Search

The rapid development of information technology has brought numerous benefits to society, but it has also led to increased security vulnerabilities in network systems. Intrusion detection systems (IDS) play a crucial role in identifying malicious activities, but they face challenges due to imbalanced datasets where the number of attack samples outweighs normal activities. This paper explores the performance of an IDS using SMOTE (Synthetic Minority Over-sampling Technique) and various classification algorithms to address imbalanced datasets and enhance detection of multi-class intrusions. Related works in the field of intrusion detection are reviewed, highlighting the effectiveness of different algorithms and techniques. The proposed work presents a model that combines SMOTE with log normalization and feature selection to improve IDS performance. Experiments are conducted on the NSL-KDD and CIC-IDS2017 datasets, evaluating different oversampling configurations and machine learning models. The results show that applying SMOTE improves overall performance, with high accuracy, precision, recall, and F1-score. Feature selection has minimal impact on model performance, suggesting the presence of redundant features. The study concludes that SMOTE effectively addresses class imbalance and enhances IDS performance, emphasizing the importance of incorporating oversampling techniques in intrusion detection systems. [ABSTRACT FROM AUTHOR]

This paper studies lessons learned from Covid-19 disaster management in Malaysia using machine learning techniques. First, we crawl Twitter data related to 'covid' with geo-location bounding-box. Then we contribute to propose LDA topics generated on citizen perception containing negative sentiment towards government response; hence, we represent the data using VOSviewer and D3.js to emphasize topic modeling with respect to timestamp due to pattern analysis. As results, LDA-based topic visualization may recognize the accounts' pattern that are assumed as the pillars of disaster management in Malaysia. This study gains insights from political science field. Implications of the results are also discussed. [ABSTRACT FROM AUTHOR]

With the extensive utilization of fossil fuels, environmental concerns have been growing. Hydrogen-powered vehicles (HPVs) as well as hydrogen refueling stations (HRSs) are expected to proliferate to alleviate the pollution. In order to promote the economic valibity of HRSs, this paper proposes an optimal scheduling model for distributed HRSs to maximize HRSs' revenue during a day. HRSs serves both the mobility sector with fuel individually and the power system with reserve demand response collaboratively. The elaborated operating of electrolysers and relaxed control of hydrogen storage are involved to enhance practicability and flexibility of the scheduling. Considering that this model has multiple variables, intractable high-dimension nonlinear constraints, a transfer multi-agent reinforcement learning algorithm is developed. The algorithm consists of two parts: the one is the multi-agent optimization method by transforming multi-decision optimization into a multi-agent optimization; the other is to transfer the empirical knowledge of the source task to reinforcement learning according to the similarity between the source task and the target task, making it cut down the blindness of exploration and accelerate convergence. Numerical studies reveal that participating in the reserve services market collaboratively increases overall revenues of HRSs by up to 32.90%, and the computation time is sharply shortened by approximately 34 times compared to the basic reinforcement learning. • A joint operation model of distributed HRSs is proposed to lift revenue by 32.90%. • Relaxed control of hydrogen storage is utilized to minimize service deviation. • An evolutionary transfer reinforcement learning shortens solving time by 34 times. [ABSTRACT FROM AUTHOR]

• Developed XGBoost model to predict refrigerant mass flow through electronic expansion valves. • Achieved improved prediction accuracy over existing models using two refrigerants. • XGBoost effectively captured complex nonlinear flow dynamics with 96.4–90.6 % accuracy. • A low RMSE of 2.2–4.23 % indicated high predictive performance of the developed model. • Advanced machine learning approach provides direction for more efficient refrigeration control. In an effort to enhance the prediction accuracy of the mass flow characteristics of refrigerants through electronic expansion valves (EEVs), this study develops a mass flow model using the XGBoost machine learning algorithm. Utilizing experimental data from open literature for refrigerants R1233zd(E) and R245fa, the model aims to accurately predict the mass flow coefficient in EEVs, a crucial aspect for improving the performance and efficiency of refrigeration systems. The model's performance is evaluated using the coefficient of determination (R2) on the training and test datasets, revealing a minimal performance gap and no overfitting issue. Remarkably, our model's predictions for R1233zd(E) and R245fa datasets align consistently with experimental data, with 96.4 % and 90.6 % of the predicted data deviating from the experimental ones within ±5 %, respectively. Further, the root-mean-square error (RMSE) and coefficient of variation of the root mean square error (CV-RMSE) values are quite low, with 2.2 % and 2.33 % for R1233zd(E), and 4.23 % and 4.47 % for R245fa, indicating high prediction accuracy. Compared to the original models, the paper approach with the XGBoost algorithm significantly improves prediction accuracy. This advancement provides a promising direction for developing more efficient and reliable control strategies for refrigeration systems in various applications. [ABSTRACT FROM AUTHOR]

Federated learning (FL) provides autonomy and privacy by design to participating peers, who cooperatively build a machine learning (ML) model while keeping their private data in their devices. However, that same autonomy opens the door for malicious peers to poison the model by conducting either untargeted or targeted poisoning attacks. The label-flipping (LF) attack is a targeted poisoning attack where the attackers poison their training data by flipping the labels of some examples from one class (i.e., the source class) to another (i.e., the target class). Unfortunately, this attack is easy to perform and hard to detect, and it negatively impacts the performance of the global model. Existing defenses against LF are limited by assumptions on the distribution of the peers' data and/or do not perform well with high-dimensional models. In this paper, we deeply investigate the LF attack behavior. We find that the contradicting objectives of attackers and honest peers on the source class examples are reflected on the parameter gradients corresponding to the neurons of the source and target classes in the output layer. This makes those gradients good discriminative features for the attack detection. Accordingly, we propose LFighter, a novel defense against the LF attack that first dynamically extracts those gradients from the peers' local updates and then clusters the extracted gradients, analyzes the resulting clusters, and filters out potential bad updates before model aggregation. Extensive empirical analysis on three data sets shows the effectiveness of the proposed defense regardless of the data distribution or model dimensionality. Also, LFighter outperforms several state-of-the-art defenses by offering lower test error, higher overall accuracy, higher source class accuracy, lower attack success rate, and higher stability of the source class accuracy. Our code and data are available for reproducibility purposes at https://github.com/NajeebJebreel/LFighter. [ABSTRACT FROM AUTHOR]

The interpretability of ML models is important, but it is not clear what it amounts to. So far, most philosophers have discussed the lack of interpretability of black-box models such as neural networks, and methods such as explainable AI that aim to make these models more transparent. The goal of this paper is to clarify the nature of interpretability by focussing on the other end of the "interpretability spectrum". The reasons why some models, linear models and decision trees, are highly interpretable will be examined, and also how more general models, MARS and GAM, retain some degree of interpretability. It is found that while there is heterogeneity in how we gain interpretability, what interpretability is in particular cases can be explicated in a clear manner. [ABSTRACT FROM AUTHOR]

The first year of the COVID-19 pandemic constituted a major life stress event for many adolescents, associated with disrupted school, behaviors, social networks, and health concerns. However, pandemic-related stress was not equivalent for everyone and could have been influenced by pre-pandemic factors including brain structure and sleep, which both undergo substantial development during adolescence. Here, we analyzed clusters of perceived stress levels across the pandemic and determined developmentally relevant pre-pandemic risk factors in brain structure and sleep of persistently high stress during the first year of the COVID-19 pandemic. We investigated longitudinal changes in perceived stress at six timepoints across the first year of the pandemic (May 2020–March 2021) in 5559 adolescents (50 % female; age range: 11–14 years) in the United States (U.S.) participating in the Adolescent Brain Cognitive Development (ABCD) study. In 3141 of these adolescents, we fitted machine learning models to identify the most important pre-pandemic predictors from structural MRI brain measures and self-reported sleep data that were associated with persistently high stress across the first year of the pandemic. Patterns of perceived stress levels varied across the pandemic, with 5 % reporting persistently high stress. Our classifiers accurately detected persistently high stress (AUC > 0.7). Pre-pandemic brain structure, specifically cortical volume in temporal regions, and cortical thickness in multiple parietal and occipital regions, predicted persistent stress. Pre-pandemic sleep difficulties and short sleep duration were also strong predictors of persistent stress, along with more advanced pubertal stage. Adolescents showed variable stress responses during the first year of the COVID-19 pandemic, and some reported persistently high stress across the whole first year. Vulnerability to persistent stress was evident in several brain structural and self-reported sleep measures, collected before the pandemic, suggesting the relevance of other pre-existing individual factors beyond pandemic-related factors, for persistently high stress responses. • The paper reports findings from the ABCD study® on U.S. youth across the first COVID-19 pandemic year: May 2020 – March 2021. • 5% of adolescents reported persistently high stress levels during the first year of the pandemic. • Persistent stress was linked to pre pandemic brain structure, sleep difficulties, and more advanced puberty stages. • The findings inform preventive and treatment approaches for persistent stress during major life stress events like pandemics. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicle-based hyperspectral imaging (HSI) and machine learning (ML) techniques are applied for crop field data collection such as yield, nitrogen content, leaf chlorophyll, biomass estimation, leaf area index (LAI), and biotic and abiotic stress. It is very difficult to identify with certainty best practices for specific applications and for targeted crop species because the results are frequently contradictory; models or indices sometimes perform well, but other times they do not. ML and HSI are useful and sophisticated techniques, but treating them as first-option methods may be detrimental in the long term. Favoring HSI in situations where a multispectral sensor performs equally well only delays end-user adoption of technology owing to cost and complexity. The past few years have seen increased interest in unmanned aerial vehicle (UAV)-based hyperspectral imaging (HSI) and machine learning (ML) in agricultural research, concomitant with an increase in published research on these topics. We provide an updated review, written for agriculturalists, highlighting the benefits in the retrieval of biophysical parameters of crops via UAVs relative to less sophisticated options. We reviewed >70 recent papers and found few consistent results between similar studies. Owing to their high complexity and cost, especially when applied to crops of low value, the benefits of most of the research reviewed are difficult to explain. Future effort will be necessary to distill research findings into lower-cost options for end-users. [ABSTRACT FROM AUTHOR]

In recent years, the advancement of deep learning technologies has significantly impacted various domains and the field of transportation is no exception. As the demand for robust and accurate traffic sign classification systems continues to rise, this study presents an in-depth exploration and comparison of various techniques employed in the field. Focusing on state-of-the-art methodologies, we assess the effectiveness and performance of multiple classification approaches for traffic sign recognition. The review presents an extensive survey of the literature, encompassing traditional computer vision methods, machine learning algorithms, and the latest advancements in deep learning. The comparative analysis aims to identify the strengths and limitations of each technique, considering factors such as computational efficiency and accuracy. Additionally, the paper implements four models—CNN, ResNet50, VGG19, and EfficientNetB7—for traffic sign classification on the GTSRB dataset, the accuracy results are reported as 99.25%, 99.28%, 98.95%, and 98.24% respectively. [ABSTRACT FROM AUTHOR]

Machine Learning as a Service, MLaaS refers to cloud-based platforms that provide machine learning tools and infrastructure to users, allowing them to access and utilize machine learning capabilities without managing the underlying hardware and software. Cloud service providers offer scalable and flexible resources, enabling businesses to train and deploy machine learning models efficiently and cost-effectively. Multi-Criteria Decision making, MCDM helps individuals or organizations make choices when multiple criteria or objectives are involved. It aims to find the best alternative among a set of available options by considering various criteria or factors that are relevant to the decision. Machine learning as a service (MLaaS) and MCDM are two distinct concepts that can be combined to create powerful decision-making solutions. The present paper proposed an integrated approach based on the Analytic Hierarchy Process and TOPSIS method for choosing the best MLaaS cloud. Four alternatives for MLaaS cloud were analyzed based on seventeen shortlisted criteria. Based on the calculations, conclusions have been reached and potential study areas have been identified. [ABSTRACT FROM AUTHOR]

The paper presents a study of the interest and opinions of students regarding online learning using a machine learning approach, as well as the evolution of different e-learning platforms based on education following the pandemic period. The study uses student data from a questionnaire-based survey of college students to improve the learning environment from the perspective of the students. The survey and questionnaire were designed with students' needs, requirements, and preferred level of quality for online learning. Survey data was subjected to data analysis and classification to gain a deeper understanding of the learner in a virtual learning environment. Through data preparation, analysis, visualization, and machine learning algorithm accuracy, machine learning classification algorithms and analysis are used to examine the collected data. The research study will illustrate the expectations and enhancement of online learning education patterns according to the requirements of students. With a 93% accuracy evaluation, the Random Forest algorithm has the best accuracy among the several classification algorithms. [ABSTRACT FROM AUTHOR]

Bluetooth (BT) mesh networks are used in several ad hoc network communication scenarios, including natural disasters, calamities, war zones, etc. However, there are situations where Bluetooth mesh networks are misused by anti-social elements during riots etc. As of now there no such research article that showcases detection of BT mesh networks using machine learning tools. Therefore, there is a need to build novel methods for detecting the very presence of Bluetooth mesh networks to aid the law enforcement agencies. This paper contributes to building a new dataset for the aid of machine learning tools to detect the presence of Bluetooth mesh networks. The dataset is extracted from a simulated Bluetooth mesh network with 52 BT network traffic attributes, using the Bridgefy application. Further, the dataset is optimized by identifying prime features, using label encoding, one-hot encoding, correlation analysis and evaluated by various Machine Learning (ML) tools. An accuracy of 99.6% is achieved after optimizing the feature set. [ABSTRACT FROM AUTHOR]

The ever-evolving tactics employed by malware authors to avoid detection pose challenges to the conventional static analysis method, which entails examining the malware code. These challenges arise from the authors' capacity to obfuscate their code. To address this matter and enhance the identification of malware, integrating dynamic detection and machine learning has emerged as a highly promising approach. This methodology has demonstrated efficacy in identifying malware specifically engineered to circumvent established detection techniques. Behavioural analysis is a crucial component in ensuring endpoints' security, with the CNN-LSTM algorithm being particularly notable for its effectiveness in identifying Zero-Day malware. This type of malware poses a substantial obstacle to conventional signature-based approaches. This paper aims to assess the efficacy of the Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) model, emphasising its significance in tackling the continuously evolving realm of cybersecurity obstacles. The research highlights the significance of transitioning from traditional signature-based detection methods to behavioural analysis techniques. It suggests utilising deep learning approaches such as Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN) to improve the ability to detect malware in an environment where threats constantly evolve. The malware detection system that has been developed encompasses a log parser analyser, API monitoring, and an extension checker module. The CNN-LSTM model demonstrates a commendable ability to accurately identify malicious behaviour, achieving a validation accuracy of 96%. This study demonstrates the efficacy of employing behavioural analysis and deep learning techniques to enhance cybersecurity, particularly in addressing sophisticated, evasive, and previously unknown malware risks. [ABSTRACT FROM AUTHOR]

The research presented in this paper addresses the critical challenge of ranking Indian villages based on their potential for socio-economic growth, inspired by the objectives of the Shyam Prasad Mukerji Rurban Mission (SPMRM). Leveraging a novel algorithm known as ClusterRank, an extension of the PageRank algorithm, we endeavor to provide a timely, efficient, and accurate solution for village ranking. The ClusterRank algorithm, an extension of the well-known PageRank algorithm, serves as the cornerstone of our approach. It excels in its ability to efficiently and accurately rank villages, outperforming alternative ranking methods. Notably, our findings reveal the superior convergence speed of the ClusterRank algorithm, affirming its capacity to produce rapid results. To assess the efficacy of ClusterRank, we employ a range of statistical ranking coefficients, including the Spearman, Kendall, and Point Biserial correlation coefficients. Our analysis demonstrates a strong positive correlation, with a Spearman correlation coefficient of 0.89, between the rankings generated by ClusterRank and the ground truth rankings provided by SPMRM. This correlation underscores the effectiveness of ClusterRank in identifying villages with high growth potential and highlights its alignment with the objectives of the SPMRM. This research presents a compelling case for the adoption of the ClusterRank algorithm by SPMRM as a valuable tool in the identification of rural areas poised for rurban development. Such adoption not only promises substantial time and resource savings but also directs the focus of SPMRM towards the implementation of targeted interventions and initiatives to uplift rural communities. Moreover, our supplementary analyses using Kendall and Point Biserial correlation coefficients further validate the robustness of the ClusterRank algorithm. [ABSTRACT FROM AUTHOR]

Pulmonary Embolism (PE) is a blood clot in the pulmonary arteries of the lungs. Currently, Computerized Tomography Pulmonary Angiography (CTPA) scans are used to diagnose this condition. However, to manually locate the presence of a PE in the scan is laborious. In this paper, the detection of PE and prediction of its features like location, Right Ventricle to Left Ventricle (RV/LV) ratio, and chronicity are automated. First, for the detection of the embolisms, image features from the RSNA Pulmonary Embolism CT (RSPECT) dataset - containing over 12,000 CTPA studies, are extracted by several pre-trained Convolutional Neural Networks (CNN) - AlexNet, Inception V3, ResNet-18, and ResNet-50. Then, various Machine Learning (ML) classifiers are trained on these features and their performances are compared. Second, for the prediction of labels, multi-label classification is performed by training these networks with Binary Cross Entropy Logits (BCE Logits) loss. The results showed that for the detection task, k-NN classifier trained on ResNet-50 features achieved the highest sensitivity of 0.98 with 1.7 false positives per scan and an AUROC score of 97.4%. This system also improved on the state-of-the-art sensitivity score by 0.0975 and AUROC score by 3.4%. For multi-label classification, ResNet-18 performed comparatively better with the best validation loss of 0.07 and weighted macro-average ROC AUC score of 0.61. [ABSTRACT FROM AUTHOR]

Next generation firewall is taking major part to secure network environment in the industry. This device will monitor all the traffic which is coming inside the network or going outside of the network. With all these security devices attackers can still perform various kind of attacks on the network. DDoS attack is one of the hardest attack to identify which will send packets to the network and which will look like normal traffic but it will act as a DDoS traffic. In this paper we used binary decision tree, XGBoost and support vector machine to identify DDoS attack traffic pattern from the different features in the packet header. Data will be fetched from the packet header and among them standard deviation of the packet bytes and packet flows are the features considered. We have applied this data on the trained dataset. Algorithm will predict whether the traffic coming inside the network is trusted or not. Out of the three algorithms Binary Decision tree algorithm is giving 99 percentage of accuracy and will predict the data as fast as possible. Here priority is to filter DDos attacks of any security level in the line speed of the NIDS or any other appliances. This method of DDoS attack detection will add extra layer of security in the next generation firewall which will make firewall more robust. [ABSTRACT FROM AUTHOR]

Mutual funds, a cornerstone of modern investment portfolios, offer investors a diversified and professionally managed approach to financial growth. These investment vehicles collect small amount from multiple investors and invests the collective investment further in diversified portfolio of stocks, bonds, or other securities. Mutual funds are characterized by their net asset value (NAV), which represents the per-share value of the fund's assets minus its liabilities. Investors benefit from the expertise of seasoned fund managers who make investment decisions based on their analysis of market trends and company performance. By providing an accessible and diversified investment option, mutual funds have become a popular choice for both novice and seasoned investors seeking to achieve their financial goals. Apart from that, the role of AI is increasing exponentially in various areas. Such AI based tools and algorithms are utilized by various MFs expert to identify the suitable investment portfolios. This paper proposes a technique to analyse the performance of the different stock's portfolios based on the past data. Combining the isolated analysis of different stocks portfolios may be utilized to predict the net asset value prediction (NAV) of MFs. The experiments carried out in this research work uses linear regression analysis to analyse the stock's performance at sub level of the MFs. A case study for the Axis Bluechip fund's is also carried out by using the proposed ML approach. The Yahoo Finance dataset is used for the case study. Previously, machine learning algorithms like linear regression (LR), decision tree regression (DTR), and multivariate regression (MR) are taken to predict and analyse the dataset. These algorithms calculate the NAV of the mutual fund with good accuracy and analyse the best result for the test dataset. The various models are being created from different portfolios to analyse the NAV of the mutual funds. This work proposed hierarchical method to perform the linear regression analysis for the NAV predicting. This work uses R-Square (R2) statistical measures to determine the goodness of models. The obtained R2 is 0.86, implying that the created models have good accuracy and performance on the dataset. [ABSTRACT FROM AUTHOR]

• A strategy is proposed to design high-performance Mg–Mn-based wrought Mg alloys based on a novel machine learning model. • The design model innovatively integrates four regression algorithms and Bayesian Optimization algorithm. • The improved Bayesian optimization active learning method outperforms traditional Bayesian optimization in terms of design precision. • Several new high-performance magnesium alloys have been designed and developed using this novel model. Magnesium (Mg), being the lightest structural metal, holds immense potential for widespread applications in various fields. The development of high-performance and cost-effective Mg alloys is crucial to further advancing their commercial utilization. With the rapid advancement of machine learning (ML) technology in recent years, the ''data-driven'' approach for alloy design has provided new perspectives and opportunities for enhancing the performance of Mg alloys. This paper introduces a novel regression-based Bayesian optimization active learning model (RBOALM) for the development of high-performance Mg-Mn-based wrought alloys. RBOALM employs active learning to automatically explore optimal alloy compositions and process parameters within predefined ranges, facilitating the discovery of superior alloy combinations. This model further integrates pre-established regression models as surrogate functions in Bayesian optimization, significantly enhancing the precision of the design process. Leveraging RBOALM, several new high-performance alloys have been successfully designed and prepared. Notably, after mechanical property testing of the designed alloys, the Mg-2.1Zn-2.0Mn-0.5Sn-0.1Ca alloy demonstrates exceptional mechanical properties, including an ultimate tensile strength of 406 MPa, a yield strength of 287 MPa, and a 23% fracture elongation. Furthermore, the Mg-2.7Mn-0.5Al-0.1Ca alloy exhibits an ultimate tensile strength of 211 MPa, coupled with a remarkable 41% fracture elongation. [ABSTRACT FROM AUTHOR]

Warehouse design and planning involve complex decisions on receiving, storage, order picking and shipping products (i.e., stock-keeping units - SKUs) and can affect the performance of entire supply chains. With the advancement of Industry 4.0 and increased data availability, high-computing power, and ample storage capacity, Machine Learning (ML) has become an appealing technology to address warehouse planning challenges such as Storage Location Assignment Problems (SLAP) and Order Picking Problems (OPP) for intelligent warehousing management. This paper presents a state-of-the-art review of ML applied to Warehouse Management Systems (WMS) through the analysis of recent research application articles. A mapping to classify the scientific literature in this new research area, including ML methods, algorithms, data sources and use cases of ML-aided WMS, as well as further research perspectives and challenges, are introduced. Preliminary results suggest that the possible research areas in ML-WMS are still incipient and need to be further explored. [ABSTRACT FROM AUTHOR]

Filter clogging represents a crucial issue in industrial filtration systems, and it can lead to various problems, such as reduced filtration efficiency, increased maintenance costs, and potential production disruptions. This paper presents a Machine Learning (ML) integrated solution, developed using Python, within a digital environment system created using LabVIEW to prevent and control filter clogging. The primary objective is to optimize the monitoring, control, and maintenance of a Bag Filter pilot plant. The digital environment incorporates a data comparison tool that trigger a compressor for filter cleaning. A Machine Learning algorithm has been integrated into the digital environment, where a comparison within real data acquired and the predicted one were performed to validate the selected algorithms and evaluate the Data Comparison tool. This initial phase's outcomes were used to develop a control system using LabVIEW software. The software compares estimated pressure drop values, reflecting optimal working conditions, with directly recorded pressure drop values. If the difference exceeds 10% of the optimal pressure drop, the controller activates a compressed air cleaning system, removing excess dust from the filter sleeves using an air jet. Additionally, when the estimated and acquired values diverge consistently over a 60-minute period, a user warning is triggered for filter sleeve replacement. Several tests were conducted at different air inlet velocities to assess the error between acquired and predicted data. The results indicated that the ML algorithm's error distribution remained below 5% for approximately 80% of the cases. [ABSTRACT FROM AUTHOR]

Addressing privacy concerns is critical in smart manufacturing where sensitive data is used for machine learning. Data protection is essential to ensure model accuracy while upholding data privacy. Homeomorphic encryption, an algorithm for privacy-preserving machine learning, achieves this by transforming data using a neural network with secret key weights. This process conceals private data while retaining the potential to learn classification models from the anonymized data. This paper introduces a comprehensive quality metric to assess homeomorphic encryption across conflicting criteria: security (regarding private data), machine learning adaptability (tolerance), and efficiency (regarding needed extra resources). Through experiments on various datasets, the metric proves its effectiveness in guiding optimal encryption parameter selection. Our findings highlight homeomorphic encryption's strong overall quality, positioning it as a valuable Industry 4.0 solution. By offering a simpler alternative to fully homomorphic encryption, it effectively addresses privacy concerns and enhances data usability in the context of smart manufacturing. [ABSTRACT FROM AUTHOR]

Product quality is a vital aspect in the operation of manufacturing systems, manufacturers need to implement at least one quality assurance method to assure the desired quality. The most recent approach for quality assurance is named Zero Defect Manufacturing (ZDM). The scope of the current paper is the implementation of ZDM approach in the automotive industry and specifically for the spot-welding process. Using a machine learning method that is utilizing linear regression and LSTM and consuming data from the production such as sensors and other engineering data to predict the quality of future spot welds. Using this quality prediction there is a root cause analysis to identify why the spot weld will fail and the appropriate prevention actions are proposed. The next step is the training and validation of the machine learning model and the calculation of the accuracy of the model. Once the accuracy of the model is validated a series of simulations, using a dynamic scheduling tool, are performed in order to calculate a series of KPIs to evaluate the impact of the proposed method to the production. [ABSTRACT FROM AUTHOR]

Machine learning is a popular tool for solving problems, however, incorporating it into a use case with additional business logic poses many challenges. Training, managing and storing many different models is not an easy task, requiring the use of multiple frameworks and languages. To take full advantage of existing frameworks it is necessary to facilitate communication between different programming languages. This paper presents an approach to integrating machine learning in a real-world use case which involves predicting demand for a diverse set of products and combining it with business rules and other components to establish a system that improves and automates the ordering process. Machine learning models are trained on real-world data from a retailer in Austria and the predictions are incorporated into a heuristic that controls and manages stock levels. This work focuses on the challenges that emerge from the integration of machine learning and presents a message bus based architecture to address them. [ABSTRACT FROM AUTHOR]

This paper presents a comparative analysis of the performance of machine learning techniques for enhancing predictive quality in thermal spray coating technology, with a focus on the high velocity oxygen fuel (HVOF) process. The study aims for accurately predicting coating properties, which are pivotal in determining coating quality in HVOF applications. By investigating five influential factors, including the fuel-to-oxygen ratio and coating velocity, this research was designed to improve the understanding and control of these properties. Through advanced statistical design of experiments, correlations between these factors and key coating properties are established. Six machine learning models are trained and evaluated to assess their predictive capabilities for coating properties. The obtained results provide valuable insights into the HVOF coating process and highlight the potential of predictive model-based techniques for accurately predicting such properties. Furthermore, this research offers guidance for selecting an effective machine learning technique in the context of thermal spray technology. [ABSTRACT FROM AUTHOR]

The implementation of intelligent techniques produces good results in automating fault finding and predicting future outcomes. These approaches have been on the increase in the past years, especially so to detect faults within Compressed Air Systems (CASs). With the use of intelligent techniques, one could minimise the manual and time-consuming aspect of CAS maintenance, improve the environmental impact of the system, while minimising downtime. This paper proposes a general framework for the implementation of intelligent analysis techniques within a real-world system. Such an approach has been implemented on the demand-side of a CAS. In literature, no open datasets are available for use by artificial intelligence models. Hence, as part of this research, a fault generating and monitoring system has been connected to an existing production machine in a manufacturing site to collect the required data. Two classification machine learning methods were implemented and compared across a number of performance metrics. Both the general framework, and its implementation, provide a stepping stone in integrating smart systems with real-time intelligent data analytics for the demand-side of a CAS. These systems would provide a sustainable CAS operation through the effective detection of anomalies and their timely repair. [ABSTRACT FROM AUTHOR]

Industry 4.0 uses artificial intelligence and machine learning algorithms to optimize processes. The main goal of the manuscript is to analyze the possibilities of applying automated machine learning to predict company bankruptcy. The data sample consists of financial data of 9,771 manufacturing companies for the years 2020 and 2021 collected from the Finstat database. Two methods of automated machine learning, AutoML and H2O, were tested. The results were compared with five other methods - linear discriminant analysis, logistic regression, naive Bayes classifier, CatBoost and XGBoost. The resulting model was cross-validated through the 10-fold approach. The best results were achieved by H2O automated machine learning algorithm with an AUC of 90.13%, followed by the gradient boosting methods CatBoost with AUC of 90.05% and XGBoost (AUC of 88.61%) and another automated learning algorithm AutoML with AUC of 81.17%. The findings of this paper indicate possibilities to apply automated machine learning methods in predicting bankruptcy. However, it is necessary to distinguish between individual automated machine learning algorithms since they provide a different range of results. [ABSTRACT FROM AUTHOR]

A neural network (NN) is known to be an efficient and learnable tool supporting decision-making processes particularly in Industry 4.0. The majority of NNs are data-driven and, therefore, depend on training data quantity and quality. The current trend in enhancing data-driven models with knowledge-based models promises to enable effective NNs with less data. So-called physics-informed NNs use additional knowledge from computational science to improve NN training. Quite much of the knowledge is available as logical constraints from domain ontologies, and NNs may benefit from using it. In this paper, we study the concept of Taxonomy-Informed NN (TINN), which combines data-driven training of NNs with ontological knowledge. We study different patterns of NN training with additional knowledge on class-subclass hierarchies and instance-class relationships with potential for federated learning. Our experiments show that additional knowledge, which influences TINNs' training process through the loss function at backpropagation, improves the quality of trained models. [ABSTRACT FROM AUTHOR]

This paper demonstrates the application of a fully automated machine learning (ML) pipeline on time series data from the domain of production engineering. The workflow aims to streamline the machine learning (ML) process and reduce manual effort by incorporating automated machine learning (AutoML) and automated featurization techniques. A comparative study is created to evaluate the proposed workflow against existing state-of-the-art methods using six datasets from production engineering, five widely used ones and a newly presented one. The study compares the performance of the automated workflow with the manual data mining process described in the literature. The results lead to two main conclusions: first, an automated featurization process cannot match the performance of manual feature generation, but still delivers good results without requiring manual work. Second, if the manually generated features are used, AutoML can outperform the manual process in solving the combined problem of algorithm selection and hyperparameter optimization, leading to better prediction results. The presented approach serves as a useful reference for other methods, showing the practicality of baseline workflow without human bias. Overall, the proposed data processing pipeline demonstrates the potential of AutoML in production engineering and provides valuable insights for practitioners in this domain. [ABSTRACT FROM AUTHOR]

This research is concerned with finding the optimal solution of a job shop scheduling problem (JSSP) in a shorter time. As a result of recent trends such as Industry 4.0, machine learning has received a lot of attention, and job shop scheduling methods using machine learning techniques have been developed. We have focused on hybridization of machine learning and mathematical optimization. A JSSP can be formulated as a 0-1 mixed integer programming, and it is expected that the optimal solution can be obtained in a shorter time by providing a good initial solution for the optimization algorithm by means of a learner constructed with data of scheduling performed previously. In our method based on this idea, the processing times of all operations are used as input features to predict a good value of each binary variable which represents the precedence relationship between two operations processed on the same machine. However, the information about the operations which are not related to the intended two operations may work as noise in learning and prediction. In this paper, two limitation methods of input features are proposed. In one of the methods, the processing times of only the operations processed on the same machine that the intended operations are processed are input to the learner. In the other methods, the processing times of those operations and their pre/post operations are input. Numerical experiments showed that these methods are effective at least from the point of view of efficient construction of a learner, because the number of nodes in the input and hidden layers can be reduced. From the aspect of better learning and prediction, both of the methods worked well, that is, they could find the optimal solution in a shorter time than the previous method in the cases where the previous method could not achieve good prediction and took a relatively long solution time. However, in the cases where the previous method could solve the problem in a relatively short time, the limitation methods could not predict a good initial solution and took a relatively long solution time. Between the results of the two limitation methods, there were no difference. These results imply that the processing times of the pre/post operations do not strongly affect performance on learning and prediction and that it is important to analyze what makes a difference between the two cases and utilize the proposed methods in the former case. [ABSTRACT FROM AUTHOR]

Due to environmental issues such as climate change, companies are required to optimize their resource and energy consumption in their production process. Predicting power consumption and processing time of all production facilities is essential for manufacturing to develop mechanisms to prevent energy and resource waste and optimize their use. Machine learning is a powerful tool for prediction tasks using data in digitalized environments. In this paper, we present power consumption and processing time prediction of CNC milling machines using five machine learning regression models, i.e., decision tree, random forest, support vector regression (SVR), extreme gradient boosting (XGBoost), and artificial neural network (ANN). Since most of those models are black-box, we applied two explainable artificial intelligence (XAI) approaches, SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME), to give post-hoc explanations of the predictions given by the machine learning models. Our experiments indicated that random forest regression performed the best in predicting power consumption and processing time. The explanation showed that the number of axis rotations and the number of travels to the machine's zero point in rapid traverse were the most important factors that affected the processing time and power consumption. The companies using CNC milling machines can use our prediction models to optimally plan and schedule the operation of the milling machines in a time and energy-efficient manner. They can also optimize the factors that affect power consumption and processing time the most. [ABSTRACT FROM AUTHOR]

Quality inspection is a critical step in ensuring the quality and efficiency of textile production processes. With the increasing complexity and scale of modern textile manufacturing systems, the need for accurate and efficient quality inspection and defect detection techniques has become paramount. This paper compares supervised and unsupervised Machine Learning techniques for defect detection in the context of industrial textile production, in terms of their respective advantages and disadvantages, and their implementation and computational costs. We explore the use of an autoencoder for the detection of defects in textiles. The goal of this preliminary work is to find out if unsupervised methods can successfully train models with good performance without the need for defect labelled data. [ABSTRACT FROM AUTHOR]

Data-driven predictive maintenance (PM) is an approach that leverages advanced analytics, artificial intelligence (AI), and sensor data to predict when equipment failure might occur, and to perform maintenance just in time to prevent it, reducing downtime and maintenance costs. In manufacturing, one of the biggest potential applications for intelligent PM systems is tool condition monitoring (TCM). TCM aims to monitor tool wear in real-time, ensuring the quality of the manufactured products and the safety of the surrounding people and equipment. In recent decades, many studies have been carried out on tool condition monitoring for different machining operations such as milling, drilling or turning, and have demonstrated the effectiveness of various AI algorithms. Recent advances in hardware have made it possible for edge devices to run complex AI algorithms locally. This technology is called Edge AI. The Edge AI approach has several key benefits such as reduced latency, scalability, data privacy and security that can accelerate the integration of the PM solution for TCM at the production level. This paper presents the design of an Edge AI system for tool condition monitoring, consisting of state-of-the-art, low-cost components and using open-source software. Based on the proposed design, a prototype was built and tested during milling process. Four machine learning (ML) models and one deep learning (DL) model were run on a low performance edge device. Their predictions were validated. Challenges faced in the implementation are concluded along with directions and suggestions for future research. [ABSTRACT FROM AUTHOR]

Within the paradigm of industry 5.0, manufacturing systems are seeking for human-centred production, where the operator finds high-level supervision tasks. In this context, low-level decision making should be performed by machines themselves. In this paper, a hybrid prognosis algorithm is developed to automatically inspect the cutting edges of drill-bits and to predict their Remaining Useful Life (RUL) and the associated probability density function. The solution relies on the automatic measurement of flank wear through convolutional filtering and edge detection. Prognosis exploits particle filter, which updates multi-layer perceptron with online data, to adaptively predict drill-bits RUL. The solution reduces the experimental preliminary run-to-failures needed for training standard machine learning algorithms, exploiting them in a real-time adaptive scenario, while predicting tool RUL under untested and variable cutting process operations. The algorithm uses direct wear observations, taken during set-up times (e.g., tool changes, workpiece change), thus not interfering with the process. [ABSTRACT FROM AUTHOR]

The dehydrogenation enthalpy, a crucial thermodynamic parameter, determines the difficulty of hydrogen desorption in V–Ti–Cr–Fe alloy, but it is unaffordable to predict and modify the dehydrogenation enthalpy and investigate the synergistic effects of structural and chemical parameters relying on conventional experimental methods. In this paper, an extreme gradient boosting (Xgboost) model with feature selection is developed, which can obtain a relative error under 15% in prediction on most of the data. Moreover, the genetic algorithm is utilized for optimizing alloy composition having suitable dehydrogenation enthalpy. The accuracy of prediction and optimization is demonstrated by the subsequent experimental validation, where the error between calculation and experiment is within 4.5%. Density function theory (DFT) is used to analyze the key features provided by machine learning, with results suggesting that the volumes, valence electrons, and bulk module factors have a significant impact. This research supplies an efficient way of using machine learning to predict and optimize the dehydrogenation enthalpy. In addition, DFT calculation also validates the feature importance outputted by machine learning and reveals the principle of feature effects at the microscopic aspect. • ML models predict precisely the dehydrogenation enthalpy of V–Ti–Cr–Fe alloy. • Properties calculation optimized by GA have good agreement with experiments. • Explanation of volume, electron and module factors affecting enthalpy using DFT. [ABSTRACT FROM AUTHOR]

Integrating a model-based and data-driven approach to generate sufficient number of training data that include time-varying operating conditions is needed to develop a prognostics and health management technique using machine learning for a reusable rocket engine. A data-driven approach was used to predict the engine behavior, which cannot be determined using a model-based approach. This paper proposes a clustered regression model to predict various operating conditions for a reusable rocket engine. The training data were divided in advance according to the operating conditions using the Gaussian mixture model, and multiple regression models were individually trained on each cluster. By switching the regression models according to the operating conditions, the time-series data comprising various operating conditions, such as the combustion and chill-down phases and transition between phases, were accurately predicted when compared with the prediction results of a single regression model. The prediction results of the present hybrid approach agree reasonably well with the static firing test results of a reusable rocket engine if the explanatory variables are adequately included. By integrating model-based and data-driven approaches, adequate training data can be generated for prognostics and health management of the reusable liquid rocket engine. • This study improves the prediction accuracy of the data-driven approach. • Training data for the data-driven approach comprised varying operating conditions. • The varying operating conditions were classified using a Gaussian mixture model. • The regression models were trained based on each classified operating condition. • The prediction accuracy was improved using multiple regression models. [ABSTRACT FROM AUTHOR]

Valid simulation models play a critical role in enhancing efficiency in development processes and minimizing experimental efforts. As a result, ensuring accurate predictions through model discrimination, Mo del Ca libration, and Val idation (MoCaVal) has become increasingly important and is a necessary step to analyze the behavior and evaluate the effectiveness of systems during their initial design stages. Additionally, to achieve the climate objectives, it is imperative that heat pumps predominantly perform the building sector's heating. The effectiveness of heat pumps hinges on the performance of the compressor. Therefore, there is a requirement for valid compressor models. However, currently, there is no universal compressor model that applies to all refrigerants and designs. Therefore, every refrigerant or design modification requires the development or adaptation of models. Since creating new models is a time-consuming procedure, automated techniques are advantageous. This paper compares two automated model development methods, Optimal Experimental Design (OED) and Machine Learning (ML), to create valid simulation models within the MoCaVal framework. OED is used to calibrate existing simulation models, while ML is employed to develop new models. Our comparison of the two methods focuses on a fixed-speed scroll compressor of 4 kW nominal power, using R410A and featuring 51 measurement points. Using the Full Factorial Plan (FFP) and the D-Optimal Experimental Design (D-OED), predefined models for mass flow rate, electrical power, isentropic and volumetric efficiency were calibrated. Employing the FFP, Machine Learning (ML) was also applied through support vector regression. The OED reduces experimental effort by 75–90 % compared to the FFP while only slightly increasing the average uncertainty by 0.30–0.79 %. For the FFP, MoCaVal achieved uncertainties of 0.52–3.9 % for calibrated models and 0.34–0.56 % with ML models. Therefore, within the design space, ML outperforms calibrated models based on the FFP and OED regarding uncertainty. However, since machine learning models were trained on the FFP, additional research is needed to demonstrate their potential for reducing test time and extrapolating results. • Experimental investigation of a scroll compressor. • Model calibration and validation using full factorial design and optimal experimental design. • Comparison of automated model development by Optimal Experimental Design and Machine Learning. • Test time reduction up to 80 % while still keeping reasonable accuracy. [ABSTRACT FROM AUTHOR]

This paper explores the classic beauty premium paradigm in the eSports Overwatch League. Using two-step probit selection models and unsupervised machine learning algorithms, we find that professional gamers rated as more attractive are more likely to receive a contract in the following year, controlling for productivity and other factors. However, there is no apparent lifetime earnings premium. Regression and cluster analyses reveal that it is not enough to be a good player – the inter-relatedness of productivity, attractiveness, and popularity on social media dictates employability. Looking at the league's wealthiest, most successful, and most appealing teams, we find that attractiveness on its own is a negative predictor of getting hired. • No earnings beauty premium paradigm in the eSports Overwatch League. • Performance always impacts employment. • In a two-step selection setup, attractive gamers have a higher chance of rehire. • Beauty is a negative predictor of securing a contract with the most successful team. • Unsupervised ML suggests that player types (by popularity and beauty) matter. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new short-term load forecasting (STLF) model based on contextually enhanced hybrid and hierarchical architecture combining exponential smoothing (ES) and a recurrent neural network (RNN). The model is composed of two simultaneously trained tracks: the context track and the main track. The context track introduces additional information to the main track. It is extracted from representative series and dynamically modulated to adjust to the individual series forecasted by the main track. The RNN architecture consists of multiple recurrent layers stacked with hierarchical dilations and equipped with recently proposed attentive dilated recurrent cells. These cells enable the model to capture short-term, long-term and seasonal dependencies across time series as well as to weight dynamically the input information. The model produces both point forecasts and predictive intervals. The experimental part of the work performed on 35 forecasting problems shows that the proposed model outperforms in terms of accuracy its predecessor as well as standard statistical models and state-of-the-art machine learning models. [ABSTRACT FROM AUTHOR]

Graph Convolutional Network (GCN) has become a hotspot in graph-based machine learning due to its powerful graph processing capability. Most of the existing GCN-based approaches are designed for single-view data. In numerous practical scenarios, data is expressed through multiple views, rather than a single view. The ability of GCN to model homogeneous graphs is indisputable, while it is insufficient in facing the heterophily property of multi-view data. In this paper, we revisit multi-view learning to propose an implicit heterogeneous graph convolutional network that efficiently captures the heterogeneity of multi-view data while exploiting the powerful feature aggregation capability of GCN. We automatically assign optimal importance to each view when constructing the meta-path graph. High-order cross-view meta-paths are explored based on the obtained graph, and a series of graph matrices are generated. Combining graph matrices with learnable global feature representation to obtain heterogeneous graph embeddings at various levels. Finally, in order to effectively utilize both local and global information, we introduce a graph-level attention mechanism at the meta-path level that allocates private information to each node individually. Extensive experimental results convincingly support the superior performance of the proposed method compared to other state-of-the-art approaches. • Explore the heterogeneity of multi-view data by introducing meta-paths. • Enable construction of meta-paths on multi-view data. • Design an attention mechanism to learn the importance of meta-path graph embeddings. [ABSTRACT FROM AUTHOR]

Supervised learning in deep neural networks is commonly performed using error backpropagation. However, the sequential propagation of errors during the backward pass limits its scalability and applicability to low-powered neuromorphic hardware. Therefore, there is growing interest in finding local alternatives to backpropagation. Recently proposed methods based on forward-mode automatic differentiation suffer from high variance in large deep neural networks, which affects convergence. In this paper, we propose the Forward Direct Feedback Alignment algorithm that combines Activity-Perturbed Forward Gradients with Direct Feedback Alignment and momentum. We provide both theoretical proofs and empirical evidence that our proposed method achieves lower variance than forward gradient techniques. In this way, our approach enables faster convergence and better performance when compared to other local alternatives to backpropagation and opens a new perspective for the development of online learning algorithms compatible with neuromorphic systems. • Forward Gradient methods suffer from high variance that hinders convergence. • Activity-Perturbed Forward Gradients can be used to learn derivatives as direct feedback connections. • Feedback learning acts as a momentum that reduces the gradient variance closer to backpropagation. • Feedback learning reduces the biasness of Direct Feedback Alignment. • Feedback learning enables learning in convolutional layers. [ABSTRACT FROM AUTHOR]

Alzheimer's Disease (AD) is a neurodegenerative disease that commonly occurs in older people. It is characterized by both cognitive and functional impairment. However, as AD has an unclear pathological cause, it can be hard to diagnose with confidence. This is even more so in the early stage of Mild Cognitive Impairment (MCI). This paper proposes a U-Net based Generative Adversarial Network (GAN) to synthesize fluorodeoxyglucose - positron emission tomography (FDG-PET) from magnetic resonance imaging - T1 weighted imaging (MRI-T1WI) for further usage in AD diagnosis including its early-stage MCI. The experiments have displayed promising results with Structural Similarity Index Measure (SSIM) reaching 0.9714. Furthermore, three types of classifiers are developed, i.e., one Multi-Layer Perceptron (MLP) based classifier, two Graph Neural Network (GNN) based classifiers where one is for graph classification and the other is for node classification. 10-fold cross-validation has been conducted on all trials of experiments for classifier comparison. The performance of these three types of classifiers has been compared with the different input modalities setting and data fusion strategies. The results have shown that GNN based node classifier surpasses the other two types of classifiers, and has achieved the state-of-the-art (SOTA) performance with the best accuracy at 90.18% for 3-class classification, namely AD, MCI and normal control (NC) with the synthesized fluorodeoxyglucose - positron emission tomography (FDG-PET) features fused at the input level. Moreover, involving synthesized FDG-PET as part of the input with proper data fusion strategies has also proved to enhance all three types of classifiers' performance. This work provides support for the notion that machine learning-derived image analysis may be a useful approach to improving the diagnosis of AD. [ABSTRACT FROM AUTHOR]

Representation learning has been increasing its impact on the research and practice of machine learning, since it enables to learn representations that can apply to various downstream tasks efficiently. However, recent works pay little attention to the fact that real-world datasets used during the stage of representation learning are commonly contaminated by noise, which can degrade the quality of learned representations. This paper tackles the problem to learn robust representations against noise in a raw dataset. To this end, inspired by recent works on denoising and the success of the cosine-similarity-based objective functions in representation learning, we propose the denoising Cosine-Similarity (dCS) loss. The dCS loss is a modified cosine-similarity loss and incorporates a denoising property, which is supported by both our theoretical and empirical findings. To make the dCS loss implementable, we also construct the estimators of the dCS loss with statistical guarantees. Finally, we empirically show the efficiency of the dCS loss over the baseline objective functions in vision and speech domains. • A modified cosine-similarity loss with a denoising property is proposed. • The denoising property of the cosine similarity loss is theoretically investigated. • An estimator of the modified loss is introduced with statistical guarantees. • The quality enhancement of representations learned by the modified loss is observed. [ABSTRACT FROM AUTHOR]

The development of the Industrial Internet of Things (IIoT) in recent years has resulted in an increase in the amount of data generated by connected devices, creating new opportunities to enhance the quality of service for machine learning in the IIoT through data sharing. Graph neural networks (GNNs) are the most popular technique in machine learning at the moment because they can learn extremely precise node representations from graph-structured data. Due to privacy issues and legal restrictions of clients in industrial IoT, it is not permissible to directly concentrate vast real-world graph-structured datasets for training on GNNs. To resolve the aforementioned difficulties, this paper proposes a federal graph learning framework based on Bayesian inference (BI-FedGNN) that performs effectively in the presence of noisy graph structure information or missing strong relational edges. BI-FedGNN extends Bayesian Inference (BI) to the process of Federal Graph Learning (FGL), adding random samples with weights and biases to the client-side local model training process, improving the accuracy and generalization ability of FGL in the training process by rendering the graph structure data involved in GNNs training more similar to the graph structure data existing in the real world. Through extensive experimental tests, the results show that BI-FedGNN has about 0.5%–5.0% accuracy improvement over other baselines of federal graph learning. In order to expand the applicability of BI-FedGNN, experiments are carried out on heterogeneous graph datasets, and the results indicate that BI-FedGNN can also have at least 1.4% improvement in classification accuracy. • BI-FedGNN uses Bayesian inference to improve client-side model training uncertainty. • The node features are processed using randomly sampled weights and biases. • KL divergence loss is used as a regular term to prevent the overfitting problem. • Numerous experiments have demonstrated the feasibility of BI-FedGNN. [ABSTRACT FROM AUTHOR]

Biomass-derived power generation presents various potential benefits compared to conventional fossil fuel-based power generation. Also, efficient integration of energy systems leads to higher sustainability and effectiveness. This paper presents a biomass-fueled energy system with two open and closed Brayton cycles in the waste heat, of which a humidification and dehumidification system is implemented. The usage of four different biomasses as the fuel of the gasifier is tested and put to comparison from the aspects of thermodynamics, economics, and environment. The Grassman diagram for each layout is presented to signpost the exact point of highest exergy destruction and irreversibility. The optimization based on machine learning techniques is conducted to pinpoint the exact optimum operational conditions. The results indicate that wood offers more sustainability compared to other biomasses, and the amount of energy efficiency, exergy efficiency, and freshwater flow rate produced for Wood biomass in the proposed system are 75.81 %, 36.98 %, and 0.4091 kg/s, respectively. Also, two optimization scenarios have been done for this study. In the initial optimal solution finding, effectivness, unit product cost, and carbon dioxide emission index are equal to 45.9 %, 12.6 $/GJ, and 0.7161 kg/kWh, correspondingly. In the latter scenario, the effectiveness, net power production, and production unit cost of products are equal to 45.9 %, 6580 kW, and 12.61 $/GJ, respectively. • A novel Tri-generation system based on supercritical CO 2 cycle and HDH cycle. • Energy, exergy, techno-economic, and environmental analyses are carried out. • Multi-objective optimization using Machine learning Algorithms is done. • Maximum exergy efficiency is obtained to be 40.39 % for MSW. • The minimum production unit cost of products is obtained to be 14.06 $/GJ for MSW. [ABSTRACT FROM AUTHOR]

[Display omitted] Three-dimensional data have become increasingly present in earth observation over the last decades. However, many 3D surveys are still underexploited due to the lack of accessible and explainable automatic classification methods, for example, new topo-bathymetric lidar data. In this work, we introduce explainable machine learning for 3D data classification using Multiple Attributes, Scales, and Clouds under 3DMASC, a new workflow. This workflow introduces multi-cloud classification through dual-cloud features, encrypting local spectral and geometrical ratios and differences. 3DMASC uses classical multi-scale descriptors adapted to all types of 3D point clouds and new ones based on their spatial variations. In this paper, we present the performances of 3DMASC for multi-class classification of topo-bathymetric lidar data in coastal and fluvial environments. We show how multivariate and embedded feature selection allows the building of optimized predictor sets of reduced complexity, and we identify features particularly relevant for coastal and riverine scene descriptions. Our results show the importance of dual-cloud features, lidar return-based attributes averaged over specific scales, and of statistics of dimensionality-based and spectral features. Additionally, they indicate that small to medium spherical neighbourhood diameters (<7 m) are sufficient to build effective classifiers, namely when combined with distance-to-ground or distance-to-water-surface features. Without using optional RGB information, and with a maximum of 37 descriptors, we obtain classification accuracies between 91 % for complex multi-class tasks and 98 % for lower-level processing using models trained on less than 2000 samples per class. Comparisons with classical point cloud classification methods show that 3DMASC features have a significantly improved descriptive power. Our contributions are made available through a plugin in the CloudCompare software, allowing non-specialist users to create classifiers for any type of 3D data characterized by 1 or 2 point clouds (airborne or terrestrial lidar, structure from motion), and two labelled topo-bathymetric lidar datasets, available on https://opentopography.org/. [ABSTRACT FROM AUTHOR]

The aerosol particles present in the atmospheric region mainly affect the climate radiative forcing directly by scattering & absorbing the sunlight. Also, it indirectly influences the formation of clouds, precipitation and acts as a considerable uncertainty in assessing Earth's radiation budget. Determination of aerosol type is significant in characterizing the aerosol role in the atmospheric processes, feedback, and climate models. This paper proposes two aerosol classification models, one based on the source and another based on the composition, to classify the aerosols using aerosol optical properties. The source based aerosol classification method helps to identify the sources which cause pollution in a particular region. Based on the results, proper control measures can be taken to reduce pollution. The composition based aerosol classification helps to identify the nature of aerosol types, such as absorbing or non-absorbing. This classification helps to study the climate of the Kanpur region. The aerosol data is taken from AERONET (AErosol RObotic NETwork) for the period 2002–2018 for the Kanpur region. The composition based aerosol classification model uses Single Scattering Albedo (SSA), Angstrom Exponent (AE), and Fine Mode Fraction (FMF) parameters to categorize aerosols based on their composition. The source based aerosol classification model classifies the aerosols based on values of AE and Aerosol Optical Depth (AOD) and describes the source of the aerosol particles. Knowledge of aerosol sources and compositions helps execute policies or controls to reduce aerosol concentrations. Machine learning algorithms, Naïve Bayes, K Nearest Neighbor, Decision Tree, Support Vector Machine, and Random Forest are used to validate classification schemes. The performance analysis of machine learning algorithms is compared using ten different metrics, and the results are also compared with the existing aerosol classification models. The results of the classification show that the source based aerosols of the desert and arid background and the composition based aerosols of types, Mixture Absorbing, Coarse absorbing (Dust), and Black Carbon are dominant over the Kanpur region during the study period considered. The Number of non-absorbing (scattering) type aerosols are least in the study region considered during the study period at all the seasons. It is found that the Random Forest and Decision Tree models outperform the other machine learning models considered and the existing classification models in terms of accuracy (99.55 %) and other performance metrics considered. [ABSTRACT FROM AUTHOR]

• Earthquake anomalies are analyzed for Mw 6.5 Idaho Earthquake America. • Significant anomalies occur in LST, AT, RH, AP and OLR. • Anomalies are studied using statistical, NARX, MLP and CWT methods. • NARX predicted anomalies are more clear than other methods. Remote sensing has became a powerful tool for identifying lithosphere and atmosphere anomalies associated with the impending Earthquakes (EQs) in the vicinity of seismic breeding zone. In this paper, Land Surface Temperature (LST) of both the daytime and nighttime from the Moderate Resolution Imaging Spectroradiometer (MODIS) along with Air Temperature (AT), Relative Humidity (RH), Air Pressure (AP) and Outgoing Longwave Radiations (OLR) are studied for the 2020 Idaho (USA) EQ of Mw 6.5. We found the EQ induced surface and atmospheric parameters anomalies just one day prior to EQ main shock using statistical analysis. Moreover, we observed a sharp increment in LST and AT followed by the drop in both AP and RH, which are responsible for cooling the hot gases emitted from epicenter during preparation period. Also, we observed a large increase in OLR on the same day confirming these anomalous variations to be related with the main shock. Furthermore, these abrupt variations are also confirmed using neural networks (nonlinear autoregressive network with exogenous inputs (NARX), multilayer perceptron (MLP) and continuous wavelet transformation (CWT). These multi-parameter and multi-technique analyses can contribute to assist in the main shock forecasting in future with an enhanced cluster of satellite observations. [ABSTRACT FROM AUTHOR]

Liquid hydrogen has attracted widespread attention due to industrial decarbonization as an excellent carrier of renewable energy accommodation. Accurate prediction of the heat transfer coefficient during flow boiling has become a fundamental prerequisite for enhancing the design rationality and safety of hydrogen devices since a slight heat leak will trigger flow boiling. A novel selection standard of the dataset for liquid hydrogen flow boiling is proposed, and an experimental database of liquid hydrogen is compiled, including 923 data points from 5 sources. The prediction performance of eight conventional empirical correlations and six machine learning models for liquid hydrogen flow boiling is compared and evaluated. Results show that the prediction ability of machine learning models for the heat transfer coefficient of liquid hydrogen flow boiling is much higher than that of traditional correlations. Fang correlation is recommended to use as the calculation benchmark due to simplicity and reliability if the inlet condition is obscure. The Extra tree model shows the most excellent evaluating performance among the six machine learning models with a mean absolute deviation of 11.44% and a fairly superior R 2 of 0.9543. The Froude number Fr exhibits an essential impact according to the feature importance analysis, which may need to be taken into account when developing new empirical correlations. An improved correlation for the flow boiling of liquid hydrogen is provided based on the Fang correlation, achieving a mean absolute deviation of 18.61% and a mean relative deviation of 16.49%. The results of this paper can offer some theoretical guidance for the design of a liquid hydrogen apparatus. [Display omitted] • A novel selection standard of data set for liquid hydrogen flow boiling is proposed. • Fang correlation is recommended as the calculation benchmark due to simplicity and reliability. • Extra tree model has the best prediction performance with MAD of 11.44% and R 2 of 0.9543. • Froude number Fr exhibits an essential impact on heat transfer. • An improved correlation is proposed with MAD of 18.61% and MRD of 16.49%. [ABSTRACT FROM AUTHOR]

Affected by a large number of radio frequency interference signals, it has become an important task for astronomical data processing to quickly and accurately identify single pulse signals from massive observation data. Designing and extracting effective data features is the key issue for efficient identification of single pulse signals using machine learning. This paper proposes an ensemble feature selection method for single pulse signal classification. The method first mixed three types of features, including the parametric features, statistical features, and abstract features of single pulse signals, and then used five individual feature selection methods to select the corresponding optimal feature set, respectively. At last, the features selected by the five individual methods are mixed, and the greedy strategy was used to select the optimal ensemble feature set. The experimental results show that the ensemble feature set can improve F1-score by a value of 1.8% at most, and can obtain higher accuracy than the features selected by individual methods. Under the background of high-speed and large-scale sky survey, the ensemble feature selection method plays an important role in reducing the number of features, improving classification performance, and speeding up data processing. [ABSTRACT FROM AUTHOR]

Analyzing and modeling the implicit semantic relationships in data sources is the key to achieving integration and sharing of heterogeneous data information. However, manual modeling of data semantics is a laborious and error-prone task that demands significant human effort and expertise. The paper proposes a novel explainable representation learning-based method that adopts an attention-based table-graph cross-modal retrieval model as a rating function during incremental search for automatic semantic modeling. Our supervised model utilizes the graph representation learning technique to extract latent semantics from data and aims to retrieve the most reliable semantic model for structured data sources. Experimental results demonstrate the effectiveness and robustness of our method. • A novel supervised table-graph cross-modal retrieval model for automatic semantic modeling. • An explainable representation learning method combining graph representation learning with an incremental search algorithm. • An attention mechanism and iterative matching method to learn fine-grained semantic matches between different modalities. • The experimental results using two different semantic labelers validate the effectiveness and robustness of our method. • The cross-modal retrieval-based method outperforms the previous best method in terms of precision, recall, and f1-score. [ABSTRACT FROM AUTHOR]