Search

In response to the issue of short-term fluctuations in photovoltaic (PV) output due to Cloud movement, this paper proposes a method for forecasting short-term PV output based on a Depthwise Separable Convolution Visual Geometry Group (DSCVGG) and a Deep Gate Recurrent Neural Network (DGN). Initially, a cloud motion prediction model is constructed using a DSCVGG, which achieves edge recognition and motion prediction of clouds by replacing the previous convolution layer of the pooling layer in VGG with a depthwise separable convolution. Subsequently, the output results of the DSCVGG network, along with historical PV output data, are introduced into a Deep Gate Recurrent Unit Network (DGN) to establish a PV output prediction model, thereby achieving precise prediction of PV output. Through experiments on actual data, the Mean Absolute Error (MAE) and Mean Squared Error (MSE) of our model are only 2.18% and 5.32 x 10-5, respectively, which validates the effectiveness, accuracy, and superiority of the proposed method. This provides new insights and methods for improving the stability of PV power generation. [ABSTRACT FROM AUTHOR]

With advancements in communication systems and measurement technologies, smart grids have become more observable and controllable, evolving into cyberphysical-power systems (CPPS). The impact of network security and secondary equipment on power system stability has become more evident. To support the existing grid toward a smart grid scenario, smart metering plays a vital role at the customer end side. Cyber-Physical systems are vulnerable to cyber-attacks and various techniques have been evolved to detect a cyber attack in the smart grid. Weighted trust-based models are suggested as one of the most effective security mechanisms. A hardware-in-loop CPPS co-simulation platform is established to facilitate the theoretical study of CPPS and the formulation of grid operation strategies. This paper examines current co-simulation platform schemes and highlights the necessity for a real-time hard-ware-in-the-loop platform to accurately simulate cyber-attack processes. This consideration takes into account the fundamental differences in modeling between power and communication systems. The architecture of the co-simulation platform based on RT-LAB and OPNET is described, including detailed modeling of the power system, communication system, and security and stability control devices. Additionally, an analysis of the latency of the co-simulation is provided. The paper focuses on modeling and implementing methods for addressing DDOS attacks and man-in-the-middle at-tacks in the communication network. The results from simulating a 7-bus system show the effectiveness and rationality of the co-simulation platform that has been designed. [ABSTRACT FROM AUTHOR]

With the proliferation of the Internet, network complexities for both commercial and state organizations have significantly increased, leading to more sophisticated and harder-to-detect network attacks. This evolution poses substantial challenges for intrusion detection systems, threatening the cybersecurity of organizations and national infrastructure alike. Although numerous deep learning techniques such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and graph neural networks (GNNs) have been applied to detect various network attacks, they face limitations due to the lack of standardized input data, affecting model accuracy and performance. This paper proposes a novel preprocessing method for flow data from network intrusion detection systems (NIDSs), enhancing the efficacy of a graph neural network model in malicious flow detection. Our approach initializes graph nodes with data derived from flow features and constructs graph edges through the analysis of IP relationships within the system. Additionally, we propose a new graph model based on the combination of the graph neural network (GCN) model and SAGEConv, a variant of the GraphSAGE model. The proposed model leverages the strengths while addressing the limitations encountered by the previous models. Evaluations on two IDS datasets, CICIDS-2017 and UNSW-NB15, demonstrate that our model outperforms existing methods, offering a significant advancement in the detection of network threats. This work not only addresses a critical gap in the standardization of input data for deep learning models in cybersecurity but also proposes a scalable solution for improving the intrusion detection accuracy. [ABSTRACT FROM AUTHOR]

A coverage prediction model helps network operators find coverage gaps, plan base station locations, evaluate quality of service, and build radio maps for spectrum sharing, interference management, localization, etc. Existing coverage prediction models rely on the height and transmission power of the base station, or the assistance of a path loss model. All of these increase the complexity of large-scale coverage predictions. In this paper, we propose a multi-modal model, DNN-SS, which combines a DNN (deep neural network) and SS (semantic segmentation) to perform coverage prediction for mobile networks. Firstly, DNN-SS filters the samples with a geospatial-temporal moving average filter algorithm, and then uses a DNN to extract numerical features. Secondly, a pre-trained model is used to perform semantic segmentation of satellite images of the measurement area. Thirdly, a DNN is used to extract features from the results after semantic segmentation to form environmental features. Finally, the prediction model is trained on the dataset consisting of numerical features and environmental features. The experimental results on campus show that for random location prediction, the model achieves a RMSE (Root Mean Square Error) of 1.97 dB and a MAE (Mean Absolute Error) of 1.41 dB, which is an improvement of 10.86% and 10.2%, respectively, compared with existing models. For the prediction of a test area, the RMSE and MAE of the model are 4.32 dB and 3.45 dB, respectively, and the RMSE is only 0.22 dB lower than that of existing models. However, the DNN-SS model does not need the height, transmission power, and antenna gain of the base station, or a path loss model, which makes it more suitable for large-scale coverage prediction. [ABSTRACT FROM AUTHOR]

In this paper, the No. 30201 working face of a specific colliery was determined as the study area in the Yushen mining area, China. The objective of this paper is to determine the optimal position for pressure regulation measures during the final mining stage. A mechanical calculation model for stabilized coal pillar was developed. The analytical solution for the front abutment pressure function was obtained. Limit equilibrium theory and beam theory were employed to compute the critical width value of the stabilized coal pillar. The analysis focused on examining the spatiotemporal relationship between the rotational deformation of the main roof and the stability of the retracement channel. The study utilized numerical simulation to investigate the failure characteristics of the surrounding rock and the stress redistribution in the stabilized coal pillar within the working face. Through comprehensive analysis, a reasonable width of 15 m for the stabilized coal pillar was determined and successfully implemented in field practices. A method of using Artificial Neural Network (ANN) to select the stabilized coal pillar width was proposed. The input characteristics of ANN were determined through theoretical analysis. Four models of BP, WOA-BP, PSO-BP, and CPSO-BP were trained. The calculation accuracy of each model is evaluated by three quantitative metrics: MAE, MRE, and RMSE. The MAE value of the CPSOBP model is 0.9489, showing a reduction of 70.87% compared to the BP model, 55.84% compared to the WOA-BP model, and 51.26% compared to the PSOBP model. The MRE value is 0.0559, which is 71.51%, 56.29%, and 53.24% lower than the other models, respectively. The RMSE value is 1.0617, which is 68.92%, 56.13%, and 53.03% lower than other models, respectively. The four models were employed to compute the width of the stabilized coal pillar. The values for the BP, WOA-BP, PSO-BP, and CPSO-BP models were 12.7 m, 16.3 m, 14.1 m, and 15.2 m, respectively, indicating that the CPSO-BP model can effectively determine the width of the stabilized coal pillar. [ABSTRACT FROM AUTHOR]

In recent years, there has been a significant increase in the design of neural network models for solving math word problems (MWPs). These neural solvers have been designed with various architectures and evaluated on diverse datasets, posing challenges in fair and effective performance evaluation. This paper presents a comparative study of representative neural solvers, aiming to elucidate their technical features and performance variations in solving different types of MWPs. Firstly, an in-depth technical analysis is conducted from the initial deep neural solver DNS to the state-of-the-art GPT-4. To enhance the technical analysis, a unified framework is introduced, which comprises highly reusable modules decoupled from existing MWP solvers. Subsequently, a testbed is established to conveniently reproduce existing solvers and develop new solvers by combing these reusable modules, and finely regrouped datasets are provided to facilitate the comparative evaluation of the designed solvers. Then, comprehensive testing is conducted and detailed results for eight representative MWP solvers on five finely regrouped datasets are reported. The comparative analysis yields several key findings: (1) Pre-trained language model-based solvers demonstrate significant accuracy advantages across nearly all datasets, although they suffer from limitations in math equation calculation. (2) Models integrated with tree decoders exhibit strong performance in generating complex math equations. (3) Identifying and appropriately representing implicit knowledge hidden in problem texts is crucial for improving the accuracy of math equation generation. Finally, the paper also discusses the major technical challenges and potential research directions in this field. The insights gained from this analysis offer valuable guidance for future research, model development, and performance optimization in the field of math word problem solving. [ABSTRACT FROM AUTHOR]

The simultaneous localization and mapping (SLAM) technique provides long-term near-seafloor navigation for autonomous underwater vehicles (AUVs). However, the stability of the interest point detector (IPD) remains challenging in the seafloor environment. This paper proposes an optical–acoustic fusion interest point detector (OAF-IPD) using a monocular camera and forward-looking sonar. Unlike the artificial feature detectors most underwater IPDs adopt, a deep neural network model based on unsupervised interest point detector (UnsuperPoint) was built to reach stronger environmental adaption. First, a feature fusion module based on feature pyramid networks (FPNs) and a depth module were integrated into the system to ensure a uniform distribution of interest points in depth for improved localization accuracy. Second, a self-supervised training procedure was developed to adapt the OAF-IPD for unsupervised training. This procedure included an auto-encoder framework for the sonar data encoder, a ground truth depth generation framework for the depth module, and optical–acoustic mutual supervision for the fuse module training. Third, a non-rigid feature filter was implemented in the camera data encoder to mitigate the interference from non-rigid structural objects, such as smoke emitted from active vents in hydrothermal areas. Evaluations were conducted using open-source datasets as well as a dataset captured by the research team of this paper from pool experiments to prove the robustness and accuracy of the newly proposed method. [ABSTRACT FROM AUTHOR]

Accurate prediction of estuarine salinity can effectively mitigate the adverse effects of saltwater intrusion and help ensure the safety of water resources in estuarine regions. Presently, diverse data-driven models, mainly neural network models, have been employed to predict tidal estuarine salinity and obtained considerable achievements. Due to the nonlinear and nonstationary features of estuarine salinity sequences, this paper proposed a multi-factor salinity prediction model using an enhanced Long Short-Term Memory (LSTM) network. To improve prediction accuracy, input variables of the model were determined through Grey Relational Analysis (GRA) combined with estuarine dynamic analysis, and hyperparameters for the LSTM model were optimized using a multi-strategy Improved Sparrow Search Algorithm (ISSA). The proposed ISSA-LSTM model was applied to predict salinity at the Cangqian and Qibao stations in the Qiantang Estuary of China, based on measured data from 2011–2012. The model performance is evaluated by mean absolute error (MAE), mean absolute percentage error (MAPE), root mean square error (RMSE), and Nash-Sutcliffe efficiency (NSE). The results show that compared to other models including Back Propagation neural network (BP), Gate Recurrent Unit (GRU), and LSTM model, the new model has smaller errors and higher prediction accuracy, with NSE improved by 8–32% and other metrics (MAP, MAPE, RMSE) improved by 15–67%. Meanwhile, compared with LSTM optimized with the original SSA (SSA-LSTM), MAE, MAPE, and RMSE values of the new model decreased by 13–16%, 15–16%, and 11–13%, and NSE value increased by 5–6%, indicating that the ISSA has a better hyperparameter optimization ability than the original SSA. Thus, the model provides a practical solution for the rapid and precise prediction of estuarine salinity. [ABSTRACT FROM AUTHOR]

This paper proposes a novel method for Virtual Metrology (VM) in plasma etch processes based on analysis of all time and wavelength samples of Optical Emission Spectroscopy (OES) signals. The new method flattens each OES signal into a single vector, after which Singular Value Decomposition (SVD) is performed on the matrix formed by vectors of flattened OES signals in the training dataset. Low rank SVD projections of flattened and standardized OES recordings served as inputs for Ridge Regression, Artificial Neural Network, and Random Forest based VM models. A VM study is then conducted on a dataset gathered from a major 300 mm wafer fabrication facility, showing that the use of newly proposed SVD-based OES features consistently outperformed benchmark VM model features. Additional analysis of feature importance performed based on the analytically tractable Ridge Regression VM model form demonstrated distinct time-frequency patterns of OES signal portions that were highly informative for prediction of relevant Critical Dimensions, clearly justifying the need to use the entire OES signals for VM. [ABSTRACT FROM AUTHOR]

This research paper explores the realm of fault detection in distributed motors through the vision of the Internet of electrical drives. This paper aims at employing artificial neural networks supported by the data collected by the Internet of distributed devices. Cross-verification of results offers reliable diagnosis of industrial motor faults. The proposed methodology involves the development of a cyber–physical system architecture and mathematical modeling framework for efficient fault detection. The mathematical model is designed to capture the intricate relationships within the cyber–physical system, incorporating the dynamic interactions between distributed motors and their edge controllers. Fast Fourier transform is employed for signal processing, enabling the extraction of meaningful frequency features that serve as indicators of potential faults. The artificial neural network based fault detection system is integrated with the solution, utilizing its ability to learn complex patterns and adapt to varying motor conditions. The effectiveness of the proposed framework and model is demonstrated through experimental results. The experimental setup involves diverse fault scenarios, and the system's performance is evaluated in terms of accuracy, sensitivity, and false positive rates. [ABSTRACT FROM AUTHOR]

In order to solve the industrial fake film problem produced by repeated imaging in the field of nondestructive testing, this paper proposes an image similarity comparison algorithm of X-ray film based on the Siamese neural network. Firstly, in order to accurately locate and detect weld areas from high-resolution X-ray film, a robust location and detection algorithm based on the Gaussian function is proposed. Next, in order to solve the problem that the deep learning model system extracts features according to squares by default, which results in the disappearance of film features with high horizontal and vertical features, effective weld regions are used and processed in blocks. Then, a small sample data set for weld similarity discrimination is established by using each block region, and an industrial fake film discrimination model based on twin neural networks is constructed. Finally, the corresponding weights are set for different fake feature information areas, and a similarity comparison system for industrial fake film detection is proposed. The experiment shows that the method in this paper can not only accurately locate the weld area but also accurately detect the fake film in the industry, avoiding the influence of the geometric transformation of the image and the insufficient number of data sets in the process of similarity comparison, and has a good detection effect. [ABSTRACT FROM AUTHOR]

The land is the material basis for human survival, and the contradiction between people and land has become increasingly prominent. The land ecological problem has gradually become a hot spot of concern. It is imperative to make a scientific evaluation of the land ecological quality and propose reasonable and feasible improvement measures and recommendations. At present, domestic research on environmental cost and environmental cost degradation mostly focuses on theoretical discussion, and there are few applications and practical research on enterprise environmental cost management. Based on the principle of protecting the ecological environment, this paper creates an ecological service assessment model to assess the real economic cost of land use development projects. From small community projects to large-scale national projects, because environmental costs are difficult to estimate, this paper uses the recovery cost method and the preventive expenditure method to quantify environmental costs. The cost of environmental degradation mainly comes from water pollution and air pollution. This paper uses the pollution function method to quantify the cost of environmental degradation. The InVEST model is used to evaluate the value of ecosystem services, and the BP neural network method is used to optimize the ecosystem service model, and the sensitivity analysis of the data is used to feedback the impact of the project on ecosystem services. The ecosystem service model based on neural network optimization makes the accuracy of data measurement results reaching 99.7%, which makes the model having a good generalization. Taking a paper mill as an example, this paper evaluates environmental costs by resource consumption cost, environmental degradation value and environmental governance cost, and estimates environmental degradation costs by major environmental governance costs. Finally, the environmental cost and environmental degradation cost are integrated, and the ecosystem service model is established. The neural network model was established in the Matlab environment based on the InVEST model, and the model simulation results of the ecosystem service system were obtained. Compared with the InVEST results, the results of this paper have better authenticity and market utilization value. Although a paper mill was used as an example, the system was evaluated and the evaluation results were analysed. Compared with the actual situation, there is a certain reliability. However, due to the limited data, the number of verifications is insufficient for the system. It is hoped that more data can be verified later to ensure its reliability. [ABSTRACT FROM AUTHOR]

This special issue of the circuits, systems and signal processing journal focuses on recent advances and improvements in leading-edge integrated machine learning algorithms and signal processing systems. Although signal processing has been studied over several decades, the computer industry is only beginning to understand how signal processing techniques can be well integrated for the development of human-machine interfaces with the advancement of machine learning algorithms. As advances in signal processing tools and machine learning algorithms are becoming more powerful in terms of functionality and communicative capabilities, their contribution to the journal of circuits, system and signal processing is becoming more significant. [Extracted from the article]

The integral invariant coordinate I and Roederer's L or L* are proxies for the second and third adiabatic invariants respectively, that characterize charged particle motion in a magnetic field. Their usefulness lies in the fact that they are expressed in more instructive ways than their counterparts: I is equivalent to the path length of the particle motion between two mirror points, whereas L*, although dimensionless, is roughly equivalent to the distance from the center of the Earth to the equatorial point of a given field line, in units of Earth radii, in the simplified case of a dipole magnetic field. However, care should be taken when calculating the above invariants, as the assumption of their adiabaticity is not valid everywhere in the Earth's magnetosphere. This is not clearly stated in state-of-the-art models that are widely used for the calculation of these invariants. In this paper, we compare the values of I and L* as calculated using LANLstar, an artificial neural network developed at the Los Alamos National Laboratory, SPENVIS, a space environment related online tool, IRBEM, a source code library dedicated to radiation belt modelling, and a 3-D particle tracing code that was developed for this purpose. We then attempt to quantify the variations between the calculations of I and L* of those models. The deviation between the results given by the models depends on particle starting position geocentric distance, pitch angle and magnetospheric conditions. Using the 3-D tracer we attempt to map the areas in the Earth's magnetosphere where I and L* can be assumed to be conserved by monitoring the constancy of I for energetic proton propagating forwards and backwards in time. These areas are found to be centered on the noon area and their size also depends on particle starting position geocentric distance, pitch angle and magnetospheric conditions. [ABSTRACT FROM AUTHOR]

Several deep learning models are presented: Ref. [[4]] designs a network intrusion detection model, DLNID, that combines an attention mechanism, a bidirectional long short-term memory (LSTM), and an adaptive synthetic sampling, and demonstrates improved performance for severely imbalanced data. In addition, there are a couple of papers on HPO: Ref. [[11]] introduces a greedy I k i -fold cross validation method that vastly reduces the average time required to find the best-performing model with or without a computational budget, and experimentally verifies its improved performance over existing methods. Since its inception as a branch of Artificial Intelligence, Machine Learning (ML) has flourished in recent years. [Extracted from the article]

This special issue of the International Journal of Computer Vision (IJCV) presents the best papers of the 28th British Machine Vision Conference (BMVC) held in Imperial College London, UK, on 4th-7th September 2017. The papers presented in this issue offer a snapshot of some of the best work in the field, on the topics of (1) learning quantised representations by deep neural networks, (2) 3D shape estimation, (3) novel image representations, (4) image descriptors and matching, and (5) data generation. I Image descriptors and matching i by local descriptors or deep neural networks remains an active research topic. [Extracted from the article]

We feature papers on recent developments in the areas of adaptive signal processing, machine learning, and deep learning using information theory and entropy to improve performance in widespread and popular problems, and also to provide effective solutions to emerging problems. Our goal is to publish recent developments in the areas of adaptive signal processing, machine learning, and deep learning using information theory and entropy to improve performance in widespread and popular problems, and also to provide effective solutions to emerging problems. This Special Issue on "Adaptive Signal Processing and Machine Learning Using Entropy and Information Theory" was birthed from observations of the recent trend in the literature. Entropy-based cost functions have replaced mean-square-error (MSE)-based ones and have been widely used in adaptive signal processing and machine learning to improve performance by designing and optimizing effective and specific models that fit the data, even in noisy and adverse conditions. [Extracted from the article]

This paper constructs a neural machine translation model for Chinese and English using encoder feature extraction with migration learning, allowing the machine to automatically perform feature migration learning, transforming Chinese and English data into word vectors using a centralized representation, and using neural networks to achieve a direct mapping between Chinese and English languages. In this paper, we study the construction of a neural machine translation model by the neural network structure. Firstly, the neural machine translation model is constructed using the neural network structure, which is simplified based on the neural network structure and achieves good performance while reducing the training complexity. To address the problem that neural machine translation cannot make good use of linguistic knowledge, a neural machine translation model with lexical sequence information is proposed. Based on the translation model of a bidirectional neural network incorporating attention mechanism, syntactic analysis is performed to obtain lexical sequence information, and then it is incorporated into the encoder part of the translation model in the form of bidirectional encoding, and the background vector is formed together by vector splicing. To address the problem that the Chinese-English language sequences of any length in the encoder part are encoded into a fixed dimensional background vector, an attention mechanism is introduced to dynamically adjust the degree of influence of the context at the source language end on the target language sequences to improve the translation model's ability to deal with long-distance dependencies. To better reflect the contextual information, this paper further proposes a machine translation model based on migration learning and neural network and conducts a comparative analysis for various translation models to verify the effectiveness of the model performance improvement. [ABSTRACT FROM AUTHOR]

Deep neural networks are exposed to the risk of adversarial attacks via the fast gradient sign method (FGSM), projected gradient descent (PGD) attacks, and other attack algorithms. Adversarial training is one of the methods used to defend against the threat of adversarial attacks. It is a training schema that utilizes an alternative objective function to provide model generalization for both adversarial data and clean data. In this systematic review, we focus particularly on adversarial training as a method of improving the defensive capacities and robustness of machine learning models. Specifically, we focus on adversarial sample accessibility through adversarial sample generation methods. The purpose of this systematic review is to survey state-of-the-art adversarial training and robust optimization methods to identify the research gaps within this field of applications. The literature search was conducted using Engineering Village (Engineering Village is an engineering literature search tool, which provides access to 14 engineering literature and patent databases), where we collected 238 related papers. The papers were filtered according to defined inclusion and exclusion criteria, and information was extracted from these papers according to a defined strategy. A total of 78 papers published between 2016 and 2021 were selected. Data were extracted and categorized using a defined strategy, and bar plots and comparison tables were used to show the data distribution. The findings of this review indicate that there are limitations to adversarial training methods and robust optimization. The most common problems are related to data generalization and overfitting. [ABSTRACT FROM AUTHOR]

Regional poverty is one of the most serious challenges facing the world today. Poverty, antipoverty, and poverty alleviation are the focus of the attention of scholars and the public. This paper takes China's counties as the research unit, selects the influencing factors of poverty from natural and socio-economic factors, establishes an evaluation index system, simulates the natural poverty index and socio-economic poverty eradication index of each county, and clarifies the distribution characteristics of spatial poverty using GIS spatial analysis and BP artificial neural network. The results indicate that natural factors are the main cause of poverty in Chinese counties, with 710 counties having a high natural poverty index, accounting for nearly 30% of the total number of counties in the country. The national county-level natural poverty index shows a clear strip distribution pattern along latitude and longitude, with a strip distribution from north to south and from west to east; socio-economic factors have played a certain role in poverty alleviation, with as many as 1521 counties with low socio-economic poverty alleviation indices, accounting for approximately 64% of the total number of counties in the country. The spatial distribution of the county-level socio-economic poverty alleviation index is relatively fragmented. Through spatial scanning statistics, a total of 44 county poverty pressure index risk clusters reached a statistical significance level, involving 243 counties and districts. In poverty reduction practice, the internal counties and districts of contiguous poverty-stricken areas should strengthen cooperation and exchange. In the process of poverty alleviation and development, targeted poverty alleviation and economic development should be carried out based on the poverty-dominant type and self-development ability of the county, in order to improve efficiency. Regions that are relatively prosperous and have taken the lead in poverty reduction should play a leading and exemplary role in strengthening the radiation power of regional central cities. The prominent feature of this study is the comprehensive utilization of multisource data and the use of new spatial analysis methods (flexible spatial scanning method is widely used in the field of infectious disease prevention and control research). By constructing a multidimensional poverty measurement system that includes natural and social factors, it distinguishes the differences between the factors that cause poverty and the factors that eliminate poverty in regional poverty. At the same time, the flexible spatial scanning detection method was used to detect the differentiation mechanism of poverty spatial patterns. [ABSTRACT FROM AUTHOR]

Sensitivity analysis of influencing factors on frost resistance is carried out in this paper, and a two-stage neural network model based on grey theory and Back Propagation Neural Networks (BPNNs) is established for the sake of predicting the frost resistance of active-admixture recycled concrete quickly and accurately. Firstly, the influence degree of cement, water, sand, natural aggregate, recycled aggregate, mineral powder, fly ash, fiber and air-entraining agent on the frost resistance of active-admixture recycled-aggregate concrete was analyzed based on the grey system theory, and the primary and secondary relationships of various factors were effectively distinguished. Then, the input layer of the model was determined as cement, water, sand, recycled aggregate and air-entraining agent, and the output layer was the relative dynamic elastic modulus. A total of 120 datasets were collected from the experimental data of another author, and the relative dynamic elastic modulus was predicted using the two-stage BPNN prediction model proposed in this paper and compared with the BPNN prediction results. The results show that the proposed two-stage BPNN model, after removing less-sensitive parameters from the input layer, has better prediction accuracy and shorter run time than the BPNN model. [ABSTRACT FROM AUTHOR]

With the development of smart grids and new power systems, the combination of non-intrusive load identification technology and smart home technology can provide users with the operating conditions of home appliances and equipment, thus reducing home energy loss and improving users' ability to demand a response. This paper proposes a non-intrusive load decomposition model with a parallel multiscale attention mechanism (PMAM). The model can extract both local and global feature information and fuse it through a parallel multiscale network. This improves the attention mechanism's ability to capture feature information over long time periods. To validate the model's decomposition ability, we combined the PMAM model with four benchmark models: the Long Short-Term Memory (LSTM) recurrent neural network model, the Time Pooling-based Load Disaggregation Model (TPNILM), the Extreme Learning Machine (ELM), and the Load Disaggregation Model without Parallel Multi-scalar Attention Mechanisms (UNPMAM). The model was trained on the publicly available UK-DALE dataset and tested. The models' test results were quantitatively evaluated using a confusion matrix. This involved calculating the F1 score of the load decomposition. A higher F1 score indicates better model decomposition performance. The results indicate that the PMAM model proposed in this paper maintains an F1 score above 0.9 for the decomposition of three types of electrical equipment under the same household user, which is 3% higher than that of the other benchmark models on average. In the cross-household test, the PMAM also demonstrated a better decomposition ability, with the F1 score maintained above 0.85, and the mean absolute error (MAE) decreased by 5.3% on average compared with that of the UNPMAM. [ABSTRACT FROM AUTHOR]

Millions of people worldwide who suffer from epilepsy are severely impacted by frequent, erratic seizures. Preventing seizures from occurring could greatly enhance patient care and safety. This paper presents an approach to real-time epileptic seizure prediction utilizing a unique kind of neural network known as Bidirectional Long ShortTerm Memory (Bi-LSTM). The existing multidimensional CNN deep neural network models have average accuracy for multi-channel EEG data in predicting seizures. The proposed model was selected for its excellent ability to interpret complex seizure patterns from both historical and prospective data. We took advantage of a big dataset of real-time EEG recordings of brain activity. The testing yielded the results with the approach of 98% accuracy in predicting seizures. Using the Bi-LSTM model in real-time systems has shown that it can make precise predictions quickly, offering hope for improving the lives of those with epilepsy. [ABSTRACT FROM AUTHOR]

In this paper, the use of artificial neural networks (ANNs) is proposed to approximate the option price sensitivities of Johannesburg Stock Exchange (JSE) Top 40 European call options in a classical and a modern multi-curve framework. The ANNs were trained on artificially generated option price data given the illiquid nature of the South African market, and the out-of-sample performance of the optimized ANNs was evaluated using an implied volatility surface constructed from published volatility skews. The results from this paper show that ANNs trained on artificially generated input data are able to accurately approximate the explicit solutions to the respective option price sensitivities of both a classical and a modern multi-curve framework in a real-world out-of-sample application to the South African market. [ABSTRACT FROM AUTHOR]

When new rail stations or lines are planned, long-term planning for decades to come is required. The short-term passenger flow prediction is no longer of practical significance, as it only takes a few factors that affect passenger flow into consideration. To overcome this problem, we propose several long-term factors affecting the passenger flow of rail transit in this paper. We also create a visual analysis of these factors using ArcGIS and construct a long-term passenger flow prediction model for rail transit based on a class neural network using an SPSS Modeler. After optimizing relevant parameters, the prediction accuracy reaches 94.6%. We compare the results with other models and find that the neural network model has a good performance in predicting long-term rail transit passenger flow. Finally, the factors affecting passenger flow are ranked in terms of importance. It is found that among these factors, bicycles available for connection have the biggest influence on the passenger flow of rail stations. [ABSTRACT FROM AUTHOR]

The early detection of pests in plants and crops is essential for the production of good quality food. Computer vision techniques can be applied for the early detection of pests and which can minimise the pesticides used on the plants. Among many pests, white flies, mites, aphids and thrips are the most hazardous pests that affect the leaves. This paper presents an automated approach for the detection of different types of pests from leaf images of plants. The images of the plant leaves were acquired using a digital camera. Image pre-processing techniques, such as noise removal, filtering and contrast enhancement, are used for improving the quality of the images. Then, the k-means clustering method and global thresholding were used for segmenting the pests from the infected leaves. Textural features are extracted from those segmented images by statistical feature extraction methods. Artificial Neural Network (ANN) and Binary Support Vector Machine (SVM) classifiers were used to classify the unaffected leaf images from the pest affected leaf images and a multi-SVM classifier was used to identify the different types of pests. [ABSTRACT FROM AUTHOR]

This document is an editorial that summarizes several research papers on the topic of human recognition and the interactions between different channels of recognition, such as voice and face processing. The papers explore various aspects of this topic, including voice processing in challenging listening conditions, the role of familiarity in voice and face recognition, and the functional reorganization of neural systems in blind individuals. The papers highlight the importance of familiarity factors in recognition, the role of brain asymmetries, and the early integration of voice and face processing. The findings suggest that voice and face recognition are closely linked and influenced by familiarity, and that the right temporal lobe may play a significant role in vocal processing abilities in blind individuals. [Extracted from the article]

The advent of autonomous vehicles has heralded a transformative era in transportation, reshaping the landscape of mobility through cutting-edge technologies. Central to this evolution is the integration of artificial intelligence (AI), propelling vehicles into realms of unprecedented autonomy. Commencing with an overview of the current industry landscape with respect to Operational Design Domain (ODD), this paper delves into the fundamental role of AI in shaping the autonomous decision-making capabilities of vehicles. It elucidates the steps involved in the AI-powered development life cycle in vehicles, addressing various challenges such as safety, security, privacy, and ethical considerations in AI-driven software development for autonomous vehicles. The study presents statistical insights into the usage and types of AI algorithms over the years, showcasing the evolving research landscape within the automotive industry. Furthermore, the paper highlights the pivotal role of parameters in refining algorithms for both trucks and cars, facilitating vehicles to adapt, learn, and improve performance over time. It concludes by outlining different levels of autonomy, elucidating the nuanced usage of AI algorithms, and discussing the automation of key tasks and the software package size at each level. Overall, the paper provides a comprehensive analysis of the current industry landscape, focusing on several critical aspects. [ABSTRACT FROM AUTHOR]

Copyright of Romanian Journal of Information Technology & Automatic Control / Revista Română de Informatică și Automatică is the property of National Institute for Research & Development in Informatics - ICI Bucharest and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

With the rapid development of semiconductor technology, the reduction in device operating voltage and threshold voltage has made integrated circuits more susceptible to the effects of particle radiation. Moreover, as process sizes decrease, the impact of charge sharing effects becomes increasingly severe, with soft errors caused by single event effects becoming one of the main causes of circuit failures. Therefore, the study of sensitivity evaluation methods for integrated circuits is of great significance for promoting the optimization of integrated circuit design, improving single event effect experimental methods, and enhancing the irradiation reliability of integrated circuits. In this paper, we first established a device model for the charge sharing effect and simulated it under reasonable conditions. Based on the simulation results, we then built a neural network model to predict the charge amounts in primary and secondary devices. We also propose a comprehensive automated method for calculating soft errors in unit circuits and validated it through TCAD simulations, achieving an error margin of 2.8–4.3%. This demonstrated the accuracy and effectiveness of the method we propose. [ABSTRACT FROM AUTHOR]

For processing streaming events from a Dynamic Vision Sensor camera, two types of neural networks can be considered. One are spiking neural networks, where simple spike-based computation is suitable for low-power consumption, but the discontinuity in spikes can make the training complicated in terms of hardware. The other one are digital Complementary Metal Oxide Semiconductor (CMOS)-based neural networks that can be trained directly using the normal backpropagation algorithm. However, the hardware and energy overhead can be significantly large, because all streaming events must be accumulated and converted into histogram data, which requires a large amount of memory such as SRAM. In this paper, to combine the spike-based operation with the normal backpropagation algorithm, memristor–CMOS hybrid circuits are proposed for implementing event-driven neural networks in hardware. The proposed hybrid circuits are composed of input neurons, synaptic crossbars, hidden/output neurons, and a neural network's controller. Firstly, the input neurons perform preprocessing for the DVS camera's events. The events are converted to histogram data using very simple memristor-based latches in the input neurons. After preprocessing the events, the converted histogram data are delivered to an ANN implemented using synaptic memristor crossbars. The memristor crossbars can perform low-power Multiply–Accumulate (MAC) calculations according to the memristor's current–voltage relationship. The hidden and output neurons can convert the crossbar's column currents to the output voltages according to the Rectified Linear Unit (ReLU) activation function. The neural network's controller adjusts the MAC calculation frequency according to the workload of the event computation. Moreover, the controller can disable the MAC calculation clock automatically to minimize unnecessary power consumption. The proposed hybrid circuits have been verified by circuit simulation for several event-based datasets such as POKER-DVS and MNIST-DVS. The circuit simulation results indicate that the neural network's performance proposed in this paper is degraded by as low as 0.5% while saving as much as 79% in power consumption for POKER-DVS. The recognition rate of the proposed scheme is lower by 0.75% compared to the conventional one, for the MNIST-DVS dataset. In spite of this little loss, the power consumption can be reduced by as much as 75% for the proposed scheme. [ABSTRACT FROM AUTHOR]

The digitization of distribution power systems has revolutionized the way data are collected and analyzed. In this paper, the critical task of harnessing this information to identify irregularities and anomalies in electricity consumption is tackled. The focus is on detecting non-technical losses (NTLs) and energy theft within distribution networks. A comprehensive overview of the methodologies employed to uncover NTLs and energy theft is presented, leveraging measurements of electricity consumption. The most common scenarios and prevalent cases of anomalies and theft among consumers are identified. Additionally, statistical indicators tailored to specific anomalies are proposed. In this research paper, the practical implementation of numerous artificial intelligence (AI) algorithms, including the artificial neural network (ANN), ANFIS, autoencoder neural network, and K-mean clustering, is highlighted. These algorithms play a central role in our research, and our primary objective is to showcase their effectiveness in identifying NTLs. Real-world data sourced directly from distribution networks are utilized. Additionally, we carefully assess how well statistical methods work and compare them to AI techniques by testing them with real data. The artificial neural network (ANN) accurately identifies various consumer types, exhibiting a frequency error of 7.62%. In contrast, the K-means algorithm shows a slightly higher frequency error of 9.26%, while the adaptive neuro-fuzzy inference system (ANFIS) fails to detect the initial anomaly type, resulting in a frequency error of 11.11%. Our research suggests that AI can make finding irregularities in electricity consumption even more effective. This approach, especially when using data from smart meters, can help us discover problems and safeguard distribution networks. [ABSTRACT FROM AUTHOR]

In this paper, we propose a learning model for tracking the isolines of fluid based on the physical properties of particles in particle-based fluid simulations. Our method involves analyzing which weights, closely related to surface tracking among the various physical properties of fluid particles, are significant. These weights are used as input values for the learning algorithm, enabling relatively accurate isoline tracking. In addition, compared to existing learning models such as linear regression, LSTM (long short-term memory), and learning representation (1-layer) models, our method obtained superior surface tracking results without accumulating errors. By using our proposed network structure to track the fluid surface, it learns and predicts values derived from existing fluid simulation algorithms, eliminating the need for computational processes for level-set values and enabling real-time surface tracking. As the scale of the simulation increases, our method significantly reduces the time and resources consumed compared to traditional methods and can track the fluid surface without additional resource consumption. Furthermore, due to our method's simple network structure, the time consumed in the initial process of loading the model into memory is faster than models such as CNN and LSTM. Our proposed model occupies less than 30 kb of storage space, making it suitable for use in middleware. Lastly, to verify the generality of our method, we conducted tests in a total of five scenes, and in all test scenes, visually natural fluid isolines were represented. [ABSTRACT FROM AUTHOR]

This document is a summary of a special issue of the journal Applied Sciences that focuses on eHealth innovative approaches and applications. It covers various topics including COVID-19 classification, AI in medical imaging, cyber security in healthcare, and the use of Large Language Models (LLMs) for coding diagnoses. The papers provide insights into the latest developments in eHealth and address issues such as data privacy, cyber security, and the challenges of implementing new technologies in healthcare. The document acknowledges the contributions of the authors and reviewers and expresses gratitude for their support. [Extracted from the article]

This study investigates the characteristics of a novel origami-based, elastomeric actuator and a soft gripper, which are controlled by hand gestures that are recognized through machine learning algorithms. The lightweight paper–elastomer structure employed in this research exhibits distinct actuation features in four key areas: (1) It requires approximately 20% less pressure for the same bending amplitude compared to pneumatic network actuators (Pneu-Net) of equivalent weight, and even less pressure compared to other actuators with non-linear bending behavior; (2) The control of the device is examined by validating the relationship between pressure and the bending angle, as well as the interaction force and pressure at a fixed bending angle; (3) A soft robotic gripper comprising three actuators is designed. Enveloping and pinch grasping experiments are conducted on various shapes, which demonstrate the gripper's potential in handling a wide range of objects for numerous applications; and (4) A gesture recognition algorithm is developed to control the gripper using electromyogram (EMG) signals from the user's muscles. [ABSTRACT FROM AUTHOR]

Visual object tracking is a key technology that is used in unmanned aerial vehicles (UAVs) to achieve autonomous navigation. In recent years, with the rapid development of deep learning, tracking algorithms based on Siamese neural networks have received widespread attention. However, because of complex and diverse tracking scenarios, as well as limited computational resources, most existing tracking algorithms struggle to ensure real-time stable operation while improving tracking performance. Therefore, studying efficient and fast-tracking frameworks, and enhancing the ability of algorithms to respond to complex scenarios has become crucial. Therefore, this paper proposes a cross-parallel attention and efficient match transformer for aerial tracking (SiamEMT). Firstly, we carefully designed the cross-parallel attention mechanism to encode global feature information and to achieve cross-dimensional interaction and feature correlation aggregation via parallel branches, highlighting feature saliency and reducing global redundancy information, as well as improving the tracking algorithm's ability to distinguish between targets and backgrounds. Meanwhile, we implemented an efficient match transformer to achieve feature matching. This network utilizes parallel, lightweight, multi-head attention mechanisms to pass template information to the search region features, better matching the global similarity between the template and search regions, and improving the algorithm's ability to perceive target location and feature information. Experiments on multiple drone public benchmark tests verified the accuracy and robustness of the proposed tracker in drone tracking scenarios. In addition, on the embedded artificial intelligence (AI) platform AGX Xavier, our algorithm achieved real-time tracking speed, indicating that our algorithm can be effectively applied to UAV tracking scenarios. [ABSTRACT FROM AUTHOR]

With the flourishing development of global economy, effective management of production supply chains is crucial for the competitiveness of enterprises. Optimizing supply chain networks can not only improve the efficiency of resource allocation but also enhance market responsiveness and systemic risk resistance. Traditional supply chain network optimization methods, focusing mostly on linear models and static analysis, fall short in addressing the growing complexity and dynamism. The emergence of Graph Neural Network (GNN) models in recent years has offered new opportunities to tackle non-linearity and structural dynamism in supply chain networks. However, existing research still faces methodological limitations in supply chain node relationship mining and benefit assessment. This study introduces an optimization and benefit assessment method for production supply chain networks based on GNNs. Firstly, by developing a node role type-aware graph neural network model, this paper achieves in-depth mining and optimization of node relationships within production supply chain networks. Secondly, a hierarchical factor analysis method is used to comprehensively assess the benefits of the production supply chain. This method can dynamically capture changes in node roles and relationships within the supply chain network, optimize the network structure, and provides a multidimensional, multilevel framework for benefit assessment. This study not only expands the application of GNN in the field of supply chain management but also provides a new analytical tool for the comprehensive assessment of supply chain benefits. [ABSTRACT FROM AUTHOR]

As digital technologies have advanced more rapidly, the number of paper documents recently converted into a digital format has exponentially increased. To respond to the urgent need to categorize the growing number of digitized documents, the classification of digitized documents in real time has been identified as the primary goal of our study. A paper classification is the first stage in automating document control and efficient knowledge discovery with no or little human involvement. Artificial intelligence methods such as Deep Learning are now combined with segmentation to study and interpret those traits, which were not conceivable ten years ago. Deep learning aids in comprehending input patterns so that object classes may be predicted. The segmentation process divides the input image into separate segments for a more thorough image study. This study proposes a deep learning-enabled framework for automated document classification, which can be implemented in higher education. To further this goal, a dataset was developed that includes seven categories: Diplomas, Personal documents, Journal of Accounting of higher education diplomas, Service letters, Orders, Production orders, and Student orders. Subsequently, a deep learning model based on Conv2D layers is proposed for the document classification process. In the final part of this research, the proposed model is evaluated and compared with other machine-learning techniques. The results demonstrate that the proposed deep learning model shows high results in document categorization overtaking the other machine learning models by reaching 94.84%, 94.79%, 94.62%, 94.43%, 94.07% in accuracy, precision, recall, F-score, and AUC-ROC, respectively. The achieved results prove that the proposed deep model is acceptable to use in practice as an assistant to an office worker. [ABSTRACT FROM AUTHOR]

Using optimal assembly relationships, companies can enhance product quality without significantly increasing production costs. However, predicting Assembly Geometric Errors presents a challenging real-world problem in the manufacturing domain. To address this challenge, this paper introduces a highly efficient Transformer-based neural network model known as Predicting Assembly Geometric Errors based on Transformer (PAGEformer). This model accurately captures long-range assembly relationships and predicts final assembly errors. The proposed model incorporates two unique features: firstly, an enhanced self-attention mechanism to more effectively handle long-range dependencies, and secondly, the generation of positional information regarding gaps and fillings to better capture assembly relationships. This paper collected actual assembly data for folding rudder blades for unmanned aerial vehicles and established a Mechanical Assembly Relationship Dataset (MARD) for a comparative study. To further illustrate PAGEformer performance, we conducted extensive testing on a large-scale dataset and performed ablation experiments. The experimental results demonstrated a 15.3% improvement in PAGEformer accuracy compared to ARIMA on the MARD. On the ETH, Weather, and ECL open datasets, PAGEformer accuracy increased by 15.17%, 17.17%, and 9.5%, respectively, compared to the mainstream neural network models. [ABSTRACT FROM AUTHOR]

Rapid mapping demands efficient methods for a fast extraction of information from satellite data while minimizing data requirements. This paper explores the potential of deep learning for the generation of high-resolution urban elevation data from Synthetic Aperture Radar (SAR) imagery. In order to mitigate occlusion effects caused by the side-looking nature of SAR remote sensing, two SAR images from opposing aspects are leveraged and processed in an end-to-end deep neural network. The presented approach is the first of its kind to implicitly handle the transition from the SAR-specific slant range geometry to a ground-based mapping geometry within the model architecture. Comparative experiments demonstrate the superiority of the dual-aspect fusion over single-image methods in terms of reconstruction quality and geolocation accuracy. Notably, the model exhibits robust performance across diverse acquisition modes and geometries, showcasing its generalizability and suitability for height mapping applications. The study's findings underscore the potential of deep learning-driven SAR techniques in generating high-quality urban surface models efficiently and economically. [ABSTRACT FROM AUTHOR]

Over the last few years, a plethora of papers presenting machine-learning-based approaches for intrusion detection have been published. However, the majority of those papers do not compare their results with a proper baseline of a signature-based intrusion detection system, thus violating good machine learning practices. In order to evaluate the pros and cons of the machine-learning-based approach, we replicated a research study that uses a deep neural network model for intrusion detection. The results of our replicated research study expose several systematic problems with the used datasets and evaluation methods. In our experiments, a signature-based intrusion detection system with a minimal setup was able to outperform the tested model even under small traffic changes. Testing the replicated neural network on a new dataset recorded in the same environment with the same attacks using the same tools showed that the accuracy of the neural network dropped to 54%. Furthermore, the often-claimed advantage of being able to detect zero-day attacks could not be seen in our experiments. [ABSTRACT FROM AUTHOR]

In this paper, we discuss the implementation of artificial self-awareness mechanisms and self-reflection abilities in deep neural networks. While the current limitations of research prevent achieving cognitive capabilities on par with natural biological entities, the incorporation of basic self-awareness and self-reflection mechanisms in deep learning architectures offers substantial advantages in tackling specific problems across various scientific fields, including geosciences. In the first section, we outline the foundational architecture of our deep learning approach termed Self-Aware Learning (SAL). The subsequent part of the paper highlights the practical benefits of this machine learning methodology through synthetic tests and applications addressed to automatic classification and image analysis of real petrological data sets. We show how Self-Aware Learning allows enhanced accuracy, reduced overfitting problems, and improved performances compared to other existing methods. [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]

Aiming at the rapid development of anti-hypersonic collaborative interception technology, this paper designs an intelligent maneuver strategy of hypersonic vehicles (HV) based on deep reinforcement learning (DRL) to evade the collaborative interception by two interceptors. Under the meticulously designed collaborative interception strategy, the uncertainty and difficulty of evasion are significantly increased and the opportunity for maneuvers is further compressed. This paper, accordingly, selects the twin delayed deep deterministic gradient (TD3) strategy acting on the continuous action space and makes targeted improvements combining deep neural networks to grasp the maneuver strategy and achieve successful evasion. Focusing on the time-coordinated interception strategy of two interceptors, the three-player pursuit and evasion (PE) problem is modeled as the Markov decision process, and the double training strategy is proposed to juggle both interceptors. In reward functions of the training process, the energy saving factor is set to achieve the trade-off between miss distance and energy consumption. In addition, the regression neural network is introduced into the deep neural network of TD3 to enhance intelligent maneuver strategies’ generalization. Finally, numerical simulations are conducted to verify that the improved TD3 algorithm can effectively evade the collaborative interception of two interceptors under tough situations, and the improvements of the algorithm in terms of convergence speed, generalization, and energysaving effect are verified. [ABSTRACT FROM AUTHOR]

Accurate prediction of sea level height is critically important for the government in assessing sea level risk in coastal areas. However, due to the nonlinear, time-varying and highly uncertain characteristics of sea level change data, sea level prediction is challenging. To improve the accuracy of sea level prediction, this paper uses a new swarm intelligence algorithm named the sparrow search algorithm (SSA), which can imitate the foraging behavior and antipredation behavior of sparrows, to determine optimal solutions. To avoid the algorithm falling into a local optimal situation, this paper integrates the sine–cosine algorithm and the Cauchy variation strategy into the SSA to obtain an algorithm named the SCSSA. The SCSSA is used to optimize the parameter values of the CNN-BiLSTM (convolutional neural network combined with bidirectional long short-term memory neural network) model; finally, a combined neural network model (named SCSSA-CNN-BiLSTM) is proposed. In this paper, the time series data of seven tidal stations located in coastal China are used for experimental analysis. First, the SCSSA-CNN-BiLSTM model is compared with the CNN-BiLSTM model to predict the time series data of SHANWEI Station. With respect to the training and test sets of data, the SCSSA-CNN-BiLSTM model outperforms the other models on all the evaluation metrics. In addition, the remaining six tide station datasets and five neural network models, including the SCSSA-CNN-BiLSTM model, are used to further study the performance of the proposed prediction model. Four evaluation indices including the root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE) and coefficient of determination (R2) are adopted. For six stations, the RMSE, MAE, MAPE and R2 of SCSSA-CNN-BiLSTM model are ranged from 20.9217 ~ 27.8427 mm, 9.4770 ~ 17.8603 mm, 0.1322% ~ 0.2482% and 0.9119 ~ 0.9759, respectively. The experimental analysis results show that the SCSSA-CNN-BiLSTM model makes effective predictions at all stations, and the prediction performance is better than that of the other models. Even though the combination of SCSSA algorithm may increase the complexity of the model, indeed the proposed model is a new prediction method with good accuracy and robustness for predicting sea level change. [ABSTRACT FROM AUTHOR]

This document provides a summary of a special issue on the application of artificial intelligence (AI) in hydraulic engineering. The papers in this issue cover a range of topics including safety monitoring, optimization algorithms, nondestructive sensors, numerical simulations, and experiments. The research presented in these papers is significant for analyzing and managing the safety of major structures in reservoir dams. The authors hope that these papers will be of interest to researchers, designers, and practitioners in the field and will inspire further research. [Extracted from the article]

Knowledge graph embedding converts knowledge graphs based on symbolic representations into low-dimensional vectors. Effective knowledge graph embedding methods are key to ensuring downstream tasks. Some studies have shown significant performance differences among various knowledge graph embedding models on different datasets. They attribute this issue to the insufficient representation ability of the models. However, what representation ability knowledge graph embedding models possess is still unknown. Therefore, this paper first selects three representative models for analysis: translation and rotation models in distance models, and the Bert model in neural network models. Based on the analysis results, it can be concluded that the translation model focuses on clustering features, the rotation model focuses on hierarchy features, and the Bert model focuses on word co-occurrence features. This paper categorize clustering and hierarchy as structure features, and word co-occurrence as semantic features. Furthermore, a model that solely focuses on a single feature will lead to a lack of accuracy and generality, making it challenging for the model to be applicable to modern large-scale knowledge graphs. Therefore, this paper proposes an ensemble model with structure and semantic features for knowledge graph embedding. Specifically, the ensemble model includes a structure part and a semantic part. The structure part consists of three models: translation, rotation and cross. Translation and rotation models serve as basic feature extraction, while the cross model enhances the interaction between them. The semantic part is built based on Bert and integrated with the structure part after fine-tuning. In addition, this paper also introduces a frequency model to mitigate the training imbalance caused by differences in entity frequencies. Finally, we verify the effectiveness of the model through link prediction. Experiments show that the ensemble model has achieved improvement on FB15k-237 and YAGO3-10, and also has good performance on WN18RR, proving the effectiveness of the model. [ABSTRACT FROM AUTHOR]

In this paper, an intelligent control method applying on numerical virtual flight is proposed. The proposed algorithm is verified and evaluated by combining with the case of the basic finner projectile model and shows a good application prospect. Firstly, a numerical virtual flight simulation model based on overlapping dynamic mesh technology is constructed. In order to verify the accuracy of the dynamic grid technology and the calculation of unsteady flow, a numerical simulation of the basic finner projectile without control is carried out. The simulation results are in good agreement with the experiment data which shows that the algorithm used in this paper can also be used in the design and evaluation of the intelligent controller in the numerical virtual flight simulation. Secondly, combined with the real-time control requirements of aerodynamic, attitude and displacement parameters of the projectile during the flight process, the numerical simulations of the basic finner projectile’s pitch channel are carried out under the traditional PID(Proportional-Integral-Derivative) control strategy and the intelligent PID control strategy respectively. The intelligent PID controller based on BP(Back Propagation) neural network can realize online learning and self-optimization of control parameters according to the acquired real-time flight parameters. Compared with the traditional PID controller, the concerned control variable overshoot, rise time, transition time and steady state error and other performance indicators have been greatly improved, and the higher the learning efficiency or the inertia coefficient, the faster the system, the larger the overshoot, and the smaller the stability error. The intelligent control method applying on numerical virtual flight is capable of solving the complicated unsteady motion and flow with the intelligent PID control strategy and has a strong promotion to engineering application. [ABSTRACT FROM AUTHOR]

This paper aims to propose an improved image classification model to reduce the cost of model construction. Aiming at the problem that network training usually requires the support of a large number of labeled samples, an image classification model based on semi-supervised deep learning is proposed, which uses labeled samples to guide the network to learn unlabeled samples. A convolutional neural network model for simultaneous processing of labeled and unlabeled data is constructed. The tagged data is used to train the Softmax classifier and provide the initial K-means clustering center for the untagged data. The nonsubsampling contourlet layer is used to replace the first convolutional layer of the full convolutional neural network to extract multi-scale depth features, and the nonsubsampling contourlet full convolutional neural network is constructed. The network can extract multi-scale information of the images to be classified, and extract more discriminative deep image features. In addition, the parameters of the nonsubsampled contourlet layers are pre-set and do not require network training. The proposed method has higher classification accuracy than the contrast method on polarimetric SAR images using the nonsubsampled contourlet full convolutional neural network. [ABSTRACT FROM AUTHOR]

This paper discusses the problem of recognizing defective epoxy drop images for the purpose of performing vision-based die attachment inspection in integrated circuit (IC) manufacturing based on deep neural networks. Two supervised and two unsupervised recognition models are considered. The supervised models examined are an autoencoder (AE) network together with a multi-layer perceptron network (MLP) and a VGG16 network, while the unsupervised models examined are an autoencoder (AE) network together with k-means clustering and a VGG16 network together with k-means clustering. Since in practice very few defective epoxy drop images are available on an actual IC production line, the emphasis in this paper is placed on the impact of data augmentation on the recognition outcome. The data augmentation is achieved by generating synthesized defective epoxy drop images via our previously developed enhanced loss function CycleGAN generative network. The experimental results indicate that when using data augmentation, the supervised and unsupervised models of VGG16 generate perfect or near perfect accuracies for recognition of defective epoxy drop images for the dataset examined. More specifically, for the supervised models of AE+MLP and VGG16, the recognition accuracy is improved by 47% and 1%, respectively, and for the unsupervised models of AE+Kmeans and VGG+Kmeans, the recognition accuracy is improved by 37% and 15%, respectively, due to the data augmentation. [ABSTRACT FROM AUTHOR]