检索结果-内蒙古大学图书馆

Enhancing Battery Exterior Defect Inspection Accuracy Through Defect-Background Separated GAN Development

IEEE ACCESS 2024年 12卷 44286-44305页

作者： Ku, Donghun Pahk, Heui Jae Seoul Natl Univ Sch Mech & Aerosp Engn Seoul 08826 South Korea

This paper aims to develop a defect-background separated generative adversarial network (GAN) using deep learning and GAN to enhance the accuracy of battery exterior defect inspection. In actual battery production lines, the occurrence rates of defects vary by defect type, making it challenging to create a large, uniform defect dataset due to the time required for defect acquisition. This leads to a reduction in the accuracy of battery exterior defect inspection. To construct a large, uniform defect dataset, this paper proposes a defect-background separated GAN based on the principles of GANs. The defect-background separated GAN performs effective defect and background separation learning by referring to the segmentation labeling of defects. Through dataset augmentation using the defect-background separated GAN, the performance quality of newly generated synthetic defect images has improved, and accuracy in battery exterior defect inspection can be enhanced through extensive dataset training. Experimental results show the lowest Frechet inception distance score among various other methods for the battery exterior defect dataset, and it generates clear synthetic defects perceptible to the human eye. By training defect segmentation on this large, uniform defect dataset, an accuracy of 96.1% and an intersection over union value of 0.71 were achieved. Ultimately, applying this defect inspection network to the actual production line demonstrated a 72% improvement in time efficiency. This demonstrates the stability and robustness of the large, uniform defect dataset generated through the defect-background separated GAN.

关键词： Inspection Generative adversarial networks Deep learning Batteries Training Data models Production Defect detection Synthetic data detection algorithms Battery exterior defect inspection deep learning defect segmentation generative adversarial network synthetic defect

来源：评论

学校读者我要写书评

暂无评论

Keeping Deep Learning Models in Check: A History-Based Approach to Mitigate Overfitting

引用

IEEE ACCESS 2024年 12卷 70676-70689页

作者： Li, Hao Rajbahadur, Gopi Krishnan Lin, Dayi Bezemer, Cor-Paul Jiang, Zhen Ming Univ Alberta Dept Elect & Comp Engn Edmonton AB T6G 2R3 Canada Huawei Technol Ctr Software Excellence Kingston ON K7L 1H3 Canada York Univ Dept Elect Engn & Comp Sci Toronto ON M3J 1P3 Canada

In software engineering, deep learning models are increasingly deployed for critical tasks such as bug detection and code review. However, overfitting remains a challenge that affects the quality, reliability, and trustworthiness of software systems that utilize deep learning models. Overfitting can be (1) prevented (e.g., using dropout or early stopping) or (2) detected in a trained model (e.g., using correlation-based approaches). Both overfitting detection and prevention approaches that are currently used have constraints (e.g., requiring modification of the model structure, and high computing resources). In this paper, we propose a simple, yet powerful approach that can both detect and prevent overfitting based on the training history (i.e., validation losses). Our approach first trains a time series classifier on training histories of overfit models. This classifier is then used to detect if a trained model is overfit. In addition, our trained classifier can be used to prevent overfitting by identifying the optimal point to stop a model's training. We evaluate our approach on its ability to identify and prevent overfitting in real-world samples. We compare our approach against correlation-based detection approaches and the most commonly used prevention approach (i.e., early stopping). Our approach achieves an F1 score of 0.91 which is at least 5% higher than the current best-performing non-intrusive overfitting detection approach. Furthermore, our approach can stop training to avoid overfitting at least 32% of the times earlier than early stopping and has the same or a better rate of returning the best model.

关键词： Training History Time series analysis Data models Hidden Markov models Measurement Training data Software engineering Deep learning Neural networks Computer bugs detection algorithms Trusted computing deep learning machine learning overfitting training history early stopping neural networks

来源：评论

学校读者我要写书评

暂无评论

FlexTrack3D: Advanced Single-Camera 3D Human Pose Tracking With FlexPoseNet and ZoeDepth

引用

IEEE ACCESS 2024年 12卷 171334-171347页

作者： Chen, Yingying Li, Zhitao Jiangsu Maritime Inst Sch Informat Engn Nanjing 211170 Peoples R China Chongqing Univ Sci & Technol Coll Met & Power Engn Chongqing 401331 Peoples R China Nanjing Xiaozhuang Univ Sch Informat Engn Sch Artificial Intelligence Nanjing 21171 Peoples R China

At present, the research of three-dimensional human pose tracking mainly focuses on the multi-camera system, but lacks a tracking algorithm for monocular cameras. Therefore, a 3D human pose tracking algorithm, FlexTrack3D, is proposed, which can track human 3D pose on monocular video. FlexTrack3D innovatively combines 2D human pose detection and monocular depth estimation technology. By integrating pixel coordinates of human keypoints provided by FlexPoseNet and depth data generated by ZoeDepth algorithm, FlexTrack3D can accurately model keypoints in three dimensions and accurately track their dynamic trajectories. FlexTrack3D shows the pose and trajectory of human motion data collected in indoor and outdoor environment through 3D point cloud model, which proves its accuracy and robustness. For tracking keypoints of human, a lightweight human pose detection model, FlexPoseNet, and a parameter sharing detector with multi-scale feature information are proposed, which strengthens the learning of key features on the premise of reducing the parameters of baseline model YOLO-Pose. Multi-Head Self-Attention module and Deformable Convolution Networks module are introduced into the backbone of FlexPoseNet model, which enhances the modeling ability of the network to the target's receptive field and improves the modeling flexibility of the network to the target structure. SlimNeck structure is introduced into the neck of the model, which effectively reduces the calculation and parameters of the model while maintaining the detection accuracy. In the experiment of COCO-Pose data set, the processing speed of FlexPoseNet is increased by 42.9% per second compared with the baseline model YOLO-Pose, and the detection accuracy of mAP50 and mAP50-95 is increased by 12.46% and 10.21%, which further improves the accuracy of the model on the premise of maintaining performance.

关键词： Three-dimensional displays Accuracy Feature extraction Cameras Target tracking Deep learning Computer vision Computational modeling detection algorithms Sensors deep learning depth estimation pose detection 3D pose tracking

来源：评论

学校读者我要写书评

暂无评论

An Interactive Prompt Based Network for Urban Floods Area Segmentation Using UAV Images

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2025年 18卷 935-948页

作者： Shi, Lingfei Yang, Kun Chen, Yunfang Chen, Gong Yunnan Normal Univ Fac Geog Kunming 650500 Peoples R China Western China Minist Educ China Engn Res Ctr GIS Technol Beijing 100816 Peoples R China Yunnan Key Lab Int Rivers & Transboundary Ecosecur Kunming 650500 Peoples R China

As climate change intensifies, extreme weather events like floods are occurring with increasing frequency. While data-driven deep learning methods are effective for extracting flood disaster information, their efficiency is constrained by the scarcity of postdisaster samples, the high cost of annotations, and the models' strong dependence on both the quantity and quality of data. This study introduces an interactive semantic segmentation model based on multisource UAV flood images, incorporating four types of prompts. By embedding expert knowledge into the prompt design, the model reduces annotation costs and enhances generalization capabilities. First, a prompt encoder is developed to map different types of prompt information into a three-channel space using convolutional techniques, thereby reducing sample labeling costs. Moreover, an image encoder that integrates Mamba and convolution is developed to effectively extract global spatial and channel features from flood images while minimizing computational load. Finally, a spatial and channel attention module with residual connections is introduced to enable multiscale fusion and filtering of prompt information and image features across both spatial and channel dimensions, improving the utilization of prompt information. To validate the model's performance, we conduct experiments using UAV flood imagery collected from diverse regions, backgrounds, and angles. The results demonstrate that, under consistent prompt conditions, our model extracts flood areas more efficiently, reducing misclassification and omission errors. Compared with the next best benchmark model, the intersection over union for the flood category improves by at least 3.75%.

关键词： Climate change Floods detection algorithms Prompt engineering Learning systems Semantic segmentation Autonomous aerial vehicles Interactive systems Meteorology Load modeling Feature extraction Weather forecasting Deep learning Satellite images Urban areas Flood detection prompt learning semantic segmentation UAV

来源：评论

学校读者我要写书评

暂无评论

algorithms for Change detection With Sparse Signals

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2020年第0期68卷 1331-1345页

作者： Jain, Aditi Sarvepalli, Pradeep Bhashyam, Srikrishna Kannu, Arun Pachai Indian Inst Technol Madras Dept Elect Engn Chennai 600036 Tamil Nadu India

We consider the change detection problem where the pre-change observation vectors are purely noise and the post-change observation vectors are noise-corrupted compressive measurements of sparse signals with a common support, measured using a sensing matrix. In general, post-change probability density function (pdf) of the observations depends on parameters such as the support and variances of the sparse signal. When these parameters are unknown, we propose two approaches. In the first approach, we approximate the post-change pdf based on the known parameters such as mutual coherence of the sensing matrix and bounds on the signal variances. In the second approach, we parameterize the post-change pdf with an unknown parameter and try to estimate this parameter using two different methods, stochastic gradient descent and generalized likelihood ratio. In both these approaches, we employ the conventional cumulative sum (CUSUM) algorithm with various decision statistics such as the energy of the observations, correlation values with columns of the sensing matrix and the maximum value of such correlations. We analytically characterize the worst case detection delay and average run length to false alarm performance of pdf-approximation based approach. We also numerically study the performance and offer insights on the relevance of various decision statistics in different signal to noise ratio (SNR) regimes. We also address the problem of designing sensing matrices with small mutual coherence by using designs from quantum information theory. One such design using equi-angular lines has an additional structure which allows exact characterization of the post-change pdf of the correlation values, even when the support set of the sparse signal is unknown. We apply our detection algorithms with sensing matrix designed from equi-angular lines to a massive random access problem and show their superior performance over conventional Gold codes.

关键词： Sensors Sparse matrices Delays Change detection algorithms Probability density function detection algorithms Correlation CUSUM algorithm detection delay average run length sensing matrix design mutual coherence quantum information theory

来源：评论

学校读者我要写书评

暂无评论

Omnidirectional Chargability With Directional Antennas

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2024年第5期23卷 4483-4500页

作者： Dai, Haipeng Zhang, Yikang Wang, Xiaoyu Liu, Alex X. Chen, Guihai Nanjing Univ State Key Lab Novel Software Technol Nanjing 210023 Jiangsu Peoples R China Soochow Univ Sch Comp Sci & Technol Suzhou 215006 Jiangsu Peoples R China Michigan State Univ Dept Comp Sci & Engn E Lansing MI 48824 USA

Wireless Power Transfer (WPT) has received more and more attention for its convenience and reliability. In this paper, we first propose the notion of omnidirectional charging. First, we consider the problem of detecting whether the target area achieves omnidirectional charging given a deterministic deployment of chargers. We use piecewise constant approximation and area discretization techniques to partition the target area and approximate charging power as constants. Next, we propose the Minimum Coverage Set extraction technique to design a fast detection algorithm. Second, we design a charger deployment scheme that satisfies omnidirectional charging. By placing the chargers at the triangle lattice points, we estimate the length of triangle lattice side length that satisfies omnidirectional charging, and derive the error bound with the optimal length. Third, we determine the probability that the target area achieves omnidirectional charging given a random deployment of chargers. We devise both analytical and numerical solutions for the problem with good accuracy. Finally, we conduct simulation and field experiments, and the results show that the running speed of our omnidirectional charging detection algorithm is at least $1\times$1x faster than comparison algorithms, and the consistency degree of our theoretical results and field experimental results is larger than $93.6 \%$93.6%.

关键词： Wireless sensor networks Wireless communication Inductive charging Mobile computing detection algorithms Cameras Lattices Charger deployment directional wireless charging network omnidirectional charging

来源：评论

学校读者我要写书评

暂无评论

On the Road to Proactive Vulnerability Analysis and Mitigation Leveraged by Software Defined Networks: A Systematic Review

引用

IEEE ACCESS 2024年 12卷 98546-98566页

作者： Polonio, Joao Moura, Jose Neto Marinheiro, Rui Inst Univ Lisboa ISCTE IUL P-1649026 Lisbon Portugal Inst Telecomun IT P-1049001 Lisbon Portugal

The discovery of security vulnerabilities and their mitigation in networked systems managed by Software-Defined Networking (SDN) are fundamental for ensuring their normal operation. The main goal of this survey was to investigate the literature on preventing system security vulnerabilities instead of detecting ongoing cyber-attacks as quickly as possible. Thus, in our opinion, organizations should fortify their systems' security by identifying and eliminating any new security vulnerabilities before they can be successfully exploited. We comprehensively discuss different vulnerability detection approaches based on important comparison parameters such as vulnerability assessment, the SDN controller used, automation capability, system risk indicators, passive scanning and active probing of system vulnerabilities. The paper also analyzes relevant literature considering the mitigation mechanisms for discovered vulnerabilities such as the proposed SDN controller, automation capability, solution adaptation to system operational changes, risk indicators, and the solution's impact on network quality metrics like latency and throughput. Despite the strengths of the surveyed work, we have also identified promising open issues that need further consideration by scholars, industry participants, and policymakers. We concluded that the majority of analyzed literature contributions are largely reactive in their implementation against running network threats. This suggests a new research domain for applying SDN in the automatic detection of security vulnerabilities and their proactive mitigation before external cyber-attackers can exploit them.

关键词： Prevention and mitigation Software defined networking Measurement Surveys Reviews Road traffic detection algorithms Risk management Network security Network systems System vulnerability assessment detection mitigation software defined networks risk evaluation automatic operation network security

来源：评论

学校读者我要写书评

暂无评论

Enhancing Participation of Widespread Distributed Energy Storage Systems in Frequency Regulation Through Partitioning-Based Control

引用

PROTECTION AND CONTROL OF MODERN POWER SYSTEMS 2025年第1期10卷 76-89页

作者： Lin, Yujun Luo, Haowen Chen, Yin Yang, Qiufan Zhou, Jianyu Chen, Xia Huazhong Univ Sci & Technol State Key Lab Adv Electromagnet Technol Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Elect & Elect Engn Wuhan 430074 Peoples R China State Grid Jingmen Power Supply Co Jingmen 448000 Peoples R China Univ Strathclyde Dept Elect & Elect Engn Glasgow G1 1XW Scotland

In recent years, a significant number of distributed small-capacity energy storage (ES) systems have been integrated into power grids to support grid frequency regulation. However, the challenges associated with high-dimensional control and synergistic operation alongside conventional generators remain unsolved. In this paper, a partitioning-based control approach is developed for the participation of widespread distributed ES systems on frequency control in power systems. The approach comprises a network partitioning method and a two-layer frequency control scheme. The partitioning method utilizes a community detection algorithm in which the weights between the buses are calculated based on the electrical distances. After partitioning the buses into different groups, an optimization-based frequency control system with two layers is established to aggregate and dis-aggregate the inertia and droop coefficients so that frequency regulation and economical operation can be achieved. The effectiveness of the proposed method is demonstrated through numerical simulations on an IEEE 39-bus system. The results confirm the successful elimination of frequency deviations and low operating cost of the proposed approach.

关键词： Costs Power systems Topology Reliability detection algorithms Sustainable development Protection Frequency control Energy storage Resilience Community detection algorithm distributed control energy storage frequency response

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Markov Dynamics for Network Community detection

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2022年第3期34卷 1206-1220页

作者： Wang, Zhen Wang, Chunyu Li, Xianghua Gao, Chao Li, Xuelong Zhu, Junyou Northwestern Polytech Univ Ctr OPTIMAL Xian 710072 Peoples R China Southwest Univ Coll Comp & Informat Sci Chongqing 400715 Peoples R China

Community structure division is a crucial problem in the field of network data analysis. algorithms based on Markov chains are easy to use and provide promising solutions for community detection. In a Markov chain-based algorithm (i.e., MCL), a flow distribution matrix and a transition matrix are used to describe stochastic flows and transition probabilities, respectively, on a network. The dynamic interaction process between stochastic flows and transition probabilities in MCLs is manifested through an iterative process of updating the abovementioned two matrices. As one of the key mechanisms of MCLs, such a dynamic process for increasing the inhomogeneity directly affects the accuracy and computational cost of MCL-based methods. Inspired by a kind of positive feedback interaction of a dendritic network of tube-like amoeba cell pseudopodia (named the Physarum foraging network), a Physarum-inspired relationship among vertices is proposed to enhance the transition probability in the dynamic process of MCL-based community detection algorithms. Specifically, the proposed hybrid community detection algorithm can adaptively search for a better combination of parameters based on a genetic algorithm. Some experiments are carried out on both static and dynamic networks. The results show that the unique Physarum inspired algorithm achieved better computational efficiency and detection performance than other algorithms.

关键词： Heuristic algorithms Clustering algorithms Markov processes Measurement detection algorithms Mathematical model Genetic algorithms Complex networks community detection physarum Markov clustering algorithm genetic algorithm dynamic networks

来源：评论

学校读者我要写书评

暂无评论

Motion-Adaptive detection of HEVC Double Compression With the Same Coding Parameters

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2022年 17卷 2015-2029页

作者： Xu, Qiang Jiang, Xinghao Sun, Tanfeng Kot, Alex C. City Univ Hong Kong Dept Elect Engn Hong Kong Peoples R China City Univ Hong Kong Ctr Intelligent Multidimens Data Anal Hong Kong Peoples R China Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Natl Engn Lab Informat Content Anal Tech Shanghai 200240 Peoples R China Nanyang Technol Univ Singapore 637553 Singapore

High Efficiency Video Coding (HEVC) double compression detection is of prime significance in video forensics. However, double compression with the same parameters and video content with high motion displacement intensity have become two main factors that limit the performance of existing algorithms. To address these issues, a novel motion-adaptive algorithm is proposed in this paper. Firstly, the analysis of GOP structure in HEVC standard and the coding process of HEVC double compression are provided. Next, sub-features composed of fluctuation intensities of intra prediction modes and unstable Prediction Units (PUs) in normal Intra-Frames (I-frames) and optical flow in adaptive I-frames are exploited in our algorithm. Each sub-feature is extracted during the process of multiple decompression. We further combine these sub-features into a 27-dimensional detection feature, which is finally fed to the Support Vector Machine (SVM) classifier. By following a separation-fusion detection strategy, the experimental result shows that the proposed algorithm outperforms the existing state-of-the-art methods and demonstrates superior robustness to various motion displacement intensities and a wide variety of coding parameter settings.

关键词： Encoding Prediction algorithms Feature extraction Standards Partitioning algorithms detection algorithms Video sequences HEVC double compression detection motion displacement intensity intra prediction modes unstable prediction units optical flow

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：