Search

Fault detection in transmission lines plays an important role in maintaining the dependability and steadiness of power networks. Traditional methods for identifying faults often struggle to handle the diverse nature of real-world fault situations. Machine learning (ML) algorithms offer a data-centered approach that can adjust and learn from datasets, potentially overcoming the limitations of traditional approaches. This paper presents a review of progress in using ML for detecting faults in transmission lines. By drawing insights from lots of studies, explores the paper how ML algorithms have evolved in fault detection, including techniques like networks, recurrent neural networks featuring long short-term memory (LSTM) and convolutional neural networks (CNN). The paper delves into the spectrum of applications where ML is used for fault detection across fault scenarios and operational settings. Additionally, it discuss the obstacles and prospects linked to putting ML-based fault detection systems into practice, such as challenges with data quality, model interpretability and integration with existing grid monitoring systems. Finally, the paper outlines future research paths focused on pushing forward the boundaries of fault detection in power transmission systems through approaches and collaborative endeavors involving academia, industry players and policymakers. In general, this review highlights how ML has the power to revolutionize fault detection methods, enhancing the resilience and dependability of power systems. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to investigate the utilization of artificial neural networks (ANNs) in learning models that address the nonlinear anisotropic flow and hysteresis retention behavior of deformable porous materials. Herein, the micro‐geometries of various networks of porous Bentheimer Sandstones subjected to several degrees of strain from the literature are considered. For the generation of the database required for the training, validation, and testing of the machine learning (ML) models, single‐phase and biphasic lattice Boltzmann (LB) simulations are performed. The anisotropic nature of the intrinsic permeability is investigated for the single‐phase LB simulations. Thereafter, the database contains the computed average fluid velocities versus the pressure gradients. In this database, the range of applied fluid pressure gradients includes Darcy as well as non‐Darcy flows. The generated output from the single‐phase flow simulations is implemented in a feed‐forward neural network, representing a path‐independent informed graph‐based model. Concerning the two‐phase LB simulations, the Shan‐Chen multiphase LB model is used to generate the retention curves of the cyclic drying/wetting processes in the deformed porous networks. Consequently, two different ML path‐dependent approaches, that is, 1D convolutional neural network and the recurrent neural network, are used to model the biphasic flow through the deformable porous materials. A comparison in terms of accuracy and speed of training between the two approaches is presented. Conclusively, the outcomes of the papers show the capability of the ML models in representing constitutive relations for permeability and hysteretic retention curves accurately and efficiently. [ABSTRACT FROM AUTHOR]

Lung cancer with the highest mortality rate has attracted public attention. For the difficulty of treating lung cancer increases sharply over time, detecting lung cancer symptoms early on chest computed tomography (CT) is crucial for the subsequent treatment. The number of slices can affect the accuracy of lung cancer examination, so a deep multiple instance learning algorithm was designed and proposed to classify lung cancer effectively. First, feature information is extracted in the patient 3D CT image using the high and low frequency high dimensional features (HLFHD) to balance local detail and global overall information of images. Secondly, to find the decisive features, a sliding recurrent neural network (MSRNN) module is used to take into account the feature variations between slices. The experimental studies in this paper were constructed on two public datasets, namely, CIA and CC-CCII data. Finally, the experimental results show that the proposed algorithm can achieve an ACC of 0.97 and an AUC of 0.99 on the datasets. These results suggest that the proposed algorithm is well suited for lung cancer classification of any number of CT slices, and it can be effectively employed in computer-aided systems to achieve state-of-the-art performance. [ABSTRACT FROM AUTHOR]

In recent years, the rapid advancement of artificial intelligence (AI) has revolutionized various industries, with image processing playing an important role in the revolution. AI-powered image analysis has opened up new possibilities in healthcare diagnostics, autonomous navigation, and security surveillance, fuelling demand for sophisticated image-processing solutions. This paper describes an innovative approach to AI image processing that combines multi-sensor data fusion with convolutional neural networks (CNNs) within a fuzzy neural network framework. This integration uses data from various sensors, including cameras, lidar, and radar, to improve the robustness and precision of image analysis and interpretation. The T–S model serves as the foundation for the information fusion strategy. A comprehensive investigation of deep learning algorithms reveals inherent strengths such as robustness and parallelism. However, it also identifies limitations, particularly in image segmentation tasks, characterized by challenges like premature convergence and prolonged computation times. The paper proposes a quantization technique for deep learning algorithms to address these issues and introduces chaotic optimization to expedite convergence rates. It also presents a novel three-dimensional Otsu threshold segmentation method based on CNNs, which overcomes noise susceptibility in traditional two-dimensional approaches. Integrating Gray morphology and this three-dimensional Otsu threshold segmentation method results in the development of a three-dimensional Gray Otsu model. This model is the basis for designing a fitness function for the CNN algorithm, optimizing its efficacy. Experimental validation demonstrates the proposed algorithm's effectiveness, achieving an impressive 91% accuracy rate while displaying robust noise resistance and versatility. Comparative assessments against other leading AI architectures, including multilayer perceptron, radial basis function network, recurrent neural network, and long short-term memory network, affirm the superior performance achieved by the proposed approach. [ABSTRACT FROM AUTHOR]

Code smells violate software development principles that make the software more prone to errors and changes. Researchers have developed code smell detectors using manual and semi-automatic methods to identify these issues. However, three key challenges have limited the practical use of these detectors: developers' subjective perceptions of code smells, lack of consensus in the detection process, and difficulty in setting appropriate detection thresholds. While code smell detection using machine learning has progressed significantly, there still appears to be a gap in understanding the effective utilization of deep learning (DL) approaches. This paper aims to review and identify current methods for code smell detection using DL techniques. A systematic literature review is conducted on 35 primary studies from a collection of 8739 publications between 2013 and the present. The analysis reveals that common code smells detected include Feature Envy, God Classes, Long Methods, Complex Classes, and Large Classes. The most popular DL algorithms used are Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN), often combined with other techniques for better results. Algorithms that train models on large datasets with fewer independent variables demonstrate exemplary performance. The paper also highlights open issues and provides guidelines for future metric identification and selection research. [ABSTRACT FROM AUTHOR]

Nowadays, machine learning (ML) has attained a high level of achievement in many contexts. Considering the significance of ML in medical and bioinformatics owing to its accuracy, many investigators discussed multiple solutions for developing the function of medical and bioinformatics challenges using deep learning (DL) techniques. The importance of DL in Internet of Things (IoT)-based bio- and medical informatics lies in its ability to analyze and interpret large amounts of complex and diverse data in real time, providing insights that can improve healthcare outcomes and increase efficiency in the healthcare industry. Several applications of DL in IoT-based bio- and medical informatics include diagnosis, treatment recommendation, clinical decision support, image analysis, wearable monitoring, and drug discovery. The review aims to comprehensively evaluate and synthesize the existing body of the literature on applying deep learning in the intersection of the IoT with bio- and medical informatics. In this paper, we categorized the most cutting-edge DL solutions for medical and bioinformatics issues into five categories based on the DL technique utilized: convolutional neural network, recurrent neural network, generative adversarial network, multilayer perception, and hybrid methods. A systematic literature review was applied to study each one in terms of effective properties, like the main idea, benefits, drawbacks, methods, simulation environment, and datasets. After that, cutting-edge research on DL approaches and applications for bioinformatics concerns was emphasized. In addition, several challenges that contributed to DL implementation for medical and bioinformatics have been addressed, which are predicted to motivate more studies to develop medical and bioinformatics research progressively. According to the findings, most articles are evaluated using features like accuracy, sensitivity, specificity, F-score, latency, adaptability, and scalability. [ABSTRACT FROM AUTHOR]

Machine learning (ML) algorithms are increasingly applied to structure health monitoring (SHM) problems. However, their application to pile damage detection (PDD) is hindered by the complexity of the problem. A novel multi-sensor pile damage detection (MSPDD) method is proposed in this paper to extend the application of ML algorithms in the automatic identification of PDD. The time-series signals collected by multiple sensors during the pile integrity test are first processed by the traveling wave decomposition (TWD) theory and are then input into a hybrid one-dimensional (1D) convolutional and recurrent neural network. The hybrid neural network can achieve the automatic multi-task identification of pile damage detection based on the time series of MSPDD results. Finally, the analytical solution-based sample set is utilized to evaluate the performance of the proposed hybrid model. The outputs of the multi-task learning framework can provide a detailed description of the actual pile quality and provide strong support for the classification of pile quality as well. [ABSTRACT FROM AUTHOR]

Multi-modal information outbreak is consistently increasing in social media. Classification of tweet sentiments using various information modalities will help the recommender systems to achieve success in digital marketing. Moreover, aspect-level sentiment analysis categorizes a target's sentiment polarity in a specific environment. Using topic modelling in aspect-level sentiment analysis enables the identification of more accurate aspect-based tweet sentiments. The existing sentiment classification techniques used for the development of recommendation systems do not focus on the aspect-based approach modelled using deep learning classifier with temporal analysis on the social media data. Hence, this paper proposes an efficient sentiment classification model that highlights the impact of topic modelling-based word feature embedding for improvising the classification of Twitter sentiments and product reviews based on temporal reasoning and analysis for performing predictive analysis. For tweets context analysis, Latent Dirichlet Allocation based topic modelling is used in this work which generates the topics. For each topic, the sentiment is calculated separately and the topic guided feature expansion is done using Senti-wordnet. Moreover, an extended deep learning classification algorithm called Long Short-Term Memory (LSTM) with word embedding and temporal reasoning(LSTMWTR) is proposed in this paper for improving the classification accuracy. Finally, the labelled data are classified using the existing machine learning algorithms namely Naïve Bayes, Support Vector Machines and also using the deep learning models such as Convolution Neural Network(CNN),LSTM, Recurrent Neural Networks (RNN) and the transformer model namelyBi-directional Encoder Representation from Transformers (BERT),Convolution Bi-directional Recurrent Neural Network (CBRNN) and the proposed deep learning algorithm namelyLSTMWTR. These sentiment classification algorithms have been evaluated with word embedding for tweet sentiment classification and product review classification. The results obtained from this work show that the proposed LSTMWTR algorithm emerges as the highly accurate model for tweet sentiment and product review classification. [ABSTRACT FROM AUTHOR]

Electromyography (EMG) signals hold critical significance in biomedical research, capturing muscle electrical activity during rest and contraction in the upper limb. Their versatility in applications, particularly in human-assisting robotic tools, drives ongoing exploration and research. This paper presents an original study focusing on leveraging machine learning techniques to classify EMG datasets and efficiently control a robotic arm based on predicted gestures. Data acquisition involves strategically placing an EMG muscle sensor on the forearm to ensure precise measurement of signals associated with hand gestures and movements. Diverse classifiers including random forest, support vector machine (SVM), K-nearest neighbors (KNN), Gaussian naïve Bayes, gated recurrent unit (GRU), long short-term memory (LSTM), artificial neural network (ANN), recurrent neural network (RNN), convolutional neural network (CNN), and vision transformer (ViT) are employed. Performance results are meticulously analyzed and presented in tabular format, showcasing the ViT classifier as the most successful, achieving an impressive 97.7% accuracy in robotic arm control. Notably, ANN, RNN, and CNN also exhibit high accuracy exceeding 90%. Furthermore, this work is comprehensively compared with existing literature, laying the groundwork for future advancements in human-robot interaction and cutting-edge assistive technologies that markedly enhance the quality of life for individuals with motor impairments or disabilities. The findings carry significant implications for designing and implementing intuitive, responsive robotic systems based on EMG signals. [ABSTRACT FROM AUTHOR]

Geological hazards often occur in mountainous areas and are sudden and hidden, so it is important to identify and assess geological hazards. In this paper, the western mountainous area of Beijing was selected as the study area. We conducted research on landslides, collapses, and unstable slopes in the study area. The surface deformation of the study area was monitored by multi-temporal interferometric synthetic aperture radar (MT-InSAR), using a combination of multi-looking point selection and permanent scatterer (PS) point selection methods. Random forest (RF), support vector machine (SVM), convolutional neural network (CNN), and recurrent neural network (RNN) models were selected for the assessment of geological hazard susceptibility. Sixteen geological hazard-influencing factors were collected, and their information values were calculated using their features. Multicollinearity analysis with the relief-F method was used to calculate the correlation and importance of the factors for factor selection. The results show that the deformation rate along the line-of-sight (LOS) direction is between −44 mm/year and 28 mm/year. A total of 60 geological hazards were identified by combining surface deformation with optical imagery and other data, including 7 collapses, 25 unstable slopes, and 28 landslides. Forty-eight of the identified geological hazards are not recorded in the Beijing geological hazards list. The most effective model in the study area was RF. The percentage of geological hazard susceptibility zoning in the study area is as follows: very low susceptibility 27.40%, low susceptibility 28.06%, moderate susceptibility 21.19%, high susceptibility 13.80%, very high susceptibility 9.57%. [ABSTRACT FROM AUTHOR]

In order to capture the complex dependencies between users and items in a recommender system and to alleviate the smoothing problem caused by the aggregation of multi-layer neighborhood information, a multi-behavior recommendation model (DNCLR) based on dual neural networks and contrast learning is proposed. In this paper, the complex dependencies between behaviors are divided into feature correlation and temporal correlation. First, we set up a personalized behavior vector for users and use a graph-convolution network to learn the features of users and items under different behaviors, and we then combine the features of self-attention mechanism to learn the correlation between behaviors. The multi-behavior interaction sequence of the user is input into the recurrent neural network, and the temporal correlation between the behaviors is captured by combining the attention mechanism. The contrast learning is introduced based on the double neural network. In the graph convolution network layer, the distances between users and similar users and between users and their preference items are shortened, and the distance between users and their short-term preference is shortened in the circular neural network layer. Finally, the personalized behavior vector is integrated into the prediction layer to obtain more accurate user, behavior and item characteristics. Compared with the sub-optimal model, the HR@10 on Yelp, ML20M and Tmall real datasets are improved by 2.5%, 0.3% and 4%, respectively. The experimental results show that the proposed model can effectively improve the recommendation accuracy compared with the existing methods. [ABSTRACT FROM AUTHOR]

Due to its automatic feature learning ability and high performance, deep learning has gradually become the mainstream of artificial intelligence in recent years, playing a role in many fields. Especially in the medical field, the accuracy rate of deep learning even exceeds that of doctors. This paper introduces several deep learning algorithms: Artificial Neural Network (NN), FM-Deep Learning, Convolutional NN and Recurrent NN, and expounds their theory, development history and applications in disease prediction; we analyze the defects in the current disease prediction field and give some current solutions; our paper expounds the two major trends in the future disease prediction and medical field—integrating Digital Twins and promoting precision medicine. This study can better inspire relevant researchers, so that they can use this article to understand related disease prediction algorithms and then make better related research. [ABSTRACT FROM AUTHOR]

Earlier, a method for constructing an initial approximation for solving the inverse problem of acoustics by a gradient method based on a convolutional neural network trained to predict the distribution of velocities in a medium from wave response was proposed [9]. It was shown that the neural network trained on responses from simple layered media can be successfully used for solving the inverse problem for a significantly more complex model. In this paper, we present algorithms for processing data about epidemics and an example of applying a neural network for modeling the propagation of COVID-19 in Novosibirsk region (Russia) based only on data. A neural network NN-COVID-19 that uses data about the epidemics is constructed. It is shown that this neural network predicts the propagation of COVID-19 for five days by an order of magnitude better than SEIR-HCD. When a new variant (Omicron) appeared, this neural network was able to predict (after retraining) the propagation of the epidemics more accurately. Note that the proposed neural network uses not only epidemiological data but also social ones (such as holidays, restrictive measures, etc.). The proposed approach makes it possible to refine mathematical models. A comparison of the curves constructed by SEIR-HCD model and by the neural network shows that the plots of solutions of the direct problem almost coincide with the plots constructed by the neural network. This helps refine coefficients of the differential model. [ABSTRACT FROM AUTHOR]

Catastrophic forgetting, which means a rapid forgetting of learned representations while learning new data/samples, is one of the main problems of deep neural networks. In this paper, we propose a novel incremental learning framework that can address the forgetting problem by learning new incoming data in an online manner. We develop a new incremental learning framework that can learn extra data or new classes with less catastrophic forgetting. We adopt the hippocampal memory process to the deep neural networks by defining the effective maximum of neural activation and its boundary to represent a feature distribution. In addition, we incorporate incremental QR factorization into the deep neural networks to learn new data with both existing labels and new labels with less forgetting. The QR factorization can provide the accurate subspace prior, and incremental QR factorization can reasonably express the collaboration between new data with both existing classes and new class with less forgetting. In our framework, a set of appropriate features (i.e., nodes) provides improved representation for each class. We apply our method to the convolutional neural network (CNN) for learning Cifar-100 and Cifar-10 datasets. The experimental results show that the proposed method efficiently alleviates the stability and plasticity dilemma in the deep neural networks by providing the performance stability of a trained network while effectively learning unseen data and additional new classes. [ABSTRACT FROM AUTHOR]

Cardiac-related disorders are rapidly growing throughout the world. Accurate classification of cardiovascular diseases is an important research topic in healthcare. During COVID-19, auscultating heart sounds was challenging as health workers and doctors wear protective clothing, and direct contact with patients can spread the outbreak. Thus, contactless auscultation of heart sound is necessary. In this paper, a low-cost ear contactless stethoscope is designed where auscultation is done with the help of a bluetooth-enabled micro speaker instead of an earpiece. The PCG recordings are further compared with other standard electronic stethoscopes like Littman 3 M. This work is made to improve the performance of deep learning-based classifiers like recurrent neural networks (RNN) and convolutional neural networks (CNN) for different valvular heart problems using tuning of hyperparameters like learning rate of optimizers, dropout rate, and hidden layer. Hyper-parameter tuning is used to optimize the performances of various deep learning models and their learning curves for real-time analysis. The acoustic, time, and frequency domain features are used in this research. The investigation is made on the heart sounds of normal and diseased patients available from the standard data repository to train the software models. The proposed CNN-based inception network model achieved an accuracy of 99.65 ± 0.06% on the test dataset with a sensitivity of 98.8 ± 0.05% and specificity of 98.2 ± 0.19%. The proposed hybrid CNN-RNN architecture attained 91.17 ± 0.03% accuracy on test data after hyperparameter optimization, whereas the LSTM-based RNN model achieved 82.32 ± 0.11% accuracy. Finally, the evaluated results were compared with machine learning algorithms, and the improved CNN-based Inception Net model is the most effective among others. [ABSTRACT FROM AUTHOR]

Humans are increasingly integrated with devices that enable the collection of vast unstructured opinionated data. Accurately analysing subjective information from this data is the task of sentiment analysis (an actively researched area in NLP). Deep learning provides a diverse selection of architectures to model sentiment analysis tasks and has surpassed other machine learning methods as the foremast approach for performing sentiment analysis tasks. Recent developments in deep learning architectures represent a shift away from Recurrent and Convolutional neural networks and the increasing adoption of Transformer language models. Utilising pre-trained Transformer language models to transfer knowledge to downstream tasks has been a breakthrough in NLP. This survey applies a task-oriented taxonomy to recent trends in architectures with a focus on the theory, design and implementation. To the best of our knowledge, this is the only survey to cover state-of-the-art Transformer-based language models and their performance on the most widely used benchmark datasets. This survey paper provides a discussion of the open challenges in NLP and sentiment analysis. The survey covers five years from 1st July 2017 to 1st July 2022. [ABSTRACT FROM AUTHOR]

Completing the classification of tactics and techniques in cyber threat intelligence (CTI) is an important way to obtain tactics, techniques and procedures (TTPs) and portray the behavior of cyber attacks. However, the high level of abstraction of tactics and techniques information and their presence in CTI, usually in the form of natural language text, make it difficult for traditional manual analysis methods and feature engineering-based machine learning methods to complete the classification of tactics and techniques effectively. Meanwhile, flat deep learning methods do not perform well in classifying more fine-grained techniques due to their inability to exploit the hierarchical relationship between tactics and techniques. Therefore, this paper regards the tactics and techniques of TTPs defined in Adversarial Tactics, Techniques and Common Knowledge knowledge base as labels and proposes a Convolutional Neural Network (CNN) model based on hierarchical knowledge migration and attention mechanism for classifying tactics and techniques in CTI, named HM-ACNN (CNN based on hierarchical knowledge migration and attention mechanism). HM-ACNN classifies tactics and techniques into two phases, and the underlying network model for both phases is the Attention-based CNN network. The first step in HM-ACNN is converting the CTI text into a two-dimensional image based on the word embedding model, and then start training the classification of tactics through the CNN structure based on the attention mechanism before the classification of techniques. Secondly, after the tactics classification training is completed, the tactic-to-technique knowledge migration is then completed by transforming the parameters of the CNN layer and the attention layer in the tactics classification process based on the special hierarchical relationship between tactics and techniques. Then, the classification of techniques is finished by fine-tuning. The experimental results show that HM-ACNN performs well in the tactics and techniques classification tasks, and the metric F1 values reach 93.66% and 86.29%, which are better than other models such as CNN, Recurrent Neural Network and CRNN (Recurrent Convolutional Neural Networks). [ABSTRACT FROM AUTHOR]

Natural Language Processing (NLP) acts towards the processing of linguistics between human and computer. The application of NLP in the chemical industry has proven to be a boon in the past decade. This paper presents a survey of deep learning (DL) models on NLP fundamentals for battery materials domain-related research. Various DL models like convolutional neural networks, recursive neural networks, recurrent neural networks, long short-term memory networks, and attention networks have been discussed while comparing their efficacy for different NLP tasks. Innovations in presented DL models provide enhanced performance for the NLP-based tasks. This paper will enlighten researchers, to get an insight into the current practices and scope for future developments on battery materials. They can apply NLP techniques for various applications like structural recognition and extraction, understanding of chemical features without a domain expert, and understanding the chemical structure and summarization approaches. Moreover, this paper will help chemists and researchers in the chemical industry to explore various areas to work upon. To empower this, various applications and future scope is discussed in this paper. [ABSTRACT FROM AUTHOR]

Human behavior is stimulated by the outside world, and the emotional response caused by it is a subjective response expressed by the body. Humans generally behave in common ways, such as lying, sitting, standing, walking, and running. In real life of human beings, there are more and more dangerous behaviors in human beings due to negative emotions in family and work. With the transformation of the information age, human beings can use Industry 4.0 smart devices to realize intelligent behavior monitoring, remote operation, and other means to effectively understand and identify human behavior characteristics. According to the literature survey, researchers at this stage analyze the characteristics of human behavior and cannot achieve the classification learning algorithm of single characteristics and composite characteristics in the process of identifying and judging human behavior. For example, the characteristic analysis of changes in the sitting and sitting process cannot be for classification and identification, and the overall detection rate also needs to be improved. In order to solve this situation, this paper develops an improved machine learning method to identify single and compound features. In this paper, the HATP algorithm is first used for sample collection and learning, which is divided into 12 categories by single and composite features; secondly, the CNN convolutional neural network algorithm dimension, recurrent neural network RNN algorithm, long- and short-term extreme value network LSTM algorithm, and gate control is used. The ring unit GRU algorithm uses the existing algorithm to design the model graph and the existing algorithm for the whole process; thirdly, the machine learning algorithm and the main control algorithm using the proposed fusion feature are used for HATP and human beings under the action of wearable sensors. The output features of each stage of behavior are fused; finally, by using SPSS data analysis and re-optimization of the fusion feature algorithm, the detection mechanism achieves an overall target sample recognition rate of about 83.6%. Finally, the research on the algorithm mechanism of machine learning for human behavior feature classification under the new algorithm is realized. [ABSTRACT FROM AUTHOR]

Recently, many efforts have been concentrated on land use land cover (LULC) classification due to rapid urbanization, environmental pollution, agriculture drought, frequent floods, and climate change. However, various aspects have attracted hyperspectral imaging due to there being informative discriminative features, such as spectral-spatial features. To this end, this paper is a comprehensive and systematic review of LULC classification using hyperspectral images by reviewing four significant research investigations. Moreover, the four investigations have addressed the following points: (1) the main components of the hyperspectral imaging, the modes of hyperspectral imaging with data acquisition methods, and the intrinsic differences between hyperspectral image and multispectral image, (2) the role of machine learning in LULC classification, and the standard deep learning methods: Convolution Neural Network (CNN), Stacked Autoencoder (SAE), Deep Belief Network (DBN), Recurrent Neural Network (RNN), and Generative Adversarial Network (GAN), (3) the standard benchmark hyperspectral datasets and the evaluation criteria, (4) the main challenges of LULC classification with the possible solutions for the limited training samples issue, the promising future directions, and finally the recent applications for LULC classification. [ABSTRACT FROM AUTHOR]

Network Application Classification (NAC) is a vital technology for intrusion detection, Quality-of-Service (QoS)-aware traffic engineering, traffic analysis, and network anomalies. Researchers have focused on designing algorithms using deep learning models based on statistical information to address the challenges of traditional payload and port-based traffic classification techniques. Internet of Things (IoT) and Software Defined Network (SDN) are two popular technologies nowadays and aims to connect devices over the internet and intelligently control networks from a centralized space. IoT aims to connect billions of devices; therefore, classification is essential for efficient processing. SDN is a new networking paradigm, which separates data plane measurement from the control plane. The emergence of deep learning algorithms with SDN provides a scalable traffic classification architecture. Due to the inadequate results of payload and port-based approaches, a statistical technique to classify network traffic into different classes using a Convolution Neural Network (CNN) and a Recurrent Neural Network (RNN) is presented in this paper. This paper provides a classification method for software defined IoT networks. The results show that, contrary to other traffic classification methods, the proposed approach offered a better accuracy rate of over 99 %, which is promising. [ABSTRACT FROM AUTHOR]

In sports, the essence of a complete technical action is a complete information structure pattern and the athlete's judgment of the action is actually the identification of the movement information structure pattern. Action recognition refers to the ability of the human brain to distinguish a perceived action from other actions and obtain predictive response information when it identifies and confirms it according to the constantly changing motion information on the field. Action recognition mainly includes two aspects: one is to obtain the required action information based on visual observation and the other is to judge the action based on the obtained action information, but the neuropsychological mechanism of this process is still unknown. In this paper, a new key frame extraction method based on the clustering algorithm and multifeature fusion is proposed for sports videos with complex content, many scenes, and rich actions. First, a variety of features are fused, and then, similarity measurement can be used to describe videos with complex content more completely and comprehensively; second, a clustering algorithm is used to cluster sports video sequences according to scenes, eliminating the need for shots in the case of many scenes. It is difficult and complicated to detect segmentation; third, extracting key frames according to the minimum motion standard can more accurately represent the video content with rich actions. At the same time, the clustering algorithm used in this paper is improved to enhance the offline computing efficiency of the key frame extraction system. Based on the analysis of the advantages and disadvantages of the classical convolutional neural network and recurrent neural network algorithms in deep learning, this paper proposes an improved convolutional network and optimization based on the recognition and analysis of human actions under complex scenes, complex actions, and fast motion compared to post-neural network and hybrid neural network algorithm. Experiments show that the algorithm achieves similar human observation of athletes' training execution and completion. Compared with other algorithms, it has been verified that it has very high learning rate and accuracy for the athlete's action recognition. [ABSTRACT FROM AUTHOR]

Breast cancer is one of the leading causes of death among women worldwide. In most cases, the misinterpretation of medical diagnosis plays a vital role in increased fatality rates due to breast cancer. Breast cancer can be diagnosed by classifying tumors. There are two different types of tumors, such as malignant and benign tumors. Identifying the type of tumor is a tedious task, even for experts. Hence, an automated diagnosis is necessary. The role of machine learning in medical diagnosis is eminent as it provides more accurate results in classifying and predicting diseases. In this paper, we propose a deep ensemble network (DEN) method for classifying and predicting breast cancer. This method uses a stacked convolutional neural network, artificial neural network and recurrent neural network as the base classifiers in the ensemble. The random forest algorithm is used as the meta‐learner for providing the final prediction. Experimental results show that the proposed DEN technique outperforms all the existing approaches in terms of accuracy, sensitivity, specificity, F‐score and area under the curve (AUC) measures. The analysis of variance test proves that the proposed DEN model is statistically more significant than the other existing classification models; thus, the proposed approach may aid in the early detection and diagnosis of breast cancer in women, hence aiding in the development of early treatment techniques to increase survival rate. [ABSTRACT FROM AUTHOR]

Careful monitoring of plant conditions and their diagnosis are necessary, but a human cannot control a large area of land where the crop grows. This paper proposes the solution of this problem. Early diagnosis and accurate detection of plant leaf diseases can prevent the spread of the disease. In the last decade, machine learning methods and image classification tools have been used to identify and diagnose plant diseases. This paper proposes an accurate approach to identify plant leaf diseases based on the deep convolutional neural network and gated recurrent units. The PlantVillage dataset of damaged and healthy plant leaves images is used. The proposed model is trained to identify common plant leaf diseases of 14 species. The experimental results are compared to other well-known models. This study shows that the proposed model based on deep learning provides the best solution in the diagnosis of plant diseases with high accuracy, and that the gated recurrent unit neural network considered as a classifier can improve the accuracy of the convolutional neural network model. The comparison results demonstrated that the proposed approach achieved higher performance than other models. [ABSTRACT FROM AUTHOR]

This paper shows the health monitoring and assessment of a three-phase induction motor in abnormal conditions using a machine learning algorithm. The convolutional neural network (CNN) and recurrent neural network (RNN) algorithms are the prominent methods used in machine learning algorithms, and the combined method is known as the CRNN method. The abnormal conditions of a three phase-induction motor are represented by three-phase faults, line-to-ground faults, etc. The pattern of fault current is traced, and key features are extracted by the CRNN algorithm. The performance parameters like THD (%), accuracy, and reliability of abnormal conditions are measured with the CRNN algorithm. The assessment of abnormal conditions is being realized at the terminals of a three-phase induction motor. A fuzzy logic controller (FLC) is also used to assess such abnormalities. It is observed that performance parameters are found to be better with the CRNN method in comparison to CNN, RNN, ANN, and other methods. Such a realization makes the system more compatible with abnormality recognition. [ABSTRACT FROM AUTHOR]

Human gait activity recognition is an emerging field of motion analysis that can be applied in various application domains. One of the most attractive applications includes monitoring of gait disorder patients, tracking their disease progression and the modification/evaluation of drugs. This paper proposes a robust, wearable gait motion data acquisition system that allows either the classification of recorded gait data into desirable activities or the identification of common risk factors, thus enhancing the subject's quality of life. Gait motion information was acquired using accelerometers and gyroscopes mounted on the lower limbs, where the sensors were exposed to inertial forces during gait. Additionally, leg muscle activity was measured using strain gauge sensors. As a matter of fact, we wanted to identify different gait activities within each gait recording by utilizing Machine Learning algorithms. In line with this, various Machine Learning methods were tested and compared to establish the best-performing algorithm for the classification of the recorded gait information. The combination of attention-based convolutional and recurrent neural networks algorithms outperformed the other tested algorithms and was individually tested further on the datasets of five subjects and delivered the following averaged results of classification: 98.9% accuracy, 96.8% precision, 97.8% sensitivity, 99.1% specificity and 97.3% F1-score. Moreover, the algorithm's robustness was also verified with the successful detection of freezing gait episodes in a Parkinson's disease patient. The results of this study indicate a feasible gait event classification method capable of complete algorithm personalization. [ABSTRACT FROM AUTHOR]

Emotions significantly impact human physical and mental health, and, therefore, emotion recognition has been a popular research area in neuroscience, psychology, and medicine. In this paper, we preprocess the raw signals acquired by millimeter-wave radar to obtain high-quality heartbeat and respiration signals. Then, we propose a deep learning model incorporating a convolutional neural network and gated recurrent unit neural network in combination with human face expression images. The model achieves a recognition accuracy of 84.5% in person-dependent experiments and 74.25% in person-independent experiments. The experiments show that it outperforms a single deep learning model compared to traditional machine learning algorithms. [ABSTRACT FROM AUTHOR]

The stock market is viewed as an unpredictable, volatile, and competitive market. The prediction of stock prices has been a challenging task for many years. In fact, many analysts are highly interested in the research area of stock price prediction. Various forecasting methods can be categorized into linear and non-linear algorithms. In this paper, we offer an overview of the use of deep learning networks for the Indian National Stock Exchange time series analysis and prediction. The networks used are Recurrent Neural Network, Long Short-Term Memory Network, and Convolutional Neural Network to predict future trends of NIFTY 50 stock prices. Comparative analysis is done using different evaluation metrics. These analysis led us to identify the impact of feature selection process and hyperparameter optimization on prediction quality and metrics used in the prediction of stock market performance and prices. The performance of the models was quantified using MSE metric. These errors in the LSTM model are found to be lower compared to RNN and CNN models. [ABSTRACT FROM AUTHOR]

Field seed maturity monitoring is essential to optimize the farming process and guarantee yield quality through high germination. Remote sensing of parsley fields through UAV multispectral imagery allows uniform scanning and better capture of crop information, in comparison to traditional limited field sampling analysis in the laboratory. Moreover, they only represent localized sub-sections of the crop field and are time consuming to process. The limited availability of seed sample maturity data is a drawback for applying deep learning methods, which have shown tremendous potential in estimating agronomic parameters, especially maturity, as they require large labeled datasets. In this paper, we propose a parametric and non-parametric-based weak labeling approach to overcome the lack of maturity labels and render possible maturity estimation by deep network regression to assist growers in harvest decision-making. We present the data acquisition protocol and the performance evaluation of the generative models and neural network architectures. Convolutional and recurrent neural networks were trained on the generated labels and evaluated on maturity ground truth labels to assess the maturity quantification quality. The results showed improvement by the semi-supervised approaches over the generative models, with a root-mean-squared error of 0.0770 for the long-short-term memory network trained on kernel-density-estimation-generated labels. Generative-model-based data labeling can unlock new possibilities for remote sensing fields where data collection is complex, and in our usage, they provide better-performing models for parsley maturity estimation based on UAV multispectral imagery. [ABSTRACT FROM AUTHOR]

Internet of Things (IoT) 's devices are ubiquitous and operate in a heterogonous environment with potential security breaches. IoT Operating Systems (IoT OSs) are the backbone software for running such devices. If IoT OSs are vulnerable to security breaches, higher-level security measures may not help. This paper aims to use Machine Learning (ML) to create a tool called iDetect for detecting vulnerabilities in C/C++ source code of IoT OSs. The source code for 16 releases of IoT OSs (RIOT, Contiki, FreeRTOS, Amazon FreeRTOS) and the Software Assurance Reference Dataset (SARD) were used to create a labeled dataset of vulnerable and benign code with the reference being the Common Weakness Enumeration (CWE) vulnerabilities present in IoT OSs. Studies showed that only a subset of CWEs is present in the C/C++ source code of low-end IoT OSs.The labeled dataset was used to train three ML models for vulnerability detection: Random Forest (RF), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN). The three models were used independently and RF; compared to CNN and RNN, gave the highest accuracy during the testing phase for binary and multiclass classification. RF was chosen as iDetect's ML classifier. Further evaluation was done on an unseen dataset of 322 code snippets taken from TinyOS. iDetect achieved a macro-averaged F1 score (mF1) of 98.5% and weighted-average F1 score (wF1) of 98% for multiclass classification, F1 score (F1) of 97.8% for binary classification, and superior results compared to all three Static Analysis Tools (SATs) used to collect the training dataset. [ABSTRACT FROM AUTHOR]

Transcription factors are important cellular components of the process of gene expression control. Transcription factor binding sites are locations where transcription factors specifically recognize DNA sequences, targeting gene-specific regions and recruiting transcription factors or chromatin regulators to fine-tune spatiotemporal gene regulation. As the common proteins, transcription factors play a meaningful role in life-related activities. In the face of the increase in the protein sequence, it is urgent how to predict the structure and function of the protein effectively. At present, protein–DNA-binding site prediction methods are based on traditional machine learning algorithms and deep learning algorithms. In the early stage, we usually used the development method based on traditional machine learning algorithm to predict protein–DNA-binding sites. In recent years, methods based on deep learning to predict protein–DNA-binding sites from sequence data have achieved remarkable success. Various statistical and machine learning methods used to predict the function of DNA-binding proteins have been proposed and continuously improved. Existing deep learning methods for predicting protein–DNA-binding sites can be roughly divided into three categories: convolutional neural network (CNN), recursive neural network (RNN) and hybrid neural network based on CNN–RNN. The purpose of this review is to provide an overview of the computational and experimental methods applied in the field of protein–DNA-binding site prediction today. This paper introduces the methods of traditional machine learning and deep learning in protein–DNA-binding site prediction from the aspects of data processing characteristics of existing learning frameworks and differences between basic learning model frameworks. Our existing methods are relatively simple compared with natural language processing, computational vision, computer graphics and other fields. Therefore, the summary of existing protein–DNA-binding site prediction methods will help researchers better understand this field. [ABSTRACT FROM AUTHOR]

Protein–protein interaction (PPI) plays an important role in biological processes such as signal transduction, immune response and membrane transport, etc. In this work, a protein sequence-based machine learning model, SeBPPI, to predict protein–protein binding was proposed. In this model, the descriptors were generated from three pre-trained models: Unirep, ESM and TAPE. The performance of SeBPPI with these pre-trained models was evaluated on several different test datasets. The accuracy of our binary prediction model shows improvement over the existing methods. We also compared the performance of two classification heads: The Recurrent convolution neural network (RCNN) and the fully connected neural network (FNN) and found that the use of RCNN is beneficial for the overall improvement in the accuracy of the model. This study helps to improve the accuracy in sequence-based protein–protein binding predictions. The model used in this work is integrated in the web server http://www.icdrug.com/ICDrug/SeBPPI. In this paper, a sequence-based protein-protein binding predictor was proposed. This machine learning model combined the RCNN model and the pre-trained models. Comparison between other machine learning models illustrated the SeBPPI model was a powerful tool. [ABSTRACT FROM AUTHOR]

With the fast development of various positioning techniques such as Global Position System (GPS), mobile devices and remote sensing, spatio-temporal data has become increasingly available nowadays. Mining valuable knowledge from spatio-temporal data is critically important to many real-world applications including human mobility understanding, smart transportation, urban planning, public safety, health care and environmental management. As the number, volume and resolution of spatio-temporal data increase rapidly, traditional data mining methods, especially statistics-based methods for dealing with such data are becoming overwhelmed. Recently deep learning models such as recurrent neural network (RNN) and convolutional neural network (CNN) have achieved remarkable success in many domains due to the powerful ability in automatic feature representation learning, and are also widely applied in various spatio-temporal data mining (STDM) tasks such as predictive learning, anomaly detection and classification. In this paper, we provide a comprehensive review of recent progress in applying deep learning techniques for STDM. We first categorize the spatio-temporal data into five different types, and then briefly introduce the deep learning models that are widely used in STDM. Next, we classify existing literature based on the types of spatio-temporal data, the data mining tasks, and the deep learning models, followed by the applications of deep learning for STDM in different domains including transportation, on-demand service, climate & weather analysis, human mobility, location-based social network, crime analysis, and neuroscience. Finally, we conclude the limitations of current research and point out future research directions. [ABSTRACT FROM AUTHOR]

Cyber Threat Intelligence (CTI) contains numerous Indicators of Compromise (IOCs) and contextual information, crucial for understanding threat actors' behavior and intentions. However, current information extraction predominantly relies on supervised learning algorithms, presenting challenges in the field of CTI for two reasons. Firstly, the scarcity of labeled data with IOCs hampers the effectiveness of supervised learning. Secondly, existing methods struggle to extract comprehensive contextual features, posing difficulties in IOC recognition within CTI. To address these limitations and better suit the unique characteristics of CTI text, this paper introduces STIOCS, a semi-supervised framework that combines active learning and self-training for IOC extraction. STIOCS enhances IOC extraction accuracy and efficiency by leveraging limited labeled data and a rich unannotated corpus. Firstly, the Active Learning (AL) approach uses the Density-based Spatial Clustering of Applications with Noise (DBSCAN) algorithm to select reliable samples that can reduce noise pollution on pseudo-labeling in self-training. The extraction model integrates Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) algorithms to extract local and sequential features from CTI text, respectively. Then, the semantic features are enhanced by using the different sizes of convolutional kernels to fuse the two types of features. Finally, the Conditional Random Fields (CRF) layer is employed to recognize IOC entities. Our experimental results demonstrate the effectiveness and robustness of our proposed method in IOC extraction, even with limited labeled data. Compared to supervised methods, our proposed method is only approximately 40% of the dataset is labeled, the F1 scores are achieved better than the existing methods and exhibit consistent performance improvements as the dataset size increases. STIOCS effectively suppresses weak label noise, reduces training costs, and enhances the recognition model's performance. It provides a cost-effective training framework for entity extraction in cyber threat intelligence. [Display omitted] • This paper proposes a semi-supervised active learning framework, STIOCS, aimed at improving the efficiency of IOC extraction in CTI and addressing the challenge of model degradation due to inadequate IOC annotation data. • Firstly, we extract valuable information from unlabeled data during self-training, but pseudo-labeling noise can potentially degrade model accuracy. • Secondly, we propose an active learning method aligned with the training objective to effectively select samples that enhance model performance. • Finally, we conduct extensive experiments on IOC extraction tasks using the fusion model, demonstrating superior performance compared to existing methods. [ABSTRACT FROM AUTHOR]

Parkinson's disease (PD) is a neurodegenerative disorder that produces both motor and non-motor complications, degrading the quality of life of PD patients. Over the past two decades, the use of wearable devices in combination with machine learning algorithms has provided promising methods for more objective and continuous monitoring of PD. Recent advances in artificial intelligence have provided new methods and algorithms for data analysis, such as deep learning (DL). The aim of this article is to provide a comprehensive review of current applications where DL algorithms are employed for the assessment of motor and non-motor manifestations (NMM) using data collected via wearable sensors. This paper provides the reader with a summary of the current applications of DL and wearable devices for the diagnosis, prognosis, and monitoring of PD, in the hope of improving the adoption, applicability, and impact of both technologies as support tools. Following PRISMA (Systematic Reviews and Meta-Analyses) guidelines, sixty-nine studies were selected and analyzed. For each study, information on sample size, sensor configuration, DL approaches, validation methods and results according to the specific symptom under study were extracted and summarized. Furthermore, quality assessment was conducted according to the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) method. The majority of studies (74%) were published within the last three years, demonstrating the increasing focus on wearable technology and DL approaches for PD assessment. However, most papers focused on monitoring (59%) and computer-assisted diagnosis (37%), while few papers attempted to predict treatment response. Motor symptoms (86%) were treated much more frequently than NMM (14%). Inertial sensors were the most commonly used technology, followed by force sensors and microphones. Finally, convolutional neural networks (52%) were preferred to other DL approaches, while extracted features (38%) and raw data (37%) were similarly used as input for DL models. The results of this review highlight several challenges related to the use of wearable technology and DL methods in the assessment of PD, despite the advantages this technology could bring in the development and implementation of automated systems for PD assessment. • Deep learning and wearable technology are used in diagnosis and monitoring. • Growing interest in the use of deep learning and wearables in Parkinson's disease. • The adoption of deep learning in Parkinson's disease is currently under development. • Technical and methodological challenges difficult the technology adoption. [ABSTRACT FROM AUTHOR]

Summary: Multiple‐input multiple‐output (MIMO) technology is much significant for achieving high data rates while considering the multiuser communication. For this purpose, the estimation of Channel State Information (CSI) is performed by the pilot. But, the estimated CSI cannot be applied for downlinks while processing an extremely high speed mobile data as it gets outdated because of the rapid channel variation. Estimating the channel in the MIMO systems is highly difficult on using non‐stationary channel characteristics under the high mobility environments. Channel estimation with received signal‐to‐noise ratio (SNR) feedback ensures an effective performance in the practical wireless MIMO systems. This paper plans to develop an intelligent deep learning strategy to solve the channel estimation problem in MIMO system. The main goal of the proposed model is to estimate the MIMO channel coefficients at a transmitter based on the received SNR feedback information from a receiver using the swarm intelligence‐based deep ensemble learning machine (SI‐DELM). For both the scenarios, the SI‐DELM is developed, in which the convolution neural network (NN) with three classifiers is used. Here, the fully connected layers of CNN are replaced by the NN, recurrent neural network (RNN), and deep neural network (DNN). In the SI‐DEL‐based channel estimation, the hyper parameter tuning is performed by the adaptive iteration assisted mixture ratio‐based cat swarm optimization (AIMR‐CSO) for minimizing the mean square error (MSE) and bit error rate (BER) of the estimated channel. Finally, by performing numerical simulations, the efficiency and better performance of the suggested model is revealed by conducting the comparison between proposed and conventional models. [ABSTRACT FROM AUTHOR]

The application of machine learning technology to intelligent music creation has become a very important field in music creation. The main current research on music intelligent creation methods uses fixed coding steps in audio data, which lead to weak feature expression ability. Based on convolutional neural network theory, this paper proposes a deep music intelligent creation method. The model uses a convolutional recurrent neural network to generate an effective hash code, first preprocesses the music signal to obtain a Mel spectrogram, and then inputs it into a pretrained CNN to extract from its convolutional layers. The network space details and the semantic information of musical symbols are used to construct the feature map sequence using selection strategy for the feature map of each convolutional layer, so as to solve the problem of high data feature dimension and poor recognition performance. In the simulation process, the Mel cepstral coefficient method (MFCC) was used to extract the features of four different music signals, and the features that could represent each signal were extracted through the convolutional neural network, and the continuous signals were discretized and reduced. The experimental results show that the high-dimensional music data are dimensionally reduced at the data level. After the data are compressed, the correct rate of intelligent creation is as high as 98%, and the characteristic signal distortion rate is reduced to 5% below, effectively improving the algorithm performance and the ability to create music intelligently. [ABSTRACT FROM AUTHOR]

• We propose a federated deep learning-based IDS for mitigating cyberattacks. • We investigate the use of three deep learning classifiers, DNN, CNN, and RNN. • The performance of each classifier is evaluated using three recent real datasets. • The results show that the FELIDS system outperforms the centralized versions. • The proposed FELIDS model achieves the highest accuracy in detecting attacks. In this paper, we propose a federated learning-based intrusion detection system, named FELIDS, for securing agricultural-IoT infrastructures. Specifically, the FELIDS system protects data privacy through local learning, where devices benefit from the knowledge of their peers by sharing only updates from their model with an aggregation server that produces an improved detection model. In order to prevent Agricultural IoTs attacks, the FELIDS system employs three deep learning classifiers, namely, deep neural networks, convolutional neural networks, and recurrent neural networks. We study the performance of the proposed IDS on three different sources, including, CSE-CIC-IDS2018, MQTTset, and InSDN. The results demonstrate that the FELIDS system outperforms the classic/centralized versions of machine learning (non-federated learning) in protecting the privacy of IoT devices data and achieves the highest accuracy in detecting attacks. [ABSTRACT FROM AUTHOR]

Convolutional neural networks also encountered some problems in the development of image recognition. The most prominent problem is that it is costly and time-consuming to collect data sets and train models. Limited data sets will cause the trained models to overfit. This paper proposes two methods to reduce overfitting based on the residual neural network architecture. The first type of method proposes a method of cross-combining waivers, reducing the size of the convolution kernel, and reducing the number of convolution kernels. The fitting method uses cross-combination to make the accuracy of Kaggle cat and dog data on the validation data set reach 95.37% and 90.31% on 30 types of engineering practice verification data set. The second method is based on the finetune residual neural network. A method of recurrent finetune residual neural network is proposed to improve the accuracy of the model. The accuracy of the finetune residual neural network on the Kaggle cat and dog validation dataset is 99.37%, and the accuracy of the dataset is verified in 30 types of engineering practice. The accuracy is 99.30%. The residual neural network method achieves 99.68% accuracy in the Kaggle cat and dog validation dataset and 99.61% in the validation dataset for 30 types of engineering practice. [ABSTRACT FROM AUTHOR]

The maintaining and initiating mechanisms of atrial fibrillation (AF) remain controversial. Deep learning is emerging as a powerful tool to better understand AF and improve its treatment, which remains suboptimal. This paper aims to provide a solution to automatically identify rotational activity drivers in endocardial electrograms (EGMs) with convolutional recurrent neural networks (CRNNs). The CRNN model was compared with two other state-of-the-art methods (SimpleCNN and attention-based time-incremental convolutional neural network (ATI-CNN)) for different input signals (unipolar EGMs, bipolar EGMs, and unipolar local activation times), sampling frequencies, and signal lengths. The proposed CRNN obtained a detection score based on the Matthews correlation coefficient of 0.680, an ATI-CNN score of 0.401, and a SimpleCNN score of 0.118, with bipolar EGMs as input signals exhibiting better overall performance. In terms of signal length and sampling frequency, no significant differences were found. The proposed architecture opens the way for new ablation strategies and driver detection methods to better understand the AF problem and its treatment. [ABSTRACT FROM AUTHOR]

Summary: Structural health monitoring of infrastructure especially bridges plays a vital role in post‐earthquake recovery. Coupling emerging techniques in machine learning with structural health monitoring can provide unprecedented tools for damage detection and identification. This paper explores the use of time‐series acceleration or displacement data collected from a shake‐table experiment of a two‐span bridge utilizing pretensioned rocking columns to predict the damage state of each bridge bent, where the major identified damage was the fracture of the longitudinal bars. To overcome the limitation of small data size collected during the shake‐table test that hindered the use of artificial neural networks and recurrent neural networks, the time‐series data were encoded into images using three methods Gramian angular summation field, Gramian angular difference field, and Markov transition field. Then, the encoded images were used as an input for convolutional neural network models. Three different data entries for the input layers were used including encoded images from recorded accelerations, drift ratios, and both. Two training/testing scenarios were proposed to test the efficacy of the convolutional neural networks. Convolutional neural network models trained on Markov transition field encoded images from acceleration performed with 100% accuracy during the training phase and more than 94% for the testing phase. [ABSTRACT FROM AUTHOR]

Neural networks (NNs) have seen an increase in popularity in the last few years. As found in several papers, they outperformed other machine learning algorithms and have improved their applicability. NNs have shown potential when working with prediction and detection algorithms by addressing a large variety of problems, such as recognition of heavy machinery, project success prediction, workers' pose assessment, price estimations, and project productivity estimation. To understand the future potential of NNs, we completed a bibliometric analysis of the existing literature, including publications since 2010. The areas in which NNs have been used in construction applications are categorized to understand their connections and underlying architectures. This work found a wider field of applications for NNs in the construction industry than originally known. New architectures such as transformer networks have not been explored fully in construction research but could lead to higher-performing networks. As far as the authors know, this is the first review to solely focus on construction, excluding areas such as structural engineering, indoor climate, occupancy modeling, and energy analysis. The limitations of NNs are discussed, and a path forward is proposed, which includes real-time models and examination of new architectures, which would allow the construction research to fully exploit the potential of NNs. [ABSTRACT FROM AUTHOR]

This paper proposes a supervised machine learning system to detect fake news in online sources published in Romanian. Additionally, this work presents a comparison of the obtained results by using recurrent neural networks based on long short-term memory and gated recurrent unit cells, a convolutional neural network, and a Bidirectional Encoder Representations from Transformers (BERT) model, namely RoBERT, a pre-trained Romanian BERT model. The deep learning architectures are compared with the results achieved by two classical classification algorithms: Naïve Bayes and Support Vector Machine. The proposed approach is based on a Romanian news corpus containing 25,841 true news items and 13,064 fake news items. The best result is over 98.20%, achieved by the convolutional neural network, which outperforms the standard classification methods and the BERT models. Moreover, based on irony detection and sentiment analysis systems, additional details are revealed about the irony phenomenon and sentiment analysis field which are used to tackle fake news challenges. [ABSTRACT FROM AUTHOR]

Based on machine learning algorithms, this paper designs a crossborder e-commerce logistics service system recommendation algorithm. First, we introduce the meaning of query recommendation, analyze the mechanism of e-commerce platform shopping search, redesign the query recommendation process on this basis, establish a Markov decision process model for the problem, and solve the optimal recommendation strategy through deep machine learning algorithms. Second, we design a simple calculation example, use Python programming through a simulated shopping environment, give the solution process of the optimal recommendation strategy in the whole process, and prove the feasibility of the algorithm. The sentiment synthesis word vector is used as the input data structure of the text, the convolutional neural network model and the recurrent neural network model in machine learning are independently designed and constructed, and a shunt is proposed. The rule (shunt) realizes the operation of judging the data and inputting the two machine learning networks. The shunt fully realizes the combination of the advantages of the local feature characterization of the convolutional neural network and the timing characteristics of the recurrent neural network and achieves a more efficient and accurate electrical system. Finally, through simulation experiments, a series of data processing work such as data outlier cleaning, sliding window construction features of data variables, and training set and test set division are designed to convert regression prediction problems into classification problems to predict commodity demand. At the same time, it also compared the effect of the time series model, random forest model, GBDT, single Xgboost model, and the model used in this topic and analyzed the reasons for this difference and the application of each model. [ABSTRACT FROM AUTHOR]

Dynamic analysis of forced-vibration systems in civil engineering could be computationally inefficient or even hard to converge if the systems are stiff or highly complicated. Rapid advances in machine learning make it possible to formulate surrogate models for forced-vibration systems using neural networks. The widely used neural networks such as the convolutional neural network (CNN), recurrent neural network (RNN), etc., usually require a constant sampling rate and data length, thus they are difficult to be implemented for real-time calculation of the dynamic system with varying sampling rates. Recently, the continuous-time state-space neural network (CSNN) has shown the capability to lift these restrictions and has been drawing growing attention from the community. In this paper, we propose a generalized CSNN model for various forced-vibration systems (linear and nonlinear). The CSNN model comprises two sets of independent neural networks aiming to compute the state derivative and system response, respectively. Both neural networks adopt linear and nonlinear layers in parallel, instead of only fully connected nonlinear layers as adopted in the literature. This configuration is aimed to enhance the CSNN model with its capability to recognize the linear and nonlinear behaviors of systems. Additionally, the bias options in the CSNN model are all turned off to improve the stability of the model in the long-term time-series forecast, premised on the assumption that the forced-vibration systems are dissipative systems without drift, which is the most common case in civil engineering. Integration on the state derivative at the current time step is executed to obtain the state at the next time step using the explicit 4th-order Runge–Kutta method. Both numerical and experimental illustrative examples are provided, demonstrating that the CSNN model can achieve high performance and training efficiency with a few hyper-parameters, and thus is highly promising for engineering applications. • A novel continuous-time state-space neural network (CSNN) model is proposed for data-driven modeling of forced-vibration linear/nonlinear systems. • The CSNN model does not require any prior knowledge of the system, and is not restricted to the pre-designated sampling rate and input data length. • The CSNN model has much fewer hyper-parameters than traditional neural network models and is unlikely to induce overfitting. • Numerical and experimental studies demonstrate that the CSNN model is superior to LSTM and PhyCNN in modeling both linear and nonlinear systems. [ABSTRACT FROM AUTHOR]

Hand gesture recognition tasks based on surface electromyography (sEMG) are vital in human-computer interaction, speech detection, robot control, and rehabilitation applications. However, existing models, whether traditional machine learnings (ML) or other state-of-the-arts, are limited in the number of movements. Targeting a large number of gesture classes, more data features such as temporal information should be persisted as much as possible. In the field of sEMG-based recognitions, the recurrent convolutional neural network (RCNN) is an advanced method due to the sequential characteristic of sEMG signals. However, the invariance of the pooling layer damages important temporal information. In the all convolutional neural network (ACNN), because of the feature-mixing convolution operation, a same output can be received from completely different inputs. This paper proposes a concatenate feature fusion (CFF) strategy and a novel concatenate feature fusion recurrent convolutional neural network (CFF-RCNN). In CFF-RCNN, a max-pooling layer and a 2-stride convolutional layer are concatenated together to replace the conventional simple dimensionality reduction layer. The featurewise pooling operation serves as a signal amplitude detector without using any parameter. The feature-mixing convolution operation calculates the contextual information. Complete evaluations are made on both the accuracy and convergence speed of the CFF-RCNN. Experiments are conducted using three sEMG benchmark databases named DB1, DB2 and DB4 from the NinaPro database. With more than 50 gestures, the classification accuracies of the CFF-RCNN are 88.87% on DB1, 99.51% on DB2, and 99.29% on DB4. These accuracies are the highest compared with reported accuracies of machine learnings and other state-of-the-art methods. To achieve accuracies of 86%, 99% and 98% for the RCNN, the training time are 2353.686 s, 816.173 s and 731.771 s, respectively. However, for the CFF-RCNN to reach the same accuracies, it needs only 1727.415 s, 542.245 s and 576.734 s, corresponding to a reduction of 26.61%, 33.56% and 21.19% in training time. We concluded that the CFF-RCNN is an improved method when classifying a large number of hand gestures. The CFF strategy significantly improved model performance with higher accuracy and faster convergence as compared to traditional RCNN. [ABSTRACT FROM AUTHOR]

. The process of damage identification in Structural Health Monitoring (SHM) gives us a lot of practical information about the current status of the inspected structure. The target of the process is to detect damage status by processing data collected from sensors, followed by identifying the difference between the damaged and the undamaged states. Different machine learning techniques have been applied to attempt to extract features or knowledge from vibration data, however, they need to learn prior knowledge about the factors affecting the structure. In this paper, a novel method of structural damage detection is proposed using a hybrid convolution neural network and recurrent neural network. A convolution neural network is used to extract deep features while recurrent neural network is trained to learn the long-term historical dependency in time series data. This proposed method which combines two types of features -spatial and temporal- helps to increase discrimination ability when being compared with the one that contains deep features only. Finally, the neural network is applied to categorize the time series into two states - undamaged and damaged. The accuracy of the proposed method was tested on a benchmark dataset of Z24-bridge (Switzerland). The result shows that the hybrid method provides a high level of accuracy in damage identification of the tested structure. [ABSTRACT FROM AUTHOR]

Bridge deterioration is inevitable in service, and the inspection and maintenance of bridges are needed to ensure structural integrity. To make cost-effective inspection plans, bridge management departments need degradation models to predict future condition ratings of bridges. Although there have been studies on bridge degradation, the input features of models are selected mostly based on engineering experience, and no effective method has been proposed. Meanwhile, most models based on machine learning (ML) and deep learning (DL) only predict the degradation of bridges in a single year and cannot cover a complete inspection cycle (usually 2 years), providing limited decision support for the transportation departments. Besides, more accurate models are needed to predict the degradation trend of bridges. In response to these problems, an improved ReliefF algorithm is proposed to select features of bridges in the paper. Meanwhile, a new degradation model combining recurrent neural network (RNN) and convolutional neural network (CNN) is established. Historical data of bridges in the US state of Texas from 1992 to 2019 are employed to verify the proposed methods. The result shows that the improved ReliefF algorithm selects the appropriate feature set as the input of the prediction model, and the model accurately predicts the future condition ratings of bridges in the next 3–4 years. The research is beneficial to infrastructure management departments in allocating bridge inspection and maintenance resources reasonably. [ABSTRACT FROM AUTHOR]