Search

With the continuous development and progress of wireless self-organizing network communication technology, how to carry out long-distance cooperative control of multiple intelligences under the framework of an air–ground integrated wireless high-mobility self-organizing network has become a hot and difficult topic that needs to be solved urgently. This paper takes the air–ground integrated wireless high-mobility self-organizing network system as the basic framework and focuses on solving the long-distance cooperative fault-tolerant control of multi-intelligent bodies and the topological stability of a wireless mobile self-organizing network. To solve the above problems, a direct neural network with a robust adaptive fault-tolerant controller is designed in this paper. By constructing a symmetric population neural network model and combining it with the Lyapunov stabilization criterion, the system feedback matrix K has the ability of autonomous adaptive learning, and symmetrically distorts, rotates, or scales the training data to instantly adjust the system's fault-tolerant corrections and adaptive adjusting factors to resist the unknown disturbances and faults, to achieve the goals of multi-intelligent body stable control and the stable operation of a wireless high-mobility self-organizing network topology. Simulation results show that with the feedback adjustment of the multi-system under the designed controller, the multi-system as a whole has good fault-tolerant performance and autonomous learning approximation performance, and the tracking error asymptotically converges to zero. The experimental results show that the multi-flight subsystems fly stably, the air–ground integrated wireless high-mobility self-organizing network topology has good stability performance, and the maximum relative improvement of the topology stability performance is 50%. [ABSTRACT FROM AUTHOR]

This paper introduces a multidisciplinary conceptual perspective encompassing artificial intelligence (AI), artificial general intelligence (AGI), and cybernetics, framed within what we call the formalism of generalized neuromorphism. Drawing from recent advancements in computing, such as neuromorphic computing and spiking neural networks, as well as principles from the theory of open dynamical systems and stochastic classical and quantum dynamics, this formalism is tailored to model generic networks comprising abstract processing events. A pivotal aspect of our approach is the incorporation of the memory space and the intrinsic non-Markovian nature of the abstract generalized neuromorphic system. We envision future computations taking place within an expanded space (memory space) and leveraging memory states. Positioned at a high abstract level, generalized neuromorphism facilitates multidisciplinary applications across various approaches within the AI community. [ABSTRACT FROM AUTHOR]

Improving velocity forecasts of blood microflows could be useful in biomedical applications. We focus on estimating the velocity of the blood in capillaries. Modeling blood microflow in capillaries is a complex process. In this paper, we use artificial intelligence techniques for this modeling: more precisely, artificial neural networks (ANNs). The selected model is able to accurately forecast the velocity, with an  R 2  of 0.8992 comparing the forecast with the actual velocity. A key part of ANN model creation is selecting the appropriate parameters for the ANN, such as the number of neurons, the number of layers and the type of training algorithm used. A grid approach with 327,600 simulations was used. It is shown that there are substantial, statistically significant differences when different types of ANN structures are used. It is also shown that the proposed model is robust regarding the initial random initialization of weights in the ANN. Additionally, the sensitivity of the selected models to additional noise was also tested. [ABSTRACT FROM AUTHOR]

Given the substantial value and considerable training costs associated with deep neural network models, the field of deep neural network model watermarking has come to the forefront. While black-box model watermarking has made commendable strides, the current methodology for constructing poisoned images in the existing literature is simplistic and susceptible to forgery. Notably, there is a scarcity of black-box model watermarking techniques capable of discerning a unique user in a multi-user model distribution setting. For this reason, this paper proposes a novel black-box model watermarking method for unique identity identification, which is denoted as the ID watermarking of neural networks (IDwNet). Specifically, to enhance the distinguishability of deep neural network models in multi-user scenarios and mitigate the likelihood of poisoned image counterfeiting, this study develops a discrete cosine transform (DCT) and singular value decomposition (SVD)-based symmetrical embedding method to form the poisoned image. As this ID embedding method leads to indistinguishable deep features, the study constructs a poisoned adversary training strategy by simultaneously inputting clean images, poisoned images with the correct ID, and poisoned adversary images with incorrect IDs to train a deep neural network. Extensive simulation experiments show that the proposed scheme achieves excellent invisibility for the concealed ID, surpassing remarkably the state-of-the-art. In addition, the proposed scheme obtains a validation success rate exceeding 99% for the poisoned images at the cost of a marginal classification accuracy reduction of less than 0.5%. Moreover, even though there is only a 1-bit discrepancy between IDs, the proposed scheme still results in an accurate validation of user copyright. These results indicate that the proposed scheme is promising. [ABSTRACT FROM AUTHOR]

This Special Issue contains 2 reviews and 17 research papers related to the following topics: Time series forecasting [[1], [3], [5]]; Image analysis [[6]]; Medical applications [[7]]; Knowledge graph analysis [[9]]; Cybersecurity [[11], [13]]; Traffic analysis [[14]]; Agriculture [[16]]; Environmental data analysis [[17]]. In [[2]], a time series analysis was applied in a different manner: their prediction of the high stock dividend (HSD) was based on a sequence of typical machine learning approaches instead of state-of-the-art methods such as ARIMA or SMA. The authors of [[1]] focused on short time series forecasting in the domain of crime data (thefts, shoplifting, vehicular crimes, and burglaries in Mexico). In this paper, the authors attempt to answer the questions what is air traffic complexity and which air traffic data variables have greater impacts on increases in complexity?. [Extracted from the article]

Long series time forecasting has become a popular research direction in recent years, due to the ability to predict weather changes, traffic conditions and so on. This paper provides a comprehensive discussion of long series time forecasting techniques and their applications, using the Informer algorithm model as a framework. Specifically, we examine sequential time prediction models published in the last two years, including the tightly coupled convolutional transformer (TCCT) algorithm, Autoformer algorithm, FEDformer algorithm, Pyraformer algorithm, and Triformer algorithm. Researchers have made significant improvements to the attention mechanism and Informer algorithm model architecture in these different neural network models, resulting in recent approaches such as wavelet enhancement structure, auto-correlation mechanism, and depth decomposition architecture. In addition to the above, attention algorithms and many models show potential and possibility in mechanical vibration prediction. In recent state-of-the-art studies, researchers have used the Informer algorithm model as an experimental control, and it can be seen that the algorithm model itself has research value. The informer algorithm model performs relatively well on various data sets and has become a more typical algorithm model for time series forecasting, and its model value is worthy of in-depth exploration and research. This paper discusses the structures and innovations of five representative models, including Informer, and reviews the performance of different neural network structures. The advantages and disadvantages of each model are discussed and compared, and finally, the future research direction of long series time forecasting is discussed. [ABSTRACT FROM AUTHOR]

Wireless electroencephalography (EEG) has emerged as a critical interface between human cognitive processes and machine learning technologies in the burgeoning field of sensor communications. This paper presents a comprehensive review of advancements in wireless EEG communication and analysis, with an emphasis on their role in next-generation green wireless networks and industrial IoT. The review explores the efficacy of modulation techniques, such as amplitude-shift keying (ASK) and frequency-shift keying (FSK) in EEG data transmission, and emphasizes the transformative role of deep learning in the joint transmission and restoration of EEG signals. In addition, we propose a novel, energy-efficient approach to deep learning-based EEG analytics, designed to enhance wireless information transfer for industrial IoT applications. By applying an autoencoder to sample the EEG data and incorporating a hidden layer to simulate a noisy communication channel, we assessed the energy efficiency and reliability of the transmission. Our results demonstrate that the chosen network topology and parameters significantly affect not only data fidelity but also energy consumption, thus providing valuable insights for the development of sustainable and efficient wireless EEG systems in industrial IoT environments. A key aspect of our study is related to symmetry. Our results demonstrate that the chosen network topology and parameters significantly impact not only data fidelity but also energy fidelity and energy consumption, thus providing valuable insights for the development of sustainable and efficient wireless EEG systems in industrial IoT environments. Furthermore, we realized that the EEG data showed mildly marked symmetry. Neural networks must also exhibit asymmetric behavior for better performance. [ABSTRACT FROM AUTHOR]

In this paper, we propose using quiver representations as a tool for understanding artificial neural network algorithms. Specifically, we construct these algorithms by utilizing the group algebra of a finite cyclic group as vertices and convolution transformations as maps. We will demonstrate the neural network using convolution operation in the group algebra. The convolution operation in the group algebra that is formed by a finite cyclic group can be seen as a circulant matrix. We will represent a circulant matrix as a map from a cycle permutation matrix to a polynomial function. Using the permutation matrix, we will see some properties of the circulant matrix. Furthermore, we will examine some properties of circulant matrices using representations of finite symmetric groups as permutation matrices. Using the properties, we also examine the properties of moduli spaces formed by the actions of the change of basis group on the set of quiver representations. Through this analysis, we can compute the dimension of the moduli spaces. [ABSTRACT FROM AUTHOR]

Diabetic Retinopathy (DR) is an eye condition that mainly affects individuals who have diabetes and is one of the important causes of blindness in adults. As the infection progresses, it may lead to permanent loss of vision. Diagnosing diabetic retinopathy manually with the help of an ophthalmologist has been a tedious and a very laborious procedure. This paper not only focuses on diabetic retinopathy detection but also on the analysis of different DR stages, which is performed with the help of Deep Learning (DL) and transfer learning algorithms. CNN, hybrid CNN with ResNet, hybrid CNN with DenseNet are used on a huge dataset with around 3662 train images to automatically detect which stage DR has progressed. Five DR stages, which are 0 (No DR), 1 (Mild DR), 2 (Moderate), 3 (Severe) and 4 (Proliferative DR) are processed in the proposed work. The patient's eye images are fed as input to the model. The proposed deep learning architectures like CNN, hybrid CNN with ResNet, hybrid CNN with DenseNet 2.1 are used to extract the features of the eye for effective classification. The models achieved an accuracy of 96.22%, 93.18% and 75.61% respectively. The paper concludes with a comparative study of the CNN, hybrid CNN with ResNet, hybrid CNN with DenseNet architectures that highlights hybrid CNN with DenseNet as the perfect deep learning classification model for automated DR detection. [ABSTRACT FROM AUTHOR]

With the rise of mobile social networks, an increasing number of consumers are shopping through Internet platforms. The information asymmetry between consumers and producers has caused producers to misjudge the positioning of agricultural products in the market and damaged the interests of consumers. This imbalance between supply and demand is detrimental to the development of the agricultural market. Sentiment tendency analysis of after-sale reviews of agricultural products on the Internet could effectively help consumers evaluate the quality of agricultural products and help enterprises optimize and upgrade their products. Targeting problems such as non-standard expressions and sparse features in agricultural product reviews, this paper proposes a sentiment analysis algorithm based on an improved Bidirectional Encoder Representations from Transformers (BERT) model with symmetrical structure to obtain sentence-level feature vectors of agricultural product evaluations containing complete semantic information. Specifically, we propose a recognition method based on speech rules to identify the emotional tendencies of consumers when evaluating agricultural products and extract consumer demand for agricultural product attributes from online reviews. Our results showed that the F1 value of the trained model reached 89.86% on the test set, which is an increase of 7.05 compared with that of the original BERT model. The agricultural evaluation classification algorithm proposed in this paper could efficiently determine the emotion expressed by the text, which helps to further analyze network evaluation data, extract effective information, and realize the visualization of emotion. [ABSTRACT FROM AUTHOR]

Natural language generation (NLG) models combined with increasingly mature and powerful deep learning techniques have been widely used in recent years. Deployed NLG models in practical applications may be stolen or used illegally, and watermarking has become an important tool to protect the Intellectual Property (IP) of these deep models. Watermarking technique designs algorithms to embed watermark information and extracts watermark information for IP identification of NLG models can be seen as a symmetric signal processing problem. In terms of IP protection of NLG models, however, the existing watermarking approaches cannot provide reliable and timely model protection and prevent illegal users from utilizing the original performance of the stolen models. In addition, the quality of watermarked text sequences generated by some watermarking approaches is not high. In view of these, this paper proposes two embedding schemes to the hidden memory state of the RNN to protect the IP of NLG models for different tasks. Besides, we add a language model loss to the model decoder to improve the grammatical correctness of the output text sequences. During the experiments, it is proved that our approach does not compromise the performance of the original NLG models on the corresponding datasets and outputs high-quality text sequences, while forged secret keys will generate unusable NLG models, thus defeating the purpose of model infringement. Besides, we also conduct sufficient experiments to prove that the proposed model has strong robustness under different attacks. [ABSTRACT FROM AUTHOR]

Fractional differential equations (FDEs) arising in engineering and other sciences describe nature sufficiently in terms of symmetry properties. This paper proposes a numerical technique to approximate ordinary fractional initial value problems by applying fractional radial basis function neural network. The fractional derivative used in the method is considered Riemann-Liouville type. This method is simple to implement and approximates the solution of any arbitrary point inside or outside the domain after training the ANN model. Finally, three examples are presented to show the validity and applicability of the method. [ABSTRACT FROM AUTHOR]

Deep neural networks have achieved remarkable success in various fields of artificial intelligence. However, these models, which contain a large number of parameters, are widely distributed and disseminated by researchers, engineers, and even unauthorized users. Except for intelligent tasks, typically overparameterized deep neural networks have become new digital covers for data hiding, which may pose significant security challenges to AI systems. To address this issue, this paper proposes a symmetric steganalysis scheme specifically designed for neural networks trained for image classification tasks. The proposed method focuses on detecting the presence of additional data without access to the internal structure or parameters of the host network. It employs a well-designed method based on histogram distribution to find the optimal decision threshold, with a symmetric determining rule where the original networks and stego networks undergo two highly symmetrical flows to generate the classification labels; the method has been shown to be practical and effective. SVM and ensemble classifiers were chosen as the binary classifier for their applicability to feature vectors output from neural networks based on different datasets and network structures. This scheme is the first of its kind, focusing on steganalysis for neural networks based on the distribution of network output, compared to conventional digital media such as images, audio, and video. Overall, the proposed scheme offers a promising approach to enhancing the security of deep neural networks against data hiding attacks. [ABSTRACT FROM AUTHOR]

A significant challenge in robust model predictive control (MPC) is the online computational complexity. This paper proposes a learning-based approach to accelerate online calculations by combining recent advances in deep learning with robust MPC. The use of soft constraint variables addresses feasibility issues in the robust MPC design, while the employment of a symmetrical structure deep neural network (DNN) approximates the robust MPC control law. The symmetry of the network structure facilitates the training process. The use of soft constraints expands the feasible region and also increases the complexity of the training data, making the network difficult to train. To overcome this issue, a dataset construction method is employed. The performance of the proposed method is demonstrated through simulated examples, and the proposed algorithm can be applied to control systems in various fields such as aerospace, three-dimensional printing, optical imaging, and chemical production. [ABSTRACT FROM AUTHOR]

Versatile Video Coding (VVC) is the latest video coding standard, but currently, most steganographic algorithms are based on High-Efficiency Video Coding (HEVC). The concept of symmetry is often adopted in deep neural networks. With the rapid rise of new multimedia, video steganography shows great research potential. This paper proposes a VVC steganographic algorithm based on Coding Units (CUs). Considering the novel techniques in VVC, the proposed steganography only uses chroma CUs to embed secret information. Based on modifying the partition modes of chroma CUs, we propose four different embedding levels to satisfy the different needs of visual quality, capacity and video bitrate. In order to reduce the bitrate of stego-videos and improve the distortion caused by modifying them, we propose a novel convolutional neural network (CNN) as an additional in-loop filter in the VVC codec to achieve better restoration. Furthermore, the proposed steganography algorithm based on chroma components has an advantage in resisting most of the video steganalysis algorithms, since few VVC steganalysis algorithms have been proposed thus far and most HEVC steganalysis algorithms are based on the luminance component. Experimental results show that the proposed VVC steganography algorithm achieves excellent performance on visual quality, bitrate cost and capacity. [ABSTRACT FROM AUTHOR]

The rutting depth is an important index to evaluate the damage degree of the pavement. Therefore, establishing an accurate rutting depth prediction model can guide pavement design and provide the necessary basis for pavement maintenance. However, the sample size of pavement rutting depth data is small, and the sampling is not standardized, which makes it hard to establish a prediction model with high accuracy. Based on the data of RIOHTrack's asphalt pavement structure, this study builds a reliable data-augmented model. In this paper, different asphalt rutting data augmented models based on Gaussian radial basis neural networks are constructed with the temperature and loading of asphalt pavements as the main features. Experimental results show that the method outperforms classical machine learning methods in data augmentation, with an average root mean square error of 3.95 and an average R-square of 0.957. Finally, the augmented data of rutting depth is constructed for training, and multiple neural network models are used for prediction. Compared with unaugmented data, the prediction accuracy is increased by 50%. [ABSTRACT FROM AUTHOR]

As a popular technique for swapping faces with someone else's in images or videos through deep neural networks, deepfake causes a serious threat to the security of multimedia content today. However, because counterfeit images are usually compressed when propagating over the Internet, and because the compression factor used is unknown, most of the existing deepfake detection models have poor robustness for the detection of compressed images with unknown compression factors. To solve this problem, we notice that an image has a high similarity with its compressed image based on symmetry, and this similarity is not easily affected by the compression factor, so this similarity feature can be used as an important clue for compressed deepfake detection. A TCNSC (Two-branch Convolutional Networks with Similarity and Classifier) method that combines compression factor independence is proposed in this paper. The TCNSC method learns two feature representations from the deepfake image, i.e., similarity of the image and its compressed counterpart and authenticity of the deepfake image. A joint training strategy is then utilized for feature extraction, in which the similarity characteristics are obtained by similarity learning while obtaining authenticity characteristics, so the proposed TCNSC model is trained for robust feature learning. Experimental results on the FaceForensics++ (FF++) dataset show that the proposed method significantly outperforms all competing methods under three compression settings of high-quality (HQ), medium-quality (MQ), and low-quality (LQ). For the LQ, MQ, and HQ settings, TCNSC achieves 91.8%, 93.4%, and 95.3% in accuracy, and outperforms the state-of-art method (Xception-RAW) by 16.9%, 10.1%, and 4.1%, respectively. [ABSTRACT FROM AUTHOR]

In recent years, the social network has become popular and people have started trading transactions on the Internet. Many counterfeit websites have begun to appear which create websites with counterfeit products or use the digital advertiser's services to promote their websites on social media. Malicious sellers disguise high-quality products to attract consumers since buyers cannot receive transparent information. If there is asymmetry information, a secondary market will be formed. To solve the above problems, this research explored the machine-learning-based method to classify counterfeit and legitimate websites with symmetry information. The data set is 1612 websites used in this paper and a total of 15 feature values and takes 804 counterfeit websites and 808 legitimate websites. The Random Forest and Deep Neural Network algorithms were used to classify fake websites. This study also used statistical tests, such as Chi-square and ANOVA detection, to compare the importance of features in feature selection. The experiment results show that the RF accuracy is 99.2% and the DNN accuracy is 93.2%. The RF Precision and Recall are 100% and 98.5%, respectively. The DNN Precision and Recall are less than RF. Then, the RF F1-score is 99.2% which is higher than DNN. [ABSTRACT FROM AUTHOR]

The transmission of high-speed data over communication channels is the function of digital communication systems. Due to linear and nonlinear distortions, data transmitted through this process is distorted. In a communication system, the channel is the medium through which signals are transmitted. The useful signal received at the receiver becomes corrupted because it is associated with noise, ISI, CCI, etc. The equalizers function at the front end of the receiver to eliminate these factors, and they are designed to make them work efficiently with proper network topology and parameters. In the case of highly dispersive and nonlinear channels, it is well known that neural network-based equalizers are more effective than linear equalizers, which use finite impulse response filters. An alternative approach to training neural network-based equalizers is to use metaheuristic algorithms. Here, in this work, to develop the symmetry-based efficient channel equalization in wireless communication, this paper proposes a modified form of bat algorithm trained with ANN for channel equalization. It adopts a population-based and local search algorithm to exploit the advantages of bats' echolocation. The foremost initiative is to boost the flexibility of both the variants of the proposed algorithm and the utilization of proper weight, topology, and the transfer function of ANN in channel equalization. To evaluate the equalizer's performance, MSE and BER can be calculated by considering popular nonlinear channels and adding nonlinearities. Experimental and statistical analyses show that, in comparison with the bat as well as variants of the bat and state-of-the-art algorithms, the proposed algorithm substantially outperforms them significantly, based on MSE and BER. [ABSTRACT FROM AUTHOR]

It is generally observed that aquatic organisms have symmetric abilities to produce oxygen (O 2) and fix carbon dioxide (C O 2) . A simulation model with time-dependent parameters was recently proposed to better understand the symmetric effects of accelerated climate change on coastal ecosystems. Changes in environmental elements and marine life are two examples of variables that are expected to change over time symmetrically. The sustainability of each equilibrium point is examined in addition to proving the existence and accuracy of the proposed model. To support the conclusions of this research compared to other studies, numerical simulations of the proposed model and a case study are investigated. This paper proposes an integrated bibliographical analysis of artificial neural networks (ANNs) using the Reverse-Propagation with Levenberg–Marquaradt Scheme (RP-LMS) to evaluate the main properties and applications of ANNs. The results obtained by RP-LMS show how to prevent global warming by improving the management of marine fish resources. The reference dataset for greenhouse gas emissions, environmental temperature, aquatic population, and fisheries population (GAPF) is obtained by varying parameters in the numerical Adam approach for different scenarios. The accuracy of the proposed RP-LMS neural network is demonstrated using mean square error (MSE), regression plots, and best-fit output. According to RP-LMS, the current scenario of rapid global warming will continue unabated over the next 50 years, damaging marine ecosystems, particularly fish stocks. [ABSTRACT FROM AUTHOR]

In the paper, shunting inhibitory cellular neural networks with impulses and the generalized piecewise constant argument are under discussion. The main modeling novelty is that the impulsive part of the systems is symmetrical to the differential part. Moreover, the model depends not only on the continuous time, but also the generalized piecewise constant argument. The process is subdued to Poisson stable inputs, which cause the new type of recurrent signals. The method of included intervals, recently introduced approach of recurrent motions checking, is effectively utilized. The existence and asymptotic properties of the unique Poisson stable motion are investigated. Simulation examples for results are provided. Finally, comparing impulsive shunting inhibitory cellular neural networks with former neural network models, we discuss the significance of the components of our model. [ABSTRACT FROM AUTHOR]

In this paper, a tracking algorithm based on the residual neural network model and machine learning is proposed. Compared with the widely used VGG network, the residual neural network has deeper characteristic layers and special additional layer structure, which break the symmetry of the network and reduce the degradation of the neural network. The additional layer and convolution layer are used for feature fusion to represent the target. The multi-features of the object can be captured by using the developed algorithm, so that the accuracy of tracking can be improved in some complex scenarios. In addition, we defined a new measure to calculate the similarity of different image regions and find the optimal matched region. The search area is delimited according to the continuity of the target motion, which improves the real-time performance of tracking. The experimental results illustrate that the proposed algorithm achieved a higher accuracy while taking into account the real time performance, especially in dealing with some complex scenarios such as deformation, rotation changes and background clutters, in comparison with the Multi-Domain Network (MDNet) algorithm based on a convolutional neural network. [ABSTRACT FROM AUTHOR]

In this paper, we study a new model that represents the symmetric connection between capacitance–voltage and Schottky diode. This model has a symmetrical shape towards the horizontal direction. In recent times, works conducted on artificial neural network structure, which is one of the greatest actual artificial intelligence apparatuses used in various fields, stated that artificial neural networks are apparatuses that proposal very high forecast performance by the side of conventional structures. In the current investigation, an artificial neural network structure has been generated to guess the capacitance voltage productions of the Schottky diode with organic polymer edge, contingent on the frequency with a symmetrical shape. Of the dataset, 130 were grouped for training, 28 for validation, and 28 for testing. In order to evaluate the effect of the number of neurons on the prediction accuracy, three different models with different neuron numbers have been developed. This study, in which an artificial neural network model, although well-trained, could not predict the output values correctly, is a first in the literature. With this aspect, the study can be considered as a pioneering study that brings a novelty to the literature. [ABSTRACT FROM AUTHOR]

Coronavirus disease (COVID-19), which affects the whole world, continues to spread. This disease has infected and killed millions of people worldwide. To limit the rate of spread of the disease, early detection should be provided and then the infected person should be quarantined. This paper proposes a Deep Learning-based application for early and accurate diagnosis of COVID-19. Compared to other studies, this application's biggest difference and contribution are that it uses Tree Seed Algorithm (TSA)-optimized Artificial Neural Networks (ANN) to classify deep architectural features. Previous studies generally use fully connected layers for end-to-end learning classification. However, this study proves that even relatively simple AlexNet features can be classified more accurately with the TSA-ANN structure. The proposed hybrid model provides diagnosis with 98.54% accuracy for COVID-19 disease, which shows asymmetric distribution on Computed Tomography (CT) images. As a result, it is shown that using the proposed classification strategy, the features of end-to-end architectures can be classified more accurately. [ABSTRACT FROM AUTHOR]

Big Data is impacting and changing the way we live, and its core lies in the use of machine learning to extract valuable information from huge amounts of data. Optimization problems are a common problem in many steps of machine learning. In the face of complex optimization problems, evolutionary computation has shown advantages over traditional methods. Therefore, many researchers are working on improving the performance of algorithms for solving various optimization problems in machine learning. The equilibrium optimizer (EO) is a member of evolutionary computation and is inspired by the mass balance model in environmental engineering. Using particles and their concentrations as search agents, it simulates the process of finding equilibrium states for optimization. In this paper, we propose an improved equilibrium optimizer (IEO) based on a decreasing equilibrium pool. IEO provides more sources of information for particle updates and maintains a higher population diversity. It can discard some exploration in later stages to enhance exploitation, thus achieving a better search balance. The performance of IEO is verified using 29 benchmark functions from IEEE CEC2017, a dynamic economic dispatch problem, a spacecraft trajectory optimization problem, and an artificial neural network model training problem. In addition, the changes in population diversity and computational complexity brought by the proposed method are analyzed. [ABSTRACT FROM AUTHOR]

In this paper, an assembly sequence planning system, based on artificial neural networks, is developed. The problem of artificial neural network itself is largely related to symmetry at every stage of its creation. A new modeling scheme, known as artificial neural networks, takes into account selected DFA (Design for Assembly) rating factors, which allow the evaluation of assembly sequences, what are the input data to the network learning and then estimate the assembly time. The input to the assembly neural network procedure is the sequences for assembling the parts, extended by the assembly's connection graph that represents the parts and relations between these parts. The operation of a neural network is to predict the assembly time based on the training dataset and indicate it as an output value. The network inputs are data based on selected DFA factors influencing the assembly time. The proposed neural network model outperforms the available assembly sequence planning model in predicting the optimum assembly time for the mechanical parts. In the neural networks, the BFGS (the Broyden–Fletcher–Goldfarb–Shanno algorithm), steepest descent and gradient scaling algorithms are used. The network efficiency was checked from a set of 20,000 test networks with randomly selected parameters: activation functions (linear, logistic, tanh, exponential and sine), the number of hidden neurons, percentage set of training and test dataset. The novelty of the article is therefore the use of parts of the DFA methodology and the neural network to estimate assembly time, under specific production conditions. This approach allows, according to the authors, to estimate which mechanical assembly sequence is the most advantageous, because the simulation results suggest that the neural predictor can be used as a predictor for an assembly sequence planning system. [ABSTRACT FROM AUTHOR]

Currently, deep-learning-based methods have been widely used in fault diagnosis to improve the diagnosis efficiency and intelligence. However, most schemes require a great deal of labeled data and many iterations for training parameters. They suffer from low accuracy and over fitting under the few-shot scenario. In addition, a large number of parameters in the model consumes high computing resources, which is far from practical. In this paper, a multi-scale and lightweight Siamese network architecture is proposed for the fault diagnosis with few samples. The architecture proposed contains two main modules. The first part implements the feature vector extraction of sample pairs. It is composed of two lightweight convolutional networks with shared weights symmetrically. Multi-scale convolutional kernels and dimensionality reduction are used in these two symmetric networks to improve feature extraction and reduce the total number of model parameters. The second part takes charge of calculating the similarity of two feature vectors to achieve fault classification. The proposed network is validated by multiple datasets with different loads and speeds. The results show that the model has better accuracy, fewer model parameters and a scale compared to the baseline approach through our experiments. Furthermore, the model is also proven to have good generalization capability. [ABSTRACT FROM AUTHOR]

Current acoustic modeling methods face problems such as complex processes or inaccurate sound absorption coefficients, etc. Therefore, this paper studies the topic. Firstly, the material samples were prepared, and standing wave tube method experiments were conducted. Material acoustic data were obtained, while a model using improved genetic algorithm and neural network was subsequently proposed. Secondly, the acoustic data obtained from the experiment were analyzed; a neural network structure was designed; and the training, verification, and test data were all divided. In order to facilitate data processing, a symmetrical method was used to inversely normalize all the data. Thirdly, by the design of real coding scheme, fitness function, crossover, and mutation operators, an improved genetic algorithm was proposed to obtain the optimal solution, as the initial weight and threshold, which were then input into the neural network along with the training and verification data. Finally, the test data were input into the trained neural network in order to test the model. The test results and statistical analysis showed that compared with other algorithms, the proposed model has the lower root mean squared error (RMSE) value, the maximum coefficient of determination (R2) value, and shorter convergence time. [ABSTRACT FROM AUTHOR]

Most trackers are only dependent on the first frame as a template to search for and locate the target location in subsequent videos. However, objects may undergo occlusions and deformation over time, and the original snapshot of the object can no longer accurately reflect the current appearance of the object, which greatly limits the performance improvement of the tracker. In this paper, we propose a novel Siamese tracking algorithm with symmetric structure called SiamRDT, which reflects the latest appearance and motion states of objects through additional reliable dynamic templates. The model decides whether to update the dynamic template according to the quality estimation score and employs the attention mechanism to enhance the reliability of the dynamic template, adopting the depth-wise correlation algorithm to integrate the initial template and the dynamic template and the search area. Through reliable dynamic templates and credible initial templates, the model can fuse initial-state information and the latest-state information of objects. We conduct sufficient ablation experiments to illustrate the effectiveness of the proposed key components, and the tracker achieves very competitive results on four large-scale tracking benchmarks, namely OTB100, GOT-10k, LaSOT, and TrackingNet. Our tracker achieves an AO score of 61.3 on GOT-10k, a precision score of 56.5 on LaSOT, a precision score of 69.3 on TrackingNet, and a precision score of 90.5 on OTB100. [ABSTRACT FROM AUTHOR]

Graph representation learning has become a mainstream method for processing network structured data, and most graph representation learning methods rely heavily on labeling information for downstream tasks. Since labeled information is rare in the real world, adopting self-supervised learning to solve the graph neural network problem is a significant challenge. Currently, existing graph neural network approaches attempt to maximize mutual information for self-supervised learning, which leads to a large amount of redundant information in the graph representation and thus affects the performance of downstream tasks. Therefore, the self-supervised graph information bottleneck (SGIB) proposed in this paper uses the symmetry and asymmetry of graphs to establish comparative learning and introduces the information bottleneck theory as a loss training model. This model extracts the common features of both views and the independent features of each view by maximizing the mutual information estimation between the local high-level representation of one view and the global summary vector of the other view. It also removes redundant information not relevant to the target task by minimizing the mutual information between the local high-level representations of the two views. Based on the extensive experimental results of three public datasets and two large-scale datasets, it has been shown that the SGIB model can learn higher quality node representations and that several classical network analysis experiments such as node classification and node clustering can be improved compared to existing models in an unsupervised environment. In addition, an in-depth network experiment is designed for in-depth analysis, and the results show that the SGIB model can also alleviate the over-smoothing problem to a certain extent. Therefore, we can infer from different network analysis experiments that it would be an effective improvement of the performance of downstream tasks through introducing information bottleneck theory to remove redundant information. [ABSTRACT FROM AUTHOR]

The linear algebraic system generated by the discretization of fractional differential equations has asymmetry, and the numerical solution of this kind of problems is more complex than that of symmetric problems due to the nonlocality of fractional order operators. In this paper, we propose the artificial neural network (ANN) algorithm to approximate the solutions of the fractional differential equations (FDEs). First, we apply truncated series expansion terms to replace unknown function in equations, then we use the neural network to get series coefficients, and the obtained series solution can make the norm value of loss function reach a satisfactory error. In the part of numerical experiments, the results verify that the proposed ANN algorithm can make the numerical results achieve high accuracy and good stability. [ABSTRACT FROM AUTHOR]

Mosaic, Rust, Brown spot, and Alternaria leaf spot are the four common types of apple leaf diseases. Early diagnosis and accurate identification of apple leaf diseases can control the spread of infection and ensure the healthy development of the apple industry. The existing research uses complex image preprocessing and cannot guarantee high recognition rates for apple leaf diseases. This paper proposes an accurate identifying approach for apple leaf diseases based on deep convolutional neural networks. It includes generating sufficient pathological images and designing a novel architecture of a deep convolutional neural network based on AlexNet to detect apple leaf diseases. Using a dataset of 13,689 images of diseased apple leaves, the proposed deep convolutional neural network model is trained to identify the four common apple leaf diseases. Under the hold-out test set, the experimental results show that the proposed disease identification approach based on the convolutional neural network achieves an overall accuracy of 97.62%, the model parameters are reduced by 51,206,928 compared with those in the standard AlexNet model, and the accuracy of the proposed model with generated pathological images obtains an improvement of 10.83%. This research indicates that the proposed deep learning model provides a better solution in disease control for apple leaf diseases with high accuracy and a faster convergence rate, and that the image generation technique proposed in this paper can enhance the robustness of the convolutional neural network model. [ABSTRACT FROM AUTHOR]

The goal of this paper is to compare and analyze the forecasting performance of two artificial neural network models (i.e., MLP (multi-layer perceptron) and DNN (deep neural network)), and to conduct an experimental investigation by data flow, not economic flow. In this paper, we investigate beyond the scope of simple predictions, and conduct research based on the merits and data of each model, so that we can predict and forecast the most efficient outcomes based on analytical methodology with fewer errors. In particular, we focus on identifying two models of neural networks (NN), a multi-layer perceptron (i.e., MLP) model and an excellent model between the neural network (i.e., DNN) model. At this time, predictability and accuracy were found to be superior in the DNN model, and in the MLP model, it was found to be highly correlated and accessible. The major purpose of this study is to analyze the performance of MLP and DNN through a practical approach based on an artificial neural network stock forecasting method. Although we do not limit S&P (i.e., Standard&Poor's 500 index) to escape other regional exits in order to see the proper flow of capital, we first measured S&P data for 100 months (i.e., 407 weeks) and found out the following facts: First, the traditional artificial neural network (ANN) model, according to the specificity of each model and depending on the depth of the layer, shows the model of the prediction well and is sensitive to the index data; Second, comparing the two models, the DNN model showed better accuracy in terms of data accessibility and prediction accuracy than MLP, and the error rate was also shown in the weekly and monthly data; Third, the difference in the prediction accuracy of each model is not statistically significant. However, these results are correlated with each other, and are considered robust because there are few error rates, thanks to the accessibility to various other prediction accuracy measurement methodologies. [ABSTRACT FROM AUTHOR]

This paper deals with a method for removing a ghost target that is not a real object from the output of a multiple object-tracking algorithm. This method uses an artificial neural network (multilayer perceptron) and introduces a structure, learning, verification, and evaluation method for the artificial neural network. The implemented system was tested at an intersection in a city center. Results from a 28-min measurement were 88% accurate when the multilayer perceptron for ghost target classification successfully detected the ghost targets, and 6.7% inaccurate when ghost targets were mistaken for actual targets. This method is expected to contribute to the advancement of intelligent transportation systems if the weaknesses revealed during the evaluation of the system are complemented and refined. [ABSTRACT FROM AUTHOR]

Passive video forensics has drawn much attention in recent years. However, research on detection of object-based forgery, especially for forged video encoded with advanced codec frameworks, is still a great challenge. In this paper, we propose a deep learning-based approach to detect object-based forgery in the advanced video. The presented deep learning approach utilizes a convolutional neural network (CNN) to automatically extract high-dimension features from the input image patches. Different from the traditional CNN models used in computer vision domain, we let video frames go through three preprocessing layers before being fed into our CNNmodel. They include a frame absolute difference layer to cut down temporal redundancy between video frames, a max pooling layer to reduce computational complexity of image convolution, and a high-pass filter layer to enhance the residual signal left by video forgery. In addition, an asymmetric data augmentation strategy has been established to get a similar number of positive and negative image patches before the training. The experiments have demonstrated that the proposed CNN-based model with the preprocessing layers has achieved excellent results. [ABSTRACT FROM AUTHOR]

Despite recent progress in the study of complex systems, reconstruction of damaged networks due to random and targeted attack has not been addressed before. In this paper, we formulate the network reconstruction problem as an identification of network structure based on much reduced link information. Furthermore, a novel method based on multilayer perceptron neural network is proposed as a solution to the problem of network reconstruction. Based on simulation results, it was demonstrated that the proposed scheme achieves very high reconstruction accuracy in small-world network model and a robust performance in scale-free network model. [ABSTRACT FROM AUTHOR]

Cost estimation is an essential issue in feasibility studies in civil engineering. Many different methods can be applied to modelling costs. These methods can be divided into several main groups: (1) artificial intelligence, (2) statistical methods, and (3) analytical methods. In this paper, the multivariate regression (MVR) method, which is one of the most popular linear models, and the artificial neural network (ANN) method, which is widely applied to solving different prediction problems with a high degree of accuracy, have been combined to provide a cost estimate model for a shovel machine. This hybrid methodology is proposed, taking the advantages of MVR and ANN models in linear and nonlinear modelling, respectively. In the proposed model, the unique advantages of the MVR model in linear modelling are used first to recognize the existing linear structure in data, and, then, the ANN for determining nonlinear patterns in preprocessed data is applied. The results with three indices indicate that the proposed model is efficient and capable of increasing the prediction accuracy. [ABSTRACT FROM AUTHOR]

Flexibility of manufacturing systems is an essential factor in maintaining the competitiveness of industrial production. Flexibility can be defined in several ways and according to several factors, but in order to obtain adequate results in implementing a flexible manufacturing system able to compete on the market, a high level of autonomy (free of human intervention) of the manufacturing system must be achieved. There are many factors that can disturb the production process and reduce the autonomy of the system, because of the need of human intervention to overcome these disturbances. One of these factors is tool wear. The aim of this paper is to present an experimental study on the possibility to determine the state of tool wear in a flexible manufacturing cell environment, using image acquisition and processing methods. [ABSTRACT FROM AUTHOR]

Most existing Siamese trackers mainly use a pre-trained convolutional neural network to extract target features. However, due to the weak discrimination of the target and background information of pre-trained depth features, the performance of the Siamese tracker can be significantly degraded when facing similar targets or changes in target appearance. This paper proposes a multi-channel-aware and adaptive hierarchical deep features module to enhance the discriminative ability of the tracker. Firstly, through the multi-channel-aware deep features module, the importance values of feature channels are obtained from both the target details and overall information, to identify more important feature channels. Secondly, by introducing the adaptive hierarchical deep features module, the importance of each feature layer can be determined according to the response value of each frame, so that the hierarchical features can be integrated to represent the target, which can better adapt to changes in the appearance of the target. Finally, the proposed two modules are integrated into the Siamese framework for target tracking. The Siamese network used in this paper is a two-input branch symmetric neural network with two input branches, and they share the same weights, which are widely used in the field of target tracking. Experiments on some Benchmarks show that the proposed Siamese tracker has several points of improvement compared to the baseline tracker. [ABSTRACT FROM AUTHOR]

For passive radar detection system, radar waveform recognition is an important research area. In this paper, we explore an automatic radar waveform recognition system to detect, track and locate the low probability of intercept (LPI) radars. The system can classify (but not identify) 12 kinds of signals, including binary phase shift keying (BPSK) (barker codes modulated), linear frequency modulation (LFM), Costas codes, Frank code, P1-P4 codesand T1-T4 codeswith a low signal-to-noise ratio (SNR). It is one of the most extensive classification systems in the open articles. A hybrid classifier is proposed, which includes two relatively independent subsidiary networks, convolutional neural network (CNN) and Elman neural network (ENN). We determine the parameters of the architecture to make networks more effectively. Specifically, we focus on how the networks are designed, what the best set of features for classification is and what the best classified strategy is. Especially, we propose several key features for the classifier based on Choi-Williams time-frequency distribution (CWD). Finally, the recognition system is simulated by experimental data. The experiments show the overall successful recognition ratio of 94.5% at an SNR of -2 dB. [ABSTRACT FROM AUTHOR]

This paper first analyzes the one-dimensional Gabor function and expands it to a two-dimensional one. The two-dimensional Gabor function generates the two-dimensional Gabor wavelet through measure stretching and rotation. At last, the two-dimensional Gabor wavelet transform is employed to extract the image feature information. Based on the back propagation (BP) neural network model, the image intelligent test model based on the Gabor wavelet and the neural network model is built. The human face image detection is adopted as an example. Results suggest that, although there are complex textures and illumination variations on the images of the face database named AT&T, the detection accuracy rate of the proposed method can reach above 0.93. In addition, extensive simulations based on the Yale and extended Yale B datasets further verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Many high formwork systems are currently equipped with health monitoring systems, and the analysis of the data obtained can determine whether high formwork is a hazard. Therefore, the post-processing of monitoring data has become an issue of widespread concern. In this paper, we discussed the fitting effect of the symmetrical high formwork monitoring data using the autoregressive–moving-average (ARMA) model and the back propagation neural networks (BPNN) combined model to process. In the actual project, the symmetry of the high formwork system allows the analysis of local monitoring results to be well extended to the whole. For the establishment of the ARMA model, the accurate judgment of the model order has a significant impact. In this paper, back propagation neural networks (BPNN) are used to simulate the ARMA process. The order of the ARMA model is estimated by determining the optimal neural network structure, which is suitable for linear or nonlinear sequences. We validated this approach from the ARMA model data simulated in Monte Carlo and compared it with the Akaike information criterion (AIC) and Bayesian information criterion (BIC). The length of the sequence, the coefficients and the order of the ARMA model are considered as factors that influence the judgment effect. Under different conditions, the BPNN always shows an accuracy rate of more than 90%, while the BIC only has a higher accuracy rate when the model order is low and the judgment efficiency of the AIC is below 50%. Finally, the proposed method successfully modeled the stress sequence and obtained the stress change trend. Compared with AIC and BIC, the efficiency of the processing time series is increased by about 50% when an order is obtained by BPNN. [ABSTRACT FROM AUTHOR]

Deepfake is one of the applications that is deemed harmful. Deepfakes are a sort of image or video manipulation in which a person's image is changed or swapped with that of another person's face using artificial neural networks. Deepfake manipulations may be done with a variety of techniques and applications. A quintessential countermeasure against deepfake or face manipulation is deepfake detection method. Most of the existing detection methods perform well under symmetric data distributions, but are still not robust to asymmetric datasets variations and novel deepfake/manipulation types. In this paper, for the identification of fake faces in videos, a new multistream deep learning algorithm is developed, where three streams are merged at the feature level using the fusion layer. After the fusion layer, the fully connected, Softmax, and classification layers are used to classify the data. The pre-trained VGG16 model is adopted for transferred CNN1stream. In transfer learning, the weights of the pre-trained CNN model are further used for training the new classification problem. In the second stream (transferred CNN2), the pre-trained VGG19 model is used. Whereas, in the third stream, the pre-trained ResNet18 model is considered. In this paper, a new large-scale dataset (i.e., World Politicians Deepfake Dataset (WPDD)) is introduced to improve deepfake detection systems. The dataset was created by downloading videos of 20 different politicians from YouTube. Over 320,000 frames were retrieved after dividing the downloaded movie into little sections and extracting the frames. Finally, various manipulations were performed to these frames, resulting in seven separate manipulation classes for men and women. In the experiments, three fake face detection scenarios are investigated. First, fake and real face discrimination is studied. Second, seven face manipulations are performed, including age, beard, face swap, glasses, hair color, hairstyle, smiling, and genuine face discrimination. Third, performance of deepfake detection system under novel type of face manipulation is analyzed. The proposed strategy outperforms the prior existing methods. The calculated performance metrics are over 99%. [ABSTRACT FROM AUTHOR]

The plastic modifications in synaptic connectivity is primarily from changes triggered by neuromodulated dopamine signals. These activities are controlled by neuromodulation, which is itself under the control of the brain. The subjective brain's self-modifying abilities play an essential role in learning and adaptation. The artificial neural networks with neuromodulated plasticity are used to implement transfer learning in the image classification domain. In particular, this has application in image detection, image segmentation, and transfer of learning parameters with significant results. This paper proposes a novel approach to enhance transfer learning accuracy in a heterogeneous source and target, using the neuromodulation of the Hebbian learning principle, called NDHTL (Neuromodulated Dopamine Hebbian Transfer Learning). Neuromodulation of plasticity offers a powerful new technique with applications in training neural networks implementing asymmetric backpropagation using Hebbian principles in transfer learning motivated CNNs (Convolutional neural networks). Biologically motivated concomitant learning, where connected brain cells activate positively, enhances the synaptic connection strength between the network neurons. Using the NDHTL algorithm, the percentage of change of the plasticity between the neurons of the CNN layer is directly managed by the dopamine signal's value. The discriminative nature of transfer learning fits well with the technique. The learned model's connection weights must adapt to unseen target datasets with the least cost and effort in transfer learning. Using distinctive learning principles such as dopamine Hebbian learning in transfer learning for asymmetric gradient weights update is a novel approach. The paper emphasizes the NDHTL algorithmic technique as synaptic plasticity controlled by dopamine signals in transfer learning to classify images using source-target datasets. The standard transfer learning using gradient backpropagation is a symmetric framework. Experimental results using CIFAR-10 and CIFAR-100 datasets show that the proposed NDHTL algorithm can enhance transfer learning efficiency compared to existing methods. [ABSTRACT FROM AUTHOR]

The accurate segmentation of retinal images is a basic step in screening for retinopathy and glaucoma. Most existing retinal image segmentation methods have insufficient feature information extraction. They are susceptible to the impact of the lesion area and poor image quality, resulting in the poor recovery of contextual information. This also causes the segmentation results of the model to be noisy and low in accuracy. Therefore, this paper proposes a multi-scale and multi-branch convolutional neural network model (multi-scale and multi-branch network (MSMB-Net)) for retinal image segmentation. The model uses atrous convolution with different expansion rates and skip connections to reduce the loss of feature information. Receiving domains of different sizes captures global context information. The model fully integrates shallow and deep semantic information and retains rich spatial information. The network embeds an improved attention mechanism to obtain more detailed information, which can improve the accuracy of segmentation. Finally, the method of this paper was validated on the fundus vascular datasets, DRIVE, STARE and CHASE datasets, with accuracies/F1 of 0.9708/0.8320, 0.9753/0.8469 and 0.9767/0.8190, respectively. The effectiveness of the method in this paper was further validated on the optic disc visual cup DRISHTI-GS1 dataset with an accuracy/F1 of 0.9985/0.9770. Experimental results show that, compared with existing retinal image segmentation methods, our proposed method has good segmentation performance in all four benchmark tests. [ABSTRACT FROM AUTHOR]

Artificial Neural Networks (ANNs) were created inspired by the neural networks in the human brain and have been widely applied in speech processing. The application areas of ANN include: Speech recognition, speech emotion recognition, language identification, speech enhancement, and speech separation, amongst others. Likewise, given that speech processing performed by humans involves complex cognitive processes known as auditory attention, there has been a growing amount of papers proposing ANNs supported by deep learning algorithms in conjunction with some mechanism to achieve symmetry with the human attention process. However, while these ANN approaches include attention, there is no categorization of attention integrated into the deep learning algorithms and their relation with human auditory attention. Therefore, we consider it necessary to have a review of the different ANN approaches inspired in attention to show both academic and industry experts the available models for a wide variety of applications. Based on the PRISMA methodology, we present a systematic review of the literature published since 2000, in which deep learning algorithms are applied to diverse problems related to speech processing. In this paper 133 research works are selected and the following aspects are described: (i) Most relevant features, (ii) ways in which attention has been implemented, (iii) their hypothetical relationship with human attention, and (iv) the evaluation metrics used. Additionally, the four publications most related with human attention were analyzed and their strengths and weaknesses were determined. [ABSTRACT FROM AUTHOR]

This paper proposes a method for discovering the primary objects in single images by learning from videos in a purely unsupervised manner—the learning process is based on videos, but the generated network is able to discover objects from a single input image. The rough idea is that an image typically consists of multiple object instances (like the foreground and background) that have spatial transformations across video frames and they can be sparsely represented. By exploring the sparsity representation of a video with a neural network, one may learn the features of each object instance without any labels, which can be used to discover, recognize, or distinguish object instances from a single image. In this paper, we consider a relatively simple scenario, where each image roughly consists of a foreground and a background. Our proposed method is based on encoder-decoder structures to sparsely represent the foreground, background, and segmentation mask, which further reconstruct the original images. We apply the feed-forward network trained from videos for object discovery in single images, which is different from the previous co-segmentation methods that require videos or collections of images as the input for inference. The experimental results on various object segmentation benchmarks demonstrate that the proposed method extracts primary objects accurately and robustly, which suggests that unsupervised image learning tasks can benefit from the sparsity of images and the inter-frame structure of videos. [ABSTRACT FROM AUTHOR]

Machine learning is a very important approach to pattern classification. This paper provides a better insight into Incremental Attribute Learning (IAL) with further analysis as to why it can exhibit better performance than conventional batch training. IAL is a novel supervised machine learning strategy, which gradually trains features in one or more chunks. Previous research showed that IAL can obtain lower classification error rates than a conventional batch training approach. Yet the reason for that is still not very clear. In this study, the feasibility of IAL is verified by mathematical approaches. Moreover, experimental results derived by IAL neural networks on benchmarks also confirm the mathematical validation. [ABSTRACT FROM AUTHOR]

In recent years, artificial intelligence techniques have become fundamental parts of various engineering research activities and practical realizations. The advantages of the neural networks, as one of the main artificial intelligence methods, make them very appropriate for different engineering design problems. However, the qualitative properties of the neural networks' states are extremely important for their design and practical performance. In addition, the variety of neural network models requires the formulation of appropriate qualitative criteria. This paper studies a class of discrete Bidirectional Associative Memory (BAM) neural networks of the Cohen–Grossberg type that can be applied in engineering design. Due to the nature of the proposed models, they are very suitable for symmetry-related problems. The notion of the practical stability of the states with respect to sets is introduced. The practical stability analysis is conducted by the method of the Lyapunov functions. Examples are presented to verify the proposed criteria and demonstrate the efficiency of the results. Since engineering design is a constrained processes, the obtained stability of the sets' results can be applied to numerous engineering design tasks of diverse interest. [ABSTRACT FROM AUTHOR]

Ensemble learning of swarm intelligence evolutionary algorithm of artificial neural network (ANN) is one of the core research directions in the field of artificial intelligence (AI). As a representative member of swarm intelligence evolutionary algorithm, shuffled frog leaping algorithm (SFLA) has the advantages of simple structure, easy implementation, short operation time, and strong global optimization ability. However, SFLA is susceptible to fall into local optimas in the face of complex and multi-dimensional symmetric function optimization, which leads to the decline of convergence accuracy. This paper proposes an improved shuffled frog leaping algorithm of threshold oscillation based on simulated annealing (SA-TO-SFLA). In this algorithm, the threshold oscillation strategy and simulated annealing strategy are introduced into the SFLA, which makes the local search behavior more diversified and the ability to escape from the local optimas stronger. By using multi-dimensional symmetric function such as drop-wave function, Schaffer function N.2, Rastrigin function, and Griewank function, two groups (i: SFLA, SA-SFLA, TO-SFLA, and SA-TO-SFLA; ii: SFLA, ISFLA, MSFLA, DSFLA, and SA-TO-SFLA) of comparative experiments are designed to analyze the convergence accuracy and convergence time. The results show that the threshold oscillation strategy has strong robustness. Moreover, compared with SFLA, the convergence accuracy of SA-TO-SFLA algorithm is significantly improved, and the median of convergence time is greatly reduced as a whole. The convergence accuracy of SFLA algorithm on these four test functions are 90%, 100%, 78%, and 92.5%, respectively, and the median of convergence time is 63.67 s, 59.71 s, 12.93 s, and 8.74 s, respectively; The convergence accuracy of SA-TO-SFLA algorithm on these four test functions is 99%, 100%, 100%, and 97.5%, respectively, and the median of convergence time is 48.64 s, 32.07 s, 24.06 s, and 3.04 s, respectively. [ABSTRACT FROM AUTHOR]