Search

In the process of fabric production, various types of defects affect the quality of a fabric. However, due to the wide variety of fabric defects, the complexity of fabric textures, and the concealment of small target defects, current fabric defect detection algorithms suffer from issues such as having a slow detection speed, low detection accuracy, and a low recognition rate of small target defects. Therefore, developing an efficient and accurate fabric defect detection system has become an urgent problem that needs to be addressed in the textile industry. Addressing the aforementioned issues, this paper proposes an improved YOLOv8n-LAW algorithm based on the YOLOv8n algorithm. First, LSKNet attention mechanisms are added to both ends of the C2f module in the backbone network to provide a broader context area, enhancing the algorithm's feature extraction capability. Next, the PAN-FPN structure of the backbone network is replaced by the AFPN structure, so that the different levels of features of the defects are closer to the semantic information in the progressive fusion. Finally, the CIoU loss is replaced with the WIoU v3 loss, allowing the model to dynamically adjust gradient gains based on the features of fabric defects, effectively focusing on distinguishing between defective and non-defective regions. The experimental results show that the improved YOLOv8n-LAW algorithm achieved an accuracy of 97.4% and a detection speed of 46 frames per second, while effectively increasing the recognition rate of small target defects. [ABSTRACT FROM AUTHOR]

Stroke is a high morbidity and mortality disease that poses a serious threat to people's health. Early recognition of the various warning signs of stroke is necessary so that timely clinical intervention can help reduce the severity of stroke. Deep neural networks have powerful feature representation capabilities and can automatically learn discriminant features from large amounts of data. This paper uses a range of physiological characteristic parameters and collaborates with deep neural networks, such as the Wasserstein generative adversarial networks with gradient penalty and regression network, to construct a stroke prediction model. Firstly, to address the problem of imbalance between positive and negative samples in the stroke public data set, we performed positive sample data augmentation and utilized WGAN‐GP to generate stroke data with high fidelity and used it for the training of the prediction network model. Then, the relationship between observable physiological characteristic parameters and the predicted risk of suffering a stroke was modeled as a nonlinear mapping transformation, and a stroke prediction model based on a deep regression network was designed. Finally, the proposed method is compared with commonly used machine learning‐based classification algorithms such as decision tree, random forest, support vector machine, and artificial neural networks. The prediction results of the proposed method are optimal in the comprehensive measurement index F. Further ablation experiments also show that the designed prediction model has certain robustness and can effectively predict stroke diseases. [ABSTRACT FROM AUTHOR]

Introduction: With the installation of advanced metering infrastructures, the operation data of EVs in the distribution networks can be obtained with time intervals of seconds and minutes. Based on these operation data, the impacts of integrating EVs into the distribution networks can be calculated and discussed. Methods: In this paper, an improved clustering algorithm with a new distance index for the daily curves of different types of EVs was proposed. The different types of EVs can be classified into several typical groups and the required number of operation scenarios can be reduced. After reducing the large-scale database to typical clusters, research can be conducted on the characteristics of EVs specific to certain scenarios. Results and discussion: In this way, the capability of integrating different types of EVs into the distribution network, such as fast EV charging stations, slow EV charging stations, and EV bus charging stations, is assessed from the perspective of load capacity size. The proposed clustering algorithm was verified with practical operation data. [ABSTRACT FROM AUTHOR]

Loop closure detection is an important component of the Simultaneous Localization and Mapping (SLAM) algorithm, which is utilized in environmental sensing. It helps to reduce drift errors during long-term operation, improving the accuracy and robustness of localization. Such improvements are sorely needed, as conventional visual-based loop detection algorithms are greatly affected by significant changes in viewpoint and lighting conditions. In this paper, we present a semantic spatial structure-based loop detection algorithm. In place of feature points, robust semantic features are used to cope with the variation in the viewpoint. In consideration of the semantic features, which are region-based, we provide a corresponding matching algorithm. Constraints on semantic information and spatial structure are used to determine the existence of loop-back. A multi-stage pipeline framework is proposed to systematically leverage semantic information at different levels, enabling efficient filtering of potential loop closure candidates. To validate the effectiveness of our algorithm, we conducted experiments using the uHumans2 dataset. Our results demonstrate that, even when there are significant changes in viewpoint, the algorithm exhibits superior robustness compared to that of traditional loop detection methods. [ABSTRACT FROM AUTHOR]

This paper considers the confrontation problem for two tank swarms of equal size and capability in a complex urban scenario. Based on the Unity platform (2022.3.20f1c1), the confrontation scenario is constructed featuring multiple crossing roads. Through the analysis of a substantial amount of biological data and wildlife videos regarding animal behavioral strategies during confrontations for hunting or food competition, two strategies are been utilized to design a novel bio-inspired intelligent swarm confrontation algorithm. The first one is the "fire concentration" strategy, which assigns a target for each tank in a way that the isolated opponent will be preferentially attacked with concentrated firepower. The second one is the "back and forth maneuver" strategy, which makes the tank tactically retreat after firing in order to avoid being hit when the shell is reloading. Two state-of-the-art swarm confrontation algorithms, namely the reinforcement learning algorithm and the assign nearest algorithm, are chosen as the opponents for the bio-inspired swarm confrontation algorithm proposed in this paper. Data of comprehensive confrontation tests show that the bio-inspired swarm confrontation algorithm has significant advantages over its opponents from the aspects of both win rate and efficiency. Moreover, we discuss how vital algorithm parameters would influence the performance indices. [ABSTRACT FROM AUTHOR]

Aim/Background: This research aims to develop an automated contextual classifier for scholarly papers by utilizing established algorithms and understanding the information retention of different parts of a scholarly article, such as the Abstract, Article Title, and Keywords. It also seeks to recommend a contextual classifier-based recommender system to help academics identify credible sources. Scholarly articles from various study fields often use similar terms in their titles and keywords. However, finding a publication venue can be challenging for researchers at the beginning of a scientific inquiry. Thus, it is crucial to classify information based on its context, especially when abstracts, keywords, and titles receive equal attention. Materials and Methods: An ensembled model was developed and trained using 114K instances from 38 classes of the Web of Science (WoS) dataset and 40 classes of the Dimensions dataset. The ensemble approach incorporated both machine learning and deep learning algorithms to build a diverse classifier. The model was evaluated by testing it with an 80:20 train-test split to assess performance. The classifier was further integrated into a recommender system designed to suggest probable publication sources based on given article information. Results: The ensemble classification approach demonstrated superior performance with faster inference and efficient training time. The balanced training model, tested on 114K instances, effectively categorized scholarly articles into one of 40 categories. The recommender system was capable of recommending up to 10 probable publication sources based on the article's Title, Keywords, and Abstract. Models utilizing abstractions yielded the best results and provided a better understanding of the context in every iteration of the experiment. Conclusion: This study successfully developed an ensemble-based contextual classifier for academic papers, which can also function as a recommender system. The system aids researchers in choosing the most appropriate sources to publish by categorizing articles into 40 categories and suggesting credible publication venues. This approach simplifies the decision-making process for academics, enabling them to identify relevant publications and suitable sources for their work more efficiently. [ABSTRACT FROM AUTHOR]

In recent years, there has been a significant development in unmanned platform technologies, specifically unmanned ground vehicles (UGVs) and unmanned aerial vehicles (UAVs). As a result, their application scenarios have expanded considerably. Unmanned platforms are considered integral components of the Internet of Things system. However, certain challenges arise when dealing with specialized tasks, such as navigating complex urban low-altitude terrain with multiple obstacles and limited communication capabilities. These challenges can greatly impact the efficiency of the system due to information isolation. To address this issue, a messenger drone mechanism is introduced in this paper, which utilizes air superiority to facilitate indirect communication between unmanned platforms. Additionally, a task sequence planning algorithm based on sampling transformation is designed. This algorithm efficiently assigns the drone to mobile UGVs by discretely sampling their paths and considering the UAV-UGV motion relationship. By transforming the problem into an asymmetric traveler problem, it allows for a fast solution. Finally, the effectiveness of the algorithm is verified through comparative analysis in different scenarios. [ABSTRACT FROM AUTHOR]

Load variation, distributed power output uncertainty and multi‐microgrids network complexity have brought great difficulties to the frequency stability of the whole microgrid. To address this problem, this paper uses a multi‐agent deep reinforcement learning(DRL) algorithm to design the controllers to control the frequency of the multi‐microgrids. Firstly, a load frequency control (LFC) model for multi‐microgrids was built. Secondly, based on the centralized training and decentralized execution (CTDE) multi‐agent reinforcement learning (RL) framework, the multi‐agent soft actor‐critic (MASAC) algorithm was designed and applied to the multi‐microgrids model. The state space and action space of multi‐agent were established according to the frequency deviation of every sub‐microgrid and the output of each distributed power source. The reward function was then established according to the frequency deviation. The appropriate neural network and training parameters were selected to generate the interconnected microgrid controllers through multiple training of pre‐learning. Finally, the simulation study shows that the MASAC controller proposed in this paper can quickly maintain frequency stability when the system is disturbed. Sensitivity analysis shows that the MASAC controller can effectively cope with the uncertainty of the system parameters. [ABSTRACT FROM AUTHOR]

Generalized target detection algorithms perform well for large- and medium-sized targets but struggle with small ones. However, with the growing importance of aerial images in urban transportation and environmental monitoring, detecting small targets in such imagery has been a promising research hotspot. The challenge in small object detection lies in the limited pixel proportion and the complexity of feature extraction. Moreover, current mainstream detection algorithms tend to be overly complex, leading to structural redundancy for small objects. To cope with these challenges, this paper recommends the PCSG model based on yolov5, which optimizes both the detection head and backbone networks. (1) An enhanced detection header is introduced, featuring a new structure that enhances the feature pyramid network and the path aggregation network. This enhancement bolsters the model's shallow feature reuse capability and introduces a dedicated detection layer for smaller objects. Additionally, redundant structures in the network are pruned, and the lightweight and versatile upsampling operator CARAFE is used to optimize the upsampling algorithm. (2) The paper proposes the module named SPD-Conv to replace the strided convolution operation and pooling structures in yolov5, thereby enhancing the backbone's feature extraction capability. Furthermore, Ghost convolution is utilized to optimize the parameter count, ensuring that the backbone meets the real-time needs of aerial image detection. The experimental results from the RSOD dataset show that the PCSG model exhibits superior detection performance. The value of mAP increases from 97.1% to 97.8%, while the number of model parameters decreases by 22.3%, from 1,761,871 to 1,368,823. These findings unequivocally highlight the effectiveness of this approach. [ABSTRACT FROM AUTHOR]

Purpose: On the one hand, this paper is to further understand the residents' differentiated power consumption behaviors and tap the residential family characteristics labels from the perspective of electricity stability. On the other hand, this paper is to address the problem of lack of causal relationship in the existing research on the association analysis of residential electricity consumption behavior and basic information data. Design/methodology/approach: First, the density-based spatial clustering of applications with noise method is used to extract the typical daily load curve of residents. Second, the degree of electricity consumption stability is described from three perspectives: daily minimum load rate, daily load rate and daily load fluctuation rate, and is evaluated comprehensively using the entropy weight method. Finally, residential customer labels are constructed from sociological characteristics, residential characteristics and energy use attitudes, and the enhanced FP-growth algorithm is employed to investigate any potential links between each factor and the stability of electricity consumption. Findings: Compared with the original FP-growth algorithm, the improved algorithm can realize the excavation of rules containing specific attribute labels, which improves the excavation efficiency. In terms of factors influencing electricity stability, characteristics such as a large number of family members, being well employed, having children in the household and newer dwelling labels may all lead to poorer electricity stability, but residents' attitudes toward energy use and dwelling type are not significantly associated with electricity stability. Originality/value: This paper aims to uncover household socioeconomic traits that influence the stability of home electricity use and to shed light on the intricate connections between them. Firstly, in this article, from the perspective of electricity stability, the characteristics of the power consumption of residents' users are refined. And the authors use the entropy weight method to comprehensively evaluate the stability of electricity usage. Secondly, the labels of residential users' household characteristics are screened and organized. Finally, the improved FP-growth algorithm is used to mine the residential household characteristic labels that are strongly associated with electricity consumption stability. Highlights: The stability of electricity consumption is important to the stable operation of the grid. An improved FP-growth algorithm is employed to explore the influencing factors. The improved algorithm enables the mining of rules containing specific attribute labels. Residents' attitudes toward energy use are largely unrelated to the stability of electricity use. [ABSTRACT FROM AUTHOR]

Pixel‐level labeling of regions of interest in an image is a key step in building a labeled training dataset for supervised deep learning networks of images. However, traditional manual labeling of cancerous regions in digital pathological images by doctors is time‐consuming and inefficient. To address this issue, this paper proposes an automatic labeling method for whole slide images, which combines clustering and edge detection techniques. The proposed method utilizes the multi‐level feature fusion model and the Long‐Short Term Memory network to discriminate the cancerous nature of the whole slide images, thereby improving the classification accuracy of the whole slide images. Subsequently, the automatic labeling of cancerous regions is achieved by integrating a density‐based clustering algorithm and an edge point extraction algorithm, both based on the discriminated results of the cancerous properties of whole slide images. The experimental results demonstrate the effectiveness of the proposed method, which offers an efficient and accurate solution to the challenging task of cancerous region labeling in digital pathological images. [ABSTRACT FROM AUTHOR]

In this paper, an improved hybrid regularized grounded network imaging algorithm (ITR-Lp) combining Tikhonov regularization and Lp regularization is proposed; through the improvement of the filtering function, the correction of small magnitude for large singular values and increasing magnitude of correction with decreasing singular values for small singular values is implemented for the improvement of the convergence of the solution. The proposed algorithm constructs a regularization matrix to achieve selective correction of singular values and improve the convergence of the solution, while Lp regularization is used to enhance the sparsity of the solution and improve the boundary contrast. the effect of node distribution on convergence is investigated, and finally the ITR-Lp algorithm is validated by simulation and experiment. The results show that the ITR-Lp algorithm proposed in this paper achieves the lowest resistivity relative errors of 0.1695 and 0.1089 for resistive networks with 1 corrosion and 2 corrosions, respectively. The method has good convergence and boundary contrast, which effectively improves the pathology of the inverse problem of imaging the electrical impedance tomography of grounding grid. [ABSTRACT FROM AUTHOR]

Peer-to-peer (P2P) energy trading has attracted a lot of attention and the number of electric vehicles (EVs) has increased in the past couple of years. Toward sustainable mobility, EVs meet the standard development goals (SDGs) for attaining a sustainable future in the transport sector. This development and increasing number of EVs creates an opportunity for prosumers to trade electricity. Considering this opportunity, this review article aims to provide an in-depth analysis of P2P energy trading of EVs using blockchain in centralized and decentralized networks, which enables prosumers to exchange energy directly with one another. The paper is aimed to provide the reader with a state-of-the-art review on the P2P energy trading for EVs, considering different blockchain algorithms that are practically implemented or still in the research phase. Moreover, the paper presents blockchain applications, current trends, and future challenges of EVs' energy trading. P2P energy trading for EVs using blockchain algorithms can be successfully implemented considering real-time scenarios and economically benefits smart sustainable societies. [ABSTRACT FROM AUTHOR]

Forest fires wreak havoc on natural ecosystems and represent a grave threat to environmental stability. Establishing a rapid and efficient network for the early detection of forest fires remains a critical challenge and afocal point of research. In response to this problem, this paper proposes Fire & Smoke - You Only Look Once (FS-YOLO) for real-time forest fire detection. FS-YOLO significantly enhances fire detection performance through the integration of three innovative modules: Mixed Attention Cross Stage Partial (MACSP), Cross Stage Feature Pyramid Network (CSFPN), and Scalable Spatial Pyramid Pooling (SSPP). First, the MACSP module targets diverse colors and shapes characteristic of forest fires. By combining channel attention with local spatial attention, it precisely weights the network's features, achieving greater accuracy in capturing fire characteristics. Second, the CSFPN method merges high-level semantic information with low-level detail via both top-down and bottom-up pathways, creating multi-scale feature maps that boast expanded receptive fields. Lastly, the SSPP method enhances the network's focus on fire targets across varied scenes through scaling factors, bolstering the model's robustness. Additionally, this paper organizes and annotates a forest fire dataset. The experimental results show that compared to the baseline model, FS-YOLO achieves an 8% improvement in mean average precision, and the average precision values for flames and smoke increase by 10.1% and 5.7%, respectively, indicating a significant overall performance improvement of the model. Compared to other object detection algorithms, FS-YOLO consistently achieves optimal performance. [ABSTRACT FROM AUTHOR]

Power shift tractors have been widely used in agricultural tractors in recent years because of their advantages of uninterrupted power during shifting, high transmission efficiency and high stability. As one of the indispensable driving states of the power shift tractor, the starting process requires a small impact and a starting speed that meets the driver's requirements. In this paper, aiming at such contradictory requirements, the starting control strategy of a power shift tractor is formulated with the goal of starting quality and the driver's intention. Firstly, the identification characteristics of the driver under three starting intentions are obtained by a real vehicle test. An extreme learning machine with fast identification speed and short training time is used to establish the basic driver's intention identification model. For the instability of the identification results of the Extreme Learning Machine (ELM), the particle swarm optimization algorithm (PSO) is used to optimize the ELM. The optimized extreme learning machine model has an accuracy of 96.891% for driver's intention identification. The wet clutch is an important part of the power shift gearbox. In this paper, the starting control strategy knowledge base of the starting clutch is established by a combination of bench tests and simulation tests. Through the fuzzy algorithm, the driver's intention is combined with the starting control strategy. Different drivers' intentions will affect the comprehensive evaluation model of the clutch (the single evaluation index of the clutch is: the maximum sliding power, the sliding power, the speed stability time, the impact degree), thus affecting the final choice of the starting clutch control strategy considering the driver's intention. On this basis, this paper studies and establishes the MPC starting controller for the power shift gearbox. Compared with the linear control strategy, the PSO-ELM-fuzzy weight starting strategy proposed in this paper can reduce the maximum sliding friction power by 45%, the sliding friction power by 69.45%, and the speed stabilization time by 0.11 s. The effectiveness of the starting control strategy considering the driver's intention proposed in this paper to improve the starting quality of the power shift tractor is verified. [ABSTRACT FROM AUTHOR]

When wireless sensor networks are used in smart homes, the connection state will be unstable due to signal masking attenuation. This will cause low packet rate, high time delay and high cost in the network. In this paper, a network routing algorithm for wireless sensing based on connection conditions is designed. Secondly, the expected number of sends is proposed to evaluate the stability of links. Based on this, the following network signal delivery situation is forecasted in real time and quickly. According to the estimated expected number of transmissions, the path is dynamically corrected to effectively avoid attenuation in the channel and achieve optimal system performance. Experimental results show that the method proposed in this paper can improve the efficiency of message sending and reduce the routing cost under the condition of masking effect. [ABSTRACT FROM AUTHOR]

A deep learning-based Visual Inertial SLAM technique is proposed in this paper to ensure accurate autonomous localization of mobile robots in environments with dynamic objects. Addressing the limitations of real-time performance in deep learning algorithms and the poor robustness of pure visual geometry algorithms, this paper presents a deep learning-based Visual Inertial SLAM technique. Firstly, a non-blocking model is designed to extract semantic information from images. Then, a motion probability hierarchy model is proposed to obtain prior motion probabilities of feature points. For image frames without semantic information, a motion probability propagation model is designed to determine the prior motion probabilities of feature points. Furthermore, considering that the output of inertial measurements is unaffected by dynamic objects, this paper integrates inertial measurement information to improve the estimation accuracy of feature point motion probabilities. An adaptive threshold-based motion probability estimation method is proposed, and finally, the positioning accuracy is enhanced by eliminating feature points with excessively high motion probabilities. Experimental results demonstrate that the proposed algorithm achieves accurate localization in dynamic environments while maintaining real-time performance. [ABSTRACT FROM AUTHOR]

INTRODUCTION: In present days, Automation of everything has become essential. Internet of things (IoT) play an important role among all medical advances of IT. In this paper, feasible solutions are discussed to compare and design better healthcare systems. A thorough investigation and survey of suitable approaches were done to select IoT based systems in hospitals consisting of various high precision sensors. OBJECTIVES: The challenge healthcare system face is to manage the real time patient’s data with high accuracy. Second challenge is at fog devices level to manage the load distribution to all sensors with limited availability of bandwidth. METHODS: This paper summarizes the selection criterions of suitable load balancing algorithms to reduce energy consumption and computational cost of fog devices and increase the network usage that are supposed to be used in IoT based healthcare systems. According to the survey BNBKnapack algorithm has been selected as best suitable approach to analyze the overall performance of fog devices and results are also verify the same. RESULTS: Comparative analysis of Overall performance of fog devices has been proposed with using SJF algorithm and Adaptive BNBKnapsack algorithm. It has been observed by analysing system performance, which is found as best among other load balancing algorithm Adaptive BNBKnapsack is successfully reduce the energy consumption by (99.29%), computational cost by (98.34%) and increase the network usage by (99.95%) of system CONCLUSION: It has been observed by analysing system performance, Adaptive BNBKnapsack Load balancing is successfully able to reduce the computational cost and energy consumption also increase the network usage of the fog network. The performance of the system is found best among other load balancing algorithm. [ABSTRACT FROM AUTHOR]

To reduce safety accidents caused by distracted driving and address issues such as low recognition accuracy and deployment difficulties in current algorithms for distracted behavior detection, this paper proposes an algorithm that utilizes an improved KNN for classifying driver posture features to predict distracted driving behavior. Firstly, the number of channels in the Lightweight OpenPose network is pruned to predict and output the coordinates of key points in the upper body of the driver. Secondly, based on the principles of ergonomics, driving behavior features are modeled, and a set of five-dimensional feature values are obtained through geometric calculations. Finally, considering the relationship between the distance between samples and the number of samples, this paper proposes an adjustable distance-weighted KNN algorithm (ADW-KNN), which is used for classification and prediction. The experimental results show that the proposed algorithm achieved a recognition rate of 94.04% for distracted driving behavior on the public dataset SFD3, with a speed of up to 50FPS, superior to mainstream deep learning algorithms in terms of accuracy and speed. The superiority of ADW-KNN was further verified through experiments on other public datasets. [ABSTRACT FROM AUTHOR]

All messaging platforms rely on a centralized server which has the vulnerability of getting hacked by outside agencies and posing risk to private data. Authentication between users is an important asset in electronic messaging today, which is one of the most widely used network applications. By replacing the need for reliable mediators, blockchain technology overcomes these threats and allows for a reduction in power-intensive operations. In this work, we propose a blockchain-based solution for secure messaging. Blockchain-based communication can increase communication effectiveness and security, and this paper proposes the creation of a blockchainbased messaging model that will improve the performance and security of blockchain-recorded data, with a smart contract to verify ownership. The system is still fully distributed and allows users to exchange messages securely. This paper has tried to implement a blockchain with a few users and implemented secure end-to-end encryption using the SHA-256 algorithm and multiple crypto techniques so that messages cannot be vulnerable. [ABSTRACT FROM AUTHOR]

This paper aims to propose a table tennis target detection (TD) method based on deep learning (DL) and multi-scale feature fusion (MFF) to improve the detection accuracy of the ball in table tennis competition, optimize the training process of athletes, and improve the technical level. In this paper, DL technology is used to improve the accuracy of table tennis TD through MFF guidance. Initially, based on the FAST Region-based Convolutional Neural Network (FAST R-CNN), the TD is carried out in the table tennis match. Then, through the method of MFF guidance, different levels of feature information are fused, which improves the accuracy of TD. Through the experimental verification on the test set, it is found that the mean Average Precision (mAP) value of the target detection algorithm (TDA) proposed here reaches 87.3%, which is obviously superior to other TDAs and has higher robustness. The DL TDA combined with the proposed MFF can be applied to various detection fields and can help the application of TD in real life. [ABSTRACT FROM AUTHOR]

This paper presents an algorithm for organizing and grouping data related to the expenditures by education levels in Bulgaria. The built database is used as a source from which the necessary information is searched depending on the entered indicators and time interval. The considered indicators include the public and private expenditures by education levels for the period2012-2020. The extracted subsets of elements are processed and analyzed. In this connection, four groups of variables are calculated and discussed. The results show that the expenditures in four of the education levels (primaryand pre-primary education as well as upper and lower secondary education) grow over the last five years (2016-2020). The quoted indicator inpost-secondary, non-tertiary education isreduced gradually in 2016-2019. During 2015, as compared to 2014, the expenditures in the considered 7 levels of education decreased in the range from 0.29% to 7.81%. This work calculates the share of expenditure for tertiary educationbachelor, master and doctor in comparison with the total expenditures for education in the indicatedtime period. The obtained value of the variable for this education level is the highest. It is 29.74%. The values of this variable are significantly lower for the following two levels of education - tertiary education-professional bachelor and postsecondary, non-tertiary education. They are 1.54% and 0.29% respectively. [ABSTRACT FROM AUTHOR]

With the rapid development of remote sensing technology, remote sensing products have found increasingly widespread applications across various fields. Nevertheless, as the volume of remote sensing image data continues to grow, traditional data retrieval techniques have encountered several challenges such as substantial query results, data overlap, and variations in data quality. Users need to manually browse and filter a large number of remote sensing datasets, which is a cumbersome and inefficient process. In order to cope with these problems of traditional remote sensing image retrieval methods, this paper proposes a remote sensing image retrieval algorithm for dense data (DD-RSIRA). The algorithm establishes evaluation metrics based on factors like imaging time, cloud coverage, and image coverage. The algorithm utilizes the global grids to create an ensemble coverage relation between images and grids. A locally optimal initial solution is obtained by a greedy algorithm, and then a local search is performed to search for the optimal solution by combining the strategies of weighted gain-loss scheme and novel mechanism. Ultimately, it achieves an optimal coverage of remote sensing images within the region of interest. In this paper, it is shown that the method obtains a smaller number of datasets with lower redundancy and higher data utilization and ensures the data quality to a certain extent in order to accurately meet the requirements of the regional coverage of remote sensing images. [ABSTRACT FROM AUTHOR]

To address the challenges of high complexity, poor real-time performance, and low detection rates for small target vehicles in existing vehicle object detection algorithms, this paper proposes a real-time lightweight architecture based on You Only Look Once (YOLO) v5m. Firstly, a lightweight upsampling operator called Content-Aware Reassembly of Features (CARAFE) is introduced in the feature fusion layer of the network to maximize the extraction of deep-level features for small target vehicles, reducing the missed detection rate and false detection rate. Secondly, a new prediction layer for tiny targets is added, and the feature fusion network is redesigned to enhance the detection capability for small targets. Finally, this paper applies L1 regularization to train the improved network, followed by pruning and fine-tuning operations to remove redundant channels, reducing computational and parameter complexity and enhancing the detection efficiency of the network. Training is conducted on the VisDrone2019-DET dataset. The experimental results show that the proposed algorithmreduces parameters and computation by 63.8% and 65.8%, respectively. The average detection accuracy improves by 5.15%, and the detection speed reaches 47 images per second, satisfying real-time requirements. Compared with existing approaches, including YOLOv5m and classical vehicle detection algorithms, our method achieves higher accuracy and faster speed for real-time detection of small target vehicles in edge computing. [ABSTRACT FROM AUTHOR]

The image processing field is considered one of the highly sensitive fields for accuracy due to the quality of the processing in view of the visual view of the user and due to the development in modern means of communication and the use of these means in the transfer of images and the impact of these means on several factors, including external, including those related to the quality of the source signal and the impact of the transmitted images by these conditions, digital correction processes have emerged to reach a high quality of the received image. Most of the studies and research on digital image correction have focused on the quality and time required for correction processes, and some have focused on using traditional optimization algorithms to obtain acceptable visual quality, while others have focused on shortening time regardless of quality, and due to the fact that all studies and research that have been viewed were focused on the use of speculative methods and hybrid algorithms to address distortion in images, as all weaknesses were related to time, quality and calculations because the size of the image data is large Very. The research aims to study digital images and then process images, optimization methods, genetic algorithms and accomplish an algorithm with high features. In this paper, the simple genetic algorithm is used in the process of correcting images of the type (.JPG), as this method is characterized by the fact that it includes many of the advantages of the previous methods in addition to additional features that provided quality, accuracy and shortening time in calculations. The paper has been completed in five phases: The first stage: Providing external protection for the system by entering the password. Second Stage: Creating the system's database. Third stage: Create (code book) in a new style based on the size of the file used. Fourth stage: Building the genetic algorithm for correction Fifth stage: Using a mathematical model to add distortion to a clear image, correct it and compare the results. [ABSTRACT FROM AUTHOR]

Machine learning has emerged as a climatic technology in contemporary and prospective cyber threat intel systems, with numerous jurisdictions seamlessly integrating it into their operations. However, the current state of machine learning in cyber defence is still in its early stages, foreshadowing a noticeable unexplored research territory and practical implementation. This paper marks the initial endeavour to offer a comprehensive understanding of machine learning within the entire spectrum of cybersecurity jurisdictions, catering to potential end users with enthusiasm in this field of study. This paper aims to serve as a source of inspiration for significant advancements in ML within the cyber defence zone, laying the groundwork for the broader adoption of ML mitigations to safeguard present and heuristic systems. [ABSTRACT FROM AUTHOR]

A lattice of integers is the collection of all linear combinations of a set of vectors for which all entries of the vectors are integers and all coefficients in the linear combinations are also integers. Lattice reduction refers to the problem of finding a set of vectors in a given lattice such that the collection of all integer linear combinations of this subset is still the entire original lattice and so that the Euclidean norms of the subset are reduced. The present paper proposes simple, efficient iterations for lattice reduction which are guaranteed to reduce the Euclidean norms of the basis vectors (the vectors in the subset) monotonically during every iteration. Each iteration selects the basis vector for which projecting off (with integer coefficients) the components of the other basis vectors along the selected vector minimizes the Euclidean norms of the reduced basis vectors. Each iteration projects off the components along the selected basis vector and efficiently updates all information required for the next iteration to select its best basis vector and perform the associated projections. [ABSTRACT FROM AUTHOR]

Aiming at the electric vehicle charging pile control system has the characteristics of multi-parameter, strong coupling and non-linearity, and the existing traditional PID control and fuzzy PID control methods have the problems of slow charging speed, poor control performance and anti-interference ability, as well as seriously affecting the service life of the battery, this paper designs a kind of improved particle swarm algorithm to optimize the PID controller of the charging control system for electric vehicle charging piles, and utilizes the improved particle swarm algorithm to Adaptive and precise adjustment of proportional, integral and differential parameters, so that the system quickly reaches stability, so as to improve the accuracy of the system control output current or voltage. Simulation results show that the optimized system response speed of the improved particle swarm algorithm is improved by 3.077 s, the overshooting amount is reduced by 1.01%, and there is no oscillation, which has strong adaptability and anti-interference ability, and can significantly improve the control accuracy and charging efficiency of the charging pile control system. [ABSTRACT FROM AUTHOR]

This paper presents a regional 3D geological modeling method based on the stacking ensemble technique to overcome the challenges of sparse borehole data in large-scale linear underground projects. The proposed method transforms the 3D geological modeling problem into a stratigraphic property classification problem within a subsurface space grid cell framework. Borehole data is pre-processed and trained using stacking method with five different machine learning algorithms. The resulting modelled regional cells are then classified, forming a regional 3D grid geological model. A case study for an area of 324 km2 along Xuzhou metro lines is presented to demonstrate the effectiveness of the proposed model. The study shows an overall prediction accuracy of 85.4%. However, the accuracy for key stratigraphy layers influencing the construction risk, such as karst carve strata, is only 4.3% due to the limited borehole data. To address this issue, an oversampling technique based on the synthetic minority oversampling technique (SMOTE) algorithm is proposed. This technique effectively increases the number of sparse stratigraphic samples and significantly improves the prediction accuracy for karst caves to 65.4%. Additionally, this study analyzes the impact of sampling distance on model accuracy. It is found that a lower sampling interval results in higher prediction accuracy, but also increases computational resources and time costs. Therefore, in this study, an optimal sampling distance of 1 m is chosen to balance prediction accuracy and computation cost. Furthermore, the number of geological strata is found to have a negative effect on prediction accuracy. To mitigate this, it is recommended to merge less significant stratigraphy layers, reducing computation time. For key strata layers, such as karst caves, which have a significant impact on construction risk, further onsite sampling or oversampling using the SMOTE technique is recommended. [ABSTRACT FROM AUTHOR]

Identifying discriminative patterns, known as shapelets, within time series is a critical step in many time series classification tasks. A major limitation of shapelet learning is that often hindered by their unsupervised methods, treating shapelet learning as an unsupervised subsequence clustering process and discovery based on pre-defined metric, which performed sequentially. This sequential procedure presents challenges, as it fails to establish a direct connection between shapelets and samples, and lacks the capacity to explicitly incorporate label information. In this paper, we proposed a novel shapelet learning algorithm called Discriminative Shapelet Learning via Temporal Clustering and Matrix Factorization (DSLMF). DSLMF introduced a joint framework that combines matrix factorization and coherent temporal clustering to discovery salient and coherent feature subsets. To further enhance discriminability and prevent arbitrary shapelet shapes, DSLMF integrates a label-specific shapelet regularization as a guiding mechanism enabling the learning of shapelets optimized for higher classification performance. The proposed algorithm has shown to be effective for capturing the temporal cluster structure and interpretability of shapelet-based method. The results of experiments showcased in this paper highlight DSLMF's effectiveness in capturing temporal cluster structures and learning meaningful shapelets, ultimately leading to promising performance on benchmark datasets. [ABSTRACT FROM AUTHOR]

Effective congestion control on the internet has been a problem since its inception. Transmission Control Protocol (TCP), being the most widely used transport layer protocol tries to mitigate it using a variety of congestion control algorithms. Cubic, Reno, and Bottleneck Bandwidth and Round-trip propagation time (BBR) are the most deployed congestion controls. BBR v2 is leading the congestion control race with its superior performance in terms of better throughput and lower latency. Furthermore, Active Queue Management (AQM) algorithms try to mitigate the congestion control at the network layer through active buffer control to avoid bufferbloat. The most efficient congestion control occurs when TCP and AQM work together. Indeed, it is the TCP-AQM algorithm "Golden pair" that can result in the most efficient performance. This paper proposes such a novel pair based on our previously tested and published BBR-n (BBR new) with the most effective of the modern AQMs, that completely gels together to provide lower latency in wireless networks based on Wireless N/AC. Real-time experiments were performed using Flent on our physical testbed with BBR-n and modern AQMs such as Fair Queuing (FQ), Constrained Delay (CoDel), Proportional Integral controller Enhanced (PIE), Common Applications Kept Enhanced (Cake) and Flow Queuing Controlled Delay (FQ_CoDel). Various tests done on our physical testbed helped us identify CAKE as the most optimum AQM that fits with our proposed BBR-n while providing optimum throughput and lower latency in 802.11N/AC-based wireless networks. [ABSTRACT FROM AUTHOR]

The unauthorized replication and distribution of digital images pose significant challenges to copyright protection. While existing solutions incorporate blockchain-based techniques such as perceptual hashing and digital watermarking, they lack large-scale experimental validation and a dedicated blockchain consensus protocol for image copyright management. This paper introduces DRPChain, a novel digital image copyright management system that addresses these issues. DRPChain employs an efficient cropping-resistant robust image hashing algorithm to defend against 14 common image attacks, demonstrating an 85% success rate in watermark extraction, 10% higher than the original scheme. Moreover, the paper designs the K-Raft consensus algorithm tailored for image copyright protection. Comparative experiments with Raft and benchmarking against PoW and PBFT algorithms show that K-Raft reduces block error rates by 2%, improves efficiency by 300ms compared to Raft, and exhibits superior efficiency,decentralization, and throughput compared to PoW and PBFT. These advantages make K-Raft more suitable for digital image copyright protection. This research contributes valuable insights into using blockchain technology for digital copyright protection, providing a solid foundation for future exploration. [ABSTRACT FROM AUTHOR]

This paper focuses on how regulatory bodies respond to artificial intelligence (AI)-enabled medical devices. To achieve this, we present a comparative overview of the United States (USA), European Union (EU), and China. Our search in the governmental database identified 59 AI medical devices approved in China as of July 2023. In comparison to the rules-based regulatory approach in China, the approaches in the USA and EU are more standards-oriented. [ABSTRACT FROM AUTHOR]

Currently, regardless of the algorithm used, motion planners for dealing with dynamic obstructions need to rely on high‐precision sensors and high performance processors. The requirements for hardware increase as the density of dynamic obstructions in an area becomes higher. Additionally, motion planners are more prone to errors in complex environments. The Rapidly‐exploring Random Tree (RRT ∗) algorithm only considers static obstructions and cannot effectively avoid densely populated regions of dynamic obstructions. This paper develops an improved RRT ∗ algorithm that is capable of avoiding densely populated regions of dynamic obstructions. In this algorithm, the cost function of the traditional RRT ∗ algorithm is modified based on the density of dynamic obstructions, allowing the planned path to bypass densely populated regions. The algorithm also introduces reasonable penalty terms to penalize segments that pass through densely populated regions, while maintaining asymptotic optimality of the traditional RRT ∗ algorithm. Numerical experiments reveal that the improved RRT ∗ algorithm is able to successfully avoid densely populated regions of dynamic obstructions with minimal time cost and exhibits better robustness during the path search process in comparison to the traditional RRT ∗ algorithm. Thus, the improved RRT ∗ algorithm possesses the ability to adapt to more complex areas for path planning. [ABSTRACT FROM AUTHOR]

Some special manufacturing fields such as aerospace may encounter mixed production of multiple research and development projects and multiple batch production projects. Under these special production conditions resource conflicts are more severe, resulting in uncertain operating times that are difficult to predict. In addition, a single project may have tens of thousands of supporting products, making it difficult to effectively control the total construction process. To address these challenges this paper proposes new methods. A model, EMA-DCPM (dynamic critical path method) incorporating attention mechanisms in Enterprise Resource Planning and Mechanical Engineering Society) has been proposed. This model predicts product job time through machine learning methods and discovers the predictive advantage of the attention mechanism through data comparison. The CPM control algorithm was improved to enhance its robustness and an efficient modeling method, "5+X" was proposed. This new method is suitable for mixed line planning management in sophisticated manufacturing projects and has value for practical applications. [ABSTRACT FROM AUTHOR]

This advanced paper presents a new approach to improving image steganography using the Ant Colony Optimization (ACO) algorithm. Image steganography, a technique of embedding hidden information in digital photographs, should ideally achieve the dual purposes of maximum data hiding and maintenance of the integrity of the cover media so that it is least suspect. The contemporary methods of steganography are at best a compromise between these two. In this paper, we present our approach, entitled Ant Colony Optimization (ACO)-Least Significant Bit (LSB), which attempts to optimize the capacity in steganographic embedding. The approach makes use of a grayscale cover image to hide the confidential data with an additional bit pair per byte, both for integrity verification and the file checksum of the secret data. This approach encodes confidential information into four pairs of bits and embeds it within uncompressed grayscale images. The ACO algorithm uses adaptive exploration to select some pixels, maximizing the capacity of data embedding while minimizing the degradation of visual quality. Pheromone evaporation is introduced through iterations to avoid stagnation in solution refinement. The levels of pheromone are modified to reinforce successful pixel choices. Experimental results obtained through the ACO-LSB method reveal that it clearly improves image steganography capabilities by providing an increase of up to 30% in the embedding capacity compared with traditional approaches; the average Peak Signal to Noise Ratio (PSNR) is 40.5 dB with a Structural Index Similarity (SSIM) of 0.98. The approach also demonstrates very high resistance to detection, cutting down the rate by 20%. Implemented in MATLAB R2023a, the model was tested against one thousand publicly available grayscale images, thus providing robust evidence of its effectiveness. [ABSTRACT FROM AUTHOR]

For the problem of slow search and tortuous paths in the Rapidly Exploring Random Tree (RRT) algorithm, a feedback-biased sampling RRT, called FS-RRT, is proposed based on RRT. Firstly, to improve the sampling efficiency of RRT to shorten the search time, the search area of the random tree is restricted to improve the sampling efficiency. Secondly, to obtain better information about obstacles to shorten the path length, a feedback-biased sampling strategy is used instead of the traditional random sampling, the collision of the expanding node with an obstacle generates feedback information so that the next expanding node avoids expanding within a specific angle range. Thirdly, this paper proposes using the inverse optimization strategy to remove redundancy points from the initial path, making the path shorter and more accurate. Finally, to satisfy the smooth operation of the robot in practice, auxiliary points are used to optimize the cubic Bezier curve to avoid path-crossing obstacles when using the Bezier curve optimization. The experimental results demonstrate that, compared to the traditional RRT algorithm, the proposed FS-RRT algorithm performs favorably against mainstream algorithms regarding running time, number of search iterations, and path length. Moreover, the improved algorithm also performs well in a narrow obstacle environment, and its effectiveness is further confirmed by experimental verification. [ABSTRACT FROM AUTHOR]

Correlation clustering problem (CorCP) is a classical clustering problem, which clusters data based on the similarity of data set, and has many applications in interaction networks, cross-lingual link detection, and communication networks, etc. In this paper, we study a practical generalization of the CorCP, called the capacitated correlation clustering problem (the capacitated CorCP), by constructing a labeled complete graph. On this labeled complete graph, each vertex represents a piece of data. If two pieces of data are similar, then the edge between the corresponding vertices is marked by a positive label +. Otherwise, this edge is marked by a negative label -. The objective of the capacitated CorCP is to group some similar data sets into one cluster as far as possible, while satisfying the cluster capacity constraint. To achieve this objective, we shall partition the vertex set of the labeled complete graph into several clusters, each cluster's size subjecting to an upper bound, so as to minimize the number of disagreements. Here the number of disagreements is defined as the total number of the edges with positive labels between clusters and the edges with negative labels within clusters. Different with the previous algorithm in [18], which subjects to the constraint on the cluster size by a penalty measure, we design an algorithm for the capacitated CorCP to directly output a feasible solution by iteratively constructing clusters based on a preset threshold. Through carefully setting the threshold and sophisticatedly analyzing, our algorithm is proved to have an improved approximation ratio of 5.37. In addition, we also conduct a series of numerical experiments to demonstrate the effectiveness of our algorithm. [ABSTRACT FROM AUTHOR]

In this paper, we used the outstanding properties of the Thompson metric to conclusively demonstrate the existence of a unique positive definite solution for the nonlinear matrix equation X− Σm i=1 Ai *X −piAi = Q without any additional assumptions. Furthermore, we designed an iterative algorithm to compute this unique positive definite solution, and derive its corresponding error estimate formula. Additionally, we presented three refined existence intervals for positive definite solutions of this equation. Finally, numerical examples were employed to validate the practicability of our iterative algorithm. [ABSTRACT FROM AUTHOR]

A fundamental assumption in addressing real-world problems is acknowledging the presence of uncertainty and dynamism. Dismissing these factors can lead to the formulation of an optimal solution for an entirely different problem. This paper presents a novel variant of the capacitated dispersion problem (CDP) referred to as the stochastic and non-static CDP. The main objective of this problem is to strategically position facilities to achieve maximum dispersion while meeting the capacity demand constraint. The proposed approach combines stochastic and non-static elements, introducing a new paradigm to address the problem. This innovation allows us to consider more realistic and flexible environments. To solve this challenging problem, a novel sim-learnheuristic algorithm is proposed. This algorithm combines a biased-randomized metaheuristic (optimization component) with a simulation component (to model the uncertainty) and a machine learning component (to model non-static behavior). The non-static part works by using black box and white box mechanisms to learn the uncertainty with some related facilities’ variables. Based on an extended set of traditional benchmarks for the CDP, a series of computational experiments were carried out. The results demonstrate the effectiveness of the proposed sim-learnheuristic approach for solving the CDP under non-static and stochastic scenarios. [ABSTRACT FROM AUTHOR]

This paper presents an optimization method for the design of marine metal sandwich plates to enhance the anti-blast performance of ship structures. The proposed method combines a neural network with the sparrow search algorithm to efficiently optimize the structure. The orthogonal design method is utilized to select appropriate sample points for the surrogate model. Dynamic responses of the ship under blast loading are obtained using the ABAQUS finite element software. By establishing an anti-blast surrogate model, the optimization problem is simplified. To overcome the limitations of the traditional backpropagation neural network, genetic algorithm and Adam algorithm are employed. Finally, the optimal solution is obtained based on the sparrow search algorithm. The results enable us to determine the structural dimensions with the best blast resistance. The proposed optimisation method can provide inspiration for improving the safety of ships. [ABSTRACT FROM AUTHOR]

This paper focuses on predicting road passenger probability and optimizing taxi driving routes based on trajectory big data. By utilizing clustering algorithms to identify key passenger points, a method for calculating and predicting road passenger probability is proposed. This method calculates the passenger probability for each road segment during different time periods and uses a BiLSTM neural network for prediction. A passenger-seeking recommendation model is then constructed with the goal of maximizing passenger probability, and it is solved using the NSGA-II algorithm. Experiments are conducted on the Chengdu taxi trajectory dataset, using MSE as the metric for model prediction accuracy. The results show that the BiLSTM prediction model improves prediction accuracy by 9.67% compared to the BP neural network and by 6.45% compared to the LSTM neural network. The proposed taxi driver passenger-seeking route selection method increases the average passenger probability by 18.95% compared to common methods. The proposed passenger-seeking recommendation framework, which includes passenger probability prediction and route optimization, maximizes road passenger efficiency and holds significant academic and practical value. [ABSTRACT FROM AUTHOR]

In response to the challenges of small-size defects and low recognition rates in Printed Circuit Boards (PCBs), as well as the need for lightweight detection models that can be embedded in portable devices, this paper proposes an improved defect detection method based on a lightweight shared convolutional head using YOLOv8n. Firstly, the Spatial and Channel reconstruction Convolution (SCConv) is embedded into the Cross Stage Partial with Convolutional Layer Fusion (C2f) structure of the backbone network, which reduces redundant computations and enhances the model's learning capacity. Secondly, an adaptive feature selection module is integrated to improve the network's ability to recognize small targets. Subsequently, a Shared Lightweight Convolutional Detection (SLCD) Head replaces the original Decoupled Head, reducing the model's computational complexity while increasing detection accuracy. Finally, the Weighted Intersection over Union (WIoU) loss function is introduced to provide more precise evaluation results and improve generalization capability. Comparative experiments conducted on a public PCB dataset demonstrate that the improved algorithm achieves a mean Average Precision (mAP) of 98.6% and an accuracy of 99.8%, representing improvements of 3.8% and 3.1%, respectively, over the original model. The model size is 4.1 M, and its FPS is 144.1, meeting the requirements for real-time and lightweight portable deployment. [ABSTRACT FROM AUTHOR]

In abstract argumentation frameworks, the computation of stable extensions is an important semantic task for evaluating the acceptability of arguments. The current approaches for the computation of stable extensions are typically conducted through methodologies that are either label-based or extension-based. Label-based algorithms operate by assigning labels to each argument, thus reducing the attack relations between arguments to constraint relations among the labels. This paper analyzes the existing two-label and three-label enumeration algorithms for stable extensions through case studies. It is found that both the two-label and three-label algorithms are not precise enough in defining types of arguments. To address these issues, this paper proposes a four-label enumeration algorithm for stable extensions. This method introduces a m u s t _ i n label to pre-mark certain i n -type arguments, thereby achieving a finer classification of i n -type arguments. This enhances the labelings' propagation ability and reduces the algorithm's search space. Our proposed four-label algorithm was tested on authoritative benchmark sets of abstract argumentation framework problems: ICCMA 2019, ICCMA 2021, and ICCMA 2023. Experimental results show that the four-label algorithm significantly improves solving efficiency compared to existing two-label and three-label algorithms. Additionally, ablation experiments confirm that both the four-label transition strategy and preprocessing strategy enhance the algorithm's performance. [ABSTRACT FROM AUTHOR]

One of the interesting discourses that has occurred in Thailand as a result of ChatGPT is how the algorithm is exploited in a growing number of workshops and seminars aimed at teaching how to use, or to 'prompt', the algorithm so as to maximise its potential. On the one hand, the organisers of these workshops aim at profiting from the growing demand for ChatGPT. On the other, there is a sense among the Thai public that they must reap the benefit of the technology for their own purposes. This trend seems to be more prominent in Thailand than in the West, where ChatGPT is viewed more with critical outlook. In this paper, we critically examine the perception of ChatGPT in the Thai context, especially when ChatGPT is used as a topic in these workshops. We will also discuss how this situation should lead to a discussion of how ChatGPT should be regulated. [ABSTRACT FROM AUTHOR]

Aiming to provide solutions for problems proposed by the inaccurate segmentation of long objects and information loss of small objects in real-time semantic segmentation algorithms, this paper proposes a lightweight multi-branch real-time semantic segmentation network based on BiseNetV2. The new auxiliary branch makes full use of spatial details and context information to cover the long object in the field of view. Meanwhile, in order to ensure the inference speed of the model, the asymmetric convolution is used in each stage of the auxiliary branch to design a structure with low computational complexity. In the multi-branch fusion stage, the alignment-and-fusion module is designed to provide guidance information for deep and shallow feature mapping, so as to make up for the problem of feature misalignment in the fusion of information at different scales, and thus reduce the loss of small target information. In order to further improve the model's awareness of key information, a global context module is designed to capture the most important features in the input data. The proposed network uses an NVIDIA GeForce RTX 3080 Laptop GPU experiment on the road street view Cityscapes and CamVid datasets, with the average simultaneously occurring ratios reaching 77.1% and 77.4%, respectively, and the running speeds reaching 127 frames/s and 112 frames/s, respectively. The experimental results show that the proposed algorithm can achieve a real-time segmentation and improve the accuracy significantly, showing good semantic segmentation performance. [ABSTRACT FROM AUTHOR]

In low-light environments, the presence of numerous small, dense, and occluded objects challenges the effectiveness of conventional object detection methods, failing to achieve desirable results. To address this, this paper proposes an efficient object detection network, YOLO_GD, which is designed for precise detection of targets in low-light scenarios. This algorithm, based on the foundational framework of YOLOv5s, implements a cross-layer feature fusion method founded on an information gathering and distribution mechanism. This method mitigates the issue of information loss during inter-layer feature exchange and, building on this, constructs a Bi-level routing spatial attention module to reduce computational redundancy caused by the self-attention mechanism, thereby enhancing the model's detection accuracy for small objects. Furthermore, through the introduction of a novel deformable convolution, a cross-stage local feature fusion module is established, enabling the model to capture the complex features of input data more accurately and improve detection precision for dense objects. Lastly, the introduction of a probabilistic distance metric in the bounding box regression loss function enhances the network model's generalization capability, further increasing detection accuracy in occluded scenarios. Experimental results on the ExDark dataset demonstrate that compared to YOLOv5, there is a 5.97% improvement in mean average precision (mAP), effectively enhancing object detection performance in low-light conditions. [ABSTRACT FROM AUTHOR]

Extracting ship velocity vectors from optical remote sensing images is a very challenging task, and ship wakes are the only motion features of ships. However, because the sensor's field of view is not sufficiently bright and the brightness is not uniform, the image contains noise, which makes it difficult to define and extract the wake of the ship. Velocity analysis of the extracted wake makes the whole process complicated and slow. Therefore, considering the above problems, this paper proposes Ship-VNet, an optical remote sensing image ship velocity analysis algorithm based on Kelvin wakes. In this model, the rotating target detection algorithm is used to detect the ship, and then, the classical relationship between the kinematic characteristics of the ship's Kelvin wake and the velocity of the ship is studied and experimentally analyzed in the frequency domain. In addition, based on optical remote sensing images and corresponding real AIS data, a ship dataset with Kelvin wakes marked with heading velocity was constructed to verify the effectiveness of the proposed method. Compared with the ship velocity analysis method based on the frequency domain, which was also used in the previous research, the experiment demonstrates the superiority of the method in terms of analysis accuracy. [ABSTRACT FROM AUTHOR]

Building facade completion is an important part of digitizing the structures of buildings using computer technology. Due to the intricate textures and structures in building facade images, existing image-completion algorithms cannot accurately restore the rich texture and detailed information. In response, this paper proposes a novel network to simultaneously recover the texture and semantic structural features of building facades. By incorporating dynamic convolutions into each layer of the feature encoder, the shallow layers of the completion network can create a global receptive field, thus enhancing the model's feature-extraction capability. Additionally, a spatial attention branch is integrated into the dynamic convolution module to boost the correlation between the completion area and its surrounding edge area, resulting in improved edge clarity and accuracy of the completed facade image. Experimental results on multiple public image datasets demonstrate that the proposed model in this paper achieves state-of-the-art results when applied to real-world datasets. [ABSTRACT FROM AUTHOR]

This paper addresses the challenge of trajectory planning for autonomous vehicles operating in complex, constrained environments. The proposed method enhances the hybrid A-star algorithm through back-end optimization. An adaptive node expansion strategy is introduced to handle varying environmental complexities. By integrating Dijkstra's shortest path search, the method improves direction selection and refines the estimated cost function. Utilizing the characteristics of hybrid A-star path planning, a quadratic programming approach with designed constraints smooths discrete path points. This results in a smoothed trajectory that supports speed planning using S-curve profiles. Both simulation and experimental results demonstrate that the improved hybrid A-star search significantly boosts efficiency. The trajectory shows continuous and smooth transitions in heading angle and speed, leading to notable improvements in trajectory planning efficiency and overall comfort for autonomous vehicles in challenging environments. [ABSTRACT FROM AUTHOR]