Search

With the proliferation of blockchain technology in decentralized applications like decentralized finance and supply chain and identity management, smart contracts operating on a blockchain frequently encounter security issues such as reentrancy vulnerabilities, timestamp dependency vulnerabilities, tx.origin vulnerabilities, and integer overflow vulnerabilities. These security concerns pose a significant risk of causing substantial losses to user accounts. Consequently, the detection of vulnerabilities in smart contracts has become a prominent area of research. Existing research exhibits limitations, including low detection accuracy in traditional smart contract vulnerability detection approaches and the tendency of deep learning-based solutions to focus on a single type of vulnerability. To address these constraints, this paper introduces a smart contract vulnerability detection method founded on multimodal feature fusion. This method adopts a multimodal perspective to extract three modal features from the lifecycle of smart contracts, leveraging both static and dynamic features comprehensively. Through deep learning models like Graph Convolutional Networks (GCNs) and bidirectional Long Short-Term Memory networks (bi-LSTMs), effective detection of vulnerabilities in smart contracts is achieved. Experimental results demonstrate that the proposed method attains detection accuracies of 85.73% for reentrancy vulnerabilities, 85.41% for timestamp dependency vulnerabilities, 83.58% for tx.origin vulnerabilities, and 90.96% for integer Overflow vulnerabilities. Furthermore, ablation experiments confirm the efficacy of the newly introduced modal features, highlighting the significance of fusing dynamic and static features in enhancing detection accuracy. [ABSTRACT FROM AUTHOR]

Applied computing and artificial intelligence methods have been attracting growing interest in recent years due to their effectiveness in solving technical problems. Hao et al. [[14]] present an unsupervised fault diagnosis methodology to leverage the generated MPCs of different working conditions to diagnose the actual unlabeled MPCs. The paper by Ainapure et al. [[17]] proposes a new cross-domain fault diagnosis method with enhanced robustness. The paper by Saeed et al. [[1]] proposes an approach to building an AutoML data-dependent CNN model (DeepPCANet) customized for DR screening automatically. [Extracted from the article]

Most of the deep-learning algorithms on stock price volatility prediction in the existing literature use data such as same-frequency market indicators or technical indicators, and less consider mixed-frequency data, such as macro-data. Compared with the traditional model that only inputs the same-frequency data such as technical indicators and market indicators, this study proposes an improved deep-learning model based on mixed-frequency big data. This paper first introduces the reserve restricted mixed-frequency data sampling (RR-MIDAS) model to deal with the mixed-frequency data and, secondly, extracts the temporal and spatial features of volatility series by using the parallel model of CNN-LSTM and LSTM, and finally utilizes the Optuna framework for hyper-parameter optimization to achieve volatility prediction. For the deep-learning model with mixed-frequency data, its RMSE, MAE, MSLE, MAPE, SMAPE, and QLIKE are reduced by 18.25%, 14.91%, 30.00%, 12.85%, 13.74%, and 23.42%, respectively. This paper provides a more accurate and robust method for forecasting the realized volatility of stock prices under mixed-frequency data. [ABSTRACT FROM AUTHOR]

In order to address the challenge of the small-scale, small-target, and complex scenes often encountered in offshore remote sensing image datasets, this paper employs an interpolation method to achieve super-resolution-assisted target detection. This approach aligns with the logic of popular GANs and generative diffusion networks in terms of super-resolution but is more lightweight. Additionally, the image count is expanded fivefold by supplementing the dataset with DOTA and data augmentation techniques. Framework-wise, based on the Faster R-CNN model, the combination of a residual backbone network and pyramid balancing structure enables our model to adapt to the characteristics of small-target scenarios. Moreover, the attention mechanism, random anchor re-selection strategy, and the strategy of replacing quantization operations with bilinear interpolation further enhance the model's detection capability at a low cost. Ablation experiments and comparative experiments show that, with a simple backbone, the algorithm in this paper achieves a mAP of 71.2% on the dataset, an improvement in accuracy of about 10% compared to the Faster R-CNN algorithm. [ABSTRACT FROM AUTHOR]

With the development of the Internet, the types and quantities of malware have grown rapidly, and how to identify unknown malware is becoming a new challenge. The traditional malware detection method based on fixed features is becoming more and more difficult. In order to improve detection accuracy and efficiency for mobile terminals, this paper proposed a malware detection method for mobile terminals based on application programming interface (API) call sequence, which was characterized by the API call sequence and used a series of feature preprocessing techniques to remove redundant processing of the API call sequence. Finally, the recurrent neural network method (RNN) was used to build the model and perform detection and verification. Furthermore, this paper constructed a malware detection model based on a two-way recurrent neural network and used the two-way long short-term memory network model (LSTM) to train the data set containing 5986 malware samples and 5065 benign software samples to obtain the final detection model and its parameters. Finally, the feature vector of the APK file to be detected was passed into the model and obtained the detection results. The experimental results indicated that the detection accuracy of this method can reach 93.68%. [ABSTRACT FROM AUTHOR]

In this paper, we propose a representation of the visual information about Multiplayer Online Battle Arena (MOBA) video games using an adapted unsupervised deep learning architecture called Convolutional Accordion Auto-Encoder (Conv_A2E). Our study includes a presentation of current representations of MOBA video game information and why our proposal offers a novel and useful solution to this task. This approach aims to achieve dimensional reduction and refined feature extraction of the visual data. To enhance the model's performance, we tested several attention mechanisms for computer vision, evaluating algorithms from the channel attention and spatial attention families, and their combination. Through experimentation, we found that the best reconstruction of the visual information with the Conv_A2E was achieved when using a spatial attention mechanism, deformable convolution, as its mean squared error (MSE) during testing was the lowest, reaching a value of 0.003893, which means that its dimensional reduction is the most generalist and representative for this case study. This paper presents one of the first approaches to applying attention mechanisms to the case study of MOBA video games, representing a new horizon of possibilities for research. [ABSTRACT FROM AUTHOR]

Vehicle re-identification employs computer vision to determine the presence of specific vehicles in images or video sequences, often using vehicle appearance for identification due to the challenge of capturing complete license plate information. Addressing the performance issues caused by fog, such as image blur and loss of key positional information, this paper introduces a multi-task learning framework incorporating a multi-scale fusion defogging method (MsF). This method effectively mitigates image blur to produce clearer images, which are then processed by the re-identification branch. Additionally, a phase attention mechanism is introduced to adaptively preserve crucial details. Utilizing advanced artificial intelligence techniques and deep learning algorithms, the framework is evaluated on both synthetic and real datasets, showing significant improvements in mean average precision (mAP)—an increase of 2.5% to 87.8% on the synthetic dataset and 1.4% to 84.1% on the real dataset. These enhancements demonstrate the method's superior performance over the semi-supervised joint defogging learning (SJDL) model, particularly under challenging foggy conditions, thus enhancing vehicle re-identification accuracy and deepening the understanding of applying multi-task learning frameworks in adverse visual environments. [ABSTRACT FROM AUTHOR]

Although numerous machine learning models have been developed for NLP applications, recently, deep learning approaches have achieved remarkable results across many NLP tasks. Natural language processing (NLP) is one of the most important technologies in use today, especially due to the large and growing amount of online text, which needs to be understood in order to fully ascertain its enormous value. Extensive experiments are conducted using the E-Khool dataset and the Coursera course dataset, with empirical results demonstrating that the proposed Taylor ChOA-based RMDL model significantly outperforms state-of-the-art methods for course recommendation tasks. Preface to the Special Issue "Natural Language Processing (NLP) and Machine Learning (ML) - Theory and Applications". [Extracted from the article]

The open-source software platform hosts a large number of software defects, and the task of relying on administrators to manually assign developers is often time consuming. Thus, it is crucial to determine how to assign software defects to appropriate developers. This paper presents DARIP, a method for assigning developers to address software defects. First, the correlation between software defects and issues is considered, predicting related issues for each defect and comprehensively calculating the textual characteristics of the defect using the BERT model. Second, a heterogeneous collaborative network is constructed based on the three development behaviors of developers: reporting, commenting, and fixing. The meta-paths are defined based on the four collaborative relationships between developers: report–comment, report–fix, comment–comment, and comment–fix. The graph-embedding algorithm metapath2vec extracts developer characteristics from the heterogeneous collaborative network. Then, a classifier based on a deep learning model calculates the probability assigned to each developer category. Finally, the assignment list is obtained according to the probability ranking. Experiments on a dataset of 20,280 defects from 9 popular projects show that the DARIP method improves the average of the Recall@5, the Recall@10, and the MRR by 31.13%, 21.40%, and 25.45%, respectively, compared to the state-of-the-art method. [ABSTRACT FROM AUTHOR]

Digital twin is the digital representation of an entity, and it drives Industry 4.0. This paper presents a bibliometric analysis of digital twin in the supply chain to help researchers, industry practitioners, and academics to understand the trend, development, and focus of the areas of digital twin in the supply chain. This paper found several key clusters of research, including the designing of a digital twin model, integration of a digital twin model, application of digital twin in quality control, and digital twin in digitalization. In the embryonic stage of research, digital twin was tested in the production line with limited optimization. In the development stage, the importance of digital twin in Industry 4.0 was observed, as big data, machine learning, Industrial Internet of Things, blockchain, edge computing, and cloud-based systems complemented digital twin models. Digital twin was applied to improve sustainability in manufacturing and production logistics. In the current prosperity stage with high annual publications, the recent trends of this topic focus on the integration of deep learning, data models, and artificial intelligence for digitalization. This bibliometric analysis also found that the COVID-19 pandemic drove the start of the prosperity stage of digital twin research in the supply chain. Researchers in this field are slowly moving towards applying digital twin for human-centric systems and mass personalization to prepare to transit to Industry 5.0. [ABSTRACT FROM AUTHOR]

Nowadays, accurate and efficient short-term traffic flow forecasting plays a critical role in intelligent transportation systems (ITS). However, due to the fact that traffic flow is susceptible to factors such as weather and road conditions, traffic flow data tend to exhibit dynamic uncertainty and nonlinearity, making the construction of a robust and reliable forecasting model still a challenging task. Aiming at this nonlinear and complex traffic flow forecasting problem, this paper constructs a short-term traffic flow forecasting hybrid optimization model, SSA-ELM, based on extreme learning machine by embedding the sparrow search algorithm in order to solve the above problem. Extreme learning machine has been widely used in short-term traffic flow forecasting due to its characteristics such as low computational complexity and fast learning speed. By using the sparrow search algorithm to optimize the input weight values and hidden layer deviations in the extreme learning machine, the sparrow search algorithm is utilized to search for the global optimal solution while taking into account the original characteristics of the extreme learning machine, so that the model improves stability while increasing prediction accuracy. Experimental results on the Amsterdam A10 road traffic flow dataset show that the traffic flow forecasting model proposed in this paper has higher forecasting accuracy and stability, revealing the potential of hybrid optimization models in the field of short-term traffic flow forecasting. [ABSTRACT FROM AUTHOR]

Deep learning, a crucial technique for achieving artificial intelligence (AI), has been successfully applied in many fields. The gradual application of the latest architectures of deep learning in the field of time series forecasting (TSF), such as Transformers, has shown excellent performance and results compared to traditional statistical methods. These applications are widely present in academia and in our daily lives, covering many areas including forecasting electricity consumption in power systems, meteorological rainfall, traffic flow, quantitative trading, risk control in finance, sales operations and price predictions for commercial companies, and pandemic prediction in the medical field. Deep learning-based TSF tasks stand out as one of the most valuable AI scenarios for research, playing an important role in explaining complex real-world phenomena. However, deep learning models still face challenges: they need to deal with the challenge of large-scale data in the information age, achieve longer forecasting ranges, reduce excessively high computational complexity, etc. Therefore, novel methods and more effective solutions are essential. In this paper, we review the latest developments in deep learning for TSF. We begin by introducing the recent development trends in the field of TSF and then propose a new taxonomy from the perspective of deep neural network models, comprehensively covering articles published over the past five years. We also organize commonly used experimental evaluation metrics and datasets. Finally, we point out current issues with the existing solutions and suggest promising future directions in the field of deep learning combined with TSF. This paper is the most comprehensive review related to TSF in recent years and will provide a detailed index for researchers in this field and those who are just starting out. [ABSTRACT FROM AUTHOR]

With the development of artificial intelligence (AI), deep learning is widely used in various industries. At CRYPTO 2019, researchers used deep learning to analyze the block cipher for the first time and constructed a differential neural network distinguisher to meet a certain accuracy. In this paper, a mixture differential neural network distinguisher using ResNet is proposed to further improve the accuracy by exploring the mixture differential properties. Experiments are conducted on SIMON32/64, and the accuracy of the 8-round mixture differential neural network distinguisher is improved from 74.7% to 92.3%, compared with that of the previous differential neural network distinguisher. The prediction accuracy of the differential neural network distinguisher is susceptible to the choice of the specified input differentials, whereas the mixture differential neural network distinguisher is less affected by the input difference and has greater robustness. Furthermore, by combining the probabilistic expansion of rounds and the neutral bit, the obtained mixture differential neural network distinguisher is extended to 11 rounds, which can realize the 12-round actual key recovery attack on SIMON32/64. With an appropriate increase in the time complexity and data complexity, the key recovery accuracy of the mixture differential neural network distinguisher can be improved to 55% as compared to 52% of the differential neural network distinguisher. The mixture differential neural network distinguisher proposed in this paper can also be applied to other lightweight block ciphers. [ABSTRACT FROM AUTHOR]

This correction notice provides updates and corrections to a research paper on deep machine learning model-based cyber-attacks detection in smart power systems. The paper proposes a deep learning-based attack detection model that addresses system disturbances caused by natural events and cyber-attacks. It discusses the use of principal component analysis (PCA) for feature selection and the potential of deep learning-based and decision tree classifiers for detecting cyber-attacks in intelligent energy grids. The notice also includes updates to references, clarifications on the experimental data set, and feature selection based on PCA. The study evaluates the effectiveness of the proposed model using various assessment indexes and compares it to conventional methods, concluding that the proposed model is effective in detecting cyber-attacks and demonstrates good performance in detecting destructive attacks. [Extracted from the article]

When a machine tool is used for a long time, its bearing experiences wear and failure due to heat and vibration, resulting in damage to the machine tool. In order to make the machine tool stable for processing, this paper proposes a smart bearing diagnosis system (SBDS), which uses a gradient-weighted class activation mapping (Grad-CAM)-based convolutional neuro-fuzzy network (GC-CNFN) to detect the bearing status of the machine tool. The developed GC-CNFN is composed of a convolutional layer and neuro-fuzzy network. The convolutional layer can automatically extract vibration signal features, which are then classified using the neuro-fuzzy network. Moreover, Grad-CAM is used to analyze the attention of the diagnosis model. To verify the performance of bearing fault classification, the 1D CNN (ODCNN) and improved 1D LeNet-5 (I1DLeNet) were adopted to compare with the proposed GC-CNFN. Experimental results showed that the proposed GC-CNFN required fewer parameters (20K), had a shorter average calculation time (117.7 s), and had a higher prediction accuracy (99.88%) in bearing fault classification. The proposed SBDS can not only accurately classify bearing faults, but also help users understand the current status of the machine tool. [ABSTRACT FROM AUTHOR]

Functional movement screening (FMS) is a crucial testing method that evaluates fundamental movement patterns in the human body and identifies functional limitations. However, due to the inherent complexity of human movements, the automated assessment of FMS poses significant challenges. Prior methodologies have struggled to effectively capture and model critical human features in video data. To address this challenge, this paper introduces an automatic assessment approach for FMS by leveraging deep learning techniques. The proposed method harnesses an I3D network to extract spatiotemporal video features across various scales and levels. Additionally, an attention mechanism (AM) module is incorporated to enable the network to focus more on human movement characteristics, enhancing its sensitivity to diverse location features. Furthermore, the multilayer perceptron (MLP) module is employed to effectively discern intricate patterns and features within the input data, facilitating its classification into multiple categories. Experimental evaluations conducted on publicly available datasets demonstrate that the proposed approach achieves state-of-the-art performance levels. Notably, in comparison to existing state-of-the-art (SOTA) methods, this approach exhibits a marked improvement in accuracy. These results corroborate the efficacy of the I3D-AM-MLP framework, indicating its significance in extracting advanced human movement feature expressions and automating the assessment of functional movement screening. [ABSTRACT FROM AUTHOR]

This paper studies the application of artificial intelligence to milling machines, focusing specifically on identifying the inputs (features) required for predicting surface roughness. Previous studies have extensively reviewed and presented useful features for surface roughness prediction. However, applying research findings to actual operational factories can be challenging due to the additional costs of sensor installations and the diverse environments present in each factory setting. To address these issues, in this paper, we introduced effective features for predicting surface roughness in situations where additional sensors are not installed in the existing environment. These features include feed per tooth,  F z ; material removal rate, Q; and the load information. These features are suitable for use in highly constrained environments where separate sensor installation is not required, making it possible to apply the research findings in various factory environments. Additionally, to efficiently select the optimal subset for surface roughness prediction among subsets formed by available features, we apply causality to the feature selection method, proposing an approach called causality-driven efficient feature selection. The experimental results demonstrate that the features introduced in this paper are quite suitable for predicting surface roughness and that the proposed feature selection approach is more effective and efficient compared to existing selection methods. [ABSTRACT FROM AUTHOR]

This study aims to understand the development trends and research structure of articles on artificial intelligence (AI) and information processing in the past 10 years. In particular, this study analyzed 13,294 papers published from 2012 to 2021 in the Web of Science, used the bibliometric analysis method to visualize the data of the papers, and drew a scientific knowledge map. By exploring the development of mainstream journals, author and country rankings, keyword evolution, and research field rankings in the past 10 years, this study uncovered key trends affecting AI progress and information processing that provide insights and serve as an important reference for future AI research and information processing. The results revealed a gradual increase in publications over the past decade, with explosive growth after 2020. The most prolific researchers in this field were Xu, Z.S.; Pedrycz, W.; Herrera-Viedma, E.; the major contributing countries were China, the USA, and Spain. In the AI and information processing research, keywords including "Deep learning", "Machine learning", and "Feature extraction" are components that play a crucial role. Additionally, the most representative research areas were "Engineering", "Operations Research and Management Science", and "Automation Control Systems". Overall, this study used bibliometric analysis to provide an overview of the latest trends in artificial intelligence and information processing. Although AI and information processing have been applied to various research areas, many other sub-topics can be further applied. Based on the findings, this study presented research insights and proposed suggestions for future research directions on AI and information processing. [ABSTRACT FROM AUTHOR]

Respiratory viruses, such as COVID-19, are spread over time and space based on human-to-human interactions. Human mobility plays a key role in the propagation of the virus. Different types of sensors in smart cities are able to continuously monitor traffic-related human mobility, showing the impact of COVID-19 on traffic volumes and patterns. In a similar way, traffic volumes measured by smart traffic sensors provide a proxy variable to capture human mobility, which is expected to have an impact on new COVID-19 infections. Adding traffic data from smart city sensors to machine learning models designed to estimate upcoming COVID-19 incidence values should provide optimized results compared to models based on COVID-19 data alone. This paper proposes a novel model to extract spatio-temporal patterns in the spread of the COVID-19 virus for short-term predictions by organizing COVID-19 incidence and traffic data as interrelated temporal sequences of spatial images. The model is trained and validated with real data from the city of Madrid in Spain for 84 weeks, combining information from 4372 traffic measuring points and 143 COVID-19 PCR test centers. The results are compared with a baseline model designed for the extraction of spatio-temporal patterns from COVID-19-only sequences of images, showing that using traffic information enhances the results when forecasting a new wave of infections (MSE values are reduced by a 70% factor). The information that traffic data has on the spread of the COVID-19 virus is also analyzed, showing that traffic data alone is not sufficient for accurate COVID-19 forecasting. [ABSTRACT FROM AUTHOR]

This paper discusses the challenges of the hyperparameter tuning in deep learning models and proposes a green approach to the neural architecture search process that minimizes its environmental impact. The traditional approach of neural architecture search involves sweeping the entire space of possible architectures, which is computationally expensive and time-consuming. Recently, to address this issue, performance predictors have been proposed to estimate the performance of different architectures, thereby reducing the search space and speeding up the exploration process. The proposed approach aims to develop a performance predictor by training only a small percentage of the possible hyperparameter configurations. The suggested predictor can be queried to find the best configurations without training them on the dataset. Numerical examples of image denoising and classification enable us to evaluate the performance of the proposed approach in terms of performance and time complexity. [ABSTRACT FROM AUTHOR]

Network public opinion plays a crucial role in the behavior and decision making of various stakeholders, including farmers, middlemen, and consumers. It also affects the price fluctuations of small-scale agricultural products. Understanding the transmission path and spillover effect of network public opinion on the price fluctuations of these products is essential for ensuring their sustainable development and price stability. This paper selects the monthly data of network public opinion and related market prices of small-scale agricultural products from January 2014 to December 2021, constructs a network public opinion value through the sentiment classification results of deep learning models, and uses the trivariate VAR-BEKK-GARCH(1,1) model and spillover index model to study the spillover effect and spillover index of network public opinion on the market prices of small-scale agricultural products (national average price and origin price). The results show that: (1) There is a bidirectional volatility spillover effect between public opinion sentiment and the market prices of small-scale agricultural products. Additionally, this two-way volatility spillover effect is also evident between the average market prices and the origin prices of these commodities. (2) The influence of network public opinion on the market prices of small-scale agricultural products is substantial, with the spillover index being more pronounced for origin prices than for national average prices and reaching its zenith earlier. Consequently, based on these results, recommendations are provided to adapt planting and inventory strategies, enhance vigilance towards price risk transmission amongst small-scale agricultural product markets, and improve the comprehensive information platform encompassing the entire industry chain. [ABSTRACT FROM AUTHOR]

Deep learning technology has made significant progress in agricultural image recognition tasks, but the parameter adjustment of deep models usually requires a lot of manual intervention, which is time-consuming and inefficient. To solve this challenge, this paper proposes an adaptive parameter tuning strategy that combines sine–cosine algorithm with Tent chaotic mapping to enhance sea horse optimization, which improves the search ability and convergence stability of standard sea horse optimization algorithm (SHO). Through adaptive optimization, this paper determines the best parameter configuration in ResNet-50 neural network and optimizes the model performance. The improved ESHO algorithm shows superior optimization effects than other algorithms in various performance indicators. The improved model achieves 96.7% accuracy in the corn disease image recognition task, and 96.4% accuracy in the jade fungus image recognition task. These results show that ESHO can not only effectively improve the accuracy of agricultural image recognition, but also reduce the need for manual parameter adjustment. [ABSTRACT FROM AUTHOR]

Urban logistics encompass transportation and delivery operations within densely populated urban areas. It faces significant challenges from the evolving dynamic and stochastic nature of on-demand and conventional logistics services. Further challenges arise with application doctrines shifting towards crowd-sourced platforms. As a result, "traditional" deterministic approaches do not adequately fulfil constantly evolving customer expectations. To maintain competitiveness, logistic service providers must adopt proactive and anticipatory systems that dynamically model and evaluate probable (future) events, i.e., stochastic information. These events manifest in problem characteristics such as customer requests, demands, travel times, parking availability, etc. The Stochastic Dynamic Vehicle Routing Problem (SDVRP) addresses the dynamic and stochastic information inherent in urban logistics. This paper aims to analyse the key concepts, challenges, and recent advancements and opportunities in the evolving urban logistics landscape and assess the evolution from classical VRPs, via DVRPs, to state-of-art SDVRPs. Further, coupled with non-reactive techniques, this paper provides an in-depth overview of cutting-edge model-based and model-free reactive solution approaches. Although potent, these approaches become restrictive due to the "curse of dimensionality". Sacrificing granularity for scalability, researchers have opted for aggregation and decomposition techniques to overcome this problem and recent approaches explore solutions using deep learning. In the scope of this research, we observed that addressing real-world SDVRPs with a comprehensive resolution encounters a set of challenges, emphasising a substantial gap in the research field that warrants further exploration. [ABSTRACT FROM AUTHOR]

The increasing complexity of deep learning models can make it difficult to interpret and fit models beyond a purely accuracy-focused evaluation. This is where interpretable and eXplainable Artificial Intelligence (XAI) come into play to facilitate an understanding of the inner workings of models. Consequently, alternatives have emerged, such as class activation mapping (CAM) techniques aimed at identifying regions of importance for an image classification model. However, the behavior of such models can be highly dependent on the type of architecture and the different variants of convolutional neural networks. Accordingly, this paper evaluates three Convolutional Neural Network (CNN) architectures (VGG16, ResNet50, ConvNext-T) against seven CAM models (GradCAM, XGradCAM, HiResCAM, LayerCAM, GradCAM++, GradCAMElementWise, and EigenCAM), indicating that the CAM maps obtained with ConvNext models show less variability among them, i.e., they are less dependent on the selected CAM approach. This study was performed on an image dataset for the classification of coffee leaf rust and evaluated using the RemOve And Debias (ROAD) metric. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of cyber-attack detection in a discrete event system by proposing a novel model. The model utilizes graph convolutional networks to extract spatial features from event sequences. Subsequently, it employs gated recurrent units to re-extract spatio-temporal features from these spatial features. The obtained spatio-temporal features are then fed into an attention model. This approach enables the model to learn the importance of different event sequences, ensuring that it is sufficiently general for identifying cyber-attacks, obviating the need to specify attack types. Compared with traditional methods that rely on synchronous product computations to synthesize diagnosers, our deep learning-based model circumvents state explosion problems. Our method facilitates real-time and efficient cyber-attack detection, eliminating the necessity to specifically identify system states or distinguish attack types, thereby significantly simplifying the diagnostic process. Additionally, we set an adjustable probability threshold to determine whether an event sequence has been compromised, allowing for customization to meet diverse requirements. Experimental results demonstrate that the proposed method performs well in cyber-attack detection, achieving over 99.9 % accuracy at a 1 % threshold and a weighted F1-score of 0.8126, validating its superior performance. [ABSTRACT FROM AUTHOR]

Accurate robot dynamics models are crucial for safe and stable control as well as for generalization to new conditions. Data-driven methods are increasingly used in robotics dynamics modeling for their superior approximation, with extrapolation performance being a critical efficacy indicator. While deep learning is widely used, it often overlooks essential physical principles, leading to weaker extrapolation capabilities. Recent innovations have introduced physics-inspired deep networks that integrate deep learning with physics, leading to improved extrapolation due to their informed structure, but potentially to underfitting in real-world scenarios due to the presence of unmodeled phenomena. This paper presents an experimental framework to assess the extrapolation capabilities of data-driven methods. Using this framework, physics-inspired deep networks are applied to learn the inverse dynamics models of a simulated robotic manipulator and two real physical systems. The results show that under ideal observation conditions physics-inspired models can learn the system's underlying structure and demonstrate strong extrapolation capabilities, indicating a promising direction in robotics by offering more accurate and interpretable models. However, in real systems their extrapolation often falls short because the physical priors do not capture all dynamic phenomena, indicating room for improvement in practical applications. [ABSTRACT FROM AUTHOR]

Weakly supervised semantic segmentation (WSSS) aims to segment objects without a heavy burden of dense annotations. Pseudo-masks serve as supervisory information for training segmentation models, which is crucial to the performance of segmentation models. However, the generated pseudo-masks contain significant noisy labels, which leads to poor performance of the segmentation models trained on these pseudo-masks. Few studies address this issue, as these noisy labels remain inevitable even after the pseudo-masks are improved. In this paper, we propose an uncertainty-weight transform module to mitigate the impact of noisy labels on model performance. It is noteworthy that our approach is not aimed at eliminating noisy labels but rather enhancing the robustness of the model to noisy labels. The proposed method adopts a frequency-based approach to estimate pixel uncertainty. Moreover, the uncertainty of pixels is transformed into loss weights through a set of well-designed functions. After dynamically assigning weights, the model allocates attention to each pixel in a significantly differentiated manner. Meanwhile, the impact of noisy labels on model performance is weakened. Experiments validate the effectiveness of the proposed method, achieving state-of-the-art results of 69.3% on PASCAL VOC 2012 and 39.3% on MS COCO 2014, respectively. [ABSTRACT FROM AUTHOR]

Due to the complexity and illegibility of medical images, it brings inconvenience and difficulty to the diagnosis of medical personnel. To address these issues, an optimization algorithm called GSL(Gradient sine linear) based on Adam algorithm improvement is proposed in this paper, which introduces gradient pruning strategy, periodic adjustment of learning rate, and linear interpolation strategy. The gradient trimming technique can scale the gradient to prevent gradient explosion, while the periodic adjustment of the learning rate and linear interpolation strategy adjusts the learning rate according to the characteristics of the sinusoidal function, accelerating the convergence while reducing the drastic parameter fluctuations, improving the efficiency and stability of training. The experimental results show that compared to the classic Adam algorithm, this algorithm can demonstrate better classification accuracy, the GSL algorithm achieves an accuracy of 78% and 75.2% on the MobileNetV2 network and ShuffleNetV2 network under the Gastroenterology dataset; and on the MobileNetV2 network and ShuffleNetV2 network under the Glaucoma dataset, an accuracy of 84.72% and 83.12%. The GSL optimizer achieved significant performance improvement on various neural network structures and datasets, proving its effectiveness and practicality in the field of deep learning, and also providing new ideas and methods for solving the difficulties in medical image recognition. [ABSTRACT FROM AUTHOR]

Person re-identification (ReID) refers to the task of retrieving target persons from image libraries captured by various distinct cameras. Over the years, person ReID has yielded favorable recognition outcomes under typical visible light conditions, yet there remains considerable scope for enhancement in challenging conditions. The challenges and research gaps include the following: multi-modal data fusion, semi-supervised and unsupervised learning, domain adaptation, ReID in 3D space, fast ReID, decentralized learning, and end-to-end systems. The main problems to be solved, which are the occlusion problem, viewpoint problem, illumination problem, background problem, resolution problem, openness problem, etc., remain challenges. For the first time, this paper uses person ReID in special scenarios as a basis for classification to categorize and analyze the related research in recent years. Starting from the perspectives of person ReID methods and research directions, we explore the current research status in special scenarios. In addition, this work conducts a detailed experimental comparison of person ReID methods employing deep learning, encompassing both system development and comparative methodologies. In addition, we offer a prospective analysis of forthcoming research approaches in person ReID and address unresolved concerns within the field. [ABSTRACT FROM AUTHOR]

This paper introduces a novel method called AcoRec, which employs an enhanced version of Continuous Ant Colony Optimization for hyper-parameter adjustment and integrates a non-deterministic model to generate diverse recommendation lists. AcoRec is designed for cold-start users and long-tail item recommendations by leveraging implicit data from collaborative filtering techniques. Continuous Ant Colony Optimization is revisited with the convenience and flexibility of deep learning solid methods and extended within the AcoRec model. The approach computes stochastic variations of item probability values based on the initial predictions derived from a selected item-similarity model. The structure of the AcoRec model enables efficient handling of high-dimensional data while maintaining an effective balance between diversity and high recall, leading to recommendation lists that are both varied and highly relevant to user tastes. Our results demonstrate that AcoRec outperforms existing state-of-the-art methods, including two random-walk models, a graph-based approach, a well-known vanilla autoencoder model, an ACO-based model, and baseline models with related similarity measures, across various evaluation scenarios. These evaluations employ well-known metrics to assess the quality of top-N recommendation lists, using popular datasets including MovieLens, Pinterest, and Netflix. [ABSTRACT FROM AUTHOR]

In this study, a gastrointestinal image classification method based on the improved Adam algorithm is proposed. Gastrointestinal image classification is of great significance in the field of medical image analysis, but it presents numerous challenges, including slow convergence, susceptibility to local minima, and the complexity and imbalance of medical image data. Although the Adam algorithm is widely used in stochastic gradient descent, it tends to suffer from overfitting and gradient explosion issues when dealing with complex data. To address these problems, this paper proposes an improved Adam algorithm, AdamW_AGC, which combines the weight decay and Adaptive Gradient Clipping (AGC) strategies. Weight decay is a common regularization technique used to prevent machine learning models from overfitting. Adaptive gradient clipping avoids the gradient explosion problem by restricting the gradient to a suitable range and helps accelerate the convergence of the optimization process. In order to verify the effectiveness of the proposed algorithm, we conducted experiments on the HyperKvasir dataset and validation experiments on the MNIST and CIFAR10 standard datasets. Experimental results on the HyperKvasir dataset demonstrate that the improved algorithm achieved a classification accuracy of 75.8%, compared to 74.2% for the traditional Adam algorithm, representing an improvement of 1.6%. Furthermore, validation experiments on the MNIST and CIFAR10 datasets resulted in classification accuracies of 98.69% and 71.7%, respectively. These results indicate that the AdamW_AGC algorithm has advantages in handling complex, high-dimensional medical image classification tasks, effectively improving both classification accuracy and training stability. This study provides new ideas and expansions for future optimizer research. [ABSTRACT FROM AUTHOR]

The abundance of publicly available data on the internet within the e-marketing domain is consistently expanding. A significant portion of this data revolve around consumers' perceptions and opinions regarding the goods or services of organizations, making it valuable for market intelligence collectors in marketing, customer relationship management, and customer retention. Sentiment analysis serves as a tool for examining customer sentiment, marketing initiatives, and product appraisals. This valuable information can inform decisions related to future product and service development, marketing campaigns, and customer service enhancements. In social media, predicting ratings is commonly employed to anticipate product ratings based on user reviews. Our study provides an extensive benchmark comparison of different deep learning models, including convolutional neural networks (CNN), recurrent neural networks (RNN), and bi-directional long short-term memory (Bi-LSTM). These models are evaluated using various word embedding techniques, such as bi-directional encoder representations from transformers (BERT) and its derivatives, FastText, and Word2Vec. The evaluation encompasses two setups: 5-class versus 3-class. This paper focuses on sentiment analysis using neural network-based models for consumer sentiment prediction by evaluating and contrasting their performance indicators on a dataset of reviews of different products from customers of an online women's clothes retailer. [ABSTRACT FROM AUTHOR]

In recent years, side-channel analysis based on deep learning has garnered significant attention from researchers. A pivotal reason for this lies in the fact that deep learning-based side-channel analysis requires minimal preprocessing of side-channel data. The automatic feature extraction property of deep learning methods drastically reduces the workload for researchers, enabling them to focus more on the core issues of side-channel analysis, namely, extracting sensitive information by attacking devices. However, in prior studies, most scholars have concentrated more on the model construction process, with little research focusing on the choice of optimizers.This paper explores a novel deep learning-based optimization algorithm—CPSGD (combined projection stochastic gradient descent). The algorithm comprises two variants, designed, respectively, for unprotected side-channel analysis (CPSGD1) and desynchronized side-channel analysis (CPSGD2), and their convergence has been theoretically proven. Experimental results demonstrate that, while maintaining the neural network structure unchanged, CPSGD1 exhibits the best performance on unprotected datasets compared to other publicly available optimizers, whereas CPSGD2 performs optimally on desynchronized datasets. [ABSTRACT FROM AUTHOR]

Currently, the decision boundary of the multi-class anomaly detection algorithm based on deep learning does not sufficiently capture the positive class region, posing a risk of abnormal sample features falling into the domain of normal sample features and potentially leading to misleading outcomes in practical applications. In response to the above problems, this paper proposes a new method called multi-class hypersphere anomaly detection (MMHAD) based on the edge outlier exposure set and margin. The method aims to utilize convolutional neural networks for joint training of all normal object classes, identifying a shared set of outlier exposures, learning compact identification features, and setting appropriate edge parameters to guide the model in mapping outliers outside the hypersphere. This approach enables more comprehensive detection of various types of exceptions. The experiments demonstrate that the algorithm is superior to the most advanced baseline method, with an improvement of 26.0%, 8.2%, and 20.1% on CIFAR-10 and 14.8%, 12.0%, and 20.1% on FMNIST in the cases of (2/8), (5/5), and (9,1), respectively. Furthermore, we investigate the challenging (2/18) case on CIFAR-100, where our method achieves approximately 17.4% AUROC gain. Lastly, for a recycling waste dataset with the (4/1) case, our MMHAD yields a notable 22% enhancement in performance. Experimental results show the effectiveness of the proposed model in multi-classification anomaly detection. [ABSTRACT FROM AUTHOR]

Medical image denoising has numerous real-world applications. Despite their widespread use, existing medical image denoising methods fail to address complex noise patterns and typically generate artifacts in numerous cases. This paper proposes a novel medical image denoising method that learns denoising using an end-to-end learning strategy. Furthermore, the proposed model introduces a novel deep–wider residual block to capture long-distance pixel dependencies for medical image denoising. Additionally, this study proposes leveraging multi-head attention-guided image reconstruction to effectively denoise medical images. Experimental results illustrate that the proposed method outperforms existing qualitative and quantitative evaluation methods for numerous medical image modalities. The proposed method can outperform state-of-the-art models for various medical image modalities. It illustrates a significant performance gain over its counterparts, with a cumulative PSNR score of 8.79 dB. The proposed method can also denoise noisy real-world medical images and improve clinical application performance such as abnormality detection. [ABSTRACT FROM AUTHOR]

In this paper, we perform neural cryptanalysis on five block ciphers: Data Encryption Standard (DES), Simplified DES (SDES), Advanced Encryption Standard (AES), Simplified AES (SAES), and SPECK. The block ciphers are investigated on three different deep learning-based attacks, Encryption Emulation (EE), Plaintext Recovery (PR), Key Recovery (KR), and Ciphertext Classification (CC) attacks. The attacks attempt to break the block ciphers in various cases, such as different types of plaintexts (i.e., block-sized bit arrays and texts), different numbers of round functions and quantity of training data, different text encryption methods (i.e., Word-based Text Encryption (WTE) and Sentence-based Text Encryption (STE)), and different deep learning model architectures. As a result, the block ciphers can be vulnerable to EE and PR attacks using a large amount of training data, and STE can improve the strength of the block ciphers, unlike WTE, which shows almost the same classification accuracy as the plaintexts, especially in a CC attack. Moreover, especially in the KR attack, the Recurrent Neural Network (RNN)-based deep learning model shows higher average Bit Accuracy Probability than the fully connected-based deep learning model. Furthermore, the RNN-based deep learning model is more suitable than the transformer-based deep learning model in the CC attack. Besides, when the keys are the same as the plaintexts, the KR attack can perfectly break the block ciphers, even if the plaintexts are randomly generated. Additionally, we identify that DES and SPECK32/64 applying two round functions are more vulnerable than those applying the single round function by performing the KR attack with randomly generated keys and randomly generated single plaintext. [ABSTRACT FROM AUTHOR]

Neuronal models have remained an important area of research in computer science. The dendritic neuron model (DNM) is a novel neuronal model in recent years. Previous studies have focused on training DNM using more appropriate algorithms. This paper proposes an improvement to DNM based on the activity of excitation and proposes three new models. Each of the three improved models are designed to mimic the excitation and inhibition activity of neurons. The improved model proposed in this paper is shown to be effective in the experimental part. All three models and original DNM have their own strengths, so it can be considered that the new model proposed in this paper well enriches the diversity of neuronal models and contributes to future research on networks models. [ABSTRACT FROM AUTHOR]

Fire detection and monitoring systems based on machine vision have been gradually developed in recent years. Traditional centralized deep learning model training methods transfer large amounts of video image data to the cloud, making image data privacy and confidentiality difficult. In order to protect the data privacy in the fire detection system with heterogeneous data and to enhance its efficiency, this paper proposes an improved federated learning algorithm incorporating computer vision: FedVIS, which uses a federated dropout and gradient selection algorithm to reduce communication overhead, and uses a transformer to replace a traditional neural network to improve the robustness of federated learning in the context of heterogeneous data. FedVIS can reduce the communication overhead in addition to reducing the catastrophic forgetting of previous devices, improving convergence, and producing superior global models. In this paper's experimental results, FedVIS outperforms the common federated learning methods FedSGD, FedAVG, FedAWS, and CMFL, and improves the detection effect by reducing communication costs. As the amount of clients increases, the accuracy of other algorithmic models decreases by 2–5%, and the number of communication rounds required increases significantly; meanwhile, our method maintains a superior detection performance while requiring roughly the same number of communication rounds. [ABSTRACT FROM AUTHOR]

Electroencephalography (EEG) signals can be used as a neuroimaging indicator to analyze brain-related diseases and mental states, such as schizophrenia, which is a common and serious mental disorder. However, the main limiting factor of using EEG data to support clinical schizophrenia diagnosis lies in the inadequacy of both objective characteristics and effective data analysis techniques. Random matrix theory (RMT) and its linear eigenvalue statistics (LES) can provide an effective mathematical modeling method for exploring the statistical properties of non-stationary nonlinear systems, such as EEG signals. To obtain an accurate classification and diagnosis of schizophrenia, this paper proposes a LES-based deep learning network scheme in which a series of random matrixes, consisting of EEG data sliding window sampling and their eigenvalues, are employed as features for deep learning. Due to the fact that the performance of the LES-based scheme is sensitive to the LES's test function, the proposed LES-based deep learning network is embedded with two ways of combining LES's test functions with learning techniques: the first is to have the LES's test function assigned, while, using the second way, the optimal LES's test function should be solved in a functional optimization problem. In this paper, various test functions and different optimal learning methods were coupled in experiments. Our results revealed a binary classification accuracy of nearly 90% in distinguishing between healthy controls (HC) and patients experiencing the first episode of schizophrenia (FES). Additionally, we achieved a ternary classification accuracy of approximately 70% by including clinical high risk for psychosis (CHR). The LES-embedded approach yielded notably higher classification accuracy compared to conventional machine learning methods and standard convolutional neural networks. As the performance of schizophrenia classification is strongly influenced by test functions, a functional optimization problem was proposed to identify an optimized test function, and an approximated parameter optimization problem was introduced to limit the search area of suitable basis functions. Furthermore, the parameterization test function optimization problem and the deep learning network were coupled to be synchronously optimized during the training process. The proposal approach achieved higher classification accuracy rates of 96.87% between HC and FES, with an additional 89.06% accuracy when CHR was included. The experimental studies demonstrated that the proposed LES-based method was significantly effective for schizophrenic EEG data classification. [ABSTRACT FROM AUTHOR]

Employee attrition and high turnover have become critical challenges faced by various sectors in today's competitive job market. In response to these pressing issues, organizations are increasingly turning to artificial intelligence (AI) to predict employee attrition and implement effective retention strategies. This paper delves into the application of explainable AI (XAI) in identifying potential employee turnover and devising data-driven solutions to address this complex problem. The first part of the paper examines the escalating problem of employee attrition in specific industries, analyzing the detrimental impact on organizational productivity, morale, and financial stability. The second section focuses on the utilization of AI techniques to predict employee attrition. AI can analyze historical data, employee behavior, and various external factors to forecast the likelihood of an employee leaving an organization. By identifying early warning signs, businesses can intervene proactively and implement personalized retention efforts. The third part introduces explainable AI techniques which enhance the transparency and interpretability of AI models. By incorporating these methods into AI-based predictive systems, organizations gain deeper insights into the factors driving employee turnover. This interpretability enables human resources (HR) professionals and decision-makers to understand the model's predictions and facilitates the development of targeted retention and recruitment strategies that align with individual employee needs. [ABSTRACT FROM AUTHOR]

Resistance spot welding poses potential challenges for automotive manufacturing enterprises with regard to ensuring the real-time and accurate quality detection of each welding spot. Nowadays, many machine learning and deep learning methods have been proposed to utilize monitored sensor data to solve these challenges. However, poor detection results or process interpretations are still unaddressed key issues. To bridge the gap, this paper takes the automotive bodies as objects, and proposes a resistance spot welding quality online detection method with dynamic current and resistance data based on a combined convolutional neural network (CNN), long short-term memory network (LSTM), and an attention mechanism. First, an overall online detection framework using an edge–cloud collaboration was proposed. Second, an online quality detection model was established. In it, the combined CNN and LSTM network were used to extract local detail features and temporal correlation features of the data. The attention mechanism was introduced to improve the interpretability of the model. Moreover, the imbalanced data problem was also solved with a multiclass imbalance algorithm and weighted cross-entropy loss function. Finally, an experimental verification and analysis were conducted. The results show that the quality detection accuracy was 98.5%. The proposed method has good detection performance and real-time detection abilities for the in-site welding processes of automobile bodies. [ABSTRACT FROM AUTHOR]

Recent advancements in deep learning have led to various challenges, one of which is the issue of data privacy in training data. To address this issue, federated learning, a technique that merges models trained by clients on servers, has emerged as an attractive solution. However, federated learning faces challenges related to data heterogeneity and system heterogeneity. Recent observations suggest that incorporating pre-trained models into federated learning can mitigate some of these challenges. Nonetheless, the main drawback of pre-trained models lies in their typically large model size, leading to excessive data transmission when clients send these models to the server. Additionally, federated learning involves multiple global steps, which means transmitting a large language model to multiple clients results in too much data exchange. In this paper, we propose a novel approach to address this challenge using adapters. Adapters demonstrate training efficiency by training a small capacity adapter layer alongside a large language model. This unique characteristic reduces the volume of data transmission, offering a practical solution to the problem. The evaluation results demonstrate that the proposed method achieves a reduction in training time of approximately 20–40% and a transmission speed improvement of over 98% compared to previous approaches. [ABSTRACT FROM AUTHOR]

(1) Background: Voiceprint recognition technology uses individual vocal characteristics for identity authentication and faces many challenges in cross-scenario applications. The sound environment, device characteristics, and recording conditions in different scenarios cause changes in sound features, which, in turn, affect the accuracy of voiceprint recognition. (2) Methods: Based on the latest trends in deep learning, this paper uses the perceptual wavelet packet entropy (PWPE) method to extract the basic voiceprint features of the speaker before using the efficient channel attention (ECA) block and the Res2Net block to extract deep features. The PWPE block removes the effect of environmental noise on voiceprint features, so the perceptual wavelet packet entropy-guided ECA–Res2Net–Time-Delay-Neural-Network (PWPE-ECA-Res2Net-TDNN) model shows an excellent robustness. The ECA-Res2Net-TDNN block uses temporal statistical pooling with a multi-head attention mechanism to weight frame-level audio features, resulting in a weighted average of the final representation of the speech-level feature vectors. The sub-center ArcFace loss function is used to enhance intra-class compactness and inter-class differences, avoiding classification via output value alone like the softmax loss function. Based on the aforementioned elements, the PWPE-ECA-Res2Net-TDNN model for speaker recognition is designed to extract speaker feature embeddings more efficiently in cross-scenario applications. (3) Conclusions: The experimental results demonstrate that, compared to the ECAPA-TDNN model using MFCC features, the PWPE-based ECAPA-TDNN model performs better in terms of cross-scene recognition accuracy, exhibiting a stronger robustness and better noise resistance. Furthermore, the model maintains a relatively short recognition time even under the highest recognition rate conditions. Finally, a set of ablation experiments targeting each module of the proposed model is conducted. The results indicate that each module contributes to an improvement in the recognition performance. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) is a key enabler technology that recently received significant attention from the scientific community across the globe. It helps transform everyone's life by connecting physical and virtual devices with each other to offer staggering benefits, such as automation and control, higher productivity, real-time information access, and improved efficiency. However, IoT devices and their accumulated data are susceptible to various security threats and vulnerabilities, such as data integrity, denial-of-service, interception, and information disclosure attacks. In recent years, the IoT with blockchain technology has seen rapid growth, where smart contracts play an essential role in validating IoT data. However, these smart contracts can be vulnerable and degrade the performance of IoT applications. Hence, besides offering indispensable features to ease human lives, there is also a need to confront IoT environment security attacks, especially data integrity attacks. Toward this aim, this paper proposed an artificial intelligence-based system model with a dual objective. It first detects the malicious user trying to compromise the IoT environment using a binary classification problem. Further, blockchain technology is utilized to offer tamper-proof storage to store non-malicious IoT data. However, a malicious user can exploit the blockchain-based smart contract to deteriorate the performance IoT environment. For that, this paper utilizes deep learning algorithms to classify malicious and non-malicious smart contracts. The proposed system model offers an end-to-end security pipeline through which the IoT data are disseminated to the recipient. Lastly, the proposed system model is evaluated by considering different assessment measures that comprise the training accuracy, training loss, classification measures (precision, recall, and F1 score), and receiver operating characteristic (ROC) curve. [ABSTRACT FROM AUTHOR]

At present, deep learning has achieved excellent achievements in image processing and computer vision and is widely used in the field of watermarking. Attention mechanism, as the research hot spot of deep learning, has not yet been applied in the field of watermarking. In this paper, we propose a deep learning and attention network for robust image watermarking (DARI-Mark). The framework includes four parts: an attention network, a watermark embedding network, a watermark extraction network, and an attack layer. The attention network used in this paper is the channel and spatial attention network, which calculates attention weights along two dimensions, channel and spatial, respectively, assigns different weights to pixels in different channels at different positions and is applied in the watermark embedding and watermark extraction stages. Through end-to-end training, the attention network can locate nonsignificant areas that are insensitive to the human eye and assign greater weights during watermark embedding, and the watermark embedding network selects this region to embed the watermark and improve the imperceptibility. In watermark extraction, by setting the loss function, larger weights can be assigned to watermark-containing features and small weights to noisy signals, so that the watermark extraction network focuses on features about the watermark and suppresses noisy signals in the attacked image to improve robustness. To avoid the phenomenon of gradient disappearance or explosion when the network is deep, both the embedding network and the extraction network have added residual modules. Experiments show that DARI-Mark can embed the watermark without affecting human subjective perception and that it has good robustness. Compared with other state-of-the-art watermarking methods, the proposed framework is more robust to JPEG compression, sharpening, cropping, and noise attacks. [ABSTRACT FROM AUTHOR]

In recent years, convolutional neural networks (CNNs) have emerged as highly efficient architectures for image and audio classification tasks, gaining widespread adoption in state-of-the-art methodologies. While CNNs excel in machine learning scenarios where the data representation exhibits a grid structure, they face challenges in generalizing to other data types. For instance, they struggle with data structured on 3D meshes (e.g., measurements from a network of meteorological stations) or data represented by graph structures (e.g., molecular graphs). To address such challenges, the scientific literature proposes novel graph-based convolutional network architectures, extending the classical convolution concept to data structures defined by graphs. In this paper, we use such a deep learning architecture to examine graphs defined using the ICD-10 codes appearing in the medical data of patients who suffered hemorrhagic stroke in Hungary in the period 2006–2012. The purpose of the analysis is to predict the risk of stroke by examining a patient's ICD graph. Finally, we also compare the effectiveness of this method with classical machine learning classification methods. The results demonstrate that the graph-based method can predict the risk of stroke with an accuracy of over 73%, which is more than 10% higher than the classical methods. [ABSTRACT FROM AUTHOR]

Wireless communication technologies have profoundly impacted the interconnectivity of mobile users and terminals. Nevertheless, the exponential increase in the number of users poses significant challenges, particularly in interference management, which is a major concern in wireless communication. Machine learning (ML) approaches have emerged as powerful tools for solving various problems in this domain. However, existing studies have not fully addressed the problem of interference management for wireless communication using ML techniques. In this paper, we explore the application of recurrent neural network (RNN) approaches to address co-channel interference in wireless communication. Specifically, we investigate the effectiveness of long short-term memory (LSTM), bidirectional LSTM (Bi-LSTM), and gated recurrent unit (GRU) network architectures in two different network settings. The first network comprises 10 connected devices, while the second network involves 20 devices. Our experimental results demonstrate that Bi-LSTM outperforms LSTM and GRU in terms of mean squared error, normalized mean squared error, and sum rate. While LSTM and GRU produce similar results, LSTM exhibits a marginal advantage over GRU. In addition, a combined RNN approach is also studied, and it can provide better results in dense networks. [ABSTRACT FROM AUTHOR]

Ship detection and identification play pivotal roles in ensuring navigation safety and facilitating efficient maritime traffic management. Aiming at ship detection in complex environments, which often faces problems such as the dense occlusion of ship targets, low detection accuracy, and variable environmental conditions, in this paper, we propose a ship detection algorithm CSD-YOLO (Context guided block module, Slim-neck, Deformable large kernel attention-You Only Look Once) based on the deformable large kernel attention (D-LKA) mechanism, which was improved based on YOLOv8 to enhance its performance. This approach integrates several innovations to bolster its performance. Initially, the utilization of the Context Guided Block module (CG block) enhanced the c2f module of the backbone network, thereby augmenting the feature extraction capabilities and enabling a more precise capture of the key image information. Subsequently, the introduction of a novel neck architecture and the incorporation of the slim-neck module facilitated more effective feature fusion, thereby enhancing both the accuracy and efficiency of detection. Furthermore, the algorithm incorporates a D-LKA mechanism to dynamically adjust the convolution kernel shape and size, thereby enhancing the model's adaptability to varying ship target shapes and sizes. To address data scarcity in complex marine environments, the experiments utilized a fused dataset comprising the SeaShips dataset and a proprietary dataset. The experimental results demonstrate that the CSD-YOLO algorithm outperformed the YOLOv8n algorithm across all model evaluation metrics. Specifically, the precision rate (precision) was 91.5%, the recall rate (recall) was 89.5%, and the mean accuracy (mAP) was 91.5%. Compared to the benchmark algorithm, the Recall was improved by 0.7% and the mAP was improved by 0.4%. These results indicate that the CSD-YOLO algorithm can effectively meet the requirements for ship target recognition and tracking in complex marine environments. [ABSTRACT FROM AUTHOR]

This paper aims to enhance the existing Automatic Meter Reading (AMR) technologies for utilities in the public services sector, such as water, electricity, and gas, by allowing users to regularly upload images of their meters, which are then automatically processed by machines for digit recognition. We propose an end-to-end AMR approach designed explicitly for unconstrained environments, offering practical solutions to common failures encountered during the automatic recognition process, such as image blur, perspective distortion, partial reflection, poor lighting, missing digits, and intermediate digit states, to reduce the failure rate of automatic meter readings. The system's first stage involves checking the quality of the user-uploaded images through the SVM method and requesting re-uploads for images unsuitable for digit extraction and recognition. The second stage employs deep learning models for digit localization and recognition, automatically detecting and correcting issues such as missing and intermediate digits to enhance the accuracy of automatic meter readings. Our research established a gas meter training dataset comprising 52,000 images, extensively annotated across various degrees, to train the deep learning models for high-precision digit recognition. Experimental results demonstrate that, with the simple SVM model, an accuracy of 87.03% is achieved for the classification of blurry image types. In addition, meter digit recognition (including intermediate digit states) can reach 97.6% (mAP), and the detection and correction of missing digits can be as high as 63.64%, showcasing the practical application value of the system developed in this study. [ABSTRACT FROM AUTHOR]

Algorithmic trading is playing an increasingly important role in the financial market, achieving more efficient trading strategies by replacing human decision-making. Among numerous trading algorithms, deep reinforcement learning is gradually replacing traditional high-frequency trading strategies and has become a mainstream research direction in the field of algorithmic trading. This paper introduces a novel approach that leverages reinforcement learning with human feedback (RLHF) within the double DQN algorithm. Traditional reward functions in algorithmic trading heavily rely on expert knowledge, posing challenges in their design and implementation. To tackle this, the reward-driven double DQN (R-DDQN) algorithm is proposed, integrating human feedback via a reward function network trained on expert demonstrations. Additionally, a classification-based training method is employed for optimizing the reward function network. The experiments, conducted on datasets including HSI, IXIC, SP500, GOOGL, MSFT, and INTC, show that the proposed method outperforms all baselines across six datasets and achieves a maximum cumulative return of 1502% within 24 months. [ABSTRACT FROM AUTHOR]