only 20-40% of patients achieve clinical benefit. Aim of our study was to find predictive biomarkers of ICI treatment. We analyzed by immunohistochemistry various cell subsets, including CD3+ cells, CD8+ cells, CD68+ cells, CD20+ cells, FoxP3+ cells, and molecules as LAG-3, IDO1, TGfβ. Comprehensive genomic profiles were analyzed. Correlation of various biomarkers with efficacy of ICI treatment in patients with advanced solid tumors was evaluated. We evaluated 56 patients treated with ICI monotherapy. Longer median progression-free survival (PFS) was found in tumors negative for nuclear FoxP3 (P = 0.002, HR 0.14) and in TMB-high tumors (P = 0.024, HR 0.38). Longer overall survival (OS) was found in patient with intraepithelial CD8 negativity (P = 0.045, HR 0.47). In malignant melanoma CD68 negativity, FoxP3 negativity and PDL TPS ≥ 1 was associated with longer PFS. In NSCLC FoxP3 was associated with longer PFS and OS. We found that absence of expression of several biomarkers such as CD68 and FoxP3 is associated with better survival. TMB-high and PD-L1 expression not universally but in certain disease could predict response.

Background Content marketing is increasingly important for online branding. Brand popularity can be more easily determined online than sales-based measures but is not yet well-explained from a content marketing perspective. Promising predictors are open data syndication policies, connectivity to e-commerce platforms, product reviews, data health, and the depth and width of a brands product portfolio. A predictive content marketing model can help brand owners to understand their e-commerce potential. Methods We used brand popularity (Brand Popularity Rank) and catalog data in combination with product reviews from an independent content aggregator. For all datasets, we selected the overlapping dataset for brand popularity and brand reviews based on a period of 90 days from June 10, 2022, till September 24, 2022 (n = 333 brands). Backward stepwise multiple linear regression was used to develop a predictive content marketing model of the Brand Popularity Rank. Results Through stepwise backward multiple linear regression five highly significant (p < 0.01) predictive factors for brand rank are selected in our content marketing model: the brand’s data syndication policy, the number of connected e-commerce platforms, a brand’s number of products, its number of products per category, and the number of product categories in which it is active. Our model explains 78% of the variance of Brand Popularity Rank and has a good and highly significant fit: F (5, 327) = 233.5, p < 0.00001. Conclusions We conclude that a content marketing model can adequately predict a Brand Popularity Rank based on online popularity. In this model an open content syndication policy, more connected e-commerce platforms, and catalog size, i.e., presence in more categories and more products per category are each related to a better (lower) Brand Popularity Rank score.

Osteosarcoma (OSA) is the most common primary malignant bone tumor. More than 40% of patients with OSA have poor prognoses. We aimed to discover a biomarker for patient stratification and therapeutic targets for these high-risk patients. Using Single Sample Gene Set Enrichment Analysis (ssGSEA) and univariate Cox analysis, six hallmarks were identified as significant prognostic factors for overall survival (OS). Three were selected to construct a multivariate Cox model. Then, WGCNA, univariate Cox regression, Kaplan-Meier (KM) survival analyses, and multivariate Cox analyses were combined to filter promising candidates and establish a seven-gene signature to predict OS, whose prognostic value was validated internally and externally. Subsequently, Differential Expression Analysis was conducted between high- and low-risk patients, and the Robust Rank Aggregation algorithm was used to determine the robust DEGs. Metascape was used to perform pathway and process enrichment analyses as well as construct protein-protein interaction (PPI) networks. Finally, RPS28 was identified as an independent risk factor by using univariate and multivariate Cox regression, which was preliminarily validated as a promising therapeutic target by using RNA interference. In conclusion, we might contribute to optimizing risk stratification and an excellent therapeutic target for high-risk patients with OSA.

Based on the resource-based theory, the current study examines the relationship between competitive strategies and strategic alliance performance. Furthermore, big data predictive analytics is treated as a boundary condition between competitive strategies and strategic alliance performance. Big data of predictive analytics in operations and industrial management has been a focal point in the current era. There has been little attention has about big data predictive analytics influences on competitive strategies and strategic alliance performance, especially in developing countries like Pakistan. A survey instrument was used to record the responses from 331 employees of the telecom sectors companies working in Pakistan. Study findings show that big competitive strategies have a positive and significant relationship with strategic alliances performance. It was also found that big data predictive analytics plays the role of moderator between competitive strategies and strategic alliance performance. The study add a new perspective and contribution to the literature on big data predictive analytics, strategic alliance performance, and competitive strategies in Pakistan's telecom sector companies. Further, the study results explain that big data analytics is just like the companies' lifeblood in the current era. The efficient and effective use of big data analytics, companies can boost their standards in a competitive environment.

This paper attempts to compare two different approaches to solve the problem of accident rates prediction based on human factors for industrial workers. One of the methods has already been done using Fuzzy c-Means Clustering and proved to be working with decent results. The second method which will be covered in this paper is using Artificial Neural Networks. The primary goal of this work is to insure that ANN will work efficiently in such prediction problem. The second goal is to reveal the fact that which one of the two selected methodologies is better at defining the estimation of accident rates among people who work in different industrial fields. The purpose has been achieved when the outcome of the ANN was obtained and compared accordingly with the output of the research previously carried out with Fuzzy c-means clustering method. Comparing the outcomes of these two different methods gave an immense insight on which features are more important than others when it comes to laborers properties with completely different background such as varying levels of health, knowledge, experience, training and physical properties. At the end of the research, it becomes clear that accident rates estimation for laborers with properly trained Artificial Neural Network gives better results when it is compared with Fuzzy c-Means Clustering method. Standard deviation method was used to calculate the validity of ANN technique. The result was compared with Fuzzy c-mean clustering technique. Impressive improvement of 8.8% in the accident rate prediction was achieved using Tailored-Made-ANN.

The efficacy of weed management depends on the correct control timing according to the seedling emergence dynamics. Since soil temperature and soil moisture are two main factors that determine weed germination, the hydrothermal time model can be used to predict their emergence. The aim of this study was to estimate the base temperature (Tb) and base water potential (Ψb) for germination of Chenopodium album, Amaranthus retroflexus, Setaria pumila and Panicum capillare collected from fields in continental Croatia and then to compare these values with those of Italian populations embedded in the AlertInf model. Germination tests were performed at seven constant temperatures (ranging from 4 to 27°C) and eight water potentials (0.00 to - 1.00 MPa). Estimated Tb and Ψb were 3.4°C, -1.38 MPa for C. album, 13.9°C, -0.36 MPa for A. retroflexus, 6.6°C, -0.71 MPa for S. pumila and 11.0°C, -0.87 MPa for P. capillare, respectively. According to the criterion of overlap of the 95% confidence intervals, only Tb of C. album, and Ψb of A. retroflexus were similar between Croatian and Italian populations. Further field experiments should be conducted in the Croatian field to monitor weed emergence patterns of C. album and to calibrate the AlerInf equation parameters.

Driving simulators are widely used for understanding human-machine interaction, driver behavior and in driver training. The effectiveness of simulators in these process depends largely on their ability to generate realistic motion cues. Though the conventional filter-based motion cueing strategies have provided reasonable results, these methods suffer from poor workspace management. To address this issue, linear MPC-based strategies have been applied in the past. However, since the kinematics of the motion platform itself is non-linear and the required motion varies with the driving conditions, this approach tends to produce sub-optimal results. This paper presents a nonlinear MPC-based algorithm which incorporates the nonlinear kinematics of the Stewart platform within the MPC algorithm in order to increase the cueing fidelity and utilize maximum workspace. Further, adaptive weights-based tuning is used to smoothen the movement of the platform towards its physical limits. Full-track simulations were carried out and performance indicators were defined to objectively compare the response of the proposed algorithm with classical washout filter and linear MPC-based algorithms. The results indicate a better reference tracking with lower root mean square error and higher shape correlation for the proposed algorithm. Lastly, the effect of the adaptive weights-based tuning was also observed in the form of smoother actuator movements and better workspace utilization.

Breast Cancer diagnosis is one of the most studied problems in the medical domain. In the medical domain, cancer diagnosis has been studied extensively which instantiates the need of early prediction of cancer disease. For obtaining advance prediction, health records are exploited and given as input to an automated system. This paper focuses on constructing an automated system by employing deep learning based recurrent neural network models. A stacked GRU-LSTM-BRNN is proposed in this paper that accepts health records of a patient for determining possibility of being affected by breast cancer. Proposed model is compared against other baseline classifiers such as stacked Simple-RNN model, stacked LSTM-RNN model, stacked GRU-RNN model. Comparative results obtained in this study indicate that stacked GRU-LSTM-BRNN yield better classification performance for predictions related to breast cancer disease.

The reactive nature of traditional frequency stability methods can lead to delayed corrective actions and unnecessary loss-of-load. This work presents a distributed model predictive control method for proactive power system frequency stability. Dynamic state estimation model is derived through a particle filter. By being able to estimate the future state of frequency, corrective actions can be taken before the system reaches a critical condition. Proactive approach makes it possible to optimize the response to a disturbance, which results in a decrease of the amount of compensation utilized. The method is tested via Matlab simulations based on Kundur's Two-Area System, and the IEEE 14-Bus system. Performance metrics are provided and evaluated against other contemporary solutions found in literature. Easy-to-derive model, without hard-to-design parameters, indicate potential towards real-life applications.

This study employs a high-fidelity numerical framework to determine the plastic material flow patterns and temperature distributions that lead to void formation during friction stir welding (FSW), and to relate the void morphologies to the underlying alloy material properties and process conditions. Three aluminum alloys, viz., 6061-T6, 7075-T6, and 5053-H18 were investigated under varying traverse speeds. The choice of aluminum alloys enables investigation of a wide range of thermal and mechanical properties. The numerical simulations were validated using experimental observations of void morphologies in these three alloys. Temperatures, plastic strain rates, and material flow patterns are considered. The key results from this study are: (1) The predicted stir zone and void morphology are in good agreement with the experimental observations, (2) The temperature and plastic strain-rate maps in the steady-state process conditions show a strong dependency on the alloy type and traverse speeds, (3) The material velocity contours provide a good insight into the material flow in the stir zone for the FSW process conditions that result in voids as well as those that do not result in voids. The numerical model and the ensuing parametric studies presented in this work provide a framework for understanding material flow under different process conditions in aluminum alloys, and potentially in other alloys. Furthermore, the utility of the numerical model for making quantitative predictions and investigating different process parameters to reduce void formation is demonstrated.

For a decade, the studies of dynamic control for unmanned aerial vehicles took a large interest, where drones as a useful technology in different areas were always suffering from several issues like instability-high energy consumption of batteries - inaccuracy of tracking targets. Different approaches are proposed for dealing with the non-linearity issues which present the most important features of this system. This paper describes our focus on the most common control strategies, known as model predictive control MPC, by developing a model based on the sensors embedded in our Tello quadrotor used for indoor purposes. The original controller of Tello quadrotor is supposed to be a slave, where the designed model predictive controller is created in MATLAB and imported to another embedded system, considered as a master; the objective of this model is to track the reference trajectory, almost keeping the stability of the system and ensure the low energy consumption. In the first part, a profound description of the modelling process of a dynamic model for drones is presented, explaining the design of MPC controller with both linear and non-linear strategies built in MATLAB. In the final part, simulation and results are discussed regarding its behaviour and performance, highlighting the MPC model's important role on drones' energy consumption profile.

High-performance motor drives that operate in harsh conditions require an accurate and robust angular position measurement to correctly estimate the speed and reduce the torque ripple produced by angular estimation error. For that reason, a resolver is used in motor drives as a position sensor due to its robustness. A resolver-to-digital converter (RDC) is an observer used to get the angular position from the resolver signals. Most RDCs are based on angle tracking observers (ATOs). On the other hand, generalized predictive control (GPC) has become a powerful tool in developing controllers and observers for industrial applications. However, no GPC-based RDC with zero steady-state error during constant speed operation was proposed. This paper proposes an RDC based on a second-order difference GPC (SOD-GPC). In SOD-GPC, the second-order difference operator is applied to design a GPC model with two embedded integrators. Thus, the SOD-GPC is used to design a type-II ATO whose steady-state angle estimation error tends to zero during constant speed operation. Simulation and experimental results prove that the proposed RDC system has better performance than other literature approaches.

Circulating tumor cells (CTCs) enumeration is a promising technique to predict cancer prognosis and treatment response. CTCs were evaluated in healthy subjects, cirrhotic controls and hepatocarcinoma (HCC) patients. CTCs were isolated using microfluidic system based on the expression of EpCAM, EGFR and three epithelial to mesenchymal transition (EMT) markers. Patients were stratified according to disease progression and exitus. Although counts of individual CTCs, clustered CTCs and α-fetoprotein (AFP) at basal level in patients with HCC were significantly increased compared with the values obtained in cirrhotic patients and control subjects, only individual CTCs (p=0.027), but not clustered CTCs (p=0.063) and AFP (p=0.072), were independent predictors of HCC development. The univariate regression model showed that basal levels of CTCs46 were related to high risk of HCC (Odds Ratio 3.467, p=0.011). The stratification of our cohort according to disease progression and death showed that basal individual CTCs 76 (Hazard Ratio 5.131, p=0.004) were related to disease progression, as well as the difference of clustered CTCs between 1-month and baseline levels 1.5 were related to death (Hazard Ratio 10.204, p=0.036). In conclusion, the preoperative and 1-month measurements of CTCs in blood constitute useful markers to predict the outcome of patients under TACE treatment.

Rapid increase in digital data coupled with advances in deep learning algorithms is opening unprecedented opportunities for incorporating multiple data sources for modeling spatial dynamics of human infectious diseases. We used Convolutional Neural Networks (CNN) in conjunction with satellite imagery-based urban housing and socio-economic data to predict disease density in a developing country setting. We explored both single (uni) and multiple input (multimodality) network architectures for this purpose. We achieved maximum test set accuracy of 81.6 per cent using a single input CNN model built with one convolutional layer and trained using housing image data. However, this fairly good performance was biased in favor of specific disease density classes due to an unbalanced data set despite our use of methods to address the problem. These results suggest CNN are promising for modeling spatial dynamics of human infectious diseases, especially in a developing country setting. Urban housing signals extracted from satellite imagery seem suitable for this purpose, under the same context.

This paper presents a cascade predictive control structure based on the field-oriented control (FOC) in the dq rotor reference frame for the synchronous reluctance machine (SynRM). The constant d-axis current control strategy was used and thus, the electromagnetic torque was directly controlled by the q-axis current. Because the model of the two axes currents from the inner loop is a coupled non-linear multivariable one, to non-interaction linear control the two currents, their decoupling was achieved through feedforward components. Following the decoupling, two independent monovariable linear systems resulted for the two currents dynamics that were controlled using model predictive control (MPC) algorithms, considering their ability to automatically handle the state bounds. The most important bounds for SynRM are the limits imposed on currents and voltages, which in the dq plane correspond to a circular limit. To avoid computational effort, linear limitations were adopted through polygonal approximations, resulting in rectangular regions in the dq plane. For the outer loop that controls the angular speed with a constrained MPC algorithm, as plant was considered the q-axis current closed loop dynamics and the torque linear equation. To evaluate the performances of the proposed cascade predictive control structure, a simulation study using MPC controllers versus PI ones was conducted.

The use of artificial intelligence (AI) applications in education has the potential to revolutionize the learning experience for international students, who face unique challenges when studying in a foreign country. This paper explores various examples of AI applications in education and their potential impact on international students. AI applications such as personalized learning experiences, adaptive testing, predictive analytics, and chatbots for learning and research are examined for their potential to improve learning efficiency and provide customized education support. It also explores the significant risks and limitations associated with AI technologies, such as privacy, cultural differences, language proficiency, and ethical implications. To maximize the potential benefits of AI applications in higher education, it is crucial to implement appropriate safeguards and regulations. This paper provides a starting point for research on the potential impact of artificial intelligence on international students’ educational experiences and how AI may be integrated into educational administration and learning processes.

Tissue programmed death ligand-1 (PD-L1) protein expression is predictive of immune checkpoint inhibitor (ICI) benefit. However, tissue PD-L1 can be fraught with tissue acquisition and heterogeneity limitations. Plasma testing can overcome these limitations. However, the overall survival (OS) predictive benefit of plasma PD-L1 assays have not been well characterized. Patients with stage IV non-small cell lung cancer (NSCLC) and plasma cfRNA PD-L1 by PCR expression were identified and assessed for OS. 16 patients treated with front-line ICI-based regimens were assessed and represented a real-world patient population with over half with a performance status of 2 or greater. 10 contemporaneous patients at the same institution treated with chemotherapy alone were also identified and assessed. With a median follow-up of 33 months, median OS was 13 months with a 30% 3-year OS for the ICI treated patients compared to a median OS of 3 months and a 10% 3-year OS for those treated with chemotherapy alone. Comparative log-rank test p-value = 0.014 and a hazard ratio 0.376 (95%-CI 0.134-1.057). Plasma cfRNA PD-L1 was associated with a statistically significant survival benefit from ICI-based treatment compared to chemotherapy in the first line treatment of a real-world patient population of advanced NSCLC.

Individual differences in the responsiveness of the brain to transcranial electrical stimulation (tES) is increasingly demonstrated in large variability in the tES effects. Anatomically detailed computational brain models have been developed to address this variability; however, static brain models are not ‘realistic’ in accounting for the dynamic state of the brain. Therefore, human-in-the-loop optimization is proposed in this perspective article based on an extensive systems analysis of the tES neurovascular effects. First, modal analysis was conducted using a physiologically detailed neurovascular model that found stable modes in the 0 Hz to 0.05 Hz range for the pathway for vessel response through the smooth muscle cells, measured with functional near-infrared spectroscopy (fNIRS). tES effects in the 0 Hz to 0.05 Hz range can also be measured with functional magnetic resonance imaging (fMRI)-tDCS data with a maximum TR=10sec. Therefore, we investigated an open-source fMRI-tDCS dataset that used a TR=3.36sec. We found that both the anodal tDCS condition and sham tDCS condition had similar Finite Impulse Response at the region of interest underlying the anode and a remote location, which indicated a global hemodynamic effect of sham tDCS beyond the intended transient sensations. Here, transient sensations can have arousal effects on the hemodynamics so we conducted a healthy case series for black box modeling of fNIRS-pupillometry of short-duration tDCS effects. The block exogeneity test rejected the claim that tDCS is not a 1-step Granger-cause of the fNIRS total hemoglobin changes (HbT) and pupil dilation changes (p<0.05). Also, grey-box modeling using fNIRS of the tDCS effects in chronic stroke showed HbT response to be significantly different (paired-sample t-test, p<0.05) between the ipsilesional and the contralesional hemisphere for primary motor cortex tDCS and cerebellar tDCS which was subserved by the smooth muscle cells. Here, our perspective is that various physiological pathways subserving tES effects can lead to state-trait variability that can be challenging for clinical translation. Therefore, we conducted a case study on human-in-the-loop optimization using our reduced dimension model and a stochastic, derivative-free Covariance Matrix Adaptation Evolution Strategy. Future studies need to investigate human-in-the-loop optimization of tES for reducing inter-subject and intra-subject variability in tES effects.

Additive manufacturing (AM) is an attractive technology for manufacturing industry due to flexibility in design and functionality, but inconsistency in quality is one of the major limitations that does not allow utilizing this technology for production of end-use parts. Prediction of mechanical properties can be one of the possible ways to improve the repeatability of the results. The part placement, part orientation, and STL model properties (number of mesh triangles, surface, and volume) are used to predict tensile modulus, nominal stress and elongation at break for polyamide 2200 (also known as PA12). EOS P395 polymer powder bed fusion system was used to fabricate 217 specimens in two identical builds (434 specimens in total). Prediction is performed for XYZ, XZY, ZYX, and Angle orientations separately, and all orientations together. The different non-linear models based on machine learning methods have higher prediction accuracy compared with linear regression models. Linear regression models have prediction accuracy higher than 80% only for Tensile Modulus and Elongation at break in Angle orientation. Since orientation-based modeling has low prediction accuracy due to a small number of data points and lack of information about material properties, these models need to be improved in the future based on additional experimental work.

BACKGROUND Epidemiological sciences have been evolving at an exponential rate paralleled only by the comparable growth within the discipline of data science. Digital epidemiological studies are playing a vital role in medical science analytics for the past few decades. To date, there are no published attempts at deploying the use of real-time analytics in connection with the disciplines of Dentistry or Medicine. AIMS AND OBJECTIVES We deployed a real-time statistical analysis in connection with topics in Dental Anatomy and Dental Pathology represented by the maxillary sinus, posterior maxillary teeth, related oral pathology. The purpose is to infer the digital epidemiology based on a continuous stream of raw data retrieved from Google Trends database. MATERIALS AND METHODS Statistical analysis was carried out via Microsoft Excel 2016 and SPSS version 24. Google Trends database was used to retrieve data for digital epidemiology. Real-time analytics and the statistical inference were based on encoding a programming script using Python high-level programming language. A systematic review of the literature was carried out via PubMed-NCBI, the Cochrane Library, and Elsevier databases. RESULTS The comprehensive review of databases of the literature, based on specific keywords search, yielded 491813 published studies. These were distributed as 488884 (PubMed-NCBI), 1611 (the Cochrane Library), and 1318 (Elsevier). However, there was no single study attempting real-time analytics. Nevertheless, we succeeded in achieving an automated real-time stream of data accompanied by a statistical inference based on data extrapolated from Google Trends. CONCLUSION Real-time analytics are of considerable impact when implemented in biological and life sciences as they will tremendously reduce the required resources for research. Predictive analytics, based on artificial neural networks and machine learning algorithms, can be the next step to be deployed in continuation of the real-time systems to prognosticate changes in the temporal trends and the digital epidemiology of phenomena of interest.

We present a generalized state-space model formulation particularly motivated by an online scheduling perspective. Through these proposed generalizations, we enable a natural way to handle routinely encountered disturbances and a rich set of corresponding counter-decisions. Thereby, greatly simplifying and extending the possible application of mathematical programming based online scheduling solutions to diverse application settings.

This article presents a forecast model that uses a hybrid architecture of recurrent neural networks (RNN) with surface neural networks (ANN), based on historical records of exported active energy (EAE) and weather data. Two types of models were developed: the first type includes six models that use EAE records and weather variables as inputs, while the second type includes eight models that use only weather variables. Different metrics were applied to assess the performance of these models, and the best model of each type was selected. Finally, a comparison of the performance between the selected models of both types is presented, and they are validated with real data provided by a solar plant, achieving acceptable levels of accuracy. The selected model of the first type has an RMSE of 0.19, MSE of 0.03, MAE of 0.09, a correlation coefficient of 0.96, and a determination coefficient of 0.93. The other selected model of the second type showed lower precision in the metrics (RMSE = 0.24, MSE = 0.06, MAE = 0.10, Corr. Coef. = 0.95, and Det. Coef. = 0.90). Both models demonstrated good performance and acceptable accuracy in forecasting the weekly photovoltaic energy production of the solar plant.

The study is based on the notion that big data predictive analytics is important for developing strategic alliances performance of companies. this study investigates the relationship between big data predictive analytics, big data culture, and competitive strategies 'techniques were adopted, such as descriptive statistics, correlation,regression, etc. using SPSS and SmartPLS statistical software. Hypotheses were tested with bootstrapped analysis using SEM (through SmartPLS). The study developed a structural equation model by using the SEM analysis. The results of the SEM analysis suggested the hypothesized model of the study was valid. The results supported all the hypotheses of the study.Through empirical analysis, demonstrated the conclusion is that the big data predictive analytics has a positive and significant relationship with strategic alliance performance

This work presents a nonlinear model predictive control scheme that challenges overcoming the obstacles holding back over decades to develop affordable autonomous control and monitoring systems applied in the large-scale industry. Among the numerous proposals in the literature, most do not consider the significant fluctuation of kinetic parameters in the reduced mathematical model ADM2, widely used for control and monitoring purposes. The prevalent cause, on a basis, is the lack of information caused by some dynamics and parameters that cannot be measured in real-time by reliable sensors. In addition, to make matters worse, those systems inherently act with nonlinear nature and have a high sensitiveness to uncontrollable inputs and perturbations. Therefore, to prevent these drawbacks, this work proposes a new methodology that reconstructs the lack of information from the non-measurable dynamics, concentration of bacterias, and the kinetic parameters related to reaction rates. Simulations results demonstrate the effectiveness of the methodology compared with traditional industrial control schemes.

One of the most important challenges in the Machine and Deep Learning areas today is to build good models using small datasets, because sometimes it is not possible to have large ones. Several techniques have been proposed in the literature to address this challenge. This paper aims at studying the different available Deep Learning techniques and performing a thorough experimentation to analyze which technique or combination thereof improves the performance and effectiveness of the models. A complete comparison with classical Machine Learning techniques was carried out, to contrast the results obtained using both techniques when working with small datasets. Thirteen algorithms were implemented and trained using three different small datasets (MNIST, Fashion MNIST, and CIFAR-10). Each experiment was evaluated using a well-established set of metrics (Accuracy, Precision, Recall, F1, and the Matthews correlation coefficient). The experimentation allowed concluding that it is possible to find a technique or combination of them to mitigate a lack of data, but this depends on the nature of the dataset, the amount of data, and the metrics used to evaluate them.

Persistent Pain after Spinal Surgery can be successfully addressed by Spinal Cord Stimulation (SCS). International guidelines strongly recommend that a lead trial be performed before any permanent implantation. Recent clinical data highlight some major limitations of this approach. First, it appears that patient outcomes, WITH OR WITHOUT lead trial, are similar. In contrast, during trialing, infection rate drops drastically within time and can compromise the therapy. Using composite pain assessment experience and previous research, we hypothesized that ma-chine learning models could be robust screening tools and reliable predictors of long-term SCS efficacy. We developed several algorithms including logistic regression, Regularized Logistic Regression (RLR), naive Bayes classifier, artificial neural networks, random forest and gradient boosted trees to test this hypothesis and to perform internal and external validations, the objec-tive being to confront model predictions with lead trial results using a 1-year composite out-come from 103 patients. While almost all models have demonstrated superiority on lead trial-ing, the RLR model appears to represent the best compromise between complexity and inter-pretability in prediction of SCS efficacy. These results underscore the need to use AI based-predictive medicine, as a synergistic mathematical approach, aimed at helping implanters to optimize their clinical choices on daily practice.

The strategy of any organization is based on the growth of its customer base, and one of its principles is that selling a product to an existing customer is much more profitable than acquiring a new customer. However, this approach has several opportunities for improvement, since it usually has a totally reactive approach, which does not give opportunity to the areas specialized in customer experience and recovery, to give an effective response for that moment, since the customer is gone at the time of the intervention. This happens because usually a diagnostic analysis of customers who have stopped buying products or services in a defined period, commonly three (3) periods or months, is performed. This thesis work challenges the way to face this problem, and proposes the development of a complete solution, which does not focus exclusively on the prediction of churn, as is usually done in the state of the art research, but to intervene in different interactions that can be carried out with customers. The above focused not only to prevent customer churn, but to generate an added value of continuous improvement in sales processes, increase customer penetration, leading to an improvement in customer experience and consequently, an increase in customer loyalty.

In this paper, the power quality of interconnected microgrids is managed using a Model Predictive Control (MPC) methodology which manipulates the power converters of the microgrids in order to achieve the requirements. The control algorithm is developed for the microgrids working modes: grid-connected, islanded and interconnected. The results and simulations are also applied to the transition between the different working modes. In order to show the potential of the control algorithm, a comparison study is carried out with classical Proportional-Integral Pulse Width Modulation (PI-PWM) based controllers. The proposed control algorithm not only improves the transient response in comparison with classical methods but also shows an optimal behavior in all the working modes, minimizing the harmonics content in current and voltage even with the presence of non-balanced and non-harmonic-free three-phase voltage and current systems

Deep behavioral covariates (DBCs) introduced in this perspective form a new class of covariates that have the potential to enhance the performance of predictive models and improve analytics in clinical decision support applications. DBCs can measure how engaged a patient tends to be and how he or she tends to respond to events, and they may be highly predictive of the patient’s outcomes for a planned treatment. DBCs may potentially serve as a standard to measure patient engagement and activation and may form highly efficient mechanisms for improving patient outcomes.

We analyze damage propagation modeling of turbo-engines in a data-driven approach. We investigate subspace tracking assuming a low dimensional manifold structure and a static behavior during the healthy state of the machines. Our damage propagation model is based on the deviation of the data from the static behavior and uses the notion of health index as a measure of the condition. Hence, we incorporate condition-based maintenance and estimate the remaining useful life based on the current and previous health indexes. This paper proposes an algorithm that adapts well to the dynamics of the data and underlying system, and reduces the computational complexity by utilizing the low dimensional manifold structure of the data. A significant performance improvement is demonstrated over existing methods by using the proposed algorithm on CMAPSS Turbo-engine datasets.

Immune checkpoint blockade (ICB) has revolutionized the prognosis of several advanced-stage solid tumors. However, its success has been far more limited in hematological malignancies and is mostly restricted to classical Hodgkin lymphoma (cHL) and primary mediastinal B cell lymphoma (PMBCL). In patients with non-Hodgkin lymphoma (NHL), response to PD-1/PD-L1 ICB monotherapy has been relatively limited, although some subtypes are more sensitive than others. Numerous predictive biomarkers have been investigated in solid malignancies, such as PD-L1 expression, tumor mutational burden (TMB) and microsatellite instability (MSI), among others. This case-illustrated review aims to appraise the current knowledge on PD-1/PD-L1 ICB efficacy in lymphoid malignancies, when used either as monotherapy or combined with other agents, and describes potential biomarkers of response in this specific setting.

This paper presents designing an attitude motion control strategy for a half-car model using an anti-jerk predictive controller. Anti-jerk predictive controller based on active aerodynamics surfaces is employed to deal with the anticipated future road maneuvers and improve vehicle ride performance by canceling out external jerks acting on the vehicle body. The body jerks are produced during vehicle traversing on a double lane-change maneuver, acceleration, or braking. The control strategy helps the vehicle to achieve a realistic operation of the active aerodynamic surface to improve the vehicle’s ride performance, i.e., ride comfort and road holding during cornering, acceleration, or braking. The anti-jerk predictive controller is developed based on the predictive control strategy, which predicts future road inputs and uses them to compensate for the vehicle’s attitude motion. The simulation results show that the proposed control strategy effectively reduces the effects of vehicle body jerks transmitted to the passengers, improving ride comfort without degrading vehicle handling. The anti-jerk predictive controller successfully tracks the desired attitude position by canceling the external body jerks.

Internet of Things (IoT) technologies can greatly benefit from machine learning techniques and Artificial Neural Networks for data mining and vice versa. In the agricultural field, this convergence could result in the development of smart farming systems suitable for use as decision support systems by peasant farmers. This work presents the design of a smart farming system for crop production, which is based on low-cost IoT sensors and popular data storage services and data analytics services on the Cloud. Moreover, a new data mining method exploiting climate data along with crop production data is proposed for the prediction of production volume from heterogeneous data sources. This method was initially validated using traditional machine learning techniques and open historical data of the northeast region of the state of Puebla, Mexico, which were collected from data sources from the National Water Commission and the Agri-food Information Service of the Mexican Government.

The strategy of any organization is based on the growth of its customer base, and one of 5 its principles is that selling a product to an existing customer is much more profitable than acquiring 6 a new customer. However, this approach has several opportunities for improvement, since it usu- 7 ally has a totally reactive approach, which does not give opportunity to the areas specialized in 8 customer experience and recovery, to give an effective response for that moment, since the customer 9 is gone at the time of the intervention. This happens because usually a diagnostic analysis of cus- 10 tomers who have stopped buying products or services in a defined period, commonly three (3) pe- 11 riods or months, is performed. This thesis work challenges the way to face this problem, and pro- 12 poses the development of a complete solution, which does not focus exclusively on the prediction 13 of churn, as is usually done in the state of the art research, but to intervene in different interactions 14 that can be carried out with customers. The above focused not only to prevent customer churn, but 15 to generate an added value of continuous improvement in sales processes, increase customer pene- 16 tration, leading to an improvement in customer experience and consequently, an increase in cus- 17 tomer loyalty.

The strategy of any organization is based on the growth of its customer base, and one of 6 its principles is that selling a product to an existing customer is much more profitable than acquiring 7 a new customer. However, this approach has several opportunities for improvement, since it usu- 8 ally has a totally reactive approach, which does not give opportunity to the areas specialized in 9 customer experience and recovery, to give an effective response for that moment, since the customer 10 is gone at the time of the intervention. This happens because usually a diagnostic analysis of cus- 11 tomers who have stopped buying products or services in a defined period, commonly three (3) pe- 12 riods or months, is performed. This paper challenges the way to face this problem, and proposes 13 the development of a complete solution, which does not focus exclusively on the prediction of 14 churn, as is usually done in the state of the art research, but to intervene in different interactions 15 that can be carried out with customers. The above focused not only to prevent customer churn, but 16 to generate an added value of continuous improvement in sales processes, increase customer pene- 17 tration, leading to an improvement in customer experience and consequently, an increase in cus- 18 tomer loyalty.

The strategy of any organization is based on the growth of its customer base, and one of 5 its principles is that selling a product to an existing customer is much more profitable than acquiring 6 a new customer. However, this approach has several opportunities for improvement, since it usu- 7 ally has a totally reactive approach, which does not give opportunity to the areas specialized in 8 customer experience and recovery, to give an effective response for that moment, since the customer 9 is gone at the time of the intervention. This happens because usually a diagnostic analysis of cus- 10 tomers who have stopped buying products or services in a defined period, commonly three (3) pe- 11 riods or months, is performed. This paper challenges the way to face this problem, and proposes 12 the development of a complete solution, which does not focus exclusively on the prediction of 13 churn, as is usually done in the state of the art research, but to intervene in different interactions 14 that can be carried out with customers. The above focused not only to prevent customer churn, but 15 to generate an added value of continuous improvement in sales processes, increase customer pene- 16 tration, leading to an improvement in customer experience and consequently, an increase in cus- 17 tomer loyalty.

Monitoring volatile organic compounds (VOCs) places a crucial role in environmental pollutants control and indoor air quality. In this study, a metal-oxide (MOx) sensor detector (used in a commercially available monitor) was employed to delineate the composition of air containing three common VOCs (ethanol, acetone and hexane) under various concentrations. Experiments with a single component and double components were conducted to investigate how the solvents interact with the metal oxide sensor. The experimental results revealed that the affinity between VOC and sensor was in the following order: acetone > ethanol > n-hexane. A mathematical model was developed, based on the experimental findings and data analysis, to convert the output resistance value of the sensor into concentration values, which in turn can be used to calculate a VOC-based air quality index. Empirical equations were established based on inferences of vapor composition versus resistance trends, and on an approach of using original and diluted air samples to generate two sets of resistance data per sample. The calibration of numerous model parameters allowed matching simulated curves to measured data. As such, the predictive mathematical model enabled quantifying not only the total concentration of sensed VOCs, but also estimating the VOC composition. This first attempt to obtain semi-quantitative data from a single MOx sensor, despite remaining selectivity challenges, is aimed at expanding the capability of mobile air pollutants monitoring devices.

The aim of this study was to develop and validate a predictive early tooth loss multivariable model for periodontitis patients before periodontal treatment. A total of 544 patients seeking periodontal care at a university dental hospital were enrolled in the study. Teeth extracted after periodontal diagnosis and due to periodontal reasons were recorded. Clinical and sociodemographic variables were analyzed, considering the risk of short-term tooth loss. This study followed the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) guidelines for development and validation, with two cohorts considered as follows: 455 patients in the development phase and 99 in the validation phase. As a result, it was possible to compute a predictive model based on tooth type and clinical attachment loss. The model explained 25.3% of the total variability and correctly ranked 98.9% of the cases. The final reduced model area under the curve (AUC) was 0.809 (95% Confidence Interval (95% CI): 0.629 - 0.989) for the validation sample and 0.920 (95% CI: 0.891 - 0.950) for the development cohort. The established model presented adequate prediction potential of early tooth loss due to periodontitis. This model may have clinical and epidemiologic relevance towards the prediction of tooth loss burden.

A novel machine learning approach is presented in this paper, based on extracting latent information and using it to assist decision making on ambulance attendance and conveyance to a hospital. The approach includes two steps: in the first, a forward model analyzes the clinical and, possibly, non-clinical factors (explanatory variables), predicting whether positive decisions (response variables) should be given to the ambulance call, or not; in the second, a backward model analyzes the latent variables extracted from the forward model to infer the decision making procedure. The forward model is implemented through a machine, or deep learning technique, whilst the backward model is implemented through unsupervised learning. An experimental study is presented, which illustrates the obtained results, by investigating emergency ambulance calls to people in nursing and residential care homes, over a one-year period, using an anonymized data set provided by East Midlands Ambulance Service in United Kingdom.

Although decision making strategy based on clinico-histopathological criteria is well established, renal cell carcinoma (RCC) represents a spectrum of biological ecosystems characterized by distinct genetic and molecular alterations, diverse clinical courses and potential specific therapeutic vulnerabilities. Given the plethora of drugs available, the subtype-tailored treatment to RCC subtype holds the potential to improve patient outcome, shrinking treatment-related morbidity and cost. The emerging knowledge of the molecular taxonomy of RCC is evolving, whilst the antiangiogenic and immunotherapy landscape maintained and reinforced their potential. Although several prognostic factors of survival in patients with RCC have been described, no reliable predictive biomarkers of treatment individual sensitivity or resistance have been identified. In this review, we summarize the available evidence able to prompt more precise and individualized patient selection in well-designed clinical trials, covering the unmet need of medical choices in the era of next-generation anti-angiogenesis and immunotherapy.

The modification the gut microbiota in metabolic syndrome and associated chronic diseases is among leading tasks of microbiome research and needs for clinical use of probiotics. Evidence lack for the implications for microbiome modification to improve metabolic health in particular when applied impersonalized. Probiotics have tremendous potential in personalized nutrition and medicine to develop healthy diets. The aim was to to conduct comprehensive overview of recent updates of role of microbiota on human health and development of metabolic syndrome and efficacy of microbiota modulation considering specific properties of probiotic strain and particular aspects of metabolic syndrome and patient`s phenotype to fill the gap between probiotic product and individual to facilitate development of individualized / personalized probiotic and prebiotic treatments. We discuss the relevance of using host phenotype-associated biomarkers, those based on imaging and molecular and patrient`s history, reliable and accessible to facilitate person-specific appication of probiotics and prebiotic substances. Microbiome phenotypes can be parameters of predictive medicine to recognize patient`s predispositions and evaluate treatment responses; the number of phenotype markers can be effectively involved to monitor microbiome modulation. The studied strain-dependent properties of probiotic strains are potentially relevant for individualized treatment for gut and distant sites microbiome modulation. The evidence regarding probiotic strains properties can be taken to account via pathophysiology-based approach for most effective individualized treatment via gut, oral and vaginal and other sites microbiome modulation according to phenotype of the patient providing individualized and personalized medical approaches. Preventive potential of probiotics is strong and well-documented. Recommendations for individualized clinical use of probiotics, and for probiotic studies design have been suggested.

A new model predictive control (MPC) algorithm is used to select optimal air conditioning setpoints for a commercial office building, considering variable electricity prices, weather, occupancy and lighting. This algorithm, Cost-Comfort Particle Swarm Optimization (CCPSO), is the first to combine a realistic, smooth representation of occupants’ willingness to pay for thermal comfort with a bottom-up, non-linear model of the building and air conditioning system under control. We find that using a quadratic preference function for temperature can yield solutions that are both more comfortable and lower-cost than previous work that used a ``brick wall'' preference function with no preference for further cooling within an allowed temperature band and infinite aversion to going outside the allowed band. Using historical pricing data for a summer month in Chicago, CCPSO provided a 3\% reduction in costs vs. a ``brick-wall'' MPC approach with similar comfort and 13\% reduction in costs vs. a standard night setback strategy. CCPSO also reduced peak-hours demand by 3\% vs. the ``brick-wall'' strategy and 15\% vs. standard night-setback. At the same time, the CCPSO strategy increased off-peak energy consumption by 15\% vs. the ``brick-wall'' strategy. This may be valuable for power systems integrating large amounts of renewable power, which can otherwise become uneconomic due to saturation of demand during off-peak hours.

Building fires are preventable incidents that have proven to be both deadly and costly. Addressing their root causes will lead to safer neighbourhoods for families and businesses to live and operate in. Multiple studies have established the effect of residents’ socioeconomic compositions on an area’s building fire rates; however, the existing model based on the classical stepwise regression procedure has several limitations. This paper aims to construct a more accurate predictive model of building fire rates based on a set of explanatory socioeconomic variables. In building the socioeconomic model, a backward elimination by Robust Final Predictor Error (RFPE) criterion is proposed to enhance the forecasting capability of the model. The proposed method has been implemented on the census data and the fire incident data of the South East Queensland region in Australia. A cross-validation was then conducted to assess the model’s accuracy. In addition, comparative analyses of other elimination criteria, such as p-value, adjusted R-squared, Akaike’s Information Criterion (AIC), Bayesian Information Criterion (BIC) and predicted residual error sum of squared (PRESS), were conducted. The cross-validation analyses demonstrate that the proposed criterion is a more accurate predictive model based on a couple of goodness-of-fit measures. All in all, the RFPE equation was found to be a suitable criterion for the backward elimination procedure in the socioeconomic modelling of building fires.

In the current age of the Fourth Industrial Revolution ($4IR$ or Industry $4.0$), the digital world has a wealth of data, such as Internet of Things (IoT) data, cybersecurity data, mobile data, business data, social media data, health data, etc. To intelligently analyze these data and develop the corresponding real-world applications, the knowledge of artificial intelligence (AI), particularly, machine learning (ML) is the key. Various types of machine learning algorithms such as supervised, unsupervised, semi-supervised, and reinforcement learning exist in the area. Besides, the deep learning, which is part of a broader family of machine learning methods, can intelligently analyze the data on a large scale. In this paper, we present a comprehensive view on these machine learning algorithms that can be applied to enhance the intelligence and the capabilities of an application. Thus, this study's key contribution is explaining the principles of different machine learning techniques and their applicability in various real-world applications areas, such as cybersecurity, smart cities, healthcare, business, agriculture, and many more. We also highlight the challenges and potential research directions based on our study. Overall, this paper aims to serve as a reference point for not only the application developers but also the decision-makers and researchers in various real-world application areas, particularly from the technical point of view.

Accurately predicting the power of solar power generation can greatly reduce the impact of the randomness and volatility of power generation on the stability of the power grid system, which is beneficial for the balanced operation and optimized dispatch of the power grid system, and reduces operating costs. Solar PV power generation depends on weather conditions, which are prone to large fluctuations under different weather conditions. Its power generation is characterized by randomness, volatility and intermittency. Recently, the demand for further investigation and effective use on the uncertainty of short-term solar PV power generation prediction has been getting increasing attention in many application of renewable energy sources. In order to improve the predictive accuracy of output power of solar PV power generation and develop a precise predictive model, the authors worked predictive algorithms for the output power of a solar PV power generation system. Moreover, since short-term solar PV power forecasting is one of the important aspects for optimizing the operation and control of renewable energy systems and electricity markets, this review focuses on the predictive models of solar PV power generation, which can be verified in the daily planning and operation of a smart grid system. In addition, the predictive methods in the reviewed literature are classified according to the input data source used for accurate predictive models, and the case studies and examples proposed are analyzed in detail. The contributions, advantages and disadvantages of the predictive probabilistic methods are compared. Finally, the future studies of short-term solar PV power forecasting is proposed.

The digital world has a wealth of data, such as Internet of Things (IoT) data, business data, health data, mobile data, urban data, security data, and many more, in the current age of the Fourth Industrial Revolution (Industry 4.0 or 4IR). Extracting knowledge or useful insights from these data can be used for smart decision-making in various applications domains. In the area of data science, advanced analytics methods including machine learning modeling can provide actionable insights or deeper knowledge about data, which makes the computing process automatic and smart. In this paper, we present a comprehensive view on "Data Science'' including various types of advanced analytics methods that can be applied to enhance the intelligence and capabilities of an application through smart decision-making in different scenarios. We also discuss and summarize ten potential real-world application domains including business, healthcare, cybersecurity, urban and rural data science, and so on by taking into account data-driven smart computing and decision making. Based on this, we finally highlight the challenges and potential research directions within the scope of our study. Overall, this paper aims to serve as a reference point on data science and advanced analytics to the researchers and decision-makers as well as application developers, particularly from the data-driven solution point of view for real-world problems.

With a reduction in the mortality rate of burn patients, patient length of stay (LOS) is increasingly adopted as an outcome measure. Some studies have attempted to identify factors that explain a burn patient's expected LOS. However, few have investigated the association between LOS and a patient's mental and socioeconomic status. There is anecdotal evidence for links between these factors and uncovering these will aid in better addressing the specific physical and emotional needs of burn patients, and facilitate the planning of scarce hospital resources. Here, we employ machine learning (clustering) and statistical models (regression) to investigate whether a segmentation by socioeconomic/mental status can improve the performance and interpretability of an upstream predictive model, relative to a unitary model derived for the full adult population of patients. Although we found no significant difference in the performance of the unitary model and segment-specific models, the interpretation of the segment-specific models reveals a reduced impact of burn severity in LOS prediction with increasing adverse socioeconomic and mental status. Furthermore, the models for the socioeconomic segments highlight an increased influence of living circumstances and source of injury on LOS. These findings suggest that, in addition to ensuring that the physical needs of patients are met, management of their mental status is crucial for delivering an effective care plan.

Heart disease is one of the most common diseases in middle-aged citizens. Among the vast number of heart diseases, coronary artery disease (CAD) is considered a common cardiovascular disease with a high death rate. The most popular tool for diagnosing CAD is the use of medical imaging, e.g., angiography. However, angiography is known for being costly and also associated with a number of side effects. Hence, the purpose of this study is to increase the accuracy of coronary heart disease diagnosis by selecting significant predictive features in order of their ranking. In this study, we propose an integrated method using machine learning. The machine learning methods of random trees (RTs), the decision tree of C5.0, support vector machine (SVM), the decision tree of Chi-squared automatic interaction detection (CHAID) are used in this study. The proposed method shows promising results and the study confirms that the RTs model outperforms other models.

Neutrophil to lymphocyte ratio (NLR) is a promising predictive and prognostic factor in breast cancer. We investigated its ability to predict disease-free survival (DFS) and overall survival (OS) in patients with luminal A or luminal B-HER2-negative breast cancer who received neoadjuvant chemotherapy (NACT). Pre-treatment complete blood cell counts from 168 consecutive patients with luminal breast cancer were evaluated to assess NLR. The study population was stratified into NLRlow or NLRhigh according to a cut-off value established by receiving operator curve (ROC) analysis. Data on additional pre- and post-treatment clinical-pathological characteristics were also collected. Kaplan-Meier curves, log-rank tests, and Cox proportional hazards models were used for statistical analyses. Patients with pre-treatment NLRlow showed a significantly shorter DFS (HR 6.97, 95% CI 1.65-10.55, p= 0.002) and OS (HR 7.79, 95% CI 1.25-15.07, p= 0.021) compared to those with NLRhigh. Non-ductal histology, luminal B subtype, and post-treatment Ki67≥ 14% were also associated with worse DFS (p= 0.016, p= 0.002, and p= 0.001, respectively). In multivariate analysis, luminal B subtype, post-treatment Ki67≥ 14%, and NLRlow remained independent prognostic factors for DFS, while only post-treatment Ki67≥ 14% and NLRlow affected OS. The present study provides evidence that pre-treatment NLRlow helps identify women at higher risk of recurrence and death among patients affected by luminal breast cancer treated with NACT.

In this work, an algorithm for the scheduling of household appliances to reduce the energy cost and the peak-power consumption is proposed. The system architecture of a home energy management system (HEMS) is presented to operate the appliances. The dynamics of thermal and non-thermal appliances is represented into state-space model to formulate the scheduling task into a mixed-integer-linear-programming (MILP) optimization problem. Model predictive control (MPC) strategy is used to operate the appliances in real-time. The HEMS schedules the appliances in a dynamic manner without any a priori knowledge of the load-consumption pattern. At the same time, HEMS responds to the real-time electricity market and the external environmental conditions (solar radiation, ambient temperature etc). Simulation results exhibit the benefits of proposed HEMS by showing the reduction of up to 47% in electricity cost and up to 48% in peak power consumption.

This work is located in a growing sector within the field of renewable energies, wave energy converters (WECs). Specifically, it focuses on one of the point absorbers wave (PAWs) of the hybrid platform W2POWER. With the aim of maximising the mechanical power extracted from the waves by these WECs and reduce their mechanical fatigue, the design of five different model predictive controllers (MPCs) with hard and soft constraints has been carried out. As contribution of this paper, two of the MPCs have been designed with the addition of an embedded integrator. In order to validate the MPCs, an exhaustive study on performance and robustness is realized through simulations carried out in which uncertainties in the WEC dynamics are considered. Furthermore, looking for realistic in these simulations, an identification methodology for PAWs is proposed and validated by means of real time series of a scale prototype.

The prediction of wind power output is part of the basic work of power grid dispatching and energy distribution. At present, the output power prediction is mainly obtained by fitting and regressing the historical data. The medium- and long-term power prediction results exhibit large deviations due to the uncertainty of wind power generation. In order to meet the demand for accessing large-scale wind power into the electricity grid and to further improve the accuracy of short-term wind power prediction, it is necessary to develop models for accurate and precise short-term wind power prediction based on advanced algorithms for studying the output power of a wind power generation system. This paper summarizes the contribution of the current advanced wind power forecasting technology and delineates the key advantages and disadvantages of various wind power forecasting models. These models have different forecasting capabilities, update the weights of each model in real time, improve the comprehensive forecasting capability of the model, and have good application prospects in wind power generation forecasting. Furthermore, the case studies and examples in the literature for accurately predicting ultra-short-term and short-term wind power generation with uncertainty and randomness are reviewed and analyzed. Finally, we present prospects for future studies that can serve as useful directions for other researchers planning to conduct similar experiments and investigations.

The main functions of the automated systems rely on the advanced sensors for detection and perception of the environment around the vehicle. Radars and cameras are commonly utilized to detect the potential obstacles and vehicles ahead on the road. Nevertheless, cameras can generate spurious detections in the extreme weather conditions such as fog, rain, dust, snow, dark, and heavy sunlight in the sky. Due to limitations in vertical field view of the radars, single radars are not reliable to detect the height of the targets precisely. In this paper, a triple radar arrangement (long-range, medium-range, and short-range radars) based on sensor fusion technique is proposed to detect objects with different size in level 2 Advanced Driver-Assistance (ADAS) system. The typical objects including truck, pedestrians, and animals are detected in different scenarios. The developed model considered ISO 26262 and ISO/PAS 21448 to reasonably address insufficient robustness and inability of the sensors. The models of sensor and level 2 ADAS systems are developed using MATLAB toolbox and Simulink. Sensor detection performance is determined by running simulations with triple radar setup. Obtained results demonstrate that the proposed approach generates accurate detections of targets in all tested scenarios.

This paper is an attempt to forecast the potential application of Digital Twin in an industrial environment by adopting scenario analysis as part of technology monitoring. In recent years Digital Twin has become one of the most emerging topics in both the tech industry and academia. This field is the latest addition to industry 4.0. It has paved a great growth opportunity in the fields of Healthcare, manufacturing, and smart city areas. The Digital twin can be defined as mirroring the physical entities into a virtual environment where the status, health, and control of these entities can be monitored and controlled. It is a field where Artificial intelligence and the Internet of Things play a major role in the handshake between the two environments. In this paper we have done a thorough analysis to find out the possible future outcome of this technology in the manufacturing industry from the perspective of our fictious company. These scenarios expose various challenges and opportunities our organization may face in our future endeavour.

Insulin-like growth factor binding proteins (IGFBPs) are critical modulators of the metabolism. In adults, IGFBPs are associated with obesity and insulin resistance but the association of IGFBPs with metabolic homeostasis in children and adolescents is not fully characterized. In this study we investigated the association of plasma IGFBPs (IGFBP-1, 3 and 7) with weight status, central adiposity and cardiovascular disease markers Hs-CRP and Ox-LDL. A total of 420 adolescents (age 11-14 years) were randomly recruited from public middle schools in Kuwait. IGFBPs were measured using bead-based multiplexing while Hs-CRP and Ox-LDL were measured using ELISA. IGFBP-1 levels were significantly lower in obese and overweight participants compared to normal weight children. Only IGFBP-1 was negatively associated with waist circumference to height (WC/Ht) ratio. IGFBP-1 was negatively correlated with Hs-CRP while IGFBP-3 and IGFBP-7 were negatively correlated with Ox-LDL. These data demonstrate a robust negative association of IGFBP-1, but not IGFBP-3 or -7, with overweight and obesity, and the inflammation marker Hs-CRP. Central adiposity (WC/Ht ratio) was a stronger predictor of IGFBP-1 than BMI-for-age z-score. IGFBP-1 could thus be used as a sensitive predictive diagnostic tool for obesity and its subsequent effects in screening and monitoring of obesity-related metabolic complications in adolescents.

The mutual information between the state of a neural network and the state of the external world represents the amount of information stored in the neural network that is associated with the external world. In contrast, the surprise of the sensory input indicates the unpredictability of the current input. In other words, this is a measure of inference ability, and an upper bound of the surprise is known as the variational free energy. According to the free-energy principle (FEP), a neural network continuously minimizes the free energy to perceive the external world. For the survival of animals, inference ability is considered to be more important than simply memorized information. In this study, the free energy is shown to represent the gap between the amount of information stored in the neural network and that available for inference. This concept involves both the FEP and the infomax principle, and will be a useful measure for quantifying the amount of information available for inference.

Powder bed fusion (PBF) process is a metal additive manufacturing process which can build parts with any complexity from a wide range of metallic materials. PBF process research has predominantly focused on the impact of only a few parameters on product properties due to the lack of a systematic approach for optimizing a large set of process parameters simultaneously. The pivotal challenges regarding this process require a quantitative approach for mapping the material properties and process parameters onto the ultimate quality; this will then enable the optimization of those parameters. In this study, we propose a two-phase framework for optimizing the process parameters and developing a predictive model for 316L stainless steel material. We also discuss the correlation between process parameters -- i.e., laser specifications -- and mechanical properties and how to achieve parts with high density (> 98%) as well as better ultimate mechanical properties. In this paper, we introduce and test an innovative approach for developing AM predictive models, with a relatively low error percentage of 10.236% that are used to optimize process parameters in accordance with user or manufacturer requirements. These models use support vector regression, random forest regression, and neural network techniques. It is shown that the intelligent selection of process parameters using these models can achieve an optimized density of up to 99.31% with uniform microstructure, which improves hardness, impact strength, and other mechanical properties.

This paper aims to provide the smart grid research community with an open and accessible general mathematical framework to develop and implement optimal flexibility mechanisms in large-scale network applications. The motivation of this paper is twofold. On the one hand, flexibility mechanisms are currently a hot topic of research, which is aimed to mitigate variation and uncertainty of electricity demand and supply in decentralised grids with a high aggregated share of renewables. On the other hand, a large part of such related research is performed by heuristic methods, which are generally inefficient (such methods do not guarantee optimality) and difficult to extrapolate for different use cases. Alternatively, this paper presents an MPC-based (Model Predictive Control) framework explicitly including a generic flexibility mechanism which is easy to particularise to specific strategies such as Demand Response, Flexible Production and Energy Efficiency Services. The proposed framework is benchmarked with other non-optimal control configurations to better show the advantages it provides. The work of this paper is completed by the implementation of a generic use case which aims to further clarify the use of the framework and thus, to ease its adoption by other researchers in their specific flexibility mechanisms applications.

Abstract: Safety issues related to the electrification of more electric aircraft (MEA) need to be addressed because of the increasing complexity of aircraft electrical power systems and the growing number of safety-critical sub-systems that need to be powered. Managing the energy storage systems and the flexibility in the load-side plays an important role in preserving the system’s safety when facing an energy shortage. This paper presents a system-level centralized operation management strategy based on model predictive control (MPC) for MEA to schedule battery systems and exploit flexibility in the demand-side while satisfying time-varying operational requirements. The proposed online control strategy aims to maintain energy storage (ES) and prolong the battery life cycle, while minimizing load shedding, with fewer switching activities to improve devices lifetime and to avoid unnecessary transients. Using a mixed-integer linear programming (MILP) formulation, different objective functions are proposed to realize the control targets, with soft constraints improving the robustness of the model. Besides, an evaluation framework is proposed to analyze the effects of various objective functions and the prediction horizon on system performance, which provides the designers and users of MEA and other complex systems with new insights into operation management problem formulation.

Patients diagnosed with unresectable locally advanced Triple Negative Breast Cancer (TNBC) usually have poor outcome for its aggressive clinical behaviour. Atezolizumab plus nanoparticle albumin-bound (nab)-Paclitaxel prolonged progression-free survival (PFS) and overall survival (OS) among patients with unresectable locally advanced TNBC but its use is hampered by the lack of reliable predictors of tumor response. Seventy-seven consecutive patients with unresectable locally advanced TNBC treated with Atezolizumab plus nab-Paclitaxel were studied by blood draws at baseline, 28 days and 56 days after initiation of treatment. Exosomal PD-L1 mRNA in plasma was determined using Bio-Rad QX100 digital droplet PCR system and exoRNeasy kit and objective responses were defined following the RECIST criteria v.1.1. The study evaluates whether PD-L1 mRNA copies per ml in plasma-derived exosomes may predict response to anti-PD-L1 antibodies early in the course of therapy. Our data showed patients with unresectable locally advanced TNBC and higher levels of PD-L1 mRNA expression in plasma-derived exosomes at baseline demonstrated greater response to atezolizumab plus nab-paclitaxel. Furthermore, the levels of mRNA decreased with successful treatment while the copy number increased in patients experiencing disease progression following atezolizumab plus nab-paclitaxel. For the first time, our data showed the usefulness of assessment of exosomal PD-L1 as non-invasive real-time biopsy in patients diagnosed with TNBC suggesting exosomal PD-L1 is significantly associated with outcome and response to Atezolizumab plus nab-Paclitaxel.

Anomaly detection is an active area of research with numerous methods and applications. This survey reviews the state-of-the-art of data-driven anomaly detection techniques and their application to the the aviation domain. After a brief introduction to the main traditional data-driven methods for anomaly detection, we review the recent advances in the area of neural networks, deep learning and temporal-logic based learning. We cover especially unsupervised techniques applicable to time series data because of their relevance to the aviation domain, where the lack of labeled data is the most usual case, and the nature of flight trajectories and sensor data is sequential, or temporal. The advantages and disadvantages of each method are presented in terms of computational efficiency and detection efficacy. The second part of the survey explores the application of anomaly detection techniques to aviation and their contributions to the improvement of the safety and performance of flight operations and aviation systems. As far as we know, some of the presented methods have not yet found an application in the aviation domain. We review applications ranging from the identification of significant operational events in air traffic operations to the prediction of potential aviation system failures for predictive maintenance.

The aim of Predictive Maintenance, within the field of Prognostics and Health Management (PHM), is to identify and anticipate potential issues in the equipment before these become critical. The main challenge to be addressed is to assess the amount of time a piece of equipment will function effectively before it fails, which is known as Remaining Useful Life (RUL). Deep Learning (DL) models, such as Deep Convolutional Neural Networks (DCNN) and Long Short-Term Memory (LSTM) networks, have been widely adopted to address the task, with great success. However, it is well known that this kind of black box models are opaque decision systems, and it may be hard to explain its outputs to stakeholders (experts in the industrial equipment). Due to the large number of parameters that determine the behavior of these complex models, understanding the reasoning behind the predictions is challenging. This work presents a critical and comparative revision on a number of XAI methods applied on time series regression model for PM. The aim is to explore XAI methods within time series regression, which have been less studied than those for time series classification. The model used during the experimentation is a DCNN trained to predict the RUL of an aircraft engine. The methods are reviewed and compared using a set of metrics that quantifies a number of desirable properties that any XAI method should fulfill. The results show that GRAD-CAM is the most robust method, and that the best layer is not the bottom one, as is commonly seen within the context of Image Processing.

This paper focuses on the so-called proportional intensity-based software reliability models (PI-SRMs), which are extensions of the common non homogeneous Poisson process (NHPP)-based SRMs, and describe the probabilistic behavior of software fault-detection process by incorporating the time-dependent software metrics data observed in the development process. Especially we generalize the seminal PI-SRM in Rinsaka, Shibata and Dohi (2006) by introducing eleven well-known fault-detection time distributions, and investigate their goodness-of-fit and predictive performances. In numerical illustrations with four data sets collected in real software development projects, we utilize the maximum likelihood estimation to estimate model parameters with three time-dependent covariates; test execution time, failure identification work and computer time-failure identification, and examine the performances of our PI SRMs in comparison with the existing NHPP-based SRMs without covariates. It is shown that our PI-STMs could give better goodness-of-fit and predictive performances in many cases.

Nowadays, according to spectacular improvement in health care and biomedical level, a tremendous amount of data is recorded by hospitals. In addition, the most effective approach to reduce disease mortality is to diagnose it as soon as possible. As a result, data mining by applying machine learning in the field of diseases provides good opportunities to examine the hidden patterns of this collection. An exact forecast of the mortality after heart surgery will cause Successful medical treatment and fewer costs. This research wants to recommend a new stacking predictive model after utilizing the random forest feature importance method to foresee the mortality after heart surgery on a highly unbalanced dataset by using the most practical features. To solve the unbalanced data problem, a combination of the SVM-SMOTE over-sampling algorithm and the Edited-Nearest-Neighbor under-sampling algorithm is used. This research compares the introduced model with some other machine learning classifiers to ensure efficiency through shuffle hold-out and 10-fold cross-validation strategies. In order to validate the performance of the implemented machine learning methods in this research, both shuffle hold-out, and 10-fold cross-validation results indicated that our model had the highest efficiency compared to the other models. Furthermore, the Friedman statistical test is applied to survey the differences between models. The result demonstrates that the introduced stacking model reached the most accurate predicting performance after Logistic Regression.