检索结果-内蒙古大学图书馆

15th IEEE Annual Computing and Communication Workshop and Conference, CCWC 2025

作者： Jung, Ho-Seok Jang, Sung Won Baek, Youngmi Changshin University Dept. of Computer Software Engineering Korea Republic of Changshin University Dept. of Computer Engineering Korea Republic of

ISBN: (纸本)9798331507695

The security of industrial networks, particularly in industrial automation systems, is critical for ensuring system reliability and protecting sensitive data. This paper proposes a deeper anomaly detection system using the ResNet34 (Residual Network) model to identify and detect cyber-attacks in industrial networks, specifically focusing on Controller Area Network (CAN) systems. The study highlights the vulnerabilities in industrial communication protocols, such as CAN, Modbus, and Ethernet/IP, which are susceptible to cyber-attacks including replay, modification, and fuzzing attacks. These attacks can disrupt the functioning of industrial systems and cause significant damage. Experimental results show that the proposed model achieves a 100% detection rate for all types of cyber-attacks, demonstrating its effectiveness in recognizing abnormal patterns and responding to changes in network behavior. The results confirm that the ResNet34-based deep anomaly detection model can be a valuable tool for strengthening the security of industrial networks by providing real-time detection of cyber-attacks, thereby ensuring the stability and safety of industrial automation systems. © 2025 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Infrared Fault Detection Method for Dense Electrolytic Bath Polar Plate Based on YOLOv5s

引用

computers, Materials & Continua 2024年第9期80卷 4859-4874页

作者： Huiling Yu Yanqiu Hang Shen Shi Kangning Wu Yizhuo Zhang Software Engineering Department of Computer ScienceChangzhou UniversityChangzhou213146China Electrical Engineering Department of Computer ScienceChangzhou UniversityChangzhou213146China

Electrolysis tanks are used to smeltmetals based on electrochemical principles,and the short-circuiting of the pole plates in the tanks in the production process will lead to high temperatures,thus affecting normal *** at the problems of time-consuming and poor accuracy of existing infrared methods for high-temperature detection of dense pole plates in electrolysis tanks,an infrared dense pole plate anomalous target detection network YOLOv5-RMF based on You Only Look Once version 5(YOLOv5)is ***,we modified the Real-Time Enhanced Super-Resolution Generative Adversarial Network(Real-ESRGAN)by changing the U-shaped network(U-Net)to Attention U-Net,to preprocess the images;secondly,we propose a new Focus module that introduces the Marr operator,which can provide more boundary information for the network;again,because Complete Intersection over Union(CIOU)cannot accommodate target borders that are increasing and decreasing,replace CIOU with Extended Intersection over Union(EIOU),while the loss function is changed to Focal and Efficient IOU(Focal-EIOU)due to the different difficulty of sample *** the homemade dataset,the precision of our method is 94%,the recall is 70.8%,and the map@.5 is 83.6%,which is an improvement of 1.3%in precision,9.7%in recall,and 7%in map@.5 over the original *** algorithm can meet the needs of electrolysis tank pole plate abnormal temperature detection,which can lay a technical foundation for improving production efficiency and reducing production waste.

关键词： Infrared polar plate fault detection YOLOv5 Real-ESRGAN Marr boundary detection operator Focal-EIoU loss

来源：评论

学校读者我要写书评

暂无评论

LoRaDIP: Low-Rank Adaptation With Deep Image Prior for Generative Low-Light Image Enhancement

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第4期6卷 909-920页

作者： Zhao, Zunjin Shi, Daming Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China

This article presents LoRaDIP, a novel low-light image enhancement (LLIE) model based on deep image priors (DIPs). While DIP-based enhancement models are known for their zero-shot learning, their expensive computational cost remains a challenge. In addressing this issue, our proposed LoRaDIP introduces a low-rank adaptation technique, significantly reducing computational expenses without compromising performance. The contributions of this work are threefold. First, we eliminate the need for estimating initial illumination and reflectance, opting instead to directly estimate the illumination map from the observed image in a generative fashion. The illumination is parameterized by a DIP network. Second, considering the overparameterization of DIP networks, we introduce a low-rank adaptation technique to decrease the number of trainable parameters, thereby reducing computational demands. Third, differing from the existing DIP-based models that rely on a preset fixed number of iterations to halt the optimization process of Retinex decomposition, we propose an automatic stopping criterion based on stable rank, preventing unnecessary iterations. LoRaDIP not only inherits the advantage of requiring only the single input image but also exhibits reduced computational costs while maintaining or even surpassing the performance of state-of-the-art models. © 2020 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Balancing Data Imbalance in Remote Sensing Image Road Segmentation with Gradient-Guided Multi-level Data Augmentation

引用

IEEE Signal Processing Letters 2025年 32卷 2404-2408页

作者： Cao, Xu Liu, Weisheng Wang, Zhijian University of Science and Technology Liaoning College of Computer Science and Software Engineering Anshan China

In remote sensing image segmentation, data imbalance remains a critical challenge, particularly in datasets from networks and natural scenes, increasing task complexity. Recent studies have explored adversarial training to address this issue, but these methods rely heavily on labeled data, introducing annotation bias and efficiency concerns. To overcome these limitations, this paper proposes a gradient-guided image-level perturbation strategy. Specifically, we design a multi-level, multi angle data augmentation framework that integrates patch-level perturbation with gradient-based adaptive region selection, enhancing the model's recognition of rare samples while preserving contextual integrity. Experimental results demonstrate that our method surpasses traditional segmentation algorithms and data balancing strategies, achieving an F1 score of 82.67% on the Massachusetts Roads dataset and exhibiting strong generalization on the LoveDA dataset. This research provides valuable insights for advancing remote sensing image analysis. © 1994-2012 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

YOLOv7-DSE: An Efficient Safety Equipment Detection Network

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2024年第6期51卷 572-581页

作者： Ren, Jiaxin Cui, Wenhua Tao, Ye Shi, Tianwei School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China

Safety equipment detection is an important application of object detection, receiving widespread attention in fields such as smart construction sites and video surveillance. Significant progress has been made in object detection due to the rapid development of deep learning. Multi-scale targets and complex scenes increase the likelihood of false positives and missed detections, which can affect the accuracy of the detection. To address this issue, this study proposes YOLOv7-DSE. It is a small complex target scene detection network based on the improved YOLOv7. Also, we have created a private dataset of safety equipment. First, we enhanced the ELAN and MP backbone networks. Backbone is replaced by ordinary convolution by the dept.wise separable convolution. We enabled the backbone network to extract deeper image features without increasing the amount of parameters and computation. Simultaneously, the model incorporates the EIOU loss function to improve its convergence speed and positioning effect. Secondly, we propose a new ELAN-SPD structure in the head network. Based on the ELAN structure, a space-to-dept. convolutional layer is added to fully downsample the feature map, preserving all learnable features. Our network model can better detect objects with significant size differences faced with complex scenes. YOLOv7-DSE achieved the mAP of 82.38%, surpassing the original YOLOv7 with 2.64%. The YOLOv7-DSE model has a minor size compared to the baseline model. Our improvement has reduced the model parameters by 22.4%. © (2024), (International Association of Engineers). All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Application of Face Detection and Recognition Algorithm Based on Deep Learning in Automatic Interception of Target Person Video Clips

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2024年第10期51卷 1546-1559页

作者： Wang, Zhibiao Tao, Ye Liu, Xu Yu, Jiayi Cui, Wenhua School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China

Current automatic segment extraction techniques for identifying target characters in videos have several limitations, including low accuracy, slow processing speeds, and poor adaptability to diverse scenes. This paper introduces an optimized algorithm to address these issues that enhance the RetinaFace and FaceNet models. We selected RetinaFace for face detection, employing MobileNetV1-0.25 as the backbone network and simplifying its Feature Pyramid Network (FPN) structure to boost detection speeds. Analysis of 460 images with a 720P resolution demonstrated an average speed improvement of 20.6%. For face recognition, we utilized FaceNet with MobileNetV3 as the backbone, augmenting its feature extraction capability by integrating four Receptive Field Block (RFB) structures and replacing the Squeeze-and-Excitation (SE) module with the Convolutional Block Attention Module (CBAM). Experimental results indicate that our enhancements elevate the maximum accuracy to 97%, outperforming the original model. Additionally, we integrated these refined algorithms and conducted disintegration experiments on segment extraction in 10 videos, evaluating various metrics. The findings show improvements in both precision and recall. We also compared our algorithm against the Dlib model;our system achieved an overall interception accuracy of 79.94%, surpassing Dlib’s 75.55%. This confirms the enhanced performance and feasibility of our proposed algorithm. © (2024), (International Association of Engineers). All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A review of optimization methods for computation offloading in edge computing networks

引用

Digital Communications and Networks 2023年第2期9卷 450-461页

作者： Kuanishbay Sadatdiynov Laizhong Cui Lei Zhang Joshua Zhexue Huang Salman Salloum Mohammad Sultan Mahmud College of Computer Science and Software Engineering Shenzhen UniversityShenzhen518061China

Handling the massive amount of data generated by Smart Mobile Devices(SMDs)is a challenging computational *** Computing is an emerging computation paradigm that is employed to conquer this *** can bring computation power closer to the end devices to reduce their computation latency and energy ***,this paradigm increases the computational ability of SMDs by collaboration with edge *** is achieved by computation offloading from the mobile devices to the edge nodes or ***,not all applications benefit from computation offloading,which is only suitable for certain types of *** properties,SMD capability,wireless channel state,and other factors must be counted when making computation offloading ***,optimization methods are important tools in scheduling computation offloading tasks in Edge Computing *** this paper,we review six types of optimization methods-they are Lyapunov optimization,convex optimization,heuristic techniques,game theory,machine learning,and *** each type,we focus on the objective functions,application areas,types of offloading methods,evaluation methods,as well as the time complexity of the proposed *** discuss a few research problems that are still *** purpose for this review is to provide a concise summary that can help new researchers get started with their computation offloading researches for Edge Computing networks.

关键词： Edge computing Computation offloading Latency and energy consumption minimization

来源：评论

学校读者我要写书评

暂无评论

Heuristic Algorithms for software Modules Clustering 3

Heuristic Algorithms for Software Modules Clustering

引用

3rd International Conference on Machine Learning and Data engineering, ICMLDE 2024

作者： Ali, Ali H. Taha, Dujan B. Software Dept. College of Computer Science and Mathematics Mosul University Iraq Computer Science Dept. College of Computer Science and Mathematics Mosul University Mosul Iraq

In the fields of software engineering, the maintenance phase takes the most effort. software Module Clustering (SMC), as a part of reverse engineering, is used for the purpose of creating structural models from the source code enhancing its comprehensibility. Finding the best clusters is an NP-hard problem. The method of software module clustering aims to extract the best clusters, which involves Increase cohesion and reduce coupling. This re-search addresses a set of problems with the aim of solving them, which are drawback found in most previous studies. This paper adopts three main methods to solve software Modules Clustering problem (SMCP), a Teaching-Learning-Based-optimization (TLBO) algorithm, a Black Widow optimization (BWO) algorithm, and the third is a hybrid algorithm combining the previous two methods. These algorithms were used to cluster software modules and were evaluated based on MQ (Modularity Quality), cohesion, coupling, and stability. To determine the optimal number of clusters for each reference program, the Louvain algorithm is used, which works on detecting communities in networks. The study also experintly examined the impact of the chaos, random, Lorenzo methods in the initial generation of solutions on the quality of the results and stability. Considering the results of the experiments conducted on eight standard applications, the hybrid algorithm performs better in SMC problems than the TLBO and BWO. The performance of these algorithms also improves significantly, when their initial populations are generated using the logistic Lorenz and Chaos method rather than a random one. 6.644548537, 6.318318013, and 4.375766992 are the average MQ of the clusters that were formed for the selected casses set using the Hybrid method, BWO, and TLBO, respectively. © 2025 The Author(s).

关键词： Reverse engineering

来源：评论

学校读者我要写书评

暂无评论

A Text-to-SQL Query Parser with Integrating Instances

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2025年第6期52卷 1764-1771页

作者： Cui, Xuxu Shen, Derong School of Computer Science and Software Engineering University of Science and Technology Liaoning Liaoning114051 China School of Computer Science and Engineering Northeastern University Liaoning114051 China

Text-to-SQL is a natural language processing task focused on translating natural language queries into Structured Query Language (SQL), aiming to facilitate interaction between non-technical users and relational databases. Currently, many existing Text-to-SQL models based on deep learning methods concentrate on encoding natural language questions and database schemas, while often neglecting the inclusion of database instance information. Additionally, these models are constrained by SQL syntax during the decoding process, which limits their generalization ability. This paper presents a Text-to-SQL query parser that integrates database instances to address these limitations. By incorporating database instance information, both natural language queries and database schema-instance pairs are represented as graph structures for encoding. Predefined relationships are utilized to unify the encoding of natural language questions, database schemas, and database instances. An instance-aware query parsing method is then applied during the decoding phase, allowing the model to fully leverage database instance information when generating SQL queries, which improves its scalability. The method is evaluated using the cross-domain Spider dataset, and pretrained language models such as GloVe, GAP, and BERT are employed to enhance model performance. Experimental results show that the proposed approach significantly improves prediction accuracy in Text-to-SQL tasks. © (2025), (International Association of Engineers). All rights reserved.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential of Llama Models in Automated Code Refinement: A Replication Study 32

Exploring the Potential of Llama Models in Automated Code Re...

引用

32nd IEEE International Conference on software Analysis, Evolution and Reengineering, SANER 2025

作者： Caumartin, Genevieve Qin, Qiaolin Chatragadda, Sharon Panjrolia, Janmitsinh Li, Heng Costa, Diego Elias Concordia University Dept of Computer Science and Software Engineering Montreal Canada Polytechnique Montreal Dept of Computer Engineering and Software Engineering Montreal Canada

ISBN: (纸本)9798331535100

Code reviews are an integral part of software development and have been recognized as a crucial practice for minimizing bugs and favouring higher code quality. They serve as an important checkpoint before committing code and play an essential role in knowledge transfer between developers. However, code reviews can be time-consuming and can stale the development of large software projects. In a recent study, Guo et al. assessed how ChatGPT3.5 can help the code review process. They evaluated the effectiveness of ChatGPT in automating the code refinement tasks, where developers recommend small changes in the submitted code. While Guo et al.'s study showed promising results, proprietary models like ChatGPT pose risks to data privacy and incur extra costs for software projects. In this study, we explore alternatives to ChatGPT in code refinement tasks by including two open-source, smaller-scale large language models: CodeLlama and Llama 2 (7B parameters). Our results show that, if properly tuned, the Llama models, particularly CodeLlama, can achieve reasonable performance, often comparable to ChatGPT in auto-mated code refinement. However, not all code refinement tasks are equally successful: tasks that require changing existing code (e.g., refactoring) are more manageable for models to automate than tasks that demand new code. Our study highlights the potential of open-source models for code refinement, offering cost-effective, privacy-conscious solutions for real-world software development. © 2025 IEEE.

关键词： software design

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

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

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：