Search

Reservoir computing (RC) is a popular class of recurrent neural networks (RNNs) with untrained dynamics. Recently, advancements on deep RC architectures have shown a great impact in time-series applications, showing a convenient trade-off between predictive performance and required training complexity. In this paper, we go more in depth into the analysis of untrained RNNs by studying the quality of recurrent dynamics developed by the layers of deep RC neural networks. We do so by assessing the richness of the neural representations in the different levels of the architecture, using measures originating from the fields of dynamical systems, numerical analysis and information theory. Our experiments, on both synthetic and real-world datasets, show that depth—as an architectural factor of RNNs design—has a natural effect on the quality of RNN dynamics (even without learning of the internal connections). The interplay between depth and the values of RC scaling hyper-parameters, especially the scaling of inter-layer connections, is crucial to design rich untrained recurrent neural systems. [ABSTRACT FROM AUTHOR]

Combining convolutional neural networks (CNNs) and recurrent neural networks (RNNs) produces a powerful architecture for video classification problems as spatial–temporal information can be processed simultaneously and effectively. Using transfer learning, this paper presents a comparative study to investigate how temporal information can be utilized to improve the performance of video classification when CNNs and RNNs are combined in various architectures. To enhance the performance of the identified architecture for effective combination of CNN and RNN, a novel action template-based keyframe extraction method is proposed by identifying the informative region of each frame and selecting keyframes based on the similarity between those regions. Extensive experiments on KTH and UCF-101 datasets with ConvLSTM-based video classifiers have been conducted. Experimental results are evaluated using one-way analysis of variance, which reveals the effectiveness of the proposed keyframe extraction method in the sense that it can significantly improve video classification accuracy. [ABSTRACT FROM AUTHOR]

This paper investigates the problem of forecasting multivariate aggregated human mobility while preserving the privacy of the individuals concerned. Differential privacy, a state-of-the-art formal notion, has been used as the privacy guarantee in two different and independent steps when training deep learning models. On one hand, we considered gradient perturbation, which uses the differentially private stochastic gradient descent algorithm to guarantee the privacy of each time series sample in the learning stage. On the other hand, we considered input perturbation, which adds differential privacy guarantees in each sample of the series before applying any learning. We compared four state-of-the-art recurrent neural networks: Long Short-Term Memory, Gated Recurrent Unit, and their Bidirectional architectures, i.e., Bidirectional-LSTM and Bidirectional-GRU. Extensive experiments were conducted with a real-world multivariate mobility dataset, which we published openly along with this paper. As shown in the results, differentially private deep learning models trained under gradient or input perturbation achieve nearly the same performance as non-private deep learning models, with loss in performance varying between 0.57 and 2.8 % . The contribution of this paper is significant for those involved in urban planning and decision-making, providing a solution to the human mobility multivariate forecast problem through differentially private deep learning models. [ABSTRACT FROM AUTHOR]

In order to improve the target recognition effect of small UAV (unmanned aerial vehicle) remote sensing image, this paper proposes a new super-resolution reconstruction method based on the recurrent convolutional network, which can achieve different degrees of super-resolution effect by controlling the number of cycles. Moreover, it can control the number of iterations of small UAVs with different degrees of blur and can be better adapted to the recognition scenarios of UAVs. In addition, this paper studies the target recognition method of small UAV remote sensing image, combines fuzzy clustering method to construct the intelligent remote sensing image target recognition model, combines it with the UAV structure, realizes remote sensing recognition by UAV, and designs experiments to analyze the effect of remote sensing recognition. Further, this paper improves the recognition algorithm and positioning algorithm of remote sensing image, so that recognition and positioning of UAV video remote sensing image can get better results. Finally, this paper verifies the performance of the system through simulation experiments. The research results show that the method proposed in this paper has certain reliability. [ABSTRACT FROM AUTHOR]

To improve the effect of landslide feature extraction, this paper improves the remote sensing image recognition algorithm with the support of a machine learning algorithm. Moreover, this paper combines UAV remote sensing images to extract landslide features, classifies and introduces the evaluation criteria for target detection and several representative target detectors. This paper also constructs the functional structure of the system according to the landslide feature extraction requirements and designs a set of optimization schemes for landslide feature data collection and control measurement suitable for field operations. In addition, this paper analyses the system kernel algorithm process and analyses the system function realization through simulation research. Finally, this paper designs an experiment to evaluate the practicability of the system constructed in this paper. From the results of experimental statistics, we can see that the system constructed in this paper has good practicability. [ABSTRACT FROM AUTHOR]

This paper analyzes the inherent relationship between convolutional neural networks and sparse representation and proposes an improved convolutional neural network model for image synthesis in response to problems with current methods. In the testing phase, the calculation of the sparse coefficients involves the solution of complex optimization problems, which greatly reduce the operating efficiency, inspired by the successful application of convolutional neural networks in the field of image reconstruction. Compared with the traditional image portrait synthesis method, this model not only has an end-to-end closed form but also does not need to solve complex optimization problems in the synthesis stage. The synthesis experiment on an image dataset shows that this method not only improves the synthesis effect but also improves the efficiency of the traditional method by one to two orders of magnitude, demonstrating its potential application value. Blocking processing is a common method for sparse domain image modeling. It improves the computational efficiency but also decreases the global structure of the image, which is difficult to compensate for through the aggregation and overlap of image blocks. In response to this problem, this paper proposes a low-rank image inpainting method based on a Gaussian mixture model. This method embeds the local statistical characteristics of image blocks into the kernel norm model and not only uses the Gaussian mixture model to maintain the local details of the image but also describes the global low-rank structure of the image through the kernel norm, thus restoring a class of image data with a potential low-rank structure and theoretically revealing the structured sparse nature of the Gaussian mixture model. This paper optimizes the strategy based on random hidden neuron nodes and proposes a dropout anti-overfitting strategy based on sparsity. The experiments show that this strategy can effectively improve the convergence speed while ensuring good performance and can effectively prevent overfitting. [ABSTRACT FROM AUTHOR]

The development of green finance and the quantitative evaluation of its impact on the ecological environment provide empirical evidence for the construction of the carbon trading accounting system. Among them, carbon trading is an important part of green finance, and the accounting of businesses related to carbon emission rights has promoted the development of regional green finance. In order to explore the relationship between green finance and carbon emissions, this paper builds an analysis model of the relationship between green finance and carbon emissions based on big data and machine learning based on big data technology and machine learning technology. Moreover, this paper conducts simulation tests through the system and compares the output results with the actual situation after system simulation to verify the effectiveness of the model in this paper. From the experimental research results, it can be seen that the correlation analysis model of green finance and carbon emissions based on big data and machine learning constructed in this paper has a good performance in the correlation analysis of green finance and carbon emissions. Moreover, it is not difficult to see through the model of this paper that there is a clear correlation between green finance and carbon emissions. [ABSTRACT FROM AUTHOR]

The path planning system is an important part of unmanned vehicles, and the development of path planning technology will surely promote the rapid development of unmanned vehicle technology. In order to prevent the node from continuously monitoring its state, a self-triggering control strategy is proposed. Before the trigger moment, the node does not need to monitor its state. Moreover, considering the unpredictable problem of the node state, a control strategy triggered by the observed event is proposed, that is, only the output state information is used to determine the trigger time. In addition, this paper analyzes and models the two major factors that affect the local planning results, the environment and the vehicle, and uses the path smoothing and optimization method based on B-spline curve and the path optimization method based on the steering controller. Finally, this paper designs experiments to analyze the vehicle local path planning method and time consistency of the unmanned driving system. From the experimental results, it can be seen that the unmanned driving system constructed in this paper has a certain effect. [ABSTRACT FROM AUTHOR]

In order to improve the effectiveness of signal processing, according to the actual needs of signal processing and the current problems in signal processing, this paper introduces an improved LSTM recurrent neural network algorithm to construct the signal processing algorithm. Moreover, this paper sets up the functional structure of this paper based on the neural network model structure, and builds an intelligent analysis system for signal processing tasks based on the LSTM recurrent neural network algorithm. In addition, this paper analyzes the system algorithm flow in detail, and combines experimental research to carry out the effectiveness of the system constructed in this paper, and conducts quantitative analysis from two aspects of signal threshold prediction and signal processing effect. Finally, this paper conducts experimental results research with the support of mathematical statistics methods. From the research point of view, it can be known that the system constructed in this paper has good signal processing functions. [ABSTRACT FROM AUTHOR]

The heterogeneity of enterprise management will have a certain impact on enterprise investment. In order to explore the strength of this correlation, this paper builds an intelligent system that can be used for enterprise analysis with the support of machine learning technology, uses embedded algorithms to improve the traditional algorithm structure, and combines machine learning to optimize and analyze data processing. Moreover, this paper combines the heterogeneity of enterprise management and the actual needs of enterprise management, the current financial market investment status to analyze the system's functional structure, and combine the actual needs to construct the overall system architecture. In addition, this paper adopts algorithm analysis to the system process, analyzes the system logic layer structure, and builds the overall system structure framework. Finally, this paper designs an experiment to analyze the performance of the system constructed in this paper. From the experimental research, it can be seen that the system constructed in this paper basically meets the expected requirements. [ABSTRACT FROM AUTHOR]

In this paper, the model and its curriculum learning method of garbage hierarchical classification and corresponding operation mode decision in home environment are proposed from the perspective of cleaning robot. In order to realize the hierarchical learning of garbage attribute concept, this paper designs a learning model with iterative feedback network as the backbone network. In the early stage of iteration, the model focuses on learning the state of garbage, in the middle stage, it focuses on the appearance attributes of garbage, and the specific categories of garbage in the later stage. At the same time, the attention module is introduced to achieve different levels of feature expression learning, which further improves the performance of the model. The evaluation was conducted on the collected garbage data set and the public CIFAR-100 and Stanford Cars data sets, which verified the effectiveness and wide applicability of the proposed method. [ABSTRACT FROM AUTHOR]

To improve the scientificity and reliability of medical behavior analysis, this paper combines machine learning and wireless sensor technology to construct an intelligent data mining system that can be used for medical behavior analysis and uses association rules to analyze and mine the implicit relationships between structural monitoring parameters. Moreover, this paper establishes strong association rules between different monitoring variables based on historical monitoring data under normal structural conditions to predict whether the structural conditions are normal. In addition, this paper constructs a system function module according to actual needs, obtains the overall system architecture, and implements the system function module in combination with algorithms. Finally, this paper designs experiments to verify the performance of the system constructed in this paper and discusses the experimental results through mathematical graph analysis methods. From the research point of view, it can be observed that the system constructed in this paper has a specific effect. [ABSTRACT FROM AUTHOR]

In order to solve the problem of crop disease detection in large-scale planting, a new crop disease detection algorithm based on multi-feature decision fusion is proposed. This paper proposes a multi-feature decision fusion disease discrimination algorithm (PD R-CNN) based on machine vision on crop surfaces. The algorithm is based on the machine vision processing model of R-CNN and integrates a disease discrimination algorithm on the basis of R-CNN. After training on crop image data sets, PD R-CNN can reach the goal of identifying crop surface lesions. This paper uses machine vision image acquisition, image processing and analysis technology to collect and analyze the growth of cucumber seedlings. The research results show that compared with manual judgment, PD R-CNN reduces the workload and can effectively distinguish crop diseases. Through experiments, during the occurrence of pests and diseases, PD R-CNN has a monitoring accuracy of 88.0% for mosaic disease, 92.0% for root rot, 88.0% for powdery mildew, and 86.0% for aphids, indicating that there are errors in actual monitoring, but the accuracy exceeds 85.0% can be put into use. [ABSTRACT FROM AUTHOR]

In order to improve the effect of rural financial ecological environment evaluation, this paper combines machine learning and improved neural network algorithms to construct a rural financial ecological environment evaluation system. First, this paper optimizes the input layer structure and its initial weight random assignment. The input layer structure is processed by factor analysis, and the initial weight random assignment is optimized by particle swarm optimization. Secondly, this paper constructs a rural financial ecological environment evaluation model based on factor analysis method and PSO-SOM to avoid the defects of traditional SOM algorithm used in financial ecological environment evaluation research. Finally, this paper constructs a system framework based on actual needs and designs experiments to verify the performance of the evaluation system constructed in this paper. The research results show that the system constructed in this paper meets the basic needs of rural financial ecological environment evaluation. [ABSTRACT FROM AUTHOR]

In order to improve the efficiency of national forest park ecotourism management, this paper analyzes the national forest park ecotourism management based on 5G network and machine learning and analyzes the prediction algorithm based on time series data used in the process of building the flow prediction network model. Moreover, this paper combines the actual data operation requirements to improve the algorithm, builds the system architecture according to the actual requirements of the national forest park ecotourism management, and performs data processing with the support of machine learning and 5G network. In addition, after constructing the system, this paper verifies the performance of the system and processes the test results through statistical methods. From the experimental analysis, it can be seen that the system constructed in this paper basically meets the needs of ecotourism management in the national forest park. [ABSTRACT FROM AUTHOR]

Studying the changes in the landscape pattern of coastal cities and analyzing their land use conditions are conducive to understanding the internal structure of the city and in-depth analysis of the law of urban development, so as to propose governance measures and improvement methods in the aspects of economy, people's livelihood, and environment. Based on geographic information system and machine learning technology, this paper analyzes the internal mechanism, temporal and spatial characteristics and change laws of the intensive use of sea areas. The selection of research scale is in the exploratory stage, which is based on the research scale of land intensive use. Moreover, this paper combines landscape ecology to construct a coastal city landscape image simulation system and uses remote sensing technology to analyze the system model. Finally, this paper analyzes the performance of the coastal city landscape image simulation system constructed in this paper through experimental analysis. From the research results, the system constructed in this paper basically meets the needs of coastal city landscape image simulation. [ABSTRACT FROM AUTHOR]

In order to improve the effect of physical education and training, this paper combines machine learning technology to identify sports training features and action prediction, and combines Internet of Things technology to process physical education and training data, and build a physical education and training system based on machine learning and Internet of Things. In order to solve some shortcomings of the original extreme learning machine, this paper gradually optimizes the hidden layer mapping and parameter optimization to further improve the accuracy of prediction. Moreover, this paper uses the Internet of Things technology to achieve long-term uninterrupted data collection, and after the data have been processed to a certain extent, an extreme learning machine is used to predict the situation of sports training. Finally, this paper designs experiments to verify the performance of the system. The research results show that the physical education and training system constructed in this paper have certain practical effects and can optimize the physical education and training process. [ABSTRACT FROM AUTHOR]

The asymptotic stability of delayed reaction-diffusion neural networks with algebraic constraints, that is, singular delayed reaction-diffusion neural networks, is studied in this paper. In terms of Green's theorem, inequality technique and linear matrix inequalities (LMIs), two less conservative criterion for the asymptotic stability of singular delayed reaction-diffusion neural networks are given by endowing Lyapunov direct method and used to design an appropriate stabilizing feedback controllers. The results address both the effects of the delay and the algebraic constraints. In addition, these conditions have higher computational efficiency and can easily detect and stabilize the actual neural networks. Finally, the numerical simulations verify the validity of the theoretical analysis. [ABSTRACT FROM AUTHOR]

Attitude detection of cooperative robots can help robots recognize environment, understand tasks, and improve the safety, accuracy and efficiency of robot work. For robots with unknown configuration parameters, their configuration can be estimated; it is convenient for further kinematics and dynamics analysis. For an economical cooperative robot, its kinematic parameters can be corrected by attitude detection. An independent robot attitude detection system can be used as a secondary auxiliary system, and the fault diagnosis system of the robot is composed of the high-precision encoder system of the robot body. This paper studies the neural network control system of cooperative robot based on genetic algorithm. In this paper, the robot is taken as the research object. Aiming at its strong conjunction, non-linearity and multivariable characteristics, the problem of robot motion control based on neural network is mainly discussed. On this basis, the basic genetic algorithm and an improved genetic algorithm called messy are used to optimize the structure of the neural network, so as to better realize the motion control problem of the robot. The results of this study show that: After optimization with messy genetic algorithm, not only the tracking effect is better, but also the number of hidden layer nodes of the network is reduced from 12 to 7. This greatly simplifies the structure of the network and makes the design and training of the network relatively simple. [ABSTRACT FROM AUTHOR]

Fire smoke detection in forest faces much more challenges than in local areas or indoors. Conventional fire smoke methods using static features extracted form single image directly cannot handle some disturbed factors exist in forest, such as shaking trees and fog/haze. On the other hand, it is difficult to capture the dynamic features of fire smoke while they are vital for fire smoke detection. This paper proposes an effective method of extracting features based on sequential images for smoke detection, quasi-dynamic features are extracted using on pixel-block arranged image sets. First, consecutive frames are rearranged into a new big image based on a pixel-block rule, so that the new image still keep the whole structure of original image on block level, and the change of different pixels in the same block, which comes from the same position of each frame, can reflect the dynamic features by special process. Second, to process the new arranged big image, driven by single image wavelet transform for denoting local signal characteristics, Dual Tree-Complex Wavelet Transform is utilized to decompose the new big image into eight images with the same size of the source image after several level-decomposition, including four directions (HH, HL, LH, LL) with two decomposed images in each direction, so that the changes from smoke in different orientation can be extracted and depicted in these subbands. Third, a multi-scale dictionary learning method is proposed to learn dictionaries of each group images. Furthermore, elastic net is introduced for sparse coding and feature coefficients extraction. All operations above contribute to a significant improvement for smoke detection in this paper. Extensive experiments are performed to validate the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Face recognition applications focus on local features to prevent detailed information from being omitted while the feature extraction processes. This paper is based on presenting a local pattern-based model to extract more discriminative features that lead to more accurate classification. In local pattern-based feature extraction, the LBP is one of the most important approaches that many variants of this method have been proposed till now. LBP calculation is based on differences between the central pixel and the desired one. In contrast, the information hidden in the selected pixel's neighborhood pixels is not included in this process. This paper proposes the DR_LBP approach to address this failure by defining distances and using some of them in a ratio form. Successful results have been earned in many experimental results. In LBP, the calculations' primary flow takes advantage of two pixels in the LBP box, the central and the desired pixel. Contrary to the original LBP, this paper's proposed approach uses three pixels of LBP box to conduct the feature vector, which leads to employing the information hidden in the relationship between neighboring pixels. This approach applies the experiments on two standard datasets, ORL Yale face and Faces94 dataset. The accuracy percent of the proposed plan is 95.95, 94.09 and 98.01 on ORL, Yale face and Faces94 dataset, respectively, which is the reason to present this model as a new face feature extraction approach. [ABSTRACT FROM AUTHOR]

Corn disease prediction is an essential part of agricultural productivity. This paper presents a novel 3D-dense convolutional neural network (3D-DCNN) optimized using the Ebola optimization search (EOS) algorithm to predict corn disease targeting the increased prediction accuracy than the conventional AI methods. Since the dataset samples are generally insufficient, the paper uses some preliminary pre-processing approaches to increase the sample set and improve the samples for corn disease. The Ebola optimization search (EOS) technique is used to reduce the classification errors of the 3D-CNN approach. As an outcome, the corn disease is predicted and classified accurately and more effectually. The accuracy of the proposed 3D-DCNN-EOS model is improved, and some necessary baseline tests are performed to project the efficacy of the anticipated model. The simulation is performed in the MATLAB 2020a environment, and the outcomes specify the significance of the proposed model over other approaches. The feature representation of the input data is learned effectually to trigger the model's performance. When the proposed method is compared to other existing techniques, it outperforms them in terms of precision, the area under receiver operating characteristics (AUC), f1 score, Kappa statistic error (KSE), accuracy, root mean square error value (RMSE), and recall. [ABSTRACT FROM AUTHOR]

A novel investigation of the bearing capacity of ring footings embedded in undrained anisotropic clays using a new hybrid soft computation technique that cooperates between finite element limit analysis (FELA) and artificial neural networks (ANNs) is presented in this paper. The undrained shear strength of clays is considered to be anisotropic and linearly increased with depth. The anisotropic undrained shear strength (AUS) model is employed to demonstrate the anisotropic behaviour of the undrained clays. The FLEA solutions of this problem based on lower bound (LB) and upper bound (UB) solutions are presented. The variations of bearing capacity factor (N) and the failure patterns of ring footings are examined by considering the changes in the geometric ratio of the internal radius and external radius (ri/ro), the embedment ratio (D/ro), the rates of increase of undrained shear with depth (ρro/suTC0), and the ratio of anisotropic (re). The results of the paper are presented in the simple dimensionless design charts and tables that show the relationships between N and all investigated parameters which will be beneficial to practitioners. Furthermore, the application of artificial neural networks (ANNs) is adopted to do sensitivity analysis and build an empirical equation for the complex relationship between the input variables and output bearing capacity factor. As the results, the radius ratio ri/ro is the most important variable on bearing capacity factor and the lower importance parameters are D/ro, ρro/suTC0, and re with relative importance 37.01, 30.37; 21.59; 11.03%, respectively. The proposed empirical equation is also proved to be an efficient method as evidenced by the high agreement between its predicted values and those from FELA with R2 of 99.95%. [ABSTRACT FROM AUTHOR]

Although current Siamese-based trackers have achieved impressive performance in visual object tracking by balancing accuracy and speed, their sensitivity to adversarial perturbation makes them face many risks in practical applications (e.g., automatic drive). In this paper, we first propose a general attack method against Siamese-based trackers, and then carefully design an online augmentation strategy based on adversarial examples to improve the tracking accuracy. To ensure both attack and augmentation trackers simultaneously, two opposing losses are proposed to push and pull the gap between the template patch and search regions. Specifically, most Siamese-based trackers employ the cross-correlation module to associate features of two branches. The similarity between the template patch and the search region will be reflected on the cross-correlation map, which is the focus of our method. SiamCAR is the main research object of this paper; the tracking accuracy after deception and enhancement is reduced by 64.62% and improved by 0.88%, respectively. We also transfer our attack method to SiamRPN++, SiamBAN, SiamGAT, and TrDiMP. Extensive experiments on the popular benchmark datasets indicate the effectiveness and universality of our method. [ABSTRACT FROM AUTHOR]

Various applications of control charts in the field of health-care monitoring and surveillance can be found in the literature. As one of the major categories, monitoring binary outcomes of cardiac surgeries with the aim of logistic regression model for the patients' death probability has been extended by different researchers. For this aim, statistical control charts, such as cumulative sum (CUSUM) chart, are applied as a risk-adjusted method to monitoring patients' mortality rate. However, employing machine learning techniques such as artificial neural network (ANN) has not been paid attention. So, this paper proposes a novel ANN-based control chart with a heuristic training approach to monitor binary surgical outcomes by control charts. Performance of the proposed approach is investigated and compared with existing studies, based on the average run lengths (ARL) criterion and the results demonstrated a superior performance of the proposed approach. Nevertheless, to demonstrate the application of the proposed approach, some real-life applications are also provided in this paper. Furthermore, robustness of the proposed method is investigated by considering Beta distribution for the death rate in addition to the logistic model. [ABSTRACT FROM AUTHOR]

The constrained 0-1 quadratic programming problem (CBQP) is an important problem of integer programming, and many combinatorial optimization problems can be converted to CBQP problem. Because BQP is NP-hard problem, the solving time and accuracy of traditional optimization algorithm are very dependent on the size of the problem, and the local optimal solution obtained by the heuristic algorithm is unstable. Deep learning algorithm has great advantages in solving such problems. In this paper, for the CBQP problem with linear constraints, we creatively apply two algorithms and models to solve it: the graph pointer network model (GPN) trained by hierarchical reinforcement learning (HRL), and the multi-head attention-based pointer network model trained by Advantage Actor-Critic (A2C), which greatly improves the solving speed, accuracy and constraint satisfaction rate of CBQP problems of different scales. At the same time, the bidirectional mask mechanism is innovatively introduced into the network so that the constraint satisfaction rate of the solution is very high. For the two algorithms, this paper solved the 0-1 knapsack (BKP) problem and the quadratic knapsack (QKP) problem, which are equivalent to the CBQP problem, and compared the results of the CBQP problem with different data distribution and scales. The experiment shows that no matter the objective function of the CBQP problem is linear or nonlinear, different data set distribution, or the scale, the pointer network trained by reinforcement learning in this paper has better results than traditional optimization algorithms in solving time, accuracy, stability and constraint satisfaction rate, and with the increase in the size of the problem, this advantage becomes more obvious. [ABSTRACT FROM AUTHOR]

The remarkable optoelectronic characteristics of hybrid metal halide perovskite semiconductors, such as high defect tolerance, extended carrier lifetime and diffusion length, and adjustable optical bandgap, have garnered much interest in the last decade. Therefore, this paper considers the experimental and mathematical modeling of triple-cation perovskite solar cells (PSCs) with two different device structures. It is challenging to construct a reliable mathematical model of triple-cation perovskite solar cells based on the three-diode model due to its complex nature. This is related to the perovskite materials' dynamics, nonlinearity, and sensitivity. This paper proposes a novel method incorporating a recent metaheuristic algorithm named COOT optimizer to estimate the optimal parameters of the three-diode equivalent circuit of triple-cation perovskite solar cells. The key idea is to use the swarm intelligence-based COOT to optimally achieve the PV panel's optimal parameters. The identification method benefits from the exploration and exploitation abilities of the COOT algorithm to obtain its parameters effortlessly and precisely. Two experiments are conducted in this work; the first is measured I–V datasets for a triple-cation perovskite (TC-per) solar cell at standard conditions. The second consists of the measured I–V datasets for a triple-cation modified perovskite (TCM-per) perovskite solar cell. During the optimization process, the nine unknown parameters of the three-diode model (TDM) are used as decision variables. The objective function to be minimized is the root-mean-square error (RMSE) between the measured and estimated data. An extensive comparative study is presented with other optimizers of the whale optimization algorithm (WOA), seagull optimization algorithm (SOA), sine cosine algorithm (SCA), ant lion optimization (ALO), and dragonfly algorithm (DA). Furthermore, statistical analysis of ANOVA is performed. The obtained results confirm the superiority of the proposed method in constructing a reliable model of the three-diode model of PSCs as it provides the least RMSE between the measured and estimated characteristics of 1.61E−05 in the first dataset. In contrast, the poorest algorithm (SCA) provides 1.03E−04. Similarly, in the second dataset of experiments, COOT achieves the least RMSE of 1.82E−05; meanwhile, the largest RMSE of 1.03E−04 using ALO. Based on the strong correlation between experimental and theoretical results using the COOT algorithm, we proposed a theoretical way (close to reality) to get the photovoltaic parameters of ideality factor and parasitic resistances in perovskite solar cell devices. [ABSTRACT FROM AUTHOR]

A nearly diagnosis and inference of Autism Spectrum Disorder (ASD) demands an automated intelligent system that can efficiently and accurately detect disorder from diverse dataset. The existing automated (machine/deep learning) state-of-the-art approaches have major limitation of being specific to the EEG dataset and have not been tested over EEG-datasets with varying metadata. Hence, this challenges how well the methods can be generalized. The present paper aims to propose and investigate a Bidirectional Stacked GRU network for ASD prediction considering diversity in EEG-signals recorded from different devices. The stacked layers in the proposed model structure performs complex mapping, nonlinear variation capturing, and temporal feature extraction for classifying individuals with ASD from Neurotypical individuals. To enhance the generalizability of the model and identify model robustness for practical implementation, the proposed framework is trained on three different EEG-dataset fed randomly to the system. The model in cross-validation framework showed an accuracy of 97% compared to the state-of-the-art methods ranging from 82 to 96% when applied on the same dataset. Furthermore, a receiver operating characteristic curve metric has quantified proposed model performance showing 0.998 as Area Under the Curve (AUC) compared to models with values in range 0.961 < AUC < 0.984. [ABSTRACT FROM AUTHOR]

In recent years, brain tumors have become one of the most common fatal diseases. Despite the existence of an important number of research studies on tumors, the proportion of research on predicting the growth of tumors remains insufficient due to the intricate nature of this research domain. Therefore, the presence of any application able to predict the growth of the tumor may have a role in eliminating the tumor by finding the appropriate treatment for it before it grows. This paper investigates tumor growth and presents a technique for tumor growth prediction based on the Discrete Time Markov Chain (DTMC) and K-Nearest Neighbor (KNN) algorithms. The design and development of this technique consists of a proposition of a stochastic model of tumor progression. This is followed by an extension of the mode to several cases that allow the derivation of new cases based on the study of predictive probabilities. The aim of this paper is to develop a model based on the KNN and DTMC algorithms that can classify tumors and predict the future state based on the current state of the tumor without the knowledge of the past state. In other words, all relevant information about the past and the present that would be useful in making predictions is available in the current state. In terms of performance evaluation metrics, the results show that the proposed method exceeds the existing methods with 97.65% accuracy, 71.65% specificity and 99.087% sensitivity. [ABSTRACT FROM AUTHOR]

Recognizing and analyzing human action is an important problem in many applications. Most studies focus on single motions, but human activity usually appears as a complex action sequence. The attendant problem is that segmenting and labeling action data manually is expensive and time-consuming, especially motions in professional fields. In this paper, we introduce Tai Chi as the background of action segmentation and propose a supervised method for Tai Chi action sequence segmentation based on trajectory primitives and geometric features. The concept of trajectory primitives is inspired by how humans recognize actions based on action fragments. They can be learned by unsupervised clustering through the self-organizing feature map. Also, we extract geometric features based on the content of motion. The work contains an experimental analysis of the proposed method on the Tai Chi dataset. In the experiment, we argued various parameters and considered the abnormal sequences. Experimental results demonstrate that our method achieves state-of-the-art performance. To allow future use by interested researchers, we release the Tai Chi dataset used in this paper. [ABSTRACT FROM AUTHOR]

Social bots are automated social media accounts governed by software and controlled by humans at the backend. Some bots have good purposes, such as automatically posting information about news and even to provide help during emergencies. Nevertheless, bots have also been used for malicious purposes, such as for posting fake news or rumour spreading or manipulating political campaigns. There are existing mechanisms that allow for detection and removal of malicious bots automatically. However, the bot landscape changes as the bot creators use more sophisticated methods to avoid being detected. Therefore, new mechanisms for discerning between legitimate and bot accounts are much needed. Over the past few years, a few review studies contributed to the social media bot detection research by presenting a comprehensive survey on various detection methods including cutting-edge solutions like machine learning (ML)/deep learning (DL) techniques. This paper, to the best of our knowledge, is the first one to only highlight the DL techniques and compare the motivation/effectiveness of these techniques among themselves and over other methods, especially the traditional ML ones. We present here a refined taxonomy of the features used in DL studies and details about the associated pre-processing strategies required to make suitable training data for a DL model. We summarize the gaps addressed by the review papers that mentioned about DL/ML studies to provide future directions in this field. Overall, DL techniques turn out to be computation and time efficient techniques for social bot detection with better or compatible performance as traditional ML techniques. [ABSTRACT FROM AUTHOR]

Financial forecasting has been greatly improved in recent years, but at long horizons, forecast accuracy may be low. Foreign trade plays an important role in introducing advanced technology and equipment, expanding employment opportunities, increasing government revenue and promoting economic growth. The main purpose of this paper is to predict the export volume of foreign trade through a back-propagation neural network (BPNN). To shed light on the characteristics of foreign trade and the export volume calculation method, this paper uses BPNN for forecasting. This method has a unique and advanced advantage in solving nonlinear problems and is very suitable for solving forecasting and decision-making problems related to nonlinear financial systems. By establishing multifactor and single-factor export forecasting models, the export volume of a single Chinese city in recent years is forecasted and compared with the actual export volume. The forecasting accuracy of our model is more than 30% higher than that of the traditional forecasting method, and the application is also approximately 15% more accurate than the traditional method, indicating that the method used in this paper is more in line with the growth trend of the actual export data. As a key part of the economic system, foreign trade is an important force driving economic growth. Therefore, developing foreign trade is a suitable path to pursue growth. [ABSTRACT FROM AUTHOR]

In today's severe situation of the global new crown virus raging, there are still efficiency problems in emergency resource scheduling, and there are still deficiencies in rescue standards. For the happiness and well-being of people's lives, adhering to the principle of a community with a shared future for mankind, the emergency resource scheduling system for urban public health emergencies needs to be improved and perfected. This paper mainly studies the optimization model of urban emergency resource scheduling, which uses the deep reinforcement learning algorithm to build the emergency resource distribution system framework, and uses the Deep Q Network path planning algorithm to optimize the system, to achieve the purpose of optimizing and upgrading the efficient scheduling of emergency resources in the city. Finally, through simulation experiments, it is concluded that the deep learning algorithm studied is helpful to the emergency resource scheduling optimization system. However, with the gradual development of deep learning, some of its disadvantages are becoming increasingly obvious. An obvious flaw is that building a deep learning-based model generally requires a lot of CPU computing resources, making the cost too high. [ABSTRACT FROM AUTHOR]

In recent years, image perception such as enhancement, classification and object detection with deep learning has achieved significant successes. However, in real world under extreme conditions, the training of a deep learning model often yields low accuracy, low efficiency in feature extraction and generalizability, due to the inner uncourteous and uninterpretable characteristics. In this paper, a maximal-entropy-attention-based convolutional neural network (MEA-CNN) framework is proposed. A maximum entropy algorithm is first used for image feature pre-extraction. An attention mechanism is then proposed by combining the extracted features on original images. By applying the mechanism, the key areas of an image are enhanced, and noised area can be ignored. Afterward, the processed images are transferred into region convolutional neural network, which is a well-known pre-trained CNN model, for further feature learning and extraction. Finally, two real-world experiments on traffic sign recognition and road surface condition monitoring are designed. The results show that the proposed framework has high testing accuracy, with improvements of 17% and 2.9%, compared with some other existing methods. In addition, the features extracted by the model are more easily interpretable. [ABSTRACT FROM AUTHOR]

An urban subway network system is a complex public transportation system. To compare rail transit braking digital command control strategies based on neural network, this article analyzes and studies the characteristics of subway vehicle driver controllers and their design methods from three aspects: mechanical, electrical and software-assisted design. The learning rule of the BP neural network is called the mentor system learning rule, which is a kind of error-correcting algorithm. In the learning and training process, the expected output value needs to be given. The weights and thresholds of the BP neural network are optimized by selecting the parameters of the SA algorithm. The search method of SA is heuristic, and it has the following advantages: The selection of the initial solution does not affect the optimal solution. The simplified model extracts the core data processing individual analysis. In this paper, the physical data are extracted from the physical entity operation process for analysis, and the twin model is established to extract the twin data for analysis. This paper uses the characteristics of physical data to test the modeling effect and utilizes the twin data to carry out algorithm experiments on physical data. The ultimate goal is to use twin data to predict the state information of physical entities. The network error in the scheme designed by the article is 6%. The smooth implementation of this research constitutes an important reference for the design of subway train network control systems in other cities in China. Therefore, this research has great application value. [ABSTRACT FROM AUTHOR]

Considering some problems of local linear embedding methods in semi-supervised scenarios, a robust scheme for generating soft labels is designed and a semi-supervised discrimination embedding method combined with soft labels in the kernel space is proposed in this paper. The method uses the kernel trick to perform the following related operations in the regenerative kernel Hilbert space. Firstly, in order to deal with the different distribution of labeled data, the confidence of generating soft labels is introduced in the label propagation process, and then the label density of data within the hypersphere whose unlabeled data is the center of the sphere is used to generate final soft labels. The scheme is experimentally demonstrated to generate more reliable soft labels even with lower labeling ratios. In order to make full use of the prior information provided by soft labels and the confidence of soft labels, a distance distortion function is used in feature learning to introduce the soft label prior information, and a penalty term about the global information is added to the optimization objective function, so that a more suitable low-dimensional representation for data classification can be obtained. Finally, the method is experimentally compared with various feature learning methods and visualized on handwritten digit dataset. The experiments show that this method performs well on various datasets of the UCI database and is successfully applied in image recognition, especially when the ratio of labeled data is in a low range. [ABSTRACT FROM AUTHOR]

Video communication gained wide popularity since it offers a more real-time mode of face-to-face interaction. This paper mainly aims to enhance the video transmission quality of multimedia applications via communication network security improvement and an adaptive resource allocation strategy. The main aim of the resource allocation strategy is to achieve efficient usage of spectrum resources since video communication utilizes the orthogonal subcarriers for data transmission and the need for conversion of non-flat channels to flat. An optimized Hybrid Deep Random Neural Network (HDRaNN) architecture is used to overcome the adaptive spectrum resource allocation problem in the single-frequency network transmission by taking into account the different time–frequency resources and regions for overlapping areas and the same time–frequency for non-overlapping areas. The Sheep Flock Optimization algorithm is used to minimize the network error rate of the HDRaNN architecture by optimizing the weights and biases. The basic purpose of communication network security in this paper is to ensure that data communicated over a network connection are safe and secure. The network security protocol offers protection from unauthorized data retrieval and attempts to obtain data. The protocols utilized for secure communication in the proposed technique are Secure Hypertext Transfer Protocol, Secure Socket Layer, Simple Network Management Protocol, and Secure File Transfer Protocol. This protocol also assures that unauthorized users, devices, or services do not have access to your network data and works on all network mediums and data types. The extensive experiments conducted using the proposed methodology show improvements in the video transmission quality in terms of high diversity gain, security, increased throughput, and minimized bit error rate. [ABSTRACT FROM AUTHOR]

Among various types of skin diseases, skin cancer is the deadliest form of the disease. This paper classifies seven types of skin diseases: Actinic keratosis and intraepithelial carcinoma, Basal cell carcinoma, Benign keratosis, Dermatofibroma, Melanoma, Melanocytic type, and Vascular lesions. The primary objective of this paper is to evaluate the performance of these deep learning networks on skin lesion images. The lesion classification is implemented through transfer learning on fourteen deep learning networks: AlexNet, GoogleNet, ResNet50, VGG16, VGG19, ResNet101, InceptionV3, InceptionResNetV2, SqueezeNet, DenseNet201, ResNet18, MobileNetV2, ShuffleNet and NasNetMobile. The dataset used for these experiments are from ISIC 2018 of about 10,154 images. The results show that DenseNet201 performs best with 0.825 accuracy and improves skin lesion classification under multiple diseases. The proposed work shows the various parameters, including the accuracy of all fourteen deep learning networks, which helped build an efficient automated classification model for multiple skin lesions. [ABSTRACT FROM AUTHOR]

Nonnegative matrix factorization (NMF) is a crucial method for image clustering. However, NMF may obtain low accurate clustering results because the factorization results contain no data structure information. In this paper, we propose an algorithm of nonnegative matrix factorization under structure constraints (SNMF). The factorization results of SNMF could maintain data global and local structure information simultaneously. In SNMF, the global structure information is captured by the cosine measure under the ℓ 2 norm constraints. Meanwhile, ℓ 2 norm constraints are utilized to get more discriminant data representations. A graph regularization term is employed to maintain the local structure. Effective updating rules are given in this paper. Moreover, the effects of different normalizations on similarities are investigated through experiments. On real datasets, the numerical results confirm the effectiveness of the SNMF. [ABSTRACT FROM AUTHOR]

Traffic sign detection is a challenging task for the unmanned driving system, especially for the detection of multi-scale targets and the real-time problem of detection. In the traffic sign detection process, the scale of the targets changes greatly, which will have a certain impact on the detection accuracy. Feature pyramid is widely used to solve this problem, but due to the diversity of traffic sign sizes, it cannot accurately extract multi-size feature maps, thus destroying the feature consistency between traffic signs. Moreover, in practical application, it is difficult for common methods to improve the detection accuracy of multi-scale traffic signs while ensuring real-time detection. In this paper, we propose an improved feature pyramid model, named AF-FPN, which utilizes the adaptive attention module (AAM) and feature enhancement module (FEM) to reduce the information loss in the process of feature map generation and enhance the representation ability of the feature pyramid. We replaced the original feature pyramid network in YOLOv5 with AF-FPN, which improves the detection performance for multi-scale targets of the YOLOv5 network under the premise of ensuring real-time detection. Furthermore, a new automatic learning data augmentation method is proposed to enrich the dataset and improve the robustness of the model to make it more suitable for practical scenarios. Extensive experimental results on the Tsinghua-Tencent 100 K (TT100K) dataset demonstrate that compared with several state-of-the-art methods, our method is more universal and superior. [ABSTRACT FROM AUTHOR]

Gestational diabetes mellitus (GDM) is one of the pregnancy complications that poses a significant risk on mothers and babies as well. GDM usually diagnosed at 22–26 of gestation. However, the early prediction is desirable as it may contribute to decrease the risk. The continuous monitoring for mother's vital signs helps in predicting any deterioration during pregnancy. The originality of this paper is to provide comprehensive framework for pregnancy women monitoring. The proposed Data Replacement and Prediction Framework consists of three layers which are: (i) IoT Layer, (ii) Fog Layer, and (iii) Cloud Layer. The first layer used IOT sensors to aggregate vital sings from pregnancies using invasive and noninvasive sensors. Then the vital signs transmitted to fog nodes to processed and finally stored in the cloud layer. The main contribution in this paper is located in the fog layer producing GDM module to implement two influential tasks which are: (i) Data Finding Methodology (DFM), and (ii) Explainable Prediction Algorithm (EPM) using DNN. First, the DFM is used to replace the unused data to free the cache space for the new incoming data items. The cache replacement is very important in the case of healthcare system as the incoming vital signs are frequent and must be replaced continuously. Second, the EPM is used to predict the incidence of GDM that may occur in the second trimester of the pregnancy. To evaluate our model, we extract data of 16,354 pregnancy women from medical information mart for intensive care (MIMIC III) benchmark dataset. For each woman, vital signs, demographic data and laboratory tests was aggregated. The results of the prediction model superior the state of the art (ACC = 0.957, AUC = 0.942). Regarding to explainability, we utilized Shapley additive explanation framework to provide local and global explanation for the developed models. Overall, the proposed framework is medically intuitive, allow the early prediction of GDM with cost effective solution. [ABSTRACT FROM AUTHOR]

Differential evolutionary (DE) algorithm is one of the most frequently used evolutionary computation method for the solution of non-differentiable, complex and discontinuous real value numerical problems. The analytical structure of the mutation and crossover operators used by DE and the initial values of the parameters of the relevant operators affect the problem-solving ability of DE. Unfortunately, there is no analytical method for selecting and initializing the best artificial genetic operators that DE can use to solve a problem. Therefore, there is a need to develop new evolutionary search methods that are parameter-free and insensitive to the artificial genetic operators they use. In this paper, the Bernstein–Levy differential evolution (BDE) algorithm, which has a unique elitist-mutation operator and a Bernstein polynomials-based stochastic parameter-free crossover operator, is introduced. The numerical problem-solving success of BDE is statistically evaluated by using 30 benchmark problems of CEC2014 in the numerical experiments presented. BDE's success in solving the related benchmark problems is statistically compared with six state-of-the-art comparison algorithms. In this paper, three real-world optimization problems are also solved by using the proposed algorithm, BDE. According to statistics generated from the experimental results, BDE is statistically better than comparison methods in solving the related real-world problems. [ABSTRACT FROM AUTHOR]

Human facial expression and emotion play pivotal roles in our day-to-day communication, and detecting them are one of the formidable tasks in the field of human–computer interfaces (HCI). This paper presents a new facial expressions detection method by exploiting textural image features such as local binary patterns (LBP), local ternary patterns (LTP) and completed local binary pattern (CLBP). This paper utilizes the advantages of textural features which are highly correlated with the facial expression changes and thereby trains a convolution neural network (CNN) model to detect facial expressions. The CNN model is trained on the images from the extended Cohn-Kanade (CK +), JAFEE and FER2013 datasets that are converted into LBP, LTP and CLBP image features. The performance of our facial expression recognition system is validated on modified CK+, JAFEE and FER2013 dataset. The results reported here illustrates that the CNN model yields better efficiency when we train the model with textural images. Moreover, we have shown that the CNN model trained with CLBP outperforms than that of with LBP and LTP images. In case of CLBP images, accuracies are 91.0%, 82.2% and 64.5% for CK+, JAFFE and FER2013 dataset, respectively. In case of LBP, accuracies are 79.5%, 75% and 58.45% and in case of LTP images accuracies are 89.2%, 77.3% and 62.79% for the datasets CK+, JAFFE and FER2013, respectively. [ABSTRACT FROM AUTHOR]

In India, rice crops are very significant. Rice cultivation comprises several phases, and it is crucial to keep an eye on the crop's development to avoid any leaf diseases and to provide a good yield. To avoid yield loss, crop diseases need to be determined at the initial stage. Deep learning-based pre-trained CNN architecture is used in this study to identify rice leaf diseases. This paper discusses four different CNN architectures to classify and identify healthy and diseased leaves such as Brown spot, Hispa, and Leaf Blast. Initially, to avoid vanishing gradient problems that degrade the performance of the Network, ResNet34 and ResNet50 are used. Even though the CNN model performs the feature extraction, Self-attention with ResNet18 and ResNet34 architecture is utilized to improve the feature selection process. As a result of enhanced feature extraction, the accuracy of rice leaf disease identification and classification has improved. Finally, high accuracy of 98.54% is achieved with the proposed ResNet34 with self-attention architecture when compared to other CNN models used in this paper. In terms of multiclass classification, the proposed model offers improved outcomes when compared to state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

ExSeisDat is designed using standard message passing interface (MPI) library for seismic data processing on high-performance super-computing clusters. These clusters are generally designed for efficient execution of complex tasks including large size IO. The IO performance degradation issues arise when multiple processes try accessing data from parallel networked storage. These complications are caused by restrictive protocols running by a parallel file system (PFS) controlling the disks and due to less advancement in storage hardware itself as well. This requires and leads to the tuning of specific configuration parameters to optimize the IO performance, commonly not considered by users focused on writing parallel application. Despite its consideration, the changes in configuration parameters are required from case to case. It adds up to further degradation in IO performance for a large SEG-Y format seismic data file scaling to petabytes. The SEG-Y IO and file sorting operations are the two of the main features of ExSeisDat. This research paper proposes technique to optimize these SEG-Y operations based on artificial neural networks (ANNs). The optimization involves auto-tuning of the related configuration parameters, using IO bandwidth prediction by the trained ANN models through machine learning (ML) process. Furthermore, we discuss the impact on prediction accuracy and statistical analysis of auto-tuning bandwidth results, by the variation in hidden layers nodes configuration of the ANNs. The results have shown the overall improvement in bandwidth performance up to 108.8% and 237.4% in the combined SEG-Y IO and file sorting operations test cases, respectively. Therefore, this paper has demonstrated the significant gain in SEG-Y seismic data bandwidth performance by auto-tuning the parameters settings on runtime by using an ML approach. [ABSTRACT FROM AUTHOR]

In this paper, we present a new approach for defining a dual proximity measure for intuitionistic fuzzy sets. The new approach utilizes an extended form of the restricted equivalence functions and receives their values as a two tuple. The two values in the two tuple are due to the dual character of the proximity measure under consideration. In fact, the computation of proximity between two intuitionistic fuzzy sets simultaneously provides the value of similarity as well as non-similarity between the intuitionistic fuzzy sets. So, the novel approach proposed in this paper provides a comprehensive information theoretic evaluation of intuitionistic fuzzy sets. Further, we investigate the application of the novel measure in pattern recognition and clustering analysis. We also contrast the performance of the proposed measure with the state-of-art in view of the structured linguistic variables, pattern classification and clustering analysis. The comparative analysis shows that the newly introduced two-valued proximity measure performs better in certain circumstances and encompasses the dualism of the human cognition. [ABSTRACT FROM AUTHOR]

Online medical consultation can significantly improve the efficiency of primary health care. Recently, many online medical question–answer services have been developed that connect the patients with relevant medical consultants based on their questions. Considering the linguistic variety in their question, social background identification of patients can improve the referral system by selecting a medical consultant with a similar social origin for efficient communication. This paper has proposed a novel fine-tuning strategy for the pre-trained transformers to identify the social origin of text authors. When fused with the existing adapter model, the proposed methods achieve an overall accuracy of 53.96% for the Arabic dialect identification task on the Nuanced Arabic Dialect Identification (NADI) dataset. The overall accuracy is 0.54% higher than the previous best for the same dataset, which establishes the utility of custom fine-tuning strategies for pre-trained transformer models. [ABSTRACT FROM AUTHOR]

Text simplification (TS) is the process of generating easy-to-understand sentences from a given sentence or piece of text. The aim of TS is to reduce both the lexical (which refers to vocabulary complexity and meaning) and syntactic (which refers to the sentence structure) complexity of a given text or sentence without the loss of meaning or nuance. In this paper, we present SimpLex, a novel simplification architecture for generating simplified English sentences. To generate a simplified sentence, the proposed architecture uses either word embeddings (i.e., Word2Vec) and perplexity, or sentence transformers (i.e., BERT, RoBERTa, and GPT2) and cosine similarity. The solution is incorporated into a user-friendly and simple-to-use software. We evaluate our system using two metrics, i.e., SARI and Perplexity Decrease. Experimentally, we observe that the transformer models outperform the other models in terms of the SARI score. However, in terms of perplexity, the word embedding-based models achieve the biggest decrease. Thus, the main contributions of this paper are: (1) We propose a new word embedding and transformer-based algorithm for text simplification; (2) we design SimpLex—a modular novel text simplification system—that can provide a baseline for further research; and (3) we perform an in-depth analysis of our solution and compare our results with two state-of-the-art models, i.e., LightLS as reported by Glavaš and Štajner (in: Proceedings of the 53rd annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing, 2015) and NTS-w2v as reported by Nisioi et al. (in: Proceedings of the 55th annual meeting of the association for computational linguistics, 2017). We also make the code publicly available online. [ABSTRACT FROM AUTHOR]

Stance detection is an evolving opinion mining research area motivated by the vast increase in the variety and volume of user-generated content. In this regard, considerable research has been recently carried out in the area of stance detection. In this study, we review the different techniques proposed in the literature for stance detection as well as other applications such as rumor veracity detection. Particularly, we conducted a systematic literature review of empirical research on the machine learning (ML) models for stance detection that were published from January 2015 to October 2022. We analyzed 96 primary studies, which spanned eight categories of ML techniques. In this paper, we categorize the analyzed studies according to a taxonomy of six dimensions: approaches, target dependency, applications, modeling, language, and resources. We further classify and analyze the corresponding techniques from each dimension's perspective and highlight their strengths and weaknesses. The analysis reveals that deep learning models that adopt a mechanism of self-attention have been used more frequently than the other approaches. It is worth noting that emerging ML techniques such as few-shot learning and multitask learning have been used extensively for stance detection. A major conclusion of our analysis is that despite that ML models have shown to be promising in this field, the application of these models in the real world is still limited. Our analysis lists challenges and gaps to be addressed in future research. Furthermore, the taxonomy presented can assist researchers in developing and positioning new techniques for stance detection-related applications. [ABSTRACT FROM AUTHOR]

The amount of digital data in the universe is growing at an exponential rate with the rapid development of digital information, and this reveals new machine learning methods. Learning algorithms using hyperboxes are a subsection of machine learning methods. Fuzzy min–max neural network (FMNN) are one of the most common and advanced methods using hyperboxes. FMNN is a special type of NeuroFuzzy system that combines the artificial neural network and fuzzy set into a common framework. This paper conducts an extensive bibliometric and network analysis of FMNN literature. Two hundred and sixty-two publications are analysed from the period of 1992–2022. Several analyses are realized in order to identify trends, challenges and key points in a more scientific and objective way that affect the development of knowledge in the FMNN domain. It can be seen from bibliometric analysis that there is rapid development in the last 10 years. Social network analysis results show that Chee Peng Lim is the most active author in the network. Besides, the modifications of FMNN are generally developed for classification. However, there are still potential future research opportunities for clustering. [ABSTRACT FROM AUTHOR]