Search

With the continuous deepening of the urbanization process and the progress of science and technology, people transform nature and develop nature on a larger and larger scale, among which the most iconic transformation is a variety of building structures built by people. And with the passage of time, the building structure in the perennial wind and sun, there will be signs of "illness", if not timely treatment, it will have a huge impact on the stability and safety of the building structure. Based on this, in this paper, according to the characteristics of crack identification on the surface of concrete structure, background subtraction algorithm is selected for image noise reduction processing. Through three steps of digital image noise reduction, crack extraction and crack parameter identification, the quantitative recognition of cracks is completed and a complete system of crack parameter identification is formed. The experimental results show that the machine learning model of building structure health monitoring and damage recognition algorithm proposed in this paper has excellent statistical performance, and the relative error accuracy of recognition can be controlled within 10%. [ABSTRACT FROM AUTHOR]

The research of biomedical data is crucial for disease diagnosis, health management, and medicine development. However, biomedical data are usually characterized by high dimensionality and class imbalance, which increase computational cost and affect the classification performance of minority class, making accurate classification difficult. In this paper, we propose a biomedical data classification method based on feature selection and data resampling. First, use the minimal-redundancy maximal-relevance (mRMR) method to select biomedical data features, reduce the feature dimension, reduce the computational cost, and improve the generalization ability; then, a new SMOTE oversampling method (Spectral-SMOTE) is proposed, which solves the noise sensitivity problem of SMOTE by an improved spectral clustering method; finally, the marine predators algorithm is improved using piecewise linear chaotic maps and random opposition-based learning strategy to improve the algorithm's optimization seeking ability and convergence speed, and the key parameters of the spectral-SMOTE are optimized using the improved marine predators algorithm, which effectively improves the performance of the over-sampling approach. In this paper, five real biomedical datasets are selected to test and evaluate the proposed method using four classifiers, and three evaluation metrics are used to compare with seven data resampling methods. The experimental results show that the method effectively improves the classification performance of biomedical data. Statistical test results also show that the proposed PRMPA-Spectral-SMOTE method outperforms other data resampling methods. [ABSTRACT FROM AUTHOR]

Under the influence of the coronavirus disease and other factors, agricultural product prices show non-stationary and non-linear characteristics, making it increasingly difficult to forecast accurately. This paper proposes an innovative combinatorial model for Chinese hog price forecasting. First, the price is decomposed using the Seasonal and Trend decomposition using the Loess (STL) model. Next, the decomposed data are trained with the Long Short-term Memory (LSTM) and Seasonal Autoregressive Integrated Moving Average (SARIMA) models. Finally, the prepared data and the multivariate influence factors after Factor analysis are predicted using the gated recurrent neural network and attention mechanisms (AttGRU) to obtain the final prediction values. Compared with other models, the STL-FA-AttGRU model produced the lowest errors and achieved more accurate forecasts of hog prices. Therefore, the model proposed in this paper has the potential for other price forecasting, contributing to the development of precision and sustainable agriculture. [ABSTRACT FROM AUTHOR]

In practical applications of machine learning, only part of data is labeled because the cost of assessing class label is relatively high. Measure of uncertainty is abbreviated as MU. This paper explores MU for partially labeled real-valued data via a discernibility relation. First, a decision information system with partially labeled real-valued data (p-RVDIS) is separated into two decision information systems: one is the decision information system with labeled real-valued data (l-RVDIS) and the other is the decision information system with unlabeled real-valued data (u-RVDIS). Then, based on a discernibility relation, dependence function, conditional information entropy and conditional information amount, four degrees of importance on an attribute subset in a p-RVDIS are defined. They are calculated by taking the weighted sum of l-RVDIS and u-RVDIS based on the missing rate, which can be considered as four MUs for a p-RVDIS. Combining l-RVDIS and u-RVDIS provides a more accurate assessment of the importance and classification ability of attribute subsets in a p-RVDIS. This is precisely the novelty of this paper. Finally, experimental analysis on several datasets verify the effectiveness of these MUs. These findings will contribute to the comprehension of the essence of the uncertainty in a p-RVDIS. [ABSTRACT FROM AUTHOR]

Sentiment analysis is a method of analyzing emotions and using text analysis techniques with natural language processing methods. Sentiment analysis uses data from various sources to identify the user’s attitude through different aspects. It is widely used for extracting opinions and recognizing sentiments, which helps Business organizations understand the user’s needs. This paper proposes a simple but compelling sentiment analysis method, showing the combined scores based on positive and negative words. Then, the tweets are categorized as Neutral, Negative, or Positive according to the scores. Sentiment analysis and opinion mining have grown significantly in the last decade. Different studies in this domain try to determine people’s feelings, opinions, and emotions about something or someone. The main objective of this analysis is to determine the sentiment of the review using a machine learning model and then compare the result with the manual review of the data. This would allow researchers to represent and analyze opinions objectively across different domains. A hybrid method that combines a supervised machine learning algorithm with natural language processing techniques is suggested for review analysis. This project aims to find the best model to predict the sentiment of the tweets on airlines. During the research process and considering various methods and variables that should be considered, we found that methods like naïve Bayes and random forest were not fully explored. The proposed system improves an effective and more feasible method for sentimental analysis using machine learning, multinomialNB, linear regression, and regular expression. [ABSTRACT FROM AUTHOR]

In the wake of the contemporary competitive business landscape, the retention of employees has become one of the most important yet difficult tasks for any corporate. Retaining top-performing employees not only improves organizational performance but also reduces recruitment costs. In this study, the authors investigate the major drivers leading to employee attrition and using machine learning algorithms implemented on a well proven and validated IBM HR data set. Although the data set tags the samples for a target variable (attrited and non-attrited), the work presented in this paper comes up with another labelling (1. likely to leave, 2. On the verge of leaving, 3. will stay). The data set is evaluated over top 10 Machine learning algorithms and a competitive analysis is made between them based on various factors. The best model has shown a prediction accuracy of over 85% +. Managers are provided with insights and recommendations at the end that will help companies to proactively identify at-risk employees and implement effective retention strategies. [ABSTRACT FROM AUTHOR]

In today’s Higher Education System (HES), Smart Learning (SL), also known as Intelligent Learning (IL) or Adaptive Learning (AL), plays an increasingly vital role. No longer is the traditional, one-size-fits-all method of education suitable for filling the several demands of students. Using SL technologies powered by Artificial Intelligence (AI) and Machine Learning (ML) algorithms can potentially revolutionize the HES. An emerging area of study, edge-based SL helps use Edge Computing (EC) to provide learners with instantaneous, specialized, and context-aware learning. Internet of Things (IoT) devices are becoming increasingly well-liked, and data is proliferating. Using video data as a primary source of learning content and delivering it via EC infrastructure is what is referred to as “Video Streaming (VS)” in Edge-Based Learning (EBL). By examining the importance of providing mobile video clients with a high-quality visual experience—especially considering that video streaming (VS) traffic makes up a significant amount of mobile network traffic—the research gap is filled. The proposed Content Delivery Scheme (CDS), which is based on long short-term memory, is intended to improve security and privacy protocols, accelerate network service response times, and increase application intelligence. The project intends to close the current gap in edge-based Smart Learning (SL) technologies, namely in the distribution of video material for adaptive learning in higher education, by concentrating on these elements. Given that VS traffic forms a considerable portion of mobile network traffic, this paper aims to investigate the significance of delivering a performing visual experience to mobile video clients. Fast network service response, enhanced application intelligence, and enhanced security and privacy are all made possible by the proposed LSTM-based Content Delivery Scheme (CDS). The proposed approach attains minimal stall time of 2347 ms, which outperforms the existing techniques. [ABSTRACT FROM AUTHOR]

In recent years, face detection has emerged as a prominent research field within Computer Vision (CV) and Deep Learning. Detecting faces in images and video sequences remains a challenging task due to various factors such as pose variation, varying illumination, occlusion, and scale differences. Despite the development of numerous face detection algorithms in deep learning, the Viola-Jones algorithm, with its simple yet effective approach, continues to be widely used in real-time camera applications. The conventional Viola-Jones algorithm employs AdaBoost for classifying faces in images and videos. The challenge lies in working with cluttered real-time facial images. AdaBoost needs to search through all possible thresholds for all samples to find the minimum training error when receiving features from Haar-like detectors. Therefore, this exhaustive search consumes significant time to discover the best threshold values and optimize feature selection to build an efficient classifier for face detection. In this paper, we propose enhancing the conventional Viola-Jones algorithm by incorporating Particle Swarm Optimization (PSO) to improve its predictive accuracy, particularly in complex face images. We leverage PSO in two key areas within the Viola-Jones framework. Firstly, PSO is employed to dynamically select optimal threshold values for feature selection, thereby improving computational efficiency. Secondly, we adapt the feature selection process using AdaBoost within the Viola-Jones algorithm, integrating PSO to identify the most discriminative features for constructing a robust classifier. Our approach significantly reduces the feature selection process time and search complexity compared to the traditional algorithm, particularly in challenging environments. We evaluated our proposed method on a comprehensive face detection benchmark dataset, achieving impressive results, including an average true positive rate of 98.73% and a 2.1% higher average prediction accuracy when compared against both the conventional Viola-Jones approach and contemporary state-of-the-art methods. [ABSTRACT FROM AUTHOR]

News text is an important branch of natural language processing. Compared to ordinary texts, news text has significant economic and scientific value. The characteristics of news text include structural hierarchy, diverse label categories, and limited high-quality annotation samples. Many machine learning and deep learning methods exist to analyze various forms of news text. However, due to label imbalance, hierarchical semantics, and confusing labels, current methods have limitations. Therefore, this paper proposes a news text classification framework based on hierarchical semantics and prior correction (HSPC). Firstly, data augmentation is used to enhance the diversity of the training set and adversarial learning is employed to improve the resistance of the model with its robustness. Then, a hierarchical feature extraction approach is employed to extract semantic features from different levels of news texts. Consequentially, a feature fusion method is designed to allow the model to focus on relevant hierarchical semantics for label classification. Finally, highly confusing label predictions are corrected to optimize the label prediction of the model and improve confidence. Multiple experiments are performed on four widely used public datasets. The experimental results indicate that HSPC achieves higher classification accuracy compared to other models. On the FCT, AGNews, THUCNews, and Ohsumed datasets, HSPC improves the accuracy by 1.03%, 1.38%, 2.55%, and 1.15%, respectively, compared to state-of-the-art methods. This validates the rationality and effectiveness of the designed mechanisms. [ABSTRACT FROM AUTHOR]

Neuroimaging technology is considered a non-invasive method research the structure and function of the brain which have been widely used in neuroscience, psychiatry, psychology, and other fields. The development of Deep Learning Neural Network (DLNN), based on the deep learning algorithms of neural imaging techniques in brain disease diagnosis plays a more and more important role. In this paper, a deep neural network imaging technology based on Stack Auto-Encoder (SAE) feature extraction is constructed, and then Support Vector Machine (SVM) was used to solve binary classification problems (Alzheimer's disease [AD] and Mild Cognitive Impairment [MCI]). Four sets of experimental data were employed to perform the training and testing stages of DLNN. The number of neurons in each of the DLNNs was determined using the grid search technique. Overall, the results of DLNNs performance indicated that the SAE feature extraction was superior over (Accuracy Rate [AR] = 74.9% with structure of 93-171-49-22-93) shallow layer features extraction (AR = 70.8% with structure of 93-22-93) and primary features extraction (AR = 69.2%). [ABSTRACT FROM AUTHOR]

The rapid growth of the Internet of Things (IoT) brings sweeping changes in various industries. Healthcare industries have become a prime example where the Internet of Healthcare Things (IoHT) is making significant progress, particularly in how we approach real-time patient care. Traditional systems for monitoring older people and people with special needs are frequently expensive, require a large workforce, and fall short of providing real-time data. This paper introduces the "3-Tier Health Care Architecture," an integrated approach to mitigating these issues. This architecture capitalizes on IoHT technologies and is constructed around three principal tiers: Sensor, Fog, and Cloud. The Sensor Tier employs Health Metrics Acquisition Units (HMAUs) fitted with an nRF5340 Development Kit, capturing an extensive range of health-related metrics via wearable sensors. These metrics are then relayed to the Local Processing Units (LPUs) in Fog Tier, which operates on Raspberry Pi Zero 2 W microprocessors for the initial data processing before forwarding to the cloud. The Cloud Tier uses a hybrid CNN-LSTM Machine Learning (ML) model to perform Real-Time Healthcare Monitoring (RTHM) status assessments and includes an Early Warning System for immediate alert issuance. The proposed architecture is resilient, scalable, and efficient, serving as a fortified and all-encompassing solution for RTHM. This enables quick medical interventions, thus elevating healthcare quality and potentially life-saving. [ABSTRACT FROM AUTHOR]

When providing patient care, healthcare professionals often rely on interpreting laboratory and clinical test results. However, their analysis is constrained by human capacity, leading to uncertainties in diagnoses. Machine learning has the potential to evaluate a larger amount of data and identify patterns and relationships that may otherwise go unnoticed. However, popular machine learning algorithms typically require abundant and labeled data, which is not always available. To address this challenge, the adoption of active learning allows for the selection of the most relevant instances for training, reducing the need for extensive labeling. Additionally, fuzzy logic offers the ability to handle uncertainties. This paper proposes a novel approach that utilizes fuzzy membership functions to transform data as a pre-processing step for active learning. The objective is to approximate similar instances, specifically for the purpose of prediction, thereby minimizing the workload of human experts in labeling data for model training. The results of this study demonstrate the effectiveness of this approach in predicting heart disease and highlight the potential of using membership functions to enhance machine learning models in the analysis of medical information. By incorporating fuzzy logic and active learning, healthcare professionals can benefit from improved accuracy and efficiency in diagnosing and predicting pacients' health conditions. [ABSTRACT FROM AUTHOR]

Smart farming is revolutionizing agriculture by integrating advanced technologies to enhance productivity, efficiency, and sustainability. This paper proposes a novel, 5G-enabled Pest and Disease Detection and Response System (PDDRS) that synergizes environmental sensor data with image analytics for comprehensive Plant Disease Detection (PDD). By leveraging the high bandwidth and ultra-low latency capabilities of 5G, our integrated system surpasses traditional communication technologies, facilitating real-time data analytics and immediate intervention strategies. We introduce two Machine Learning (ML) models: an image-based Mask R-CNN with FPN, which achieves a precision of 91.1% and an accuracy of 95.1%, and an environmental-based FFNN + LSTM model, evaluated for ACC, AUC, and F1-Score, showing promising results in disease forecasting. Our experiments demonstrate that the PDDRS significantly enhances throughput and latency performance under various connected devices, showcasing a scalable, cost-effective solution suitable for next-generation smart farming. These advancements collectively empower the PDDRS to deliver actionable insights, enabling targeted applications such as precise pesticide deployment, and stand as a testament to the potential of 5G in agricultural innovation. [ABSTRACT FROM AUTHOR]

Mild cognitive impairment (MCI) is a syndrome that occurs in the preclinical stage of Alzheimer's disease (AD) and is also an early signal of the onset of AD. Early detection and accurate differentiation between MCI and AD populations, and providing them with effective intervention and treatment, are of great significance for preventing or delaying the onset of AD. In this paper, we propose a deep learning model, SE-DenseNet, that combines channel attention and dense connectivity networks and apply it to the field of magnetic resonance imaging (MRI) data recognition for the diagnosis of AD and MCI. First, to extract MRI features with high quality, a slicing algorithm based on two-dimensional image information entropy is proposed to obtain AD brain lesion features with stronger representation ability. Second, in terms of model structure, SENet is introduced as a channel attention module and redistribute the weight of image features in the channel dimension; use DenseNet as the main architecture to maximize information flow, and each layer is directly interconnected with subsequent layers. It enables the network to learn and extract relevant features from the input data and improve the classification ability of the network. Finally, our proposed model is validated on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, the results have shown that the accuracy for the four classification tasks of AD-NC, AD-MCI, NC-MCI, and AD-NC-MCI can reach 98.12%, 97.42%, 97.42%, and 95.24%, respectively. At the same time, the sensitivity and specificity have also achieved satisfactory results, exhibited a high performance in comparison with the classic machine learning algorithm and several existing state-of-the-art deep learning methods, demonstrating the proposed method is a powerful tool for the early diagnosis and detection of AD. [ABSTRACT FROM AUTHOR]

Detection and classification methods for the melt pool state in laser direct energy deposition (L-DED) can significantly help predict defects and mechanical properties of L-DED metal parts. Although traditional machine learning algorithms based on physical modeling methods and convolutional neural networks have recently been introduced into melt pool state identification, these methods rely on complex artificially designed features or cannot simultaneously detect defects in multiple dimensions. In this paper, a novel bilateral stream neural network was designed for melt pool identification, which performs defect identification in two label dimensions simultaneously. Two sets of single-channel experiments were designed to collect the dataset captured by a high-speed camera. By cutting the metal parts and marking them with professional equipment operated by professionals, the dataset was labeled according to the bonding condition and dilution rate criteria. Without an additive model structure, the model achieved 95.2% accuracy in identifying defects in the bonding condition and 92.8% in determining deficiencies in the dilution rate. In order to explain the identification mechanism of the model, the CAM method was utilized for the visual display of the model recognition process, which provides a potential application solution for the online monitoring method of the L-DED. [ABSTRACT FROM AUTHOR]

Nowadays, cancer has become more alarming. This paper discusses the most significant Ovarian Cancer, Epithelial Ovarian Cancer (EOC), due to the low survival rate. The proposed algorithm for this work is a 'Multi classifier ShapRFECV based EOC' (MSRFECV-EOC) subtype analysis technique that utilized the EOC data from the National Centre for Biotechnology Information and Cancer Cell Line Encyclopedia websites for early identification of EOC using Machine Learning Techniques. This approach increases the data size, balances different classes of the data, and cuts down the enormous number of features unrelated to the disease of interest to prevent overfitting. To incorporate these functionalities, in the data preprocessing stage, OC-related gene names were taken from the Cancermine database and other OC-related works. Moreover, OC datasets were merged based on OC genes, and missing values of EOC subtypes were identified and imputed using Iterative Logistic Imputation. Synthetic Minority Oversampling Technique with an Edited Nearest Neighbors approach is applied to the imputed dataset. Next, in the Feature Selection phase, the most significant features for subtypes of EOC were identified by applying the Shapley Additive Explanations based on the Recursive Feature Elimination Cross-Validation (ShapRFECV) algorithm, preserving predefined features while selecting new EOC features. Eventually, an accuracy of 97% was achieved with Optuna-optimized Random Forest, which outperformed the existing models. SHAP plotted the most prominent features behind the classification. The Pickle tool saves much training time by preserving hidden parameter values of the model. In the final phase, by using the Stratified K Fold Stacking Classifier, the accuracy was improved to 98.9%. [ABSTRACT FROM AUTHOR]

Parkinson disease (PD) is a type of neurodegenerative disorder that affects the motor movement of the patient. But each technique has its own advantages or disadvantages. In gene, speech and handwriting data model, the feature extraction and reduction is an important step for efficient classification. These two steps require proper attention for selection and also require high processing time as compared to other data model like images. Because in image modality, the deep learning algorithm can be applied that can perform all process and automate the classification. As compared to these domains, the signal produces better and best results. Because the electroencephalogram (EEG) signal are taken from the brain using electrodes and it helps to observe the brain signals effectively and immediately as compared to the other data modals. Hence, in this paper, the wavelet transform will be used to decompose the signals and statistical features will be extracted from the transformed signal. Here, the satin bower bird optimization will be used for both type of wavelet selection and feature reduction process for final classification. The reduced feature set will be classified using Ensemble Neural Network type including InceptionV3, DenseNet, MobileNet, Xception, and NasNet) recently proposed for medical image classification. The whole process will be realized using MATLAB R2021a software and its performance will be evaluated in terms of Accuracy and is compared against Automated Tunable Q-wavelet transform performance. The proposed ensemble method, employing EEG signal processing and neural networks, achieved a 97% success rate in discriminating PD datasets, surpassing Convolutional Neural Network (CNN) and Machine Learning (ML) classifications (88% –92%). Utilizing MATLAB R2021a, its superiority over Q-wavelet transform was evident, signifying improved PD dataset discrimination. [ABSTRACT FROM AUTHOR]

Aiming at the problem of inaccurate transformer fault diagnosis in dissolved gas analysis, this paper proposes a novel diagnostic method that integrates an enhanced honey badger algorithm (EHBA) with an ensemble learning-based deep hybrid kernel extreme learning machine (DHKELM). First, kernel principal component analysis (KPCA) was deployed for feature fusion of the gas data, thus extracting more effective features. The DHKELM, combining polynomial and RBF kernel functions, was used as a base learning to build a powerful classifier with Adaboost framework. The EHBA introduces information sharing and firefly perturbation strategies based on HBA. This EHBA was harnessed to optimize the DHKELM's critical parameters, establishing the EHBA-DHKELM-Adaboost transformer fault diagnosis model. Finally, the features garnered by KPCA were fed into the model, simulating and validating various fault diagnosis models. The findings reveal that EHBA-DHKELM-Adaboost achieves 98.75% diagnostic accuracy in transformer faults, surpassing other models. [ABSTRACT FROM AUTHOR]

Malware attack is a growing problem on the Android mobile platform due to its popularity and openness. Although numerous malware detection approaches have been proposed, it still remains challenging for malware detection due to a large amount of constantly mutating apps. The opcode, as the most fundamental part of Android app, possesses good resistance against obfuscation and Android version updates. Due to the large number of opcodes, most opcode-based methods employ statistical-based feature selection, which disrupts the correlation and semantic information among opcodes. In this paper, we propose an Android malware detection framework based on sensitive opcodes and deep reinforcement learning. Firstly, we extract sensitive opcode fragments based on sensitive elements and then encode the features using n-gram. Next, we use deep reinforcement learning to select the optimal subset of features. During the process of handling opcodes, we focus on preserving semantic information and the correlation among opcodes. Finally, our experimental results show an accuracy of 0.9670 by using the 25 opcode features we obtained. [ABSTRACT FROM AUTHOR]

Solar power generation forecasting plays a vital role in optimizing grid management and stability, particularly in renewable energy-integrated power systems. This research paper presents a comprehensive study on solar power generation forecasting, evaluating traditional and advanced machine learning methods, including ARIMA, Exponential Smoothing, Support Vector Regression, Random Forest, Gradient Boosting, and Physics-based Models. Moreover, we propose an innovative Enhanced Artificial Neural Network (ANN) model, which incorporates Weather Modulation and Leveraging Prior Forecasts to enhance prediction accuracy. The proposed model is evaluated using real-world solar power generation data, and the results demonstrate its superior performance compared to traditional methods and other machine learning approaches. The Enhanced ANN model achieves an impressive Root Mean Square Error (RMSE) of 0.116 and a Mean Absolute Percentage Error (MAPE) of 36.26%. The integration of Weather Modulation allows the model to adapt to changing weather conditions, ensuring reliable forecasts even during adverse scenarios. Leveraging Prior Forecasts enables the model to capture short-term trends, reducing forecasting errors arising from abrupt weather changes. The proposed Enhanced ANN model showcases its potential as a promising tool for precise and reliable solar power generation forecasting, contributing to the efficient integration of solar energy into the power grid and advancing sustainable energy practices. [ABSTRACT FROM AUTHOR]

Mechanical fault diagnosis is currently a highly trending topic, facing two significant challenges. Firstly, the acquisition of an ample number of fault samples proves to be difficult, thereby limiting access to sufficient data samples. Secondly, intricate and non-mathematically describable associations often exist among different faults. Most algorithms treat fault samples as isolated entities, consequently impacting the accuracy of fault diagnosis. This paper proposes a novel machine learning framework called Domain Graph Attention Neural Network (DGAT), which leverages the topological structure of graphs to effectively capture the interrelationships among fault samples. Additionally, this framework incorporates domain information during node updates to obtain richer embeddings, particularly in scenarios with limited available samples. It effectively overcomes the fixed receptive field limitation of the original Graph Attention Network (GAT). In order to validate the effectiveness of the model, we conducted extensive comparative experiments on diverse datasets, which demonstrated the superior performance of the proposed model. [ABSTRACT FROM AUTHOR]

Along with the booming of intelligent manufacturing, the reliability management of intelligent manufacturing systems appears to be becoming more significant. Failure mode and effects analysis (FMEA) is a prospective reliability management instrument extensively utilized to manage failure modes of systems, products, processes, and services in various industries. However, the conventional FMEA method has been criticized for its inherent limitations. Machine learning can handle large amounts of data and has merits in reliability analysis and prediction, which can help in failure mode classification and risk management under limited resources. Therefore, this paper devises a method for complex systems based on an improved FMEA model combined with machine learning and applies it to the reliability management of intelligent manufacturing systems. First, the structured network of failure modes is constructed based on the knowledge graph for intelligent manufacturing systems. Then, the grey relation analysis (GRA) is applied to determine the risk prioritization of failure modes. Hereafter, the k-means algorithm in unsupervised machine learning is employed to cluster failure modes into priority classes. Finally, a case study and further comparative analysis are implemented. The results demonstrate that failure modes in system security, production quality, and information integration are high-risk and require more resources for prevention. In addition, recommendations for risk prevention and monitoring of intelligent manufacturing systems were given based on the clustering results. In comparison to the conventional FMEA method, the proposed method can more precisely capture the coupling relationship between the failure modes compared with. This research provides significant support for the reliability and risk management of complex systems such as intelligent manufacturing systems. [ABSTRACT FROM AUTHOR]

The concept of entropy and information gain of BE-algebras in scientific disciplines such as information theory, data science, supply chain and machine learning assists us to calculate the uncertanity of the scientific processes of phenomena. In this respect the notion of filter entropy for a transitive BE-algebra is introduced and its properties are investigated. The notion of a dynamical system on a transitive BE-algebra is introduced. The concept of the entropy for a transitive BE-algebra dynamical system is developed and, its characteristics are considered. The notion of equivalent transitive BE-algebra dynamical systems is defined, and it is proved the fact that two equivalent BE-algebra dynamical systems have the same entropy. Theorems to help calculate the entropy are given. Specifically, a new version of Kolmogorov– Sinai Theorem has been proved. The study introduces the concept of information gain of a transitive BE-algebra with respect to its filters and investigates its properties. This study proposes the use of filter entropy to approximate the level of risk introduced by a BE-algebra dynamical system. This aim is reached by defining the information gain with respect to the filters of a BE-algebra. This methodology is well developed for use in engineering, especially in industrial networks. This paper proposes a novel approach to assess the quantity of uncertainty, and the impact of information gain of a BE-algebra dynamical system. [ABSTRACT FROM AUTHOR]

A Single-valued neutrosophic set (SVNS) has recently been explored as a comprehensive tool to assess uncertain information due to varied human cognition. This notion stretches the domain of application of the classical fuzzy set and its extended versions. Various comparison measures based on SVNSs like distance measure, similarity measure, and, divergence measure have practical significance in the study of clustering analysis, pattern recognition, machine learning, and computer vision-related problems. Existing measures have some drawbacks in terms of precision and exclusion of information and produce unreasonable results in categorization problems. In this paper, we propose a generic method to define new divergence measures based on common aggregation operators and discuss some algebraic properties of the proposed divergence measures. To further appreciate the proposed divergence measures, their application to pattern recognition has been investigated in conjunction with the prominent existing comparison measures based on SVNSs. The comparative assessment sensitivity analysis of the proposed measures establishes their edge over the existing ones because of appropriate classification results. [ABSTRACT FROM AUTHOR]

Gait analysis is a widely used technique for passive human identification and tracking, with potential applications in security and surveillance systems. However, existing gait recognition methods face challenges in handling changing angles and uncertain features. In this paper, we propose a novel gait recognition approach that leverages real-time spatio-temporal gait features, including step length, gait cycle, height, cadence, swing ratio, and foot length. We apply the Extreme Learning Machines (ELM) algorithm for classification, which has been shown to be effective in various applications due to its fast-learning speed and good generalization performance. To further enhance the recognition rate, we introduce an evolutionary BAT-optimized ELM algorithm that addresses the instability issue in ELM. The proposed BAT-ELM algorithm can optimize the hidden nodes and weights of ELM, which leads to improved efficiency in recognizing gait from multiple view angles ranging from 0° to 180°. Our comprehensive analysis of the proposed approach indicates that it outperforms other reported algorithms in terms of recognition rate and efficiency. Our work demonstrates the effectiveness of combining real-time spatio-temporal gait features with the BAT-ELM algorithm for gait recognition. The proposed approach has potential applications in various fields, including security and surveillance systems, healthcare, and robotics. Our findings highlight the importance of leveraging evolutionary algorithms to optimize machine learning models and achieve better performance in complex recognition tasks. [ABSTRACT FROM AUTHOR]

This paper proposes a method of using machine learning and an evolutionary algorithm to solve the flexible job shop problem (FJSP). Specifically, a back propagation (BP) neural network is used as the machine learning method, the most widely used genetic algorithm (GA) is employed as the optimized object to address the machine-selection sub-problem of the FJSP, and particle swarm optimization (PSO) is utilized to solve the operation-order sub-problem of the FJSP. At present, evolutionary algorithms such as the GA, PSO, ant colony algorithm, simulated annealing algorithm, and their optimization algorithms are widely used to solve the FJSP; however, none of them optimizes the initial solutions. Because each of these algorithms only focuses on solving a single FJSP, they can only use randomly generated initial solutions and cannot determine whether the initial solutions are good or bad. Based on these standard evolutionary algorithms and their optimized versions, the JSON object was introduced in this study to cluster and reconstruct FJSPs such that the machine learning strategies can be used to optimize the initial solutions. Specifically, the BP neural networks are trained so that the generalization of BP neural networks can be used to judge whether the initial solutions of the FJSPs are good or bad. This approach enables the bad solutions to be filtered out and the good solutions to be maintained as the initial solutions. Extensive experiments were performed to test the proposed algorithm. They demonstrated that it was feasible and effective. The contribution of this approach consists of reconstructing the mathematical model of the FJSP so that machine learning strategies can be introduced to optimize the algorithms for the FJSP. This approach seems to be a new direction for introducing more interesting machine learning methodologies to solve the FJSP. [ABSTRACT FROM AUTHOR]

Industry experts are motivated to collect, collate, and analyse historical data in the legal sector in attempt to predict court case outcomes as the amount of historical data available in this field has increased over time. But using judicial data to predict and defend court judgements is no simple undertaking. Using Machine Learning (ML) models and traditional approaches for categorical feature encoding, previous research on predicting court outcomes using limited experimental datasets produced a number of unexpected predictions. The paper proposes an ensemble model combining Convolutional Neural Network (CNN), attention mechanism and eXtreme Gradient Boosting (XGB) algorithm. This model is primarily based on a self-attention network, which could simultaneously capture linguistic relationships over lengthy sequences like RNN (Recurrent Neural Network) and is nevertheless speedy to train like CNN. C-XGB can obtain accuracy that surpasses the state-of-art model on numerous classification/prediction tasks simultaneously as being twice as speedy to train. The proposed C-XGB model is designed to process the documents hierarchically and calculates the attention weights. Two convolutional layers are used to calculate the attention weights, one at the word level and another at the sentence level. And finally, at the last layer, the XGB algorithm predicts the input case file’s outcome. The experimental results shows that the proposed model outperforms the existing model with 4.67% improvement in accuracy value. [ABSTRACT FROM AUTHOR]

Vehicle Edge Computing (VEC) is a promising technique to improve the quality of service (QoS) and quality of experience (QoE) in autonomous driving by exploiting the resources at the network edge. However, the high mobility of the vehicles leads to stochastic communication link duration, and the tasks generated by various applications in autonomous driving incur fierce competition for resources. These challenges cause excessive task completion delays. In this paper, we propose a vehicle-to-vehicle (V2V) partial computation offloading scheme that leverages the prediction results of the communication link lifetime between vehicles. A History track, Current interactions and Future planning trajectory-aware Gated Recurrent Units (HCF-GRU) network is built to capture the essential factors to improve the prediction accuracy. Then, we design a GRU-based Proximal Policy Optimization (GRU-PPO) algorithm to obtain an optimal one-to-many offloading decision to minimize the task execution cost. The HCF-GRU prediction algorithm is evaluated on a real world vehicle trajectory dataset, and the performance of the GRU-PPO algorithm is analyzed on extensive numerical simulations. Experimental results demonstrate that our prediction network and offloading decision algorithm outperform the baseline methods in terms of prediction accuracy and task execution cost. [ABSTRACT FROM AUTHOR]

The contemporary real-world datasets often suffer from the problem of class imbalance as well as high dimensionality. For combating class imbalance, data resampling is a commonly used approach whereas for tackling high dimensionality feature selection is used. The aforesaid problems have been studied extensively as independent problems in the literature but the possible synergy between them is still not clear. This paper studies the effects of addressing both the issues in conjunction by using a combination of resampling and feature selection techniques on binary-class imbalance classification. In particular, the primary goal of this study is to prioritize the sequence or pipeline of using these techniques and to analyze the performance of the two opposite pipelines that apply feature selection before or after resampling techniques i.e., F + S or S + F. For this, a comprehensive empirical study is carried out by conducting a total of 34,560 tests on 30 publicly available datasets using a combination of 12 resampling techniques for class imbalance and 12 feature selection methods, evaluating the performance on 4 different classifiers. Through the experiments we conclude that there is no specific pipeline that proves better than the other and both the pipelines should be considered for obtaining the best classification results on high dimensional imbalanced data. Additionally, while using Decision Tree (DT) or Random Forest (RF) as base learner the predominance of S + F over F + S is observed whereas in case of Support Vector Machine (SVM) and Logistic Regression (LR), F + S outperforms S + F in most cases. According to the mean ranking obtained from Friedman test the best combination of resampling and feature selection techniques for DT, SVM, LR and RF are SMOTE + RFE (Synthetic Minority Oversampling Technique and Recursive Feature Elimination), Least Absolute Shrinkage and Selection Operator (LASSO) + SMOTE, SMOTE + Embedded feature selection using RF and SMOTE + RFE respectively. [ABSTRACT FROM AUTHOR]

Structure learning is the core of graph model Bayesian Network learning, and the current mainstream single search algorithm has problems such as poor learning effect, fuzzy initial network, and easy falling into local optimum. In this paper, we propose a heuristic learning algorithm HC-PSO combining the HC (Hill Climbing) algorithm and PSO (Particle Swarm Optimization) algorithm, which firstly uses HC algorithm to search for locally optimal network structures, takes these networks as the initial networks, then introduces mutation operator and crossover operator, and uses PSO algorithm for global search. Meanwhile, we use the DE (Differential Evolution) strategy to select the mutation operator and crossover operator. Finally, experiments are conducted in four different datasets to calculate BIC (Bayesian Information Criterion) and HD (Hamming Distance), and comparative analysis is made with other algorithms, the structure shows that the HC-PSO algorithm is superior in feasibility and accuracy. [ABSTRACT FROM AUTHOR]

Intelligent Transportation Systems (ITS) have experienced significant growth over the past decade thanks to advances in control, communication, and information technology applied to vehicles, roads, and traffic control systems. Vehicle type classification plays a vital role in implementing ITS because of its ability to collect useful traffic information, enable future development of transport infrastructures, and increase human comfort. As a branch of machine learning, deep learning represents a frontier for artificial intelligence, which seeks to be closer to its primary goal. Deep learning is a powerful tool for classifying vehicle types because it can capture complex traffic data characteristics and learn from large amounts of data. This means that it can be used to accurately classify traffic data and generate valuable insights that can be used to improve traffic management. Researchers have successfully adopted these algorithms as a solution to propose optimal vehicle-type classification strategies. This paper highlights the role of deep learning algorithms in solving the vehicle type classification problem, reviewing the state-of-the-art approaches in this field. [ABSTRACT FROM AUTHOR]

Feature selection can remove data noise and redundancy and reduce computational complexity, which is vital for machine learning. Because the difference between nominal attribute values is difficult to measure, feature selection for hybrid information systems faces challenges. In addition, many existing feature selection methods are susceptible to noise, such as Fisher, LASSO, random forest, mutual information, rough-set-based methods, etc. This paper proposes some techniques that consider the above problems from the perspective of fuzzy evidence theory. Firstly, a new distance incorporating decision attributes is defined, and then a relation between fuzzy evidence theory and fuzzy β covering with an anti-noise mechanism is established. Based on fuzzy belief and fuzzy plausibility, two robust feature selection algorithms for hybrid data are proposed in this framework. Experiments on 10 datasets of various types have shown that the proposed algorithms achieved the highest classification accuracy 11 times out of 20 experiments, significantly surpassing the performance of the other 6 state-of-the-art algorithms, achieved dimension reduction of 84.13% on seven UCI datasets and 99.90% on three large-scale gene datasets, and have a noise tolerance that is at least 6% higher than the other 6 state-of-the-art algorithms. Therefore, it can be concluded that the proposed algorithms have excellent anti-noise ability while maintaining good feature selection ability. [ABSTRACT FROM AUTHOR]

The present study focuses on the implementation of Deep Reinforcement Learning (Deep-RL) techniques for a parallel manipulator robot, specifically the Delta Robot, within a simulated setting. We introduced a simulation framework designed to guide the Delta Robot's end-effector to a designated spatial point accurately. Within this environment, the robotic agent undergoes a learning process grounded in trial and error. It garners positive rewards for successful predictions regarding the next action and faces negative repercussions for inaccuracies. Through this iterative learning mechanism, the robot refines its strategies, thereby establishing improved decision-making rules based on the ever-evolving environment states. Our investigation delved into three distinct Deep-RL algorithms: the Deep Q-Network Algorithm (DQN), the Double Deep Q-Network (DDQN), and the Trust Region Policy Optimization Algorithm (TRPO). All three methodologies were adept at addressing the challenge presented, and a comprehensive discussion of the findings is encapsulated in the subsequent sections of the paper. [ABSTRACT FROM AUTHOR]

The concept of endorsing AI in embedded systems is growing in all sectors including the development of Accident Avoidance Systems. Although real-time road crash prediction is vital for enhancing road user safety, there has been limited focus on the analysis of real-time crash events within ensemble and deep learning fused systems. The main aim of this paper is to design an advanced Accident Avoidance System established on a deep learning and ensemble fusion strategy in order to acquire more performant crash predictions. As such, four highly optimized models for crash prediction have been designed based on the popular ensemble techniques: CatBoost, AdaBoost and Bagging and the deep learning CNN. Additionally, four categories of features, including driver inputs, vehicle kinematics, driver states and weather conditions, were measured during the execution of various driving tasks performed on a driving simulator. Moreover, given the infrequent nature of crash events, an imbalance-control procedure was adopted using the SMOTE and ADASYN techniques. The highest performances results have been acquired using CatBoost along with ADASYN on almost all the adopted metrics during the different weather conditions, and more than 50% of all crashes have occurred in rainy weather conditions, whereas 31% have been exhibited in fog patterns. The sensitivity analysis results indicate that the fusing all the acquired features has the highest impact on the prediction performance. To our knowledge, there has been a limited interest, if not at all, at adopting a fused ensemble deep learning system examining the real-time impact of the adopted features' combinations on the prediction of road crashes while taking into account class imbalance. The findings provide new insights into crash prediction and emphasize the relevance of the explanatory features which can be endorsed in designing efficient Accident Avoidance Systems. [ABSTRACT FROM AUTHOR]

A new era in communication has been ushered in by MANET networks, in which users (nodes) interact with one another through a self-configuring network of handheld devices linked by wireless links. Nodes are capable of participating and enthusiastic about sending packets to other nodes. Consequently, the need for a routing protocol materializes. The most difficult aspect is dealing with the network's dynamic topology as a result of node mobility. This is because limited resources like storage space, battery life, and bandwidth require a protocol that can quickly adapt to topology changes while periodically updating messages. On the other hand, security is another important aspect of routing since the involvement of attackers will exhaust the network resources. This paper addresses the main issue of designing a routing protocol that handles all the adversaries and achieves better efficiency. For that, we proposed a Hybrid Machine Learning (HyML) model which evaluates the. Initially, the network is segregated by the Secure Stable Clustering (SSC) approach which first verifies the node's legacy and forms clusters based on stability. The HyML is designed by combining two important ML techniques such as ANN and fuzzy-C Means (FCM) algorithm. The ANN model learns multiple attributes of the trust value and computes the cumulative trust score. Next, FCM determines the node position upon trust score. After the computation of the trust value, optimal route selection is performed by the Spider Monkey Optimization (SMO) technique. The overall work is evaluated through comprehensive simulations based on network longevity, throughput, energy usage, PDR, attack detection efficiency, and delay. [ABSTRACT FROM AUTHOR]

In response to the evolving landscape of the modern era, the requirements for engineering audit have undergone significant changes. To achieve efficient audit tasks and obtain accurate and reliable results, the integration of machine learning and wireless network technology has become essential, leading to the emergence of digital and information-based audit modes. This paper focuses on the development of a digital audit system that combines engineering audit management fusion with machine learning and wireless network technology. Such an approach reflects the dynamic shift in internal audit functions and objectives, providing clear guidelines for the future of digital audit management. By harnessing the power of machine learning and wireless networks, the digital audit system effectively addresses challenges associated with data management, sharing, exchange, and security during the audit process. Through seamless integration, it enables comprehensive electronic and digital management of internal and audit business processes. This research explores the platform's functionalities and its potential application, using actual audit data for analysis. The proposed digital audit system showcases superior real-time data querying performance, heightened accuracy in checks, and enhanced retrieval capabilities. The simulation results validate the system's efficacy, highlighting its ability to deliver true and dependable audit outcomes. By embracing digital transformation, the engineering audit field can harness the potential of cutting-edge technologies, thus paving the way for a more efficient, reliable, and future-ready approach to audit management. [ABSTRACT FROM AUTHOR]

Wireless Sensor Networks (WSNs) have gained significant attention in recent years due to their wide range of applications, such as environmental monitoring, smart agriculture, and structural health monitoring. With the increasing volume of data generated by WSNs, efficient data analytics techniques are crucial for improving the overall performance and reducing energy consumption. This paper presents a novel distributed data analytics approach for WSNs using fuzzy logic-based machine learning. The proposed method combines the advantages of fuzzy logic for handling uncertainty and imprecision with the adaptability of machine learning techniques. It enables sensor nodes to process and analyze data locally, reducing the need for data transmission and consequently saving energy. Furthermore, this approach enhances data accuracy and fault tolerance by incorporating the fusion of heterogeneous sensor data. The proposed technique is evaluated on a series of real-world and synthetic datasets, demonstrating its effectiveness in improving the overall network performance, energy efficiency, and fault tolerance. The results indicate the potential of our approach to be applied in various WSN applications that demand low-energy consumption and reliable data analysis. [ABSTRACT FROM AUTHOR]

Arrhythmia disorders are the leading cause of death worldwide and are primarily recognized by the patient's irregular cardiac rhythms. Wearable Internet of Things (IoT) devices can reliably measure patients' heart rhythms by producing electrocardiogram (ECG) signals. Due to their non-invasive nature, ECG signals have been frequently employed to detect arrhythmias. The manual procedure, however, takes a long time and is prone to error. Utilizing deep learning models for early automatic identification of cardiac arrhythmias is a preferable approach that will improve diagnosis and therapy. Though ECG analysis using cloud-based methods can perform satisfactorily, they still suffer from security issues. It is essential to provide secure data transmission and storage for IoT medical data because of its significant development in the healthcare system. So, this paper proposes a secure arrhythmia classification system with the help of effective encryption and a deep learning (DL) system. The proposed method mainly involved two phases: ECG signal transmission and arrhythmia disease classification. In the ECG signal transmission phase, the patient's ECG data collected through the IoT sensors is encrypted using the optimal key-based elgamal elliptic curve cryptography (OKEGECC) mechanism, and the encrypted data is securely transmitted to the cloud. After that, in the arrhythmia disease classification phase, the system collects the data from the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) database to perform training. The collected data is preprocessed by applying the continuous wavelet transform (CWT) to improve the quality of the ECG data. Next, the feature extraction is carried out by deformable attention-centered residual network 50 (DARNet-50), and finally, the classification is performed using butterfly-optimized Bi-directional long short-term memory (BOBLSTM). The experimental outcomes showed that the proposed system achieves 99.76% accuracy, which is better than the existing related schemes. [ABSTRACT FROM AUTHOR]

Globally, heart disease is the primary cause of death. Early detection of this disease enables cardiologists to make more accurate judgments regarding the health of their patients. Due to machine learning's ability to identify patterns in data, its use in the medical industry has increased. Many heart disease prediction models have been developed by various researchers utilizing machine learning techniques (MLTs). The performance of MLTs on heart disease prediction may vary for different accuracy measures. Thus, the choice of the appropriate machine-learning technique for heart disease prediction is a challenging task. This paper proposes a multi-criteria decision-making (MCDM)-based method to evaluate the MLTs for heart disease prediction considering various performance measures taken into account altogether. The proposed approach uses the concept of a combined compromise solution (CoCoSo)- an MCDM method. For validation of the proposed approach, an experimental study was conducted to evaluate the performance of fifteen machine learning techniques for predicting heart disease over three heart disease datasets considering six performance measures taken into account altogether. Results show that the logistic regression and support vector machine are recommended as the most suitable MLTs for heart disease prediction modeling with respect to six performance measures considered simultaneously. [ABSTRACT FROM AUTHOR]

In the current industry, quality inspection in semiconductor manufacturing is of immense significance. Significant achievements have been made in fault diagnosis in fabricated semiconductor wafer manufacturing due to the development of machine learning. Since real-time intermediate signals are non-linear and time-varying, the signals undergo various distortions due to changes in equipment, material, and process. This leads to a drastic change in information in intermediate signals. This paper presents a fault diagnosis model for semiconductor manufacturing processes using a generative adversarial network (GAN). The study aims to address the challenges associated with efficient and accurate fault identification in these complex processes. Our approach involves the extraction of relevant components, development of a paired generator model, and implementation of a deep convolutional neural network. Experimental evaluations were conducted using a comprehensive dataset and compared against six existing models. The results demonstrate the superiority of our proposed model, showcasing higher accuracy, specificity, and sensitivity across various shift tasks. This research contributes to the field by introducing a novel approach for fault diagnosis, paving the way for improved process control and product quality in semiconductor manufacturing. Future work will focus on further optimizing the model and extending its applicability to other manufacturing domains. [ABSTRACT FROM AUTHOR]

PCB defect detection aims to identify the presence of gaps, open circuits, short circuits, and other defects in the PCB boards produced in the industry. Designing effective deep learning algorithms is crucial to finding a solution. Previously proposed PCB defect detection algorithms are limited in detecting tiny objects in high-density. Directly applying previous models to tackle PCB defect detection tasks will cause serious issues, such as missed detection and false detection. In this paper, we present a detection algorithm for tiny PCB defect targets in high-density regions to solve the above-mentioned problems. We firstly propose a detection head to detect tiny objects. Then, we design a four-channel feature fusion mechanism to fuse four different scale features and add an attention mechanism to find the attention region in scenarios with dense objects. Finally, we achieved accurate detection of tiny targets in high-density areas. Experiments were performed on the publicly available PCB defect dataset from Peking University. Our mAP@.5:.95 achieves 48.6%, while mAP@0.5 exceeds 90%. Compared with YOLOX and YOLOv5, our improved model can better localize tiny objects in high-density scenes. The experimental results certify that our model can obtain higher performance in comparison with the baseline and the state of the art. [ABSTRACT FROM AUTHOR]