Search

The presentation and modeling of turbulence anisotropy are crucial for studying large-scale turbulence structures and constructing turbulence models. However, accurately capturing anisotropic Reynolds stresses often relies on expensive direct numerical simulations (DNS). Recently, a hot topic in data-driven turbulence modeling is how to acquire accurate Reynolds stresses by the Reynolds-averaged Navier-Stokes (RANS) simulation and a limited amount of data from DNS. Many existing studies use mean flow characteristics as the input features of machine learning models to predict high-fidelity Reynolds stresses, but these approaches still lack robust generalization capabilities. In this paper, a deep neural network (DNN) is employed to build a model, mapping from tensor invariants of RANS mean flow features to the anisotropy invariants of high-fidelity Reynolds stresses. From the aspects of tensor analysis and input-output feature design, we try to enhance the generalization of the model while preserving invariance. A functional framework of Reynolds stress anisotropy invariants is derived theoretically. Complete irreducible invariants are then constructed from a tensor group, serving as alternative input features for DNN. Additionally, we propose a feature selection method based on the Fourier transform of periodic flows. The results demonstrate that the data-driven model achieves a high level of accuracy in predicting turbulence anisotropy of flows over periodic hills and converging-diverging channels. Moreover, the well-trained model exhibits strong generalization capabilities concerning various shapes and higher Reynolds numbers. This approach can also provide valuable insights for feature selection and data generation for data-driven turbulence models. [ABSTRACT FROM AUTHOR]

Maintenance planning and control should prioritize predictive techniques (e.g., vibration analysis on critical components such as belt conveyors and idlers) for addressing the low reliability of bulk transportation systems. The extensive length of the belt conveyor hampers manual inspections and machine learning based on vibration measurements becomes an effective method for fault diagnosis. Models that classify faults, such as Gradient Boosting Decision Tree (GBDT), offer flexible algorithms that optimize decision tree classification through gradient-based techniques for minimizing predictive function errors. However, in case of non-stationary and nonlinear vibration signals, traditional techniques like Fourier Transform can hinder vibration analysis. Methods such as Wavelet Packet Decomposition (WPD) have emerged as an alternative to improve defect detection by extracting energy from signal frequency bands. This paper proposes a combination of WPD and GBDT for feature extraction and classification, respectively, for diagnosing two different failure modes in laboratory belt conveyor idlers, namely, bearing faults and surface wear. GBDT hyperparameters were well-fitted from 21 boosting stages, corroborating the high flexibility of the classification algorithm applied for less robust datasets. Furthermore, GBDT models achieved diagnosis accuracies of 100% for bearing defects and 97.5% for surface wear, showing the effectiveness of the combination for fault identification. [ABSTRACT FROM AUTHOR]

High performance of clutch control is essential for dual-clutch transmission (DCT) system to ensure good shifting smoothness of vehicle driving. The control performance of clutch in DCT driven by proportional solenoid valve depends on the output pressure control of the solenoid valve, while the output pressure of the solenoid valve is directly controlled by the energized current. Therefore, the relationship between working current and output pressure of the solenoid valve has significant impact on the clutch control and affects driving performance of the vehicle accordingly. However, the pressure-to-current (P/I) relationship of proportional solenoid valve has nonlinear hysteresis characteristic caused by magnetic materials, oil viscous friction, operation temperature, etc., which has negative effects on the accuracy and stability of solenoid valve pressure control. To cope with this problem, a machine learning model called long short-term memory (LSTM) for P/I of solenoid valve based on data mining is adopted in this paper, which is then used as feedforward compensation for closed-loop control of solenoid valve. The test result demonstrates that the machine learning model can effectively predict the output pressure at rising and falling phase of the same working current. Besides, this smart control method which has better applicability in engineering can effectively improve the control performance of proportional solenoid valve and further improve clutch control and vehicle driving performance. [ABSTRACT FROM AUTHOR]

With the increasing popularity of machine learning (ML) in image processing, privacy concerns have emerged as a significant issue in deploying and using ML services. However, current privacy protection approaches often require computationally expensive training from scratch or extensive fine-tuning of models, posing significant barriers to the development of privacy-conscious models, particularly for smaller organizations seeking to comply with data privacy laws. In this paper, we address the privacy challenges in computer vision by investigating the effectiveness of two recent fine-tuning methods, Model Reprogramming and Low-Rank Adaptation. We adapt these techniques to provide attribute protection for pre-trained models, minimizing computational overhead and training time. Specifically, we modify the models to produce privacy-preserving latent representations of images that cannot be used to identify unintended attributes. We integrate these methods into an adversarial min–max framework, allowing us to conceal sensitive information from feature outputs without extensive modifications to the pre-trained model, but rather focusing on a small set of new parameters. We demonstrate the effectiveness of our methods by conducting experiments on the CelebA dataset, achieving state-of-the-art performance while significantly reducing computational complexity and cost. Our research provides a valuable contribution to the field of computer vision and privacy, offering practical solutions to enhance the privacy of machine learning services without compromising efficiency. [ABSTRACT FROM AUTHOR]

The vehicular ad-hoc network is a technology that enables vehicles to interact with each other and the surrounding infrastructure, aiming to enhance road safety and driver comfort. However, it is susceptible to various security attacks. Among these attacks, the position falsification attack is regarded as one of the most serious, in which the malicious nodes tamper with their transmitted location. Thus, developing effective misbehavior detection schemes capable of detecting such attacks is crucial. Many of these schemes employ machine learning techniques to detect misbehavior based on the features of the exchanged messages. However, the studies that identify the impact of feature engineering on schemes' performance and highlight the most efficient features and algorithms are limited. This paper conducts a comprehensive literature survey to identify the key features and algorithms used in the literature that lead to the best-performing models. Then, a comparative study using the VeReMi dataset, which is publicly available, is performed to assess six models implemented using three different machine learning algorithms and two feature sets: one comprising selected and derived features and the other including all message features. The findings show that two of the suggested models that employ feature engineering perform almost equally to existing studies in identifying two types of position falsification attacks while exhibiting performance improvements in detecting other types. Furthermore, the results of evaluating the proposed models using another simulation exhibit a substantial improvement achieved by employing feature engineering techniques, where the average accuracy of the models is increased by 6.31–47%, depending on the algorithm used. [ABSTRACT FROM AUTHOR]

In recent years, machine learning (ML) has become increasingly popular in various fields of activity. Cloud platforms have also grown in popularity, as they offer services that are more secure and accessible worldwide. In this context, cloud-based technologies emerged to support ML, giving rise to the machine learning as a service (MLaaS) concept. However, the clients accessing ML services in order to obtain classification results on private data may be reluctant to upload sensitive information to cloud. The model owners may also prefer not to outsource their models in order to prevent model inversion attacks and to protect intellectual property. The privacy-preserving evaluation of ML models is possible through multi-key homomorphic encryption (MKHE), that allows both the client data and the model to be encrypted under different keys. In this paper, we propose an MKHE evaluation method for decision trees and we extend the proposed method for random forests. Each decision tree is evaluated as a single lookup table, and voting is performed at the level of groups of decision trees in the random forest. We provide both theoretical and experimental evaluations for the proposed method. The aim is to minimize the performance degradation introduced by the encrypted model compared to a plaintext model while also obtaining practical classification times. In our experiments with the proposed MKHE random forest evaluation method, we obtained minimal (less than 0.6%) impact on the main ML performance metrics considered for each scenario, while also achieving reasonable classification times (of the order of seconds). [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) has garnered considerable attention from academic and industrial circles as a pivotal technology in recent years. The escalation of security risks is observed to be associated with the growing interest in IoT applications. Intrusion detection systems (IDS) have been devised as viable instruments for identifying and averting malicious actions in this context. Several techniques described in academic papers are thought to be very accurate, but they cannot be used in the real world because the datasets used to build and test the models do not accurately reflect and simulate the IoT network. Existing methods, on the other hand, deal with these issues, but they are not good enough for commercial use because of their lack of precision, low detection rate, receiver operating characteristic (ROC), and false acceptance rate (FAR). The effectiveness of these solutions is predominantly dependent on individual learners and is consequently influenced by the inherent limitations of each learning algorithm. This study introduces a new approach for detecting intrusion attacks in an IoT network, which involves the use of an ensemble learning technique based on gray wolf optimizer (GWO). The novelty of this study lies in the proposed voting gray wolf optimizer (GWO) ensemble model, which incorporates two crucial components: a traffic analyzer and a classification phase engine. The model employs a voting technique to combine the probability averages of the base learners. Secondly, the combination of feature selection and feature extraction techniques is to reduce dimensionality. Thirdly, the utilization of GWO is employed to optimize the parameters of ensemble models. Similarly, the approach employs the most authentic intrusion detection datasets that are accessible and amalgamates multiple learners to generate ensemble learners. The hybridization of information gain (IG) and principal component analysis (PCA) was employed to reduce dimensionality. The study utilized a novel GWO ensemble learning approach that incorporated a decision tree, random forest, K-nearest neighbor, and multilayer perceptron for classification. To evaluate the efficacy of the proposed model, two authentic datasets, namely, BoT-IoT and UNSW-NB15, were scrutinized. The GWO-optimized ensemble model demonstrates superior accuracy when compared to other machine learning-based and deep learning models. Specifically, the model achieves an accuracy rate of 99.98%, a DR of 99.97%, a precision rate of 99.94%, an ROC rate of 99.99%, and an FAR rate of 1.30 on the BoT-IoT dataset. According to the experimental results, the proposed ensemble model optimized by GWO achieved an accuracy of 100%, a DR of 99.9%, a precision of 99.59%, an ROC of 99.40%, and an FAR of 1.5 when tested on the UNSW-NB15 dataset. [ABSTRACT FROM AUTHOR]

An intrusion detection system (IDS) is a system that monitors network traffic for malicious activity and generates alerts. In anomaly-based detection, machine learning (ML) algorithms exploit various statistical and probabilistic methods to learn from past or historical experience and detect valuable patterns from large, unstructured, and complex datasets. ML-based network intrusion detection aims to identify malicious behavior and alert a system administrator when an intruder tries to penetrate the network. This paper deals with the study, strategic construction, and implementation of a network intrusion detection model based on ML methods. Among the available IDS datasets, five of the most relevant are chosen for the experimental analysis, which are NSL-KDD-2009, CIC-IDS2017, CIC-IDS2018, IoTID20, and UNSW-NB15 datasets. In order to reduce the computation time in the training sample and achieve computational complexity O (N 2.38 ± δ) , we propose a computationally efficient and feasible algorithmic framework for analyzing the network traffic data. The developed approach mainly consists of two phases, i.e., "Scatter Matrices and Eigenvalue Computation based feature Selection" and "Classification procedure for the reduced dimension data." Experimental evaluation of various test case scenarios for the chosen datasets is carried out in the simulation setting. It is observed that the test results outperform the existing intrusion detection methods for detecting certain attack categories. [ABSTRACT FROM AUTHOR]

Objectives: Research in criminology and criminal justice is a rapidly growing interdisciplinary, international network of intersecting research topics. Quantifying the substantive content of criminology allows us to empirically disentangle this network and analyze how the interplay of research topic and international context influences knowledge production in the study of crime. Methods: In this paper we apply the topic embedding model, top2vec, mapping two decades of research in criminology and criminal justice (2001–2020). Using data generated by top2vec we enrich coauthorship network data—introducing themes and subdisciplines, and topical similarity measures—and analyze the relationship between topical and subdisciplinary overlap, geospatial distance, and publication coauthorship in a sample of mid-career researchers (N = 4068). Results: We find that these researchers disproportionately favor collaboration within their immediate network of collaborators and subdiscipline of criminology, but tend to establish new, synergistic collaborations with topically adjacent researchers. New collaborations appear to be independent of geographic distance, but US criminologists are less likely to collaborate internationally than Eurasian and Oceanic criminologists. Conclusions: Facilitating communication between researchers and organizations from adjacent subdisciplines could benefit researchers and produce new, innovative research. Encouraging comparative research would help international scholars, many of whom may rely on US collaborators, benefit more from US scholarship. Further applications for top2vec in the scientometric study of criminology, criminal justice, and legal studies are discussed. [ABSTRACT FROM AUTHOR]

Machine learning, and more broadly artificial intelligence (AI), is a fascinating technology and can be considered as the closest approximation to the Cartesian “thinking thing” that humans have ever created. Just as the industrial revolution required a new ethos, the age of intelligent machines will create its own, challenging the established moral, economic, and political presuppositions. This paper discusses the relationship between AI and society; it presents several thought experiments to explore the complexity of the relationship and highlights the insufficiency of the current normative paradigm in addressing technological expansion. I argue that many of the externalities, such as security risks, loss of privacy, and economic instability will result from trying to fit the emerging technologies into the existing frame of efficiency and utility, by redefining the notions of human value, identity, autonomy, purity, and truth, among others. The age of the intelligent machine is elevating alienation to new levels, treating the individual as mere patterns in data—its primary commodity. I further argue that while the possibility of unintended consequences, due to the potential misuse of AI is ever present, the intelligent machine per se is unlikely to engage in a zero-sum game for power on its own initiative. I question whether singularity is at all attainable and argue that technology will forever remain a proxy for human interests. I conclude by posing questions for charting the path forward. Through this analysis, I aim to provide a more nuanced understanding of the complex relationship between the AI and humans. [ABSTRACT FROM AUTHOR]

In this paper, a streak camera system is used for obtaining the spectral images in laser-induced breakdown spectroscopy. Streak images are time-resolved, thus enabling tracking of the temporal development of the atomic and ionic emission lines from the plasma plume. To make our study more comprehensive, we have used a machine-learning approach to data analysis. We propose how to reduce the level of noise on streak images by applying the principal component analysis technique. The usual method of improving the signal-to-noise ratio by taking a large number of expositions in streak camera photon counting mode is often not practical. [ABSTRACT FROM AUTHOR]

In the context of solid-state electrolytes for batteries, ambient temperature ionic conductivity stands as a pivotal attribute. This investigation presents a compilation of potential candidates for solid-state electrolytes in lithium-ion batteries, employing clustering—an unsupervised machine-learning technique. To achieve this, a fusion of data from two distinct datasets was undertaken: a smaller dataset consisting of 51 compounds endowed with experimental lithium-ion conductivity data and a substantially larger dataset of 15,530 compounds devoid of such information. The compounds in our dataset were divided into various groups based on several characteristics that influence the conductivity of lithium-ion batteries. Then, the location of the compounds known to have high lithium-ion conductivity (>10−4 S cm−1) at room temperature was observed. The 427 compounds (i.e., unique material project IDs) found in the same cluster as most of these high-conducting compounds are then further examined. This paper concludes by offering a catalog of solid-state compounds that can be utilized to choose compounds for solid-state electrolytes in batteries. Synopsis: The above plot shows the 15530 lithium-based compounds clustered into 7 clusters based on several factors that were identified to affect lithium-ion conductivity. We observe the location of the already known good lithium-ion conductors (represented by the golden stars) to identify other similar compounds. [ABSTRACT FROM AUTHOR]

The automotive S-rail plays a crucial role in frontal car crashes, aiming to absorb impact energy and reduce passenger injury. This paper innovatively presents an optimization approach to determine the optimal configuration of an S-rail featuring a tapered, multicell front section. The structural design of the S-rail is conceptualized within the design space of a heavy quadricycle vehicle and subsequently subjected to numerical investigation through LS-DYNA using nonlinear explicit dynamics analyses. The objective is to maximize energy absorption while minimizing the S-rail's initial peak force (IPF) and mass. An artificial neural network (ANN) is employed to construct surrogate models for the optimization process. The non dominated sorting genetic algorithm, integrated with the ANN, yields an optimal S-rail design. The Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method, using the mean weighting method on the Pareto frontier optimal solution set, is appropriately applied to select the optimal solution. The optimized S-rail shows improved specific energy absorption compared to the baseline model while maintaining a low IPF. In conclusion, this study highlights the superior predictability of an ANN over conventional quadratic response surface methodology. The results confirm the effectiveness of the ANN-based optimization approach and the selection of a compromise solution using the TOPSIS technique. The proposed procedure has substantial potential to enhance the safety and performance of automotive S-rails. [ABSTRACT FROM AUTHOR]

Background: Calibrating material models to experimental measurements is crucial for realistic computational analysis of components. For complex material models, however, optimization-based identification procedures can become time-consuming, particularly if the optimization problem is ill-posed. Objective: The objective of this paper is to assess the feasibility of using machine learning to identify the parameters of a Chaboche-type material model that describes copper alloys. Specifically, we apply and analyze this identification approach using short-term uniaxial relaxation tests on a C19010 copper alloy. Methods: A genetic algorithm forms the basis for identifying the parameters of the Chaboche-type material model. The approach is accelerated by replacing the numerical simulation of the experimental setup by a neural network surrogate. The neural networks-based approach is compared against a classic approach using both, synthetic and experimental data. Results: The results show that on the one hand, a sufficiently accurate identification of the material model parameters can be achieved by a classic but time-consuming genetic algorithm. On the other hand, it is shown that machine learning enables a much more time-efficient identification procedure, however, suffering from the ill-posedness of the identification problem. Conclusion: Compared to classic parameter identification approaches, machine learning techniques can significantly accelerate the identification procedure for parameters of Chaboche-type material models with acceptable loss of accuracy. [ABSTRACT FROM AUTHOR]

Hyperspectral data has a significant count of spectral channels with an enhanced spectral resolution, which provides detailed information at each pixel. This data can be used in numerous remote sensing (RS) applications, along with mineral mapping. Mineral mapping is an important component of geological mapping, which helps in investigating the mineralization potential of an area. This work can be completed effectively by applying machine learning (ML) techniques to RS data. This paper proposes a stacked ensemble-based framework for mineral mapping using the dataset obtained by the Airborne Visible Infrared Imaging Spectrometer-Next Generation (AVIRIS-NG). The study area is situated in Jahazpur, Rajasthan, India. The purpose of this stacked ensemble-based model is to enhance the performance of ML-based mineral mapping. The proposed stacked ensemble model consists of two major elements: a base learner (Naïve Bayes, KNN, artificial neural network, decision tree, and support vector machine) and a stacked learner (random forest). The results of the experiments show that the stacked ensemble-based model has a lot of potential for accurately mapping the minerals talc, montmorillonite, kaolionite, and kaosmec. The proposed model has obtained an overall accuracy of 98.96%, an average accuracy of 98.21%, and a Kappa coefficient of 0.9628. Research highlights: A stacked ensemble-based model for mineral mapping is proposed. The well-known five conventional machine learning models (called base models) are investigated for mineral mapping. The performance of the proposed model is evaluated on the AVIRIG–NG dataset. The study area is situated in Jahazpur, Rajasthan, India. The proposed method outperformed all base models. [ABSTRACT FROM AUTHOR]

Enormous information is an accumulation of vast measures of information that contains copied things gathered from different sources. Distinguishing copied information from enormous information is a difficult issue. In this paper secure deduplication scheme has been presented for huge information stockpiling. Customers may store and transmit data effectively and efficiently due to cloud service providers. Providers of cloud services are drawn to the application of data de-duplication tools to lower storage costs and conserve bandwidth. To secure the data they share on the cloud, users of the cloud are interested in having a secure and private connection. As a result, the priory is transferred to the cloud, and the data is encrypted. Because the encryption objective conflicts with the purpose of data deduplication, this feature presents a difficult problem. The author then suggested brand-new hybrid chunking methods to boost deduplication performance in cloud storage. Content-based hybrid chunking algorithm of Two Threshold Two Divisor (TTTD) with a Dynamic Prime Coding (DPC) algorithm is suggested for reducing the deduplication data. To increase throughput, which means reducing execution time and CPU resource utilisation, an index method must be incorporated into the deduplication matching process. For chunks with higher security levels, it offers greater security protection, while for chunks with lower security levels, it trades off security for greater deduplication effectiveness. When moving data to open, semi-trusted systems like public clouds, identity management, secure data exchange, and privacy preservation become more challenging than they are in closed, trusted systems where security and privacy can be controlled more simply. Accordingly, the article proposed a cross-domain authentication technique for the verification process. Evaluations of the real-world datasets show the efficiency of the design. With other methods, the proposed hybrid Content-based TTTD-DPC analyses many performance parameters, including chunk distribution, processing time, chunking time, throughput, average chunk size, and deduplication ratio. The deduplication system's total throughput and processing speed are both enhanced by the proposed approach. In addition, the recommended methodology reduces computational cost (772 ms) in terms of hash function compared to other existing methods. [ABSTRACT FROM AUTHOR]

With rapid development and deployment of artificial intelligence methods, the Industrial Internet of Things (IIoT) has highly developed to fast tracing industrial communications and optimizing manufacturing processes. In Industry 5.0, hyper-automation process as one of technological trends navigates industrial entities to intelligent devices of the IIoT, cloud computing, smart robotics, smart agile software and embedded components by high complexity and reliability. By increasing data communication in the IIoT environments and cloud computing, the security and safety of hyper-automation process is also increasingly unstable and challengeable with respect to cyber-attacks, unstructured malwares and abnormal activities. With the diversification and unexpected behaviors of cyber-security threats, traditional cyber-attack detection systems have some critical problems with increasing massive data including unappropriated feature selection and extraction, high computation time in prediction and inaccurate classification models. Due to the above-mentioned challenges, this paper presents a new cloud-based cyber-attack detection architecture based on Ensemble Bagged Trees Detection (EBTD) algorithm for predicting malicious behaviors and types of cyber-attacks for hyper-automation process in the IIoT. The proposed architecture uses Analysis of Variance (ANOVA) and a priority-based feature selection and extraction model to find the optimal features with highly dependent on the network traffic, computation time, malicious behaviors, and types of attacks. Then, experimental results are conducted using the technical data sets UNSW-NB15 and NSL-KDD. The simulation results show that the proposed architecture performance performs better than other case studies and prediction models and effective on optimization of large-scale cyber-attack detection systems for critical hyper-automation process in the IIoT environment. [ABSTRACT FROM AUTHOR]

The Vehicular Ad Hoc Network (VANET) is a novel and innovative technology which is part of the Intelligent Transportation Systems (ITS). VANET is a network composed of a collection of vehicles and other roadside components that are interconnected wirelessly. The intention underlying the development of this technology is the improvement of the vehicle environment and the enhancement of vehicle and driver safety. Nevertheless, since VANETs operate wirelessly and under complicated conditions, they are susceptible to a variety of attacks by malicious actors. Traditional techniques such as encryption are no longer effective, so new techniques using intrusion detection systems IDS have attracted the attention of a large number of researchers. The IDS scans the entire network and identifies all the possible harmful nodes present in the network. The present paper covers the problem of the identification of attacks in VANET by using XGBoost. The effectiveness analysis of the proposed models has been realized on the NSL-KDD and 5RoutingMetrics datasets combined with various feature selection techniques Boruta and Adaptive Synthetic Sampling Approach (ADASYN). Furthermore, the acquired results are being compared to two of the last most used ensemble methods CatBoost and convolutional neural networks CNN.In comparison with the other IDSs, our model approach achieves high performance in accuracy, recall and precision. [ABSTRACT FROM AUTHOR]

With more personal devices being connected to the internet, individuals are becoming increasingly concerned about privacy. Therefore, it is important to develop machine learning algorithms that can use customer data to create personalized models while still adhering to strict privacy laws. In this paper, we propose a robust solution to this problem in a distributed, asynchronous environment with a verifiable convergence rate. Our proposed framework trains a Convolutional Neural Network on each client and sends the feature embeddings to other clients for data aggregation. This allows each client to train a deep-learning model on feature embeddings gathered from various clients in a single communication cycle. We provide a detailed description of the architecture and execution of our suggested approach. Our technique's effectiveness is evaluated by comparing it to the top central training and federated learning (FL) algorithms, and our tests on diverse datasets demonstrate that our method outperforms FL in terms of accuracy and is comparable to central training algorithms. Our findings also show that our proposed method reduces data transfer by over 75% compared to FL, resulting in significant bandwidth savings. As a result, model training can assist companies with high security and data protection concerns in setting up reliable collaboration platforms without requiring a central service provider. [ABSTRACT FROM AUTHOR]

User reviews can play a big part in deciding a company's income in the e-commerce industry. Before making selections regarding any product or service, online users rely on reviews. As a result, the trustworthiness of online evaluations is vital for organisations and can directly impact their reputation and revenue. Because of this, some firms pay spammers to publish false reviews. Most recent studies to detect fake reviews utilise supervised learning. However, neural network techniques, a recent form of advanced technology, have been utilised extensively to detect fake reviews and have demonstrated their ability to do so. Thus, this paper first provides a benchmark study to analyse the performance of various machine learning algorithms with different feature extraction methods on five fake review datasets to present our results. Second, we propose three advanced language models for embedding reviews into the classifiers. Third, we conduct an exhaustive feature set evaluation study to find the best features in detecting fake reviews. Fourth, we analyse the performance of traditional machine learning, deep learning, and advanced deep learning models using different feature extraction methods on five fake review datasets. Finally, we integrate the ELECTRA model with CNN which can identify real or fake reviews. Our proposed technique utilises accuracy, precision, recall, and F1 score as assessment criteria to determine the leniency of the proposed model. For deep contextualised representation and neural classification, we integrate Single-Layer Perceptron (SLP), Multi-Layer Perceptron (MLP), and Convolutional Neural Networks (CNN) following the embedding layer of unique pre-trained models like ELMo, ELECTRA, and GPT2. The experimental results indicate that our proposed model outperforms state-of-the-art methods with improvements ranging from 1 to 7% in terms of the accuracy, F1 score. To the best of our knowledge, no prior work has evaluated such advanced pre-trained models' efficiency in detecting fake reviews. Further, this research comprehensively evaluates several machine-learning approaches and feature extraction strategies for fake online review detection. [ABSTRACT FROM AUTHOR]

Concept drift is one of the most prominent issues in streaming data that machine learning models need to address. Most of the research in the field of concept drift targets updating the prediction model for recovery from concept drift. A little effort has been put into the development of a learning system that can learn drifting concepts with minimal overhead. In this paper, a dynamic ensemble classifier is designed to detect and adapt the concept drifts in streaming data. Thereupon, a novel approach- Selective Ensemble using Transfer Learning (SETL) is proposed that has the ability to adapt the new concept of data. It employs a transfer learning and a weighted majority voting scheme to enable resource optimization. It also overcomes the issues, such as negative transfer and overfitting that may occur during the process of transfer learning. The experiments are performed using real-world open-source datasets. The results indicate that SETL outperforms existing state-of-the-art algorithms for most of the datasets in terms of performance metrics such as Accuracy, F1-score, Kappa measure, precision and recall. [ABSTRACT FROM AUTHOR]

For the global-scale multimedia live streaming services, both of the cost-efficiency at the service provider side and the Quality of Experience (QoE) satisfaction at the viewer side need to be achieved. This is a difficult challenge because the request patterns of global live-streaming services are highly dynamic. In this paper, we solve this issue by cloud-based adaptive resource allocation. We first present a cloud-based multi-tier architecture, called MaaS (Media as a Service), which consists of four types of modules. The main issue that we focus on is the deployment of properly dimensioned MaaS modules in proper geographical regions. We take the QoE of the Dynamic Adaptive Streaming over HTTP viewers into account for this decision. We propose a combination of deep-learning based demand prediction scheme and a dynamic-programming based heuristic to make a good tradeoff between viewers' QoE and the cloud resource cost. Extensive evaluation shows that the proposed scheme clearly outperforms the existing schemes. [ABSTRACT FROM AUTHOR]

Traditional machine learning classifiers can automatically evaluate human behaviour and emotion recognition tasks. However, prior research work does not secure users' privacy and personal information because they need complete access to sensitive physiological data. The recently introduced Federated Learning (FL) paradigm can address this problem. FL allows the local model updates to be sent to a central server, combining them to create a global model. It does not allow the global model to access the raw data used to train it. Motivated by the core concept of FL, this paper proposes a novel FL-based Multi-modal Emotion Recognition System (F-MERS) framework combining EEG, GSR, ECG, and RESP physiological sensors data. It uses Multi-layer Perceptron (MLP) as a base model for classifying complex emotions in three dimensions: Valence, Arousal, and Dominance (VAD). The work validates the F-MERS framework with three emotion benchmark datasets, DEAP, AMIGOS, and DREAMER, achieving accuracies of 87.90%, 89.02%, and 79.02%, respectively. It is the first FL-enabled framework for recognizing complex emotions in three dimensions (VAD) with multi-modal physiological sensors. The proposed study assesses the F-MERS framework in two scenarios: (1). Subject dependent and (2). Subject independent, making the framework more generalized and robust. The experimental outcomes indicate that the F-MERS framework is scalable, efficient in communication, and offers privacy preservation over the baseline Non-FL MLP model. [ABSTRACT FROM AUTHOR]

In this paper, a novel machine-learning based models are presented to predict the effect of notch depth on elastic new strain-concentration factor of rectangular bars with single edge U-notch under combined loading of static tension and pure bending. Regarding the importance of this study, the database with 162 samples is utilized to develop the new methodology of machine learning based models. The database includes the notch radius, the Poisson's ratio, and the thick ratio that represent the influential inputs. The predicted key feature is the elastic new strain-concentration factor under combined loading of static tension and pure bending. These samples were tested with high precision and the predicted values of SNCF were obtained. For comparison, adaptive neural fuzzy inference system, artificial neural network, fine tree, ensemble boosted tree, and ensemble optimized bagged tree were designed and developed in this study. To evaluate and compare the performance of the models, four statistical indices of MAE, MSE, root mean square error (RMSE)and determination coefficient (R) were utilized. Based on the results, all models can predict the SNCF appropriately. However, the Ensemble optimized Bagged tree model had a better performance than other models and it had a significant priority in term of prediction accuracy. Finally, the results indicated that the elastic SNCF increased with increasing notch depth from 0.2 ≤ ho/Ho ≤ 0.7 and sharply decreases with increasing notch depth for shallow notches (0.8 ≤ ho/Ho ≤ 0.95). [ABSTRACT FROM AUTHOR]

Internet of Things (IoTs) has been playing an important role in many sectors, such as smart cities, smart agriculture, smart healthcare, and smart manufacturing. However, IoT devices are highly vulnerable to cyber-attacks, which may result in security breaches and data leakages. To effectively prevent these attacks, a variety of machine learning-based network intrusion detection methods for IoT networks have been developed, which often rely on either feature extraction or feature selection techniques for reducing the dimension of input data before being fed into machine learning models. This aims to make the detection complexity low enough for real-time operations, which is particularly vital in any intrusion detection systems. This paper provides a comprehensive comparison between these two feature reduction methods of intrusion detection in terms of various performance metrics, namely, precision rate, recall rate, detection accuracy, as well as runtime complexity, in the presence of the modern UNSW-NB15 dataset as well as both binary and multiclass classification. For example, in general, the feature selection method not only provides better detection performance but also lower training and inference time compared to its feature extraction counterpart, especially when the number of reduced features K increases. However, the feature extraction method is much more reliable than its selection counterpart, particularly when K is very small, such as K = 4 . Additionally, feature extraction is less sensitive to changing the number of reduced features K than feature selection, and this holds true for both binary and multiclass classifications. Based on this comparison, we provide a useful guideline for selecting a suitable intrusion detection type for each specific scenario, as detailed in Table 14 at the end of Sect. 4. Note that such the comparison between feature selection and feature extraction over UNSW-NB15 as well as theoretical guideline have been overlooked in the literature. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoTs) is a complex and large network of all kinds of equipment and things that covers various areas such as military networks, industrial networks, smart urban infrastructures, education, and many other areas, high volume of traffic, and the growing number of connected equipment. to these networks has made intrusion detection in these networks a challenging issue; Therefore, protecting these networks from various attacks is of particular importance and can be established through planning and establishing effective security controls. One of these important and effective methods of security control is the use of an intrusion detection system (IDS). Due to the ability of machine learning and deep learning methods to learn from existing real examples, they are used to prevent, predict, and intelligently and quickly track complex and unknown future examples. The most important ability and feature of these methods are to detect and predict new attacks, which in many cases are mutated or inspired by previous attacks. Therefore, IoTs control and security systems use and develop new methods in creating safe and intelligent communication between their devices and equipment, which are activated using advanced deep learning and machine methods. Also, the success and advancements of deep learning methods in various fields and fields with extensive data have made activists in the field of the internet interested in these methods. In this paper, to solve the mentioned problems and challenges, we also present a new and effective method of detection based on long short-term memory (LSTM)–recurrent neural network (RNN) and kernel principal component analysis (PCA). To achieve data preprocessing, high accuracy detection rate, feature extraction, and attack detection is embedded in an end-to-end or global detection method. We have used the NSL-KDD dataset to evaluate the results and check the presented idea. The results of our experiments and simulations show that the proposed IDS-LSTM attack detection strategy and idea has better performance than several detection and prediction strategies that use neural networks, support vector machines (SVM). [ABSTRACT FROM AUTHOR]

Android is the most targeted mobile operating system for malware attacks. Most modern anti-malware solutions largely incorporate deep learning or machine learning techniques to detect malwares. In this paper, we conduct a comprehensive analysis on 10 deep learning and 5 machine learning classifiers in their abilities to identify Android malware applications. We used 1-gram dataset, 2-gram dataset and image dataset generated from the system call co-occurrence matrix for our experiments. Among the machine learning classifiers, XGBoost with 2-gram dataset showed the highest F1-score of 0.98. Also, the deep learning classifiers such as extreme learning machine with the system call images demonstrated the best F1-score of 0.952. We experimented using Gabor filters to investigate classifier performance on textures extracted from system call images. We observed an F1-score of 0.953 using the extreme learning machine with the Gabor images. We generated the Gabor image dataset by combining the images generated by passing system call images through 25 different Gabor configurations. In addition, to enhance the performance of the baseline classifiers, we considered the combination of autoencoders with machine learning classifiers. We observed that the amalgam of autoencoder with Random Forest displayed the best F1-score of 0.98. To evaluate the effectiveness of the aforesaid classifiers with diverse features on adversarial examples, we simulated a black-box based attack using a Generative Adversarial Network. The True Positive Rate of XGBoost on the 1-gram dataset, Random Forest on the 2-gram dataset and the Extreme Learning Machine on the system call image dataset significantly dropped to 0 from 0.98, 0.001 from 0.99 and 0 from 0.984 after the attack. Our experiments exposed a crucial vulnerability in classifiers used in modern anti-malware systems. A similar event in a real-world system could potentially render grave catastrophes. To defend against such probable attacks, we should continue further research and develop adequate security mechanisms. [ABSTRACT FROM AUTHOR]

This paper presents an analysis and prediction of the shear strength of wide-shallow reinforced concrete beams, utilizing Finite Element Analysis (FEA) and machine learning techniques. The methodology involves validating a detailed Finite Element Model (FEM) against experimental results, conducting a parametric study, and developing three Machine Learning prediction equations. The FEM captures concrete and steel behaviors, including cracking and crushing for concrete and linear isotropic properties for steel reinforcement. Loading and boundary conditions are defined for accuracy and validated against 13 experimental specimens, exhibiting a maximum 8% and 12% difference in loads and deflections, respectively. A parametric study generates a dataset of 77 wide beam configurations, exploring variations in beam widths, concrete strengths, compression rebars, and shear reinforcement. This dataset is used to develop machine learning models, including "Genetic Programming (GP)", "Evolutionary Polynomial Regression (EPR)", and "Artificial Neural Network (ANN)". Comparative analysis reveals GP and EPR models with over 95% correlation, while the ANN model outperforms with 99% accuracy. Sensitivity analysis underscores the significant influence of concrete strength and beam aspect ratio on shear strength. In conclusion, the study demonstrates the potential of FEA and machine learning models to predict shear strength in wide-shallow reinforced concrete beams, providing valuable insights for architectural design and engineering practices and emphasizing the role of concrete strength and beam geometry in shear behavior. [ABSTRACT FROM AUTHOR]

This paper aims to estimate the permeability of concrete by replacing the laboratory tests with robust machine learning (ML)-based models. For this purpose, the potential of twelve well-known ML techniques was investigated in estimating the water penetration depth (WPD) of nano natural pozzolana (NNP)-reinforced concrete based on 840 data points. The preparation of concrete specimens was based on the different combinations of NNP content, water-to-cement (W/C) ratio, median particle size (MPS) of NNP, and curing time (CT). Comparing the results estimated by the ML models with the laboratory results revealed that the hist-gradient boosting regressor (HGBR) and K-nearest neighbors (KNN) algorithms were the most and least robust models to estimate the WPD of NNP-reinforced concrete, respectively. Both laboratory and ML results showed that the WPD of NNP-reinforced concrete decreased with the increase of the NNP content from 1 to 4%, the decrease of the W/C ratio and the MPS, and the increase of the CT. To further aid in the estimation of concrete's WPD for engineering challenges, a graphical user interface for the ML-based models was developed. Proposing such a model may be effectively employed in the management of concrete quality. [ABSTRACT FROM AUTHOR]

Effective management of dementia requires the timely detection of mild cognitive impairment (MCI). This paper introduces a multi-objective optimization approach for selecting EEG channels (and features) for the purpose of detecting MCI. Firstly, each EEG signal from each channel is decomposed into subbands using either variational mode decomposition (VMD) or discrete wavelet transform (DWT). A feature is then extracted from each subband using one of the following measures: standard deviation, interquartile range, band power, Teager energy, Katz's and Higuchi's fractal dimensions, Shannon entropy, sure entropy, or threshold entropy. Different machine learning techniques are used to classify the features of MCI cases from those of healthy controls. The classifier's performance is validated using leave-one-subject-out (LOSO) cross-validation (CV). The non-dominated sorting genetic algorithm (NSGA)-II is designed with the aim of minimizing the number of EEG channels (or features) and maximizing classification accuracy. The performance is evaluated using a publicly available online dataset containing EEGs from 19 channels recorded from 24 participants. The results demonstrate a significant improvement in performance when utilizing the NSGA-II algorithm. By selecting only a few appropriate EEG channels, the LOSO CV-based results show a significant improvement compared to using all 19 channels. Additionally, the outcomes indicate that accuracy can be further improved by selecting suitable features from different channels. For instance, by combining VMD and Teager energy, the SVM accuracy obtained using all channels is 74.24%. Interestingly, when only five channels are selected using NSGA-II, the accuracy increases to 91.56%. The accuracy is further improved to 95.28% when using only 8 features selected from 7 channels. This demonstrates that by choosing informative features or channels while excluding noisy or irrelevant information, the impact of noise is reduced, resulting in improved accuracy. These promising findings indicate that, with a limited number of channels and features, accurate diagnosis of MCI is achievable, which opens the door for its application in clinical practice. [ABSTRACT FROM AUTHOR]

Conventional photography can only provide a two-dimensional image of the scene, whereas emerging imaging modalities such as light field enable the representation of higher dimensional visual information by capturing light rays from different directions. Light fields provide immersive experiences, a sense of presence in the scene, and can enhance different vision tasks. Hence, research into light field processing methods has become increasingly popular. It does, however, come at the cost of higher data volume and computational complexity. With the growing deployment of machine-learning and deep architectures in image processing applications, a paradigm shift toward learning-based approaches has also been observed in the design of light field processing methods. Various learning-based approaches are developed to process the high volume of light field data efficiently for different vision tasks while improving performance. Taking into account the diversity of light field vision tasks and the deployed learning-based frameworks, it is necessary to survey the scattered learning-based works in the domain to gain insight into the current trends and challenges. This paper aims to review the existing learning-based solutions for light field imaging and to summarize the most promising frameworks. Moreover, evaluation methods and available light field datasets are highlighted. Lastly, the review concludes with a brief outlook for future research directions. [ABSTRACT FROM AUTHOR]

For market players and policy officials, commodity price forecasts are crucial problems that are challenging to address due to the complexity of price time series. Given its strategic importance, corn crops are hardly an exception. The current paper evaluates the forecasting issue for China's weekly wholesale price index for yellow corn from January 1, 2010 to January 10, 2020. We develop a Gaussian process regression model using cross validation and Bayesian optimizations over various kernels and basis functions that could effectively handle this sophisticated commodity price forecast problem. The model provides precise out-of-sample forecasts from January 4, 2019 to January 10, 2020, with a relative root mean square error, root mean square error, and mean absolute error of 1.245%, 1.605, and 0.936, respectively. The models developed here might be used by market players for market evaluations and decision-making as well as by policymakers for policy creation and execution. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel pricing model for delivery insurance in a food delivery company in Latin America, with the aim of reducing the high costs associated with the premium paid to the insurer. To achieve this goal, a thorough analysis was conducted to estimate the probability of losses based on delivery routes, transportation modes, and delivery drivers' profiles. A large amount of data was collected and used as a database, and various statistical models and machine learning techniques were employed to construct a comprehensive risk profile and perform risk classification. Based on the risk classification and the estimated probability associated with it, a new pricing model for delivery insurance was developed using advanced mathematical algorithms and machine learning techniques. This new pricing model took into account the pattern of loss occurrence and high and low-risk behaviors, resulting in a significant reduction of insurance costs for both the contracting company and the insurer. The proposed pricing model also allowed for greater flexibility in insurance contracting, making it more accessible and appealing to delivery drivers. The use of estimated loss probabilities and a risk score for the pricing of delivery insurance proved to be a highly effective and efficient alternative for reducing the high costs associated with insurance, while also improving the profitability and competitiveness of the food delivery company in Latin America. [ABSTRACT FROM AUTHOR]

Internet of Medical Things (IoMT) can be leveraged for periodic sensing and recording of different health parameters using sensors, wireless communications, and computation platforms. Health care systems can be enhanced by using IoMT for remote patient monitoring and data-driven diagnosis powered by machine learning algorithms. In the context of IoMT, federated learning (FL) is an excellent choice to manage machine learning (ML) algorithms to drive this analysis. This is because FL models can be trained in a distributed manner on local heterogeneous datasets that all contribute to the "collective wisdom". The model parameters can be regulated and shared without sharing the actual health data, ensuring confidentiality and security. This paper makes a case for the viability of FL-based analysis of data acquired via IoMT by presenting some use cases and recent work in this area and proposing a novel framework for data analysis using FL specifically in the context of mental stress detection. It shows that FL-based methods can significantly reduce the required communication overhead for each local device from 10.02MB/day up to only 754B/day as compared to non-FL techniques. [ABSTRACT FROM AUTHOR]

Asthma, a common chronic respiratory disease among children and adults, affects more than 200 million people worldwide and causes about 450,000 deaths each year. Machine learning is increasingly applied in healthcare to assist health practitioners in decision-making. In asthma management, machine learning excels in performing well-defined tasks, such as diagnosis, prediction, medication, and management. However, there remain uncertainties about how machine learning can be applied to predict asthma exacerbation. This study aimed to systematically review recent applications of machine learning techniques in predicting the risk of asthma attacks to assist asthma control and management. A total of 860 studies were initially identified from five databases. After the screening and full-text review, 20 studies were selected for inclusion in this review. The review considered recent studies published from January 2010 to February 2023. The 20 studies used machine learning techniques to support future asthma risk prediction by using various data sources such as clinical, medical, biological, and socio-demographic data sources, as well as environmental and meteorological data. While some studies considered prediction as a category, other studies predicted the probability of exacerbation. Only a group of studies applied prediction windows. The paper proposes a conceptual model to summarise how machine learning and available data sources can be leveraged to produce effective models for the early detection of asthma attacks. The review also generated a list of data sources that other researchers may use in similar work. Furthermore, we present opportunities for further research and the limitations of the preceding studies. [ABSTRACT FROM AUTHOR]

Petrophysical properties estimation is vital in reservoir characterisation domain to identify the prospect locations of presence of petroleum. Geophysical sensing with seismic survey and well logging provide such information of subsurface without completely digging over the reservoir. Machine learning models are popular in this domain to estimate the petrophysical properties from seismic signals and well logging. However, the performance is affected when the available labelled data are limited to model a reservoir. Transfer learning has a significant contribution in handling the limited labelled data issue in many application domains. But its applicability is almost unexplored in this domain as it is necessary to first identify the relevant model to transfer. In this paper, we propose a novel transfer learning approach for the estimation of petrophysical properties in a real-world reservoir dataset having inadequate labelled data samples. The proposed solution transfers the contextual knowledge of reservoir facies classes to the predictive model of petrophysical properties. Both the tasks share the common domain information and provided the improved generalisation performance considering the out-of-fold prediction in blind wells. Moreover, the analysis of results depicts better convergence and accuracy compared to its considered baselines. [ABSTRACT FROM AUTHOR]

Federated Learning (FL) is a collaborative training method for machine learning (ML) that aggregates model weights from multiple participants during the training phase. The learning phase of machine learning techniques is distributed, in which each participating device trains a model using its local data set and sends model weights to a centralized node. The central node aggregates weights and sends the updated weights back to devices. The process continues until a specific threshold is reached such accuracy, response time. In this paper, we present a performance evaluation of FL in a clustering-based multi-hop network to simulate the effect of the dynamic environment on the accuracy of the global model. It is observed that a minimum number of participating nodes is required within a cluster to maintain a high level of global accuracy. A global threshold value needs to be defined to maintain high global accuracy and avoid degradation of model performance. [ABSTRACT FROM AUTHOR]

Ground penetrating radar (GPR) systems are effective sensors for discovering various types of objects buried underground, such as military mines, metal objects, and pieces of underground infrastructures. A GPR system can be manually operated by a human or can be an integral part of a host platform. The host platform may be semi- or fully autonomous and may operate in different environments such as land vehicles or more recently air-borne drones. One challenge for the fully or semi-autonomous host platforms in particular is to find an efficient search procedure that would reduce the operation time and optimize resource utilization. Most of the current approaches are based on pre-defined search patterns which, for large and sparse areas, could mean unnecessary waste of time and resources. In this paper, we introduce a method that combines a coarse and therefore relatively low cost initial search pattern with a Reinforcement Learning (RL) driven efficient navigation path for eventual target detection, by exploiting the signal processing pipeline of the onboard GPR. We illustrate the applicability of the method using a well-known, high fidelity GPR simulation environment and a novel RL framework. Our results suggest that combination of a coarse navigation scheme and an RL-based training procedure based on GPR scan returns can lead to a more efficient target discovery procedure for host platforms. [ABSTRACT FROM AUTHOR]

The challenge of developing an Android malware detection framework that can identify malware in real-world apps is difficult for academicians and researchers. The vulnerability lies in the permission model of Android. Therefore, it has attracted the attention of various researchers to develop an Android malware detection model using permission or a set of permissions. Academicians and researchers have used all extracted features in previous studies, resulting in overburdening while creating malware detection models. But, the effectiveness of the machine learning model depends on the relevant features, which help in reducing the value of misclassification errors and have excellent discriminative power. A feature selection framework is proposed in this research paper that helps in selecting the relevant features. In the first stage of the proposed framework, t-test, and univariate logistic regression are implemented on our collected feature data set to classify their capacity for detecting malware. Multivariate linear regression stepwise forward selection and correlation analysis are implemented in the second stage to evaluate the correctness of the features selected in the first stage. Furthermore, the resulting features are used as input in the development of malware detection models using three ensemble methods and a neural network with six different machine-learning algorithms. The developed models' performance is compared using two performance parameters: F-measure and Accuracy. The experiment is performed by using half a million different Android apps. The empirical findings reveal that malware detection model developed using features selected by implementing proposed feature selection framework achieved higher detection rate as compared to the model developed using all extracted features data set. Further, when compared to previously developed frameworks or methodologies, the experimental results indicates that model developed in this study achieved an accuracy of 98.8%. [ABSTRACT FROM AUTHOR]

Variational quantum circuits are one of the promising ways to exploit the advantages of quantum computing in the noisy intermediate-scale quantum technology era. The design of the quantum circuit architecture might greatly affect the performance capability of the quantum algorithms. The quantum architecture search is the process of automatically designing quantum circuit architecture, aiming at finding the optimal quantum circuit composition architecture by the algorithm for a given task, so that the algorithm can learn to design the circuit architecture. Compared to manual design, quantum architecture search algorithms are more effective in finding quantum circuits with better performance capabilities. In this paper, based on the deep reinforcement learning, we propose an approach for quantum circuit architecture search. The sampling of the circuit architecture is learnt through reinforcement learning-based controller. Layer-based search is also used to accelerate the computational efficiency of the search algorithm. Applying to data classification tasks, we show that the method can search for quantum circuit architectures with better accuracies. Moreover, the circuit has a smaller number of quantum gates and parameters. [ABSTRACT FROM AUTHOR]

An industry-wide paradigm change has been sparked by the growth of Internet of Things (IoT)-based Wireless Sensor Networks (WSNs), which has made reliable and effective routing methods necessary. This thorough analysis looks at how Machine Learning (ML) techniques may be used to solve the problems that come with WSN routing. A summary of standard routing algorithms and an examination of their shortcomings comprise the first portion of the paper. The integration of ML approaches, such as reinforcement learning and supervised and unsupervised learning, is then explored in order to improve WSN routing efficiency. The article examines the difficulties and factors related to ML-based routing, including data quality, energy efficiency, scalability, and security. Applications and case studies show how ML is really used in WSN routing, offering insights into effective tactics and lessons discovered. Evaluation metrics and performance assessments are included in a separate section that uses simulation and experimental data to compare ML-based and conventional techniques. Looking forward, the study describes new breakthroughs in ML for WSNs and points out unresolved issues, providing a guide for future research paths. The important results and their consequences are outlined in the conclusion, which also highlights how ML has the potential to revolutionize WSN routing in the future. [ABSTRACT FROM AUTHOR]

Hazelnut is an agricultural product that contributes greatly to the economy of the countries where it is grown. The human factor plays a major role in hazelnut classification. The typical approach involves manual inspection of each sample by experts, a process that is both labor-intensive and time-consuming, and often suffers from limited sensitivity. The deep learning techniques are extremely important in the classification and detection of agricultural products. Deep learning has great potential in the agricultural sector. This technology can improve product quality, increase productivity, and offer farmers the ability to classify and detect their produce more effectively. This is important for sustainability and efficiency in the agricultural industry. In this paper aims to the application of deep learning algorithms to streamline hazelnut classification, reducing the need for manual labor, time, and cost in the sorting process. The study utilized hazelnut images from three different varieties: Giresun, Ordu, and Van, comprising a dataset of 1165 images for Giresun, 1324 for Ordu, and 1138 for Van hazelnuts. This dataset is an open-access dataset. In the study, experiments were carried out on the determination of hazelnut varieties with BigTransfer (BiT)-M R50 × 1, BiT-M R101 × 3 and BiT-M R152 × 4 models. Deep learning models, including big transfer was employed for classification. The classification task involved 3627 nut images and resulted in a remarkable accuracy of 99.49% with the BiT-M R152 × 4 model. These innovative methods can also lead to patentable products and devices in various industries, thereby boosting the economic value of the country. [ABSTRACT FROM AUTHOR]

To properly evaluate the quantity of mineral resources in a deposit, modeling the rock units of the deposit is essential since it informs the deposit's mineralization controls. The deterministic methods of modeling include geological assumptions, especially between drill holes, and therefore, might predict the deposit's complexity biasedly. Additionally, the uncertainty of rock units at unsampled locations cannot be quantified. Truncated/plurigaussian Gaussian and sequential indicator simulations are two most frequent stochastic approaches better suited to address these shortcomings. The ability to precisely depict the spatial correlation between rock units and quantify their uncertainties has made the truncated Gaussian simulation an essential technique for delineating rock units. However, using this method, long-range geological features like veins, faults, and fractures are often loosely modeled thus necessitating the use of soft data such as deterministic interpretive geological model to avert this inaccuracy. In this paper, the truncated Gaussian simulation is used to assess the spatial variability of rock units and quantify the uncertainty in their occurrence in a vein-dominated gold deposit. A novel approach is presented to model the rock units, particularly the veins, by incorporating a collocated co-simulation algorithm via a global correlation coefficient parameter. The realizations are conditioned to drill hole data and a collocated interpretive geological model created by a machine learning algorithm. The outcome shows realistic reproduction of the veins and other rock units, as representing the drill hole data and assessing their uncertainties thereof. [ABSTRACT FROM AUTHOR]

Mental health services are experiencing notable transformations as innovative technologies and artificial intelligence (AI) are increasingly utilized in a growing number of studies and services. These cutting-edge technologies carry the promise of substantial improvements in the field of mental health. Nevertheless, questions emerge about the alignment of novel technologies and AI systems with human needs, especially in the context of vulnerable populations receiving mental healthcare. The practice-oriented research (POR) model is pivotal in seamlessly integrating these emerging technologies into clinical research and practice. It underscores the importance of tight collaboration between clinicians and researchers, all driven by the central goal of ensuring and elevating client well-being. This paper focuses on how novel technologies can enhance the POR model and highlights its pivotal role in integrating these technologies into clinical research and practice. We discuss two key phases: pre-treatment, and during treatment. For each phase, we describe the challenges, present the major technological innovations, describe recent studies exemplifying technology use, and suggest future directions. Ethical concerns and the importance of aligning humans and technology are also considered, in addition to implications for practice and training. [ABSTRACT FROM AUTHOR]

The ever-increasing use of artificial intelligence (AI) to optimize embedding a watermark or find the optimal location in the host image for inserting a watermark might solve some problems in this field. However, the main problem, which is finding the optimum trade-off point among several watermarking criteria, has still not been investigated by researchers in this field, especially for speech signals. This paper aims to find the best trade-off among the watermarking requirements such as capacity, inaudibility, and robustness by applying an AI model. Moreover, a novel watermarking technique is proposed by modification of the probability density function (PDF) of the linear predictive (LP) residual and wavelet detail coefficient. For this method, a mathematical model is developed based on applying higher-order statistics for embedding and extracting the watermark. Sinh-arcsinh is used to shape the skewness and kurtosis of normal distribution for the LP residual or the wavelet high-frequency sub-bands, respectively, based on the watermark bits. Experimental results will show that although LP residual is not robust and it shows random behavior for modeling its PDF, the wavelet high-frequency band is quite robust and it can model the PDF of the wavelet. Moreover, it is demonstrated that AI has the capability to compromise among the watermarking criteria. Conclusions are drawn based on theoretical (maximum likelihood) and AI (machine learning) approaches, which confirm the effectiveness of the proposed model. Finally, in conclusion, several potential areas are discussed for further exploration. [ABSTRACT FROM AUTHOR]

This research paper focuses on the challenges associated with learning classifiers from large-scale, highly imbalanced datasets prevalent in many real-world applications. Traditional algorithms learning often need better performance and high computational efficiency when dealing with imbalanced data. Factors such as class imbalance, noise, and class overlap make it demanding to learn effective classifiers. In this study, we propose a novel self-paced ensemble framework for classifying imbalanced data. The framework employs under-sampling to self-harmonize data hardness and build a robust ensemble. Extensive experimental testing demonstrates promising results in handling overlapping classes and skewed distributions while maintaining computational efficiency. The self-paced ensemble method addresses the challenges of high imbalance ratios, class overlap, and noise presence in large-scale imbalanced classification problems. By incorporating the knowledge of these challenges into our learning framework, we establish the concept of classification hardness distribution, and the self-paced ensemble is a revolutionary learning paradigm for massive imbalance categorization, capable of improving the performance of existing learning algorithms on imbalanced data and providing better results for future applications. [ABSTRACT FROM AUTHOR]

Classifying imbalanced data presents a significant challenge, and many studies have proposed methodologies to address this issue. Among them, Convolutional Neural Networks have demonstrated superior performance for imbalanced image classification. This paper initially employs various data pre-processing methods such as over-sampling, under-sampling, and SMOTE to enhance the original dataset. Subsequently, an Ensemble CNN learning model is used to train and predict the data. In order to comprehensively evaluate models trained on imbalanced data, we used metrics such as Accuracy, Recall, Precision, F1-score, and G-mean. On the CIFAR-10 and Fashion-MNIST datasets, different samples from each category were extracted as imbalanced data for experimental research. Compared to the AdaBoost-DenseNet model, our proposed methodology increases the test accuracy on the CIFAR-10 dataset by 9%. Similarly, the F1-score and G-mean improved by 0.096 and 0.069, respectively. Compared to traditional methodologies, our proposed method significantly improves accuracy, recall, precision, and other performance indicators. [ABSTRACT FROM AUTHOR]

This paper presents a data-driven framework for evaluating collaboration efficiency within scientific research teams. The framework introduces a team efficiency evaluation system consisting of 40 specific indicators, which are analyzed and modeled using statistical methods. The adaptive enhancement algorithm model achieves the highest accuracy, recall, and F1 values, with scores of 0.852, 0.530, and 0.620, respectively. These findings demonstrate the feasibility of the proposed data-driven research team collaboration model, offering theoretical support for enhancing the effectiveness of group collaboration. Moreover, the study is significant for further research on group collaboration in diverse fields. [ABSTRACT FROM AUTHOR]

The paper studies the effectiveness of machine learning techniques in predicting the microhardness of composite materials manufactured from a mixture of iron-copper (Fe-Cu) nanopowders and hydroxyapatite (HA) particles. It is shown that the different proportion of Fe-Cu and HA powders and the polymer fraction in the composite significantly affect its hardness. A surrogate model based on the artificial neural network (ANN) and the analytical model, is proposed to quantitatively evaluate the microhardness, depending on the powder/polymer ratio. The ANN models show the probability distribution of indentation values after microhardness testing, which is the input data for the analytical model to compute the hardness. This approach can reduce the time and cost of the material research and minimizes the reliance on expensive materials and experimental equipment. [ABSTRACT FROM AUTHOR]

Development of a reliable and intelligent traffic monitoring system is highly desired to improve the transportation safety and establish future transportation plans due to the fast growth of vehicle population. Vehicle classification is one of the most critical subsystems where existing ones suffer from privacy concerns, requirements of complicated systems, and high maintenance cost. This paper reports a novel vehicle classification method by utilizing a triboelectric sensor to accurately identify vehicles. Novelty of this method originates from using triboelectric sensor and machine learning method with important advantages over current alternatives by providing an easy installation, simple operation, noninvasive measurement, cost-effective manufacturing, and highly accurate classification. To make a classification, vehicle toys' signals were acquired from triboelectric sensor and then applied to a deep learning algorithm. The 1932 sensor output data were grouped into a set of seven vehicle toys with different wheelbases, and number of tires passing on are used to train and optimize 1D-CNN model. The utilized 1D-CNN model achieved accuracy, f1-score, precision, and recall as 96.38%, 0.9638, 0.9658, and 0.9637, respectively. [ABSTRACT FROM AUTHOR]