Search

This document discusses the societal impact of applying artificial intelligence (AI) to traffic and transportation. Sustainable transport is considered crucial for sustainable cities and communities, and AI has the potential to significantly influence daily life in urban areas. The document highlights the interdisciplinary challenges of understanding and coordinating transportation systems, which involve various players with conflicting goals and constraints. It also presents a selection of innovative solutions related to traffic management, including machine learning, reinforcement learning, and optimization approaches. The document concludes by expressing gratitude to the authors, reviewers, and committee members involved in the creation of the special issue. [Extracted from the article]

Peer review is under pressure. Without fair, transparent and efficient peer review we cannot ensure the right proposals get funded and the correct manuscripts get published. In the era of Open Access, which is driving an exponential increase in the number of submitted publications, how we carry out peer review is becoming increasingly important and how we find reviewers is coming under scrutiny. The current methods are slow and produce bias pools of reviewers. As such we need an improved way. At Prophy we have developed a state-of-the-art referee finder that can find experts to review any manuscript from any scientific field in seconds. Then through post-processing filters we can find appropriate candidate referees who are most likely to review a paper, whilst highlighting important conflicts of interest through our complex citation networks. These methods can ensure fair and independent experts who can review interdisciplinary papers from any discipline. These methods are being delivered through APIs and the editorial workflow of editors ensure the right people get access to these tools. Finally, as large-language models improve, so does Prophy and as such we will be looking to drive real innovation in this area in years to come. [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]

Debugging and repairing Web Ontology Language (OWL) ontologies has been a key field of research since OWL became a W3C recommendation. One way to understand errors and fix them is through explanations. These explanations are usually extracted from the reasoner and displayed to the ontology authors as is. In the meantime, there has been a recent call in the eXplainable AI (XAI) field to use expert knowledge in the form of knowledge graphs and ontologies. In this paper, a parallel between explanations for machine learning and for ontologies is drawn. This link enables the adaptation of XAI methods to explain ontologies and their entailments. Counterfactual explanations have been identified as a good candidate to solve the explainability problem in machine learning. The CEO (Counterfactual Explanations for Ontologies) method is thus proposed to explain inconsistent ontologies using counterfactual explanations. A preliminary user study is conducted to ensure that using XAI methods for ontologies is relevant and worth pursuing. [ABSTRACT FROM AUTHOR]

Spam reviews are a pervasive problem on online platforms due to its significant impact on reputation. However, research into spam detection in data streams is scarce. Another concern lies in their need for transparency. Consequently, this paper addresses those problems by proposing an online solution for identifying and explaining spam reviews, incorporating data drift adaptation. It integrates (i) incremental profiling, (ii) data drift detection & adaptation, and (iii) identification of spam reviews employing Machine Learning. The explainable mechanism displays a visual and textual prediction explanation in a dashboard. The best results obtained reached up to 87% spam F-measure. [ABSTRACT FROM AUTHOR]

The increasing demand for mobility in our society poses various challenges to traffic engineering, computer science in general, and artificial intelligence in particular. Increasing the capacity of road networks is not always possible, thus a more efficient use of the available transportation infrastructure is required. Another issue is that many problems in traffic management and control are inherently decentralized and/or require adaptation to the traffic situation. Hence, there is a close relationship to multiagent reinforcement learning. However, using reinforcement learning poses the challenge that the state space is normally large and continuous, thus it is necessary to find appropriate schemes to deal with discretization of the state space. To address these issues, a multiagent system with agents learning independently via a learning algorithm was proposed, which is based on estimating Q-values from k-nearest neighbors. In the present paper, we extend this approach and include transfer of experiences among the agents, especially when an agent does not have a good set of k experiences. We deal with traffic signal control, running experiments on a traffic network in which we vary the traffic situation along time, and compare our approach to two baselines (one involving reinforcement learning and one based on fixed times). Our results show that the extended method pays off when an agent returns to an already experienced traffic situation. [ABSTRACT FROM AUTHOR]

The number of scientific papers has been increasing ever more rapidly. Researchers have to spend a lot of time classifying papers relevant to their study, especially into fine-grained subfields. However, almost all existing paper classification models are coarse-grained, which can not meet the needs of researchers. Observing this, we propose a lightweight fine-grained classification model for scientific paper. Dynamic weighting coefficients on feature words are incorporated into the model to improve the classification accuracy. The feature word weight is optimized by the Mean Decrease Accuracy (MDA) algorithm. Considering applicability, the lightweight processing is conducted through algorithm pruning and training sample pruning. Comparison with mainstream models shows simultaneous improvement in accuracy and time efficiency by our model. [ABSTRACT FROM AUTHOR]

Credit fraud is a common financial crime that causes significant economic losses to financial institutions. To address this issue, researchers have proposed various fraud detection methods. Recently, research on deep forests has opened up a new path for exploring deep models beyond neural networks. It combines the features of neural networks and ensemble learning, and has achieved good results in various fields. This paper mainly studies the application of deep forests to the field of fraud detection and proposes a distributed dense rotation deep forest algorithm (DRDF-spark) based on the improved RotBoost. The model has three main characteristics: firstly, it solves the problem of multi-granularity scanning due to the lack of spatial correlation in the data by introducing RotBoost. Secondly, Spark is used for parallel construction to improve the processing speed and efficiency of data. Thirdly, a pre-aggregation mechanism is added to the distributed algorithm to locally aggregate the statistical results of sub-forests in the same node in advance to improve communication efficiency. The experiments show that DRDF-spark performs better than deep forests and some mainstream ensemble learning algorithms on the fraud dataset in this paper, and the training speed is up to 3.53 times faster. Furthermore, if the number of nodes is further increased, the speedup ratio will continue to increase. [ABSTRACT FROM AUTHOR]

The role of explanations in intelligent systems has in the last few years entered the spotlight as AI-based solutions appear in an ever-growing set of applications. Though data-driven (or machine learning) techniques are often used as examples of how opaque (also called black box) approaches can lead to problems such as bias and general lack of explainability and interpretability, in reality these features are difficult to tame in general, even for approaches that are based on tools typically considered to be more amenable, like knowledge-based formalisms. In this paper, we continue a line of research and development towards building tools that facilitate the implementation of explainable and interpretable hybrid intelligent socio-technical systems, focusing on features that users can leverage to build explanations to their queries. In particular, we present the implementation of a recently-proposed application framework (and make available its source code) for developing such systems, and explore user-centered mechanisms for building explanations based both on the kinds of explanations required (such as counterfactual, contextual, etc.) and the inputs used for building them (coming from various sources, such as the knowledge base and lower-level data-driven modules). In order to validate our approach, we develop two use cases, one as a running example for detecting hate speech in social platforms and the other as an extension that also contemplates cyberbullying scenarios. [ABSTRACT FROM AUTHOR]

Background: Dementia is a general term for several progressive neurodegenerative disorders including Alzheimer's disease. Timely and accurate detection is crucial for early intervention. Advancements in artificial intelligence present significant potential for using machine learning to aid in early detection. Objective: Summarize the state-of-the-art machine learning-based approaches for dementia prediction, focusing on non-invasive methods, as the burden on the patients is lower. Specifically, the analysis of gait and speech performance can offer insights into cognitive health through clinically cost-effective screening methods. Methods: A systematic literature review was conducted following the PRISMA protocol (Preferred Reporting Items for Systematic Reviews and Meta-Analyses). The search was performed on three electronic databases (Scopus, Web of Science, and PubMed) to identify the relevant studies published between 2017 to 2022. A total of 40 papers were selected for review. Results: The most common machine learning methods employed were support vector machine followed by deep learning. Studies suggested the use of multimodal approaches as they can provide comprehensive and better prediction performance. Deep learning application in gait studies is still in the early stages as few studies have applied it. Moreover, including features of whole body movement contribute to better classification accuracy. Regarding speech studies, the combination of different parameters (acoustic, linguistic, cognitive testing) produced better results. Conclusions: The review highlights the potential of machine learning, particularly non-invasive approaches, in the early prediction of dementia. The comparable prediction accuracies of manual and automatic speech analysis indicate an imminent fully automated approach for dementia detection. [ABSTRACT FROM AUTHOR]

Machine Learning (ML) heavily relies on optimization techniques built upon gradient descent. Numerous gradient-based update methods have been proposed in the scientific literature, particularly in the context of neural networks, and have gained widespread adoption as optimizers in ML software libraries. This paper introduces a novel perspective by framing gradient-based update strategies using the Moreau-Yosida (MY) approximation of the loss function. Leveraging a first-order Taylor expansion, we demonstrate the concrete exploitability of the MY approximation to generalize the model update process. This enables the evaluation and comparison of regularization properties underlying popular optimizers like gradient descent with momentum, ADAGRAD, RMSprop, and ADAM. The MY-based unifying view opens up possibilities for designing new update schemes with customizable regularization properties. To illustrate this potential, we propose a case study that redefines the concept of closeness in the parameter space using network outputs. We present a proof-of-concept experimental procedure, demonstrating the effectiveness of this approach in continual learning scenarios. Specifically, we employ the well-known permuted MNIST dataset, a progressively-permuted MNIST and CIFAR-10 benchmarks, and a non i.i.d. stream. Additionally, we validate the update scheme's efficacy in an offline-learning scenario. By embracing the MY-based unifying view, we pave the way for advancements in optimization techniques for machine learning. [ABSTRACT FROM AUTHOR]

Nowadays, as an indispensable part of urban infrastructure, urban rail transit (URT) vehicles have also developed rapidly. A large amount of manpower, material resources, and financial resources need to be invested in the construction process of URT. For URT vehicles, research on more accurate fault prediction methods can save a lot of maintenance costs and improve the reliability of URT construction. As an important electrical equipment for urban rail transit vehicles to obtain electric energy from the catenary, the operation of rail transit vehicles puts forward higher performance requirements for the pantograph. For solving the problems of low accuracy of fault prediction, over reliance on practical experience and high cost of fault prediction in the application of traditional URT vehicle pantograph fault prediction model. Combining sensor network and artificial intelligence algorithm, this paper analyzed the traditional rail transit vehicle pantograph fault prediction model, and verified it through comparative experiments. Through the comparative analysis of the experimental results, this paper can draw a conclusion that compared with the traditional rail transit vehicle pantograph fault prediction model, the rail transit vehicle pantograph fault prediction model has higher fault prediction accuracy, less model response time, lower risk of pantograph failure, higher model application satisfaction, and the accuracy of fault prediction increased by about 6.6%. The rail transit vehicle pantograph fault prediction model can effectively improve the accuracy of vehicle pantograph fault prediction, which can greatly promote the safety of URT and promote the intelligent process of URT. [ABSTRACT FROM AUTHOR]

Knowledge graph embeddings represent a group of machine learning techniques which project entities and relations of a knowledge graph to continuous vector spaces. RDF2vec is a scalable embedding approach rooted in the combination of random walks with a language model. It has been successfully used in various applications. Recently, multiple variants to the RDF2vec approach have been proposed, introducing variations both on the walk generation and on the language modeling side. The combination of those different approaches has lead to an increasing family of RDF2vec variants. In this paper, we evaluate a total of twelve RDF2vec variants on a comprehensive set of benchmark models, and compare them to seven existing knowledge graph embedding methods from the family of link prediction approaches. Besides the established GEval benchmark introducing various downstream machine learning tasks on the DBpedia knowledge graph, we also use the new DLCC (Description Logic Class Constructors) benchmark consisting of two gold standards, one based on DBpedia, and one based on synthetically generated graphs. The latter allows for analyzing which ontological patterns in a knowledge graph can actually be learned by different embedding. With this evaluation, we observe that certain tailored RDF2vec variants can lead to improved performance on different downstream tasks, given the nature of the underlying problem, and that they, in particular, have a different behavior in modeling similarity and relatedness. The findings can be used to provide guidance in selecting a particular RDF2vec method for a given task. [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]

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]

In the ever-evolving world of cricket, the T20 format has captured the imaginations of fans worldwide, intensifying the anticipation for match outcomes with each passing delivery. This study explores the realm of predictive analytics, leveraging the power of machine learning to alleviate the suspense by forecasting T20 cricket match winners before the first ball is bowled. Drawing on a rich dataset encompassing factors such as past team performance and rankings, a diverse ensemble of predictive models, including logistic regression, support vector machine (SVM), random forest, decision tree, and XGBoost, is meticulously employed. Among these, the random forest Classifier emerges as the standout performer, boasting an impressive prediction accuracy rate of 84.06%. To assess the real-world applicability of our predictive framework, a post-case study is conducted, focusing on the high-stakes World Cup T20 matches of 2022, where England emerges as the triumphant team. The dataset underpinning this study is meticulously curated from ESPN CricInfo, ensuring the robustness of our analysis. Moreover, this paper extends its contribution by offering a comprehensive comparative analysis, scrutinizing performance metrics such as accuracy, precision, recall, and the F1-score across benchmark machine learning models for cricket match prediction. This in-depth evaluation not only validates the efficacy of our models but also sheds light on their superior execution time and statistical robustness, further bolstering their utility in the realm of cricket outcome forecasting. [ABSTRACT FROM AUTHOR]

The machine learning technique has been used to increase cloud management's intelligence. Effective resource provisioning also preserves the environment. Manual cloud management has some difficult problems, such as complexity in cloud systems and scale issues. Hence, this paper introduces a new task for managing the resources in the cloud using deep learning. The aim is to predict the overall workload and server status prediction to the cloud resource management. Initially, performance monitoring is performed to keep aware of the performance of the application and guarantee the cloud application's performance. In the suggested work, the required data is collected for the resource utilization on multiple Virtual Machine (VM) metrics. The VM provisioning is performed next to rectify the issues of resource provisioning. After that, the workload and server status prediction is conducted, where the Weighted Recurrent Neural Network (W-RNN) is adopted. After attaining the predicted workload, the VM placement module is carried out. Here, the virtual resource's quantity is attained. Moreover, the multi-objective functions like resource utilization; cost, energy, time, and Quality of Service (QoS) are derived in this phase with the help of the Improved Rain Optimization Algorithm (IROA). Subsequently, the VM recycling is performed in the suggested work. Here, a resource collector is given for the virtual resources recycling task. It scans the applications of the cloud in the data centre and processes the VM recycling for every application. While considering the statistical analysis of the IROA-W-RNN-based resource management system achieved a mean of 56.27% than JAYA-W-RNN, 21.09% than SCO-W-RNN, 60.2% than MFOA-W-RNN, and 16.74% than DA-W-RNN for configuration 4. Finally, the numerical analysis is conducted to validate the presented resource management task with the aid of various conventional tasks. [ABSTRACT FROM AUTHOR]

Ontologies play a vital role in organizing and constructing knowledge across various domains, enabling effective knowledge management and sharing. The development of domain-specific ontologies, such as the ONTO-TDM ontology for teaching domain modeling, is essential for providing a comprehensive and standardized representation of knowledge within a given discipline. However, to maximize the usefulness and relevance of such ontologies, it is crucial to automate their population with domain-specific information, reducing manual work and ensuring scalability. This paper presents a novel method for ontology population by extracting and integrating relevant information from diverse sources. The method combines the TextRank algorithm with Word2Vec to enhance keyword extraction, capturing both semantic meaning and textual importance. Keywords are then annotated and used to train a machine learning classifier, which aids in integrating new instances into the ontology. Experiments show that the proposed method achieves a precision of 63.33%, a recall of 61.29% and an F1-score of 62.28%, significantly improving keyword extraction and ontology population accuracy compared to existing methods. This validates the method's effectiveness in semi-automatically extracting relevant instances from diverse data sources, enhancing the efficiency and accuracy of ontology population, and advancing automated knowledge management in domain-specific contexts. [ABSTRACT FROM AUTHOR]

For the pattern recognition, most classification models are solved iteratively, except for Linear LDA, KLDA and ELM etc. In this paper, a nonlinear classification network model based on predefined evenly-distributed class centroids (PEDCC) is proposed. Its analytical solution can be obtained and has good interpretability. Using the characteristics of maximizing the inter-class distance of PEDCC and derivative weighted minimum mean square error loss function to minimize the intra-class distance, we can not only realize the effective nonlinearity of the network, but also obtain the analytical solution of the network weight. Then, the sample is classified based on GDA. In order to further improve the performance of classification, PCA is used to reduces the dimensionality of the original sample, meanwhile, the CReLU activation function are adopted to enhances the expression ability of the features. The network transforms the samples into the higher dimensional feature space through the weighted minimum mean square error, so as to find a better separation hyperplane. In experiments, the feasibility of the network structure is verified from pure linear 푾 , 푾 + Tanh, and PCA + 푾 + Tanh respectively on many small data sets and large data sets, and compared with SVM and ELM in terms of training speed and recognition rate. The results show that, in general, this model has advantages on small data set both in recognition accuracy and training speed, while it has advantages in training speed on large data sets. Finally, by introducing a multi-stage network structure based on the latent feature norm, the classifier network can further significantly improve the classification performance, the recognition rate of small data sets is effectively improved and much higher than that of existing methods, while the recognition rate of large data sets is similar to that of SVM. [ABSTRACT FROM AUTHOR]

With the proposal and development of the Material Genome Engineering program, artificial intelligence has played a significant role in accelerating the research and development of new materials. In the field of electrical engineering materials, high-throughput experimental and computational methods provide a huge amount of data. It also poses new challenges to how to manage material data scientifically and efficiently. Database technology has become a hot topic for material scientists and engineers. This paper makes a comprehensive overview of the development, demand analysis and application of database technology in the electrical engineering materials, and discusses the existing problems and the future development trend of the database. Compared with many materials, such as energy materials, catalytic materials, biomedical materials, etc., the electrical material database still has a long way to go in the process of database platform construction, management and operation, and practical application. However, driven by governmental support and market demand, the construction of electrical material database will gradually improve and play an important role in the data-driven new materials researches. [ABSTRACT FROM AUTHOR]

Background: Alzheimer's disease (AD) is a progressive neurodegenerative disease that is not easily detected in the early stage. Handwriting and walking have been shown to be potential indicators of cognitive decline and are often affected by AD. Objective: This study proposes an assisted screening framework for AD based on multimodal analysis of handwriting and gait and explores whether using a combination of multiple modalities can improve the accuracy of single modality classification. Methods: We recruited 90 participants (38 AD patients and 52 healthy controls). The handwriting data was collected under four handwriting tasks using dot-matrix digital pens, and the gait data was collected using an electronic trail. The two kinds of features were fused as inputs for several different machine learning models (Logistic Regression, SVM, XGBoost, Adaboost, LightGBM), and the model performance was compared. Results: The accuracy of each model ranged from 71.95% to 96.17%. Among them, the model constructed by LightGBM had the best performance, with an accuracy of 96.17%, sensitivity of 95.32%, specificity of 96.78%, PPV of 95.94%, NPV of 96.74%, and AUC of 0.991. However, the highest accuracy of a single modality was 93.53%, which was achieved by XGBoost in gait features. Conclusions: The research results show that the combination of handwriting features and gait features can achieve better classification results than a single modality. In addition, the assisted screening model proposed in this study can achieve effective classification of AD, which has development and application prospects. [ABSTRACT FROM AUTHOR]

The genetic algorithm with aggressive mutations GAAM, is a specialised algorithm for feature selection. This algorithm is dedicated to the selection of a small number of features and allows the user to specify the maximum number of features desired. A major obstacle to the use of this algorithm is its high computational cost, which increases significantly with the number of dimensions to be retained. To solve this problem, we introduce a surrogate model based on machine learning, which reduces the number of evaluations of the fitness function by an average of 48% on the datasets tested, using the standard parameters specified in the original paper. Additionally, we experimentally demonstrate that eliminating the crossover step in the original algorithm does not result in any visible changes in the algorithm's results. We also demonstrate that the original algorithm uses an artificially complex mutation method that could be replaced by a simpler method without loss of efficiency. The sum of the improvements resulted in an average reduction of 53% in the number of evaluations of the fitness functions. Finally, we have shown that these outcomes apply to parameters beyond those utilized in the initial article, while still achieving a comparable decrease in the count of evaluation function calls. Tests were conducted on 9 datasets of varying dimensions, using two different classifiers. [ABSTRACT FROM AUTHOR]

This paper presents a multi-objective optimization approach for developing efficient and environmentally friendly Machine Learning models. The proposed approach uses Genetic Algorithms to simultaneously optimize the accuracy, time-to-solution, and energy consumption simultaneously. This solution proposed to be part of an Automated Machine Learning pipeline and focuses on architecture and hyperparameter search. A customized Genetic Algorithm scheme and operators were developed, and its feasibility was evaluated using the XGBoost ML algorithm for classification and regression tasks. The results demonstrate the effectiveness of the Genetic Algorithm for multi-objective optimization, indicating that it is possible to reduce energy consumption while minimizing predictive performance losses. [ABSTRACT FROM AUTHOR]

The editorial from the Intelligent Data Analysis (IDA) Journal's volume 28(5) introduces a collection of papers covering theoretical and applied topics in the field of Intelligent Data Analysis. The theoretical contributions include papers on hyperparameter tuning techniques, nonlinear classification network models, active learning in natural language processing, and efficient Vision Transformer models. The applied techniques section focuses on road traffic modeling and forecasting, aspect-based sentiment analysis using multimodal data, and support techniques for general Intelligent Data Analysis problems like blockchain technology in IoT applications and fast-density peak clustering for analyzing power load anomalies. The issue concludes with a paper on predicting viewer sentiments on platforms like YouTube using spark-based machine learning algorithms. [Extracted from the article]

In order to better evaluate and promote human health, this paper analyzes the influence of different inertial-measurement-unit signals, different sensor locations, different activity intensities and different signal fusion schemes on the accuracy of physical strength consumption estimation during walking and running activities. Different pattern recognition methods, such as the Counts-based linear regression model, the typical non-linear model based on decision tree and artificial neural network, and the end-to-end convolutional neural network model, are analyzed and compared. Our findings are as follows: 1) For the locations of sensors during walking and running activities, the physical strength consumption prediction accuracy at the ankle location is higher than that at the hip location. Therefore, wearing an inertial-measurement-unit at the ankle can improve the accuracy of the model. 2) Regarding the types of activity signals during walking and running activities, the impact of accelerometer signals on hip and ankle prediction accuracy is not significantly different, while the gyroscope model is more sensitive to the location, with higher prediction accuracy at the ankle than at the hip. In addition, the physical strength consumption prediction accuracy of accelerometer signals is higher than that of gyroscope signals, and fusion of accelerometer and gyroscope signals can improve the accuracy of physical strength consumption prediction. 3) For different data analysis models during walking and running activities, the artificial neural network model that integrates different sensor locations and inertial-measurement-unit signals with different activity intensities has the lowest mean squared error for the measurement of physical strength consumption. The non-linear models based on decision tree and artificial neural network have better physical strength consumption prediction capabilities than the Counts-based linear regression model, especially for high-intensity activity energy consumption prediction. In addition, feature engineering models are generally better than convolutional neural network model in terms of overall performance and prediction results under the three different activity intensities. Furthermore, as the activity intensity increases, the performance of all physical strength consumption calculation models decreases. We recommend using the artificial neural network model based on multi-signal fusion to estimate physical strength consumption during walking and running activities because this model exhibits strong generalization ability in cross-validation and test results, and its stability under different activity intensities is better than that of the other three models. To the best of our knowledge, this paper is the first to delve deeply and in detail into methods for estimating physical strength consumption. Undoubtedly, our paper will have an impact on research related to topics such as intelligent wearable devices and subsequent methods for estimating physical strength consumption, which are directly related to physical health. [ABSTRACT FROM AUTHOR]

Data driven deep learning methods have become the mainstream method of building extraction from remote sensing images. In this paper, deep learning algorithm is used to classify and extract buildings from remote sensing images of rural areas around the Great Wall in the suburbs of Beijing captured by unmanned aerial vehicles. Aiming at the shortcomings of the current mainstream instance segmentation algorithm Mask R-CNN in feature fusion and poor prediction of instance mask boundaries, this paper proposes a boundary optimization algorithm for building instance segmentation based on discrete wavelet transform. Firstly, the discrete wavelet transform is introduced into the segmentation task branch of Mask R-CNN algorithm to extract the low-frequency and high-frequency information of the real mask, in which the high-frequency information includes the boundary information. Secondly, the pixel by pixel prediction of the mask turns into the learning of the low-frequency and high-frequency information of the real mask. The learning of the high-frequency information helps the segmentation network to learn the boundary features better. Finally, using the reversibility of discrete wavelet transform, the low-frequency and high-frequency information of the learned mask is inversely transformed to reconstruct the final mask. The improved algorithm is evaluated on the dataset COCO, and applied to the automatic extraction of buildings. The DWT Mask R-CNN algorithm model achieved 70.2% segmentation accuracy and 71.4% detection accuracy, which were improved by 1% and 0.7% respectively compared with the Mask R-CNN and Cascade Mask R-CNN models. The experimental results show that the instance segmentation edge optimization algorithm combined with wavelet transform has achieved better results on the segmentation boundary, improved the poor effect of mask edge detection and achieved higher detection accuracy, and can accurately extract village buildings. [ABSTRACT FROM AUTHOR]

Nowadays, people spend a lot of time in the information space, communicating within various social platforms. Content of those platforms can influence people's feelings and personalities, which is especially relevant for young people. In this research, we made an attempt to prove this hypothesis. For the experiment, we selected the VKontakte social network and analysed users profiles together with the results of the psychological tests passed by them. The goal of the experiment was to find correlations between the information provided within the social network communities and the users' personalities. Moreover, in this paper, we made an attempt to enhance the results of the classifier accuracy using the sentiment analysis. The experiments were conducted to test the sentiment analysis models, to analyse the proposed feature based on posts' sentiment, and test the classifier for the detection of the potentially destructive impacts. The analysis of the correlation of the proposed feature with the communities that have potentially destructive impacts on anxiety is conducted. The analysis of the obtained results is provided. During the experiments, the authors found out that consideration of the posts' sentiment allows increasing accuracy of the classifier for anxiety destructive impacts on 12.24 %. Additionally, we analysed the relationship between the user sentiments metric and destructiveness. We confirmed that the assessment of the user's posts' sentiment can be used to compile his psychological characteristics and determine possibility of destructiveness. [ABSTRACT FROM AUTHOR]

The paper discusses biases in medical imaging analysis, particularly focusing on the challenges posed by the development of machine learning algorithms and generative models. It introduces a taxonomy of bias problems and addresses them through a data infrastructure initiative: the PADME (Platform for Analytics and Distributed Machine-Learning for Enterprises), which is a part of the National Research Data Infrastructure for Personal Health Data (NFDI4Health) project. The PADME facilitates the structuring and sharing of health data while ensuring privacy and adherence to FAIR principles. The paper presents experimental results that show that generative methods can be effective in data augmentation. Complying with PADME infrastructure, this work proposes a solution framework to deal with bias in the different data stations and preserve privacy when transferring images. It highlights the importance of standardized data infrastructure in mitigating biases and promoting FAIR, reusable, and privacypreserving research environments in healthcare. [ABSTRACT FROM AUTHOR]

Computer security consists in protecting access and manipulating system data by several mechanisms. However, conventional protection technologies are ineffective against current attacks. Thus, new tools have appeared, such as the intrusion detection and prediction systems which are important defense elements for network security since they detect the ongoing intrusions and predict the upcoming attacks. Besides, most of conventional protection technologies remain insufficient in terms of actions since they are all passive systems, unable to provide recommendations in order to block or stop the attacks. In this paper, a distributed detection and prediction system, composed of three major parts, is proposed. The first part deals with the detection of intrusions based on the decision tree learning algorithm. The second part deals with intrusions prediction using the chronicle algorithm. The third part proposes an expert system for security recommendations in response to detected intrusions, able to provide appropriate recommendations to stop the attacks. The proposed system gives good results in terms of accuracy and precision in detecting and predicting attacks, and efficiency in proposing the right recommendations to stop the attacks. [ABSTRACT FROM AUTHOR]

Many colleges in China have adopted the policy of recruiting students by academic subject categories in order to optimize the talent training mode. To solve the problems in major selection after enrollment, this paper has designed an intelligent algorithm model for recommending college majors. Compared with existing methods for assigning college majors, the model uses deep neural networks and clustering algorithms to simulate complex calculations in the human brain. It uses historical learning data from senior students or graduates to predict the future grades of freshmen, judge their adaptability to various college majors, reduce human interference in the college major selection process, recommend the most suitable college major to students. [ABSTRACT FROM AUTHOR]

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]

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]

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]

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]

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]

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]

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]

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]

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]

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]

Adverse weather conditions, such as snow-covered roads, represent a challenge for autonomous vehicle research. This is particularly challenging as it might cause misalignment between the longitudinal axis of the vehicle and the actual direction of travel. In this paper, we extend previous work in the field of autonomous vehicles on snow-covered roads and present a novel approach for side-slip angle estimation that combines perception with a hybrid artificial neural network pushing the prediction horizon beyond existing approaches. We exploited the feature extraction capabilities of convolutional neural networks and the dynamic time series relationship learning capabilities of gated recurrent units and combined them with a motion model to estimate the side-slip angle. Subsequently, we evaluated the model using the 3DCoAutoSim simulation platform, where we designed a suitable simulation environment with snowfall, friction, and car tracks in snow. The results revealed that our approach outperforms the baseline model for prediction horizons ⩾ 2 seconds. This extended prediction horizon has practical implications, by providing drivers and autonomous systems with more time to make informed decisions, thereby enhancing road safety. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel Reinforcement Learning (RL) algorithm for robotic motion control, that is, a constrained Deep Deterministic Policy Gradient (DDPG) deviation learning strategy to assist biped robots in walking safely and accurately. The previous research on this topic highlighted the limitations in the controller's ability to accurately track foot placement on discrete terrains and the lack of consideration for safety concerns. In this study, we address these challenges by focusing on ensuring the overall system's safety. To begin with, we tackle the inverse kinematics problem by introducing constraints to the damping least squares method. This enhancement not only addresses singularity issues but also guarantees safe ranges for joint angles, thus ensuring the stability and reliability of the system. Based on this, we propose the adoption of the constrained DDPG method to correct controller deviations. In constrained DDPG, we incorporate a constraint layer into the Actor network, incorporating joint deviations as state inputs. By conducting offline training within the range of safe angles, it serves as a deviation corrector. Lastly, we validate the effectiveness of our proposed approach by conducting dynamic simulations using the CRANE biped robot. Through comprehensive assessments, including singularity analysis, constraint effectiveness evaluation, and walking experiments on discrete terrains, we demonstrate the superiority and practicality of our approach in enhancing walking performance while ensuring safety. Overall, our research contributes to the advancement of biped robot locomotion by addressing gait optimisation from multiple perspectives, including singularity handling, safety constraints, and deviation learning. [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]

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]

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]

In this paper, a novel Z-number based Fuzzy Neural Network (Z-FNN) based on the integration of Z-valued fuzzy logic and neural networks is proposed. Z-valued fuzzy rule base is presented and its inference process is described using interpolative approximate reasoning. Accordingly, the structure of the Z-FNN is proposed using a distance measure and interpolative approximate reasoning scheme. Based on presented architecture the learning algorithm of Z-FNN is designed. The updating of the unknown parameters of the network is carried out using Genetic Algorithms (GA). The proposed Z-FNN system is utilized for dynamic plant identification. The effectiveness of Z-FNN has been tested by comparing its performance with the performances of other fuzzy systems available in the literature. The proposed approach has been proven to be a suitable alternative for the identification of nonlinear systems characterized by uncertain and imprecise information. [ABSTRACT FROM AUTHOR]

The paper aims to analyze and compare various deep learning (DL) algorithms in order to develop a Suspicious Activity Recognition (SAR) system for closed-circuit television (CCTV) surveillance. Automated systems for detecting and classifying suspicious activities are crucial as technology's role in safety and security expands. This paper addresses these challenges by creating a robust SAR system using machine learning techniques. It analyzes and compares evaluation metrics such as Precision, Recall, F1 Score, and Accuracy using various deep learning methods (convolutional neural network (CNN), Long short-term memory (LSTM) – Visual Geometry Group 16 (VGG16), LSTM – ResNet50, LSTM – EfficientNetB0, LSTM – InceptionNetV3, LSTM – DenseNet121, and Long-term Recurrent Convolutional Network (LRCN)). The proposed system improves threat identification, vandalism deterrence, fight prevention, and video surveillance. It aids emergency response by accurately classifying suspicious activities from CCTV footage, reducing reliance on human security personnel and addressing limitations in manual monitoring. The objectives of the paper include analyzing existing works, extracting features from CCTV videos, training robust deep learning models, evaluating algorithms, and improving accuracy. The conclusion highlights the superior performance of the LSTM-DenseNet121 algorithm, achieving an overall accuracy of 91.17% in detecting suspicious activities. This enhances security monitoring capabilities and reduces response time. Limitations of the system include subjectivity, contextual understanding, occlusion, false alarms, and privacy concerns. Future improvements involve real-time object tracking, collaboration with law enforcement agencies, and performance optimization. Ongoing research is necessary to overcome limitations and enhance the effectiveness of CCTV surveillance. [ABSTRACT FROM AUTHOR]

A recent application in machine learning has introduced a novel approach, complemented by big data sources, aimed at providing precise estimates for small geographical areas. This method employs a dual strategy: (a) hybrid estimation, involving the integration of big data sources with imputed values derived from K nearest neighbours (KNN) to address missing target variable values from the big data source; and (b) calibration of the collective sum of small area estimates to an independent yet efficient national total. Evaluating its efficacy using simulated data from the 2016 Australian population census, the calibrated KNN (CKNN) method demonstrated superior performance compared to the Fay-Herriot method based on area-level covariates. This paper enhances the comparative analysis by contrasting the CKNN method with a hierarchical Bayes method using the logit-normal model (LN) relevant for binary data. Broadly speaking, the LN method can be viewed as the Bayesian equivalent of Battese-Harter-Fuller (BHF) method, which incorporates unit-level covariates. Our results demonstrate the CKNN method's superiority over the LN method. However, the application of hybrid estimation to the LN method significantly diminishes this superiority. Although CKNN estimates maintain better precision, they are not as accurate as the estimates from the hybridized LN method. [ABSTRACT FROM AUTHOR]

The genetic algorithm with aggressive mutations GAAM, is a specialised algorithm for feature selection. This algorithm is dedicated to the selection of a small number of features and allows the user to specify the maximum number of features desired. A major obstacle to the use of this algorithm is its high computational cost, which increases significantly with the number of dimensions to be retained. To solve this problem, we introduce a surrogate model based on machine learning, which reduces the number of evaluations of the fitness function by an average of 48% on the datasets tested, using the standard parameters specified in the original paper. Additionally, we experimentally demonstrate that eliminating the crossover step in the original algorithm does not result in any visible changes in the algorithm's results. We also demonstrate that the original algorithm uses an artificially complex mutation method that could be replaced by a simpler method without loss of efficiency. The sum of the improvements resulted in an average reduction of 53% in the number of evaluations of the fitness functions. Finally, we have shown that these outcomes apply to parameters beyond those utilized in the initial article, while still achieving a comparable decrease in the count of evaluation function calls. Tests were conducted on 9 datasets of varying dimensions, using two different classifiers. [ABSTRACT FROM AUTHOR]