检索结果-内蒙古大学图书馆

15th IEEE Global Reliability and Prognostics and Health Management Conference, PHM-Beijing 2024

作者： Gou, Pengfei Zheng, Daiwei Tang, Lei Liu, Mengjuan School of Information and Software Engineering University of Electronic Science and Technology of China UESTC Chengdu China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China NPIC Chengdu China

ISBN: (纸本)9798350354010

Prognostics and Health Management (PHM) is currently the mainstream solution for the condition monitoring and maintenance of industrial systems. In PHM, the system condition is monitored by monitoring the operational status parameters of the system to diagnose equipment faults, predict the remaining useful life, etc. Utilizing sequential operational status parameters to complete prediction and classification tasks is usually modeled as a time series processing task. Therefore, a high-performance time series prediction model is crucial for PHM. This paper focuses on the use of time series prediction models to achieve the prediction of key state parameters of the nuclear power system. However, there are still some challenges when directly applying existing time series prediction models to industrial systems. First, obtaining operational data on the nuclear power system is relatively difficult, resulting in a small amount of training data, which causes many models to face the risk of insufficient training or overfitting. Second, most of the existing time series prediction models are composed of high- and low-frequency decoupling modules, while the operational data of nuclear power systems often have fewer high-frequency components, making it difficult for many existing SOTA models to achieve good results. In order to address these challenges, we have developed a Transformer-based time series prediction model with contrastive learning for monitoring the status of nuclear power systems. We evaluated the new model on three nuclear power simulation datasets and four power transformer datasets. The experimental results show that the new model's performance is superior to baseline models. We also proved the effectiveness of our improvement through ablation experiments. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

A Defect Detection Method Based on Code Defect Knowledge Graph 9

A Defect Detection Method Based on Code Defect Knowledge Gra...

引用

9th International Conference on Computer and Communications, ICCC 2023

作者： Yang, He Le, Wei Yumin, Li Chengdu University of Information Technology School of Software Engineering Chengdu China Chengdu University of Information Technology Automatic Software Generation & Intelligence Service Key Laboratory of Sichuan Province Sichuan Manufacturing Information Industry Collaborative Innovation Center Chengdu China Sichuan Top It Vocational Institute College of Information Engineering Chengdu China

ISBN: (纸本)9798350317251

To address the limitations of existing code defect detection methods, which only analyze code defects from a single perspective and produce uninterpretable results, we introduce a new approach known as Defect Detection Method based on code defect knowledge Graph (DDMB). This method involves several steps. First, we clean and organize defect-related knowledge, defining concepts of defect entities, attributes, and relationships to establish a code defect knowledge graph. Next, using abstract syntax trees, we extract various information from the code, including control flow diagrams, control dependency graphs, data dependency graphs, program dependency graphs, and code attribute graphs, to capture relevant details about nodes and edges. Based on the structural and logical information represented by node-edge associations, we employ the Deepwalk algorithm to construct a directed graph of the code and generate random walk sequences. These sequences serve as a foundation for learning and vector representation. Finally, we compare the vector similarities between the generated representations and a candidate code list from the defect knowledge graph, which has undergone initial semantic threshold filtering. By querying the defect labels of the most similar code in the defect code knowledge graph, we determine whether the code under inspection contains defects. Experimental results reveal that DDMB improves defect detection accuracy by 2.02% compared to existing methods. Additionally, it enhances the interpretability and reliability of defect detection while facilitating multi-dimensional analysis of code defects, thus providing better support for practical applications. © 2023 IEEE.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Identification of energy facilities in remote sensing images: comparison of single and joint models

Identification of energy facilities in remote sensing images...

引用

2024 International Conference on Remote Sensing, Mapping, and Geographic information Systems, RSMG 2024

作者： Liu, Kun Chen, Xingfeng Zheng, Fengjie Meng, Lei Jiang, Mingyong Li, Zhiliang Li, Kaitao Li, Jiaguo Zhang, Yunli Liu, Shumin School of Software Engineering Jiangxi University of Science and Technology Nanchang330013 China Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China School of Space Information Space Engineering University Beijing101416 China

ISBN: (纸本)9781510685826

Wind turbines and high-voltage transmission towers, as critical energy facilities, pose certain challenges in detection under extreme weather conditions. To enhance the accuracy of target identification for these two facilities, this study designed an experiment using the YOLOv5-CBAM model, where a mixed dataset of wind turbines and high-voltage transmission towers was trained under this model to create a joint model for combined recognition. Additionally, single models were trained using individual datasets for wind turbines and high-voltage transmission towers to perform independent identifications, the experimental results indicate a clear advantage in accuracy for the independent identification method. Specifically, in the joint model, the accuracy rates for wind turbines and high-voltage transmission towers were 92.1% and 74.1%, respectively, while in the single models, these rates increased to 99% and 92.3%. This improvement is significant for enhancing the performance of automatic monitoring of energy facilities in complex environments. © 2024 SPIE.

关键词： Windmill

来源：评论

学校读者我要写书评

暂无评论

An Efficient and Privacy-Preserving Spatial Crowdsourcing Protocol from Hash Functions for IoT

引用

IEEE Internet of Things Journal 2025年第12期12卷 19231-19243页

作者： Abla, Parhat Fang, Wan Li, Taotao Deng, Zhihong Xie, Anke South China Normal University School of Software Foshan528225 China Sun Yat-Sen University School of Software Engineering Zhuhai528478 China Guangzhou University School of Mathematics and Information Science Guangzhou510006 China Yunnan Innovation Institute of Beihang University Yunnan Key Laboratory of Blockchain Application Technology Kunming650233 China

The proliferation of smart devices has propelled the advancement of IoT-based spatial crowdsourcing. The issue of location privacy in task allocation for IoT-based spatial crowdsourcing has attracted significant attention. Therefore, the main goals of privacy-preserving spatial crowdsourcing are i) achieving better location privacy for both participants and tasks;ii) achieving better allocation performance, i.e., accuracy and average moving distance. The homomorphic encryption-based approaches can achieve these goals, yet they suffer from heavy computation and large communication overhead. Although the differential privacy-based approaches are very efficient, these approaches leverage allocation performance to achieve better location privacy. Motivated by the deficiencies of these existing approaches, we propose a lightweight hash-based spatial crowdsourcing protocol, which not only protects both task location and participant location from the server but also reduces service providers' computation and communication overhead. Besides, our design is independent of the concrete hash function and thus can be instantiated by any collision-resistant cryptographic hash function. Experiment results demonstrate that our protocol outperforms related works in terms of accuracy and average moving distance. © 2014 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

A New RISC-V CPU for Safety-Critical Systems 12

A New RISC-V CPU for Safety-Critical Systems

引用

12th Mediterranean Conference on Embedded Computing, MECO 2023

作者： Mach, Jan Kohutka, Lukas Cicak, Pavel Institute of Computer Engineering and Applied Informatics Slovak University of Technology Bratislava842 16 Slovakia Institute of Informatics Information Systems and Software Engineering Slovak University of Technology Bratislava842 16 Slovakia

ISBN: (纸本)9798350322910

In this paper, we propose a novel hardening technique against Single Event Effects, which enables high-frequency operation and does not cause large power consumption and area overhead. The protection is based on redundancy, separation of the pipeline into two main sections, and is fully applicable at Register Transfer Level. It provides fast detection of faults, simple recovery by a flush of the pipeline, and allows a large prediction unit to be unprotected. We present the protection scheme at the core with the RISC-V instruction set. Simulations confirm that the protection can handle the injected faults. Synthesis shows that protection lowers the maximum frequency by only 3.9%. The area increase is only 108% and can be even lower. Total power consumption increased by 119%. © 2023 IEEE.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

An Approach for Performance Calculation of AVS/RS in Multi-floor Workshop 3rd

An Approach for Performance Calculation of AVS/RS in Multi-f...

引用

3rd International Conference on Smart Manufacturing, Industrial and Logistics engineering, SMILE 2023 and the 7th Asian Conference of Management Science and Applications, ACMSA 2023

作者： Liu, Xiaopeng Wu, Cuiying Zhang, Baolin Xi, An Chen, Xuanrui Ministry of Industry and Information Technology Key Laboratory of Industrial Software Engineering Application Technology China Electronic Product Reliability and Environmental Testing Research Institute Guangzhou510619 China School of Computer and Information Engineering Hanshan Normal University Guangdong Chaozhou521041 China

ISBN: (纸本)9789819701933

Warehouse management is an important part of the production process. As a result of the development of technology, more and more companies tend to use automated logistics technologies such as AVS/RS to handle the internal logistics of the production system. Especially in multi-floor workshops, the production process on each floor are connected with each other through AVS/RS. It is becoming more and more important to study the integration process of AVS/RS and multi-floor workshop production process. In this paper, an integrated queuing network model of multi-floor workshop and AVS/RS was established, and a calculation method of system performance index was proposed. The accuracy and efficiency of the proposed method are demonstrated by comparing the results with simulations from numerical experiments. The work of this article can provide a basis for the design of autonomous vehicle storage and retrieve systems in multi-floor workshop, and the calculation method can be used as the support of WMS technology base. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Floors

来源：评论

学校读者我要写书评

暂无评论

Global video object segmentation with spatial constraint module

引用

Computational Visual Media 2023年第2期9卷 385-400页

作者： Yadang Chen Duolin Wang Zhiguo Chen Zhi-Xin Yang Enhua Wu Engineering Research Center of Digital Forensics Ministry of EducationSchool of Computer and SoftwareNanjing University of Information Science and TechnologyNanjing 210044China State Key Laboratory of Internet of Things for Smart City Department of Electromechanical EngineeringUniversity of MacaoMacao 999078China State Key Laboratory of Computer Science Institute of SoftwareUniversity of Chinese Academy of SciencesBeijing 100190China Faculty of Science and Technology University of MacaoMacao 999078China

We present a lightweight and efficient semisupervised video object segmentation network based on the space-time memory *** some extent,our method solves the two difficulties encountered in traditional video object segmentation:one is that the single frame calculation time is too long,and the other is that the current frame’s segmentation should use more information from past *** algorithm uses a global context(GC)module to achieve highperformance,real-time *** GC module can effectively integrate multi-frame image information without increased memory and can process each frame in real ***,the prediction mask of the previous frame is helpful for the segmentation of the current frame,so we input it into a spatial constraint module(SCM),which constrains the areas of segments in the current *** SCM effectively alleviates mismatching of similar targets yet consumes few additional *** added a refinement module to the decoder to improve boundary *** model achieves state-of-the-art results on various datasets,scoring 80.1%on YouTube-VOS 2018 and a J&F score of 78.0%on DAVIS 2017,while taking 0.05 s per frame on the DAVIS 2016 validation dataset.

关键词： video object segmentation semantic segmentation global context(GC)module spatial constraint

来源：评论

学校读者我要写书评

暂无评论

DRDnet22: Advanced convolutional techniques for early diabetic retinopathy detection in retinal images 15

DRDnet22: Advanced convolutional techniques for early diabet...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Mazumder, Md. Sakib Ali Shamrat, F M Javed Mehedi Mahmud, Imran Sharmin, Sharmin Hossain, Tanzim Biplab, Ekramul Kabir Daffodil International University Department of Software Engineering Dhaka Bangladesh Universiti Malaya Department of Computer System and Technology Kuala Lumpur Malaysia Institute of Information Technology University of Dhaka Dhaka Bangladesh

ISBN: (纸本)9798350370249

Diabetic Retinopathy (DR) is a prevalent eye complication among individuals with diabetes. Early detection of DR can prevent vision loss and lower associated problems. Manual diagnosis via retinal fundus images requires the expertise of medical professionals to assess several complex characteristics, including visual acuity tests, pupil dilation, and optical consistency tomography. The process is challenging, time-consuming, and prone to errors. This paper proposes a deep learning (DL) technique, DRDnet22, to detect and categorize DR into five distinct stages. The APTOS 2019 dataset is utilized in this study, which contains 3662 images. The study employs dense block and transition layer with global average pooling (GAP) techniques, and the combination of distinct Convolutional Networks (ConvNets) results in an enhanced representation beyond the utilization of features from a single ConvNet alone. To conduct an ablation analysis, the conventional pre-trained model's performance was compared. The performance evaluation points out that the proposed model achieved 81.6% accuracy, which is an advantage over other DCNN models. Despite facing a few inaccuracies, the model's competence in spotting vital features underscores its diagnostic potential. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Testing Intelligent Traffic Control Solutions efficiency in reducing traffic and pollution in Tirana

Testing Intelligent Traffic Control Solutions efficiency in ...

引用

2024 International Workshop on Quantum and Biomedical Applications, Technologies, and Sensors, Q-BATS 2024

作者： Musta, Eugen Elmazi, Donald Elmazi, Klea Mehmeti, Fatjon Hidri, Florenc Department of Finance Canadian Institute of Technology Tirana Albania Department of Computer Engineering University Metropolitan Tirana Tirana Albania Dept. of Information Technology Innovation Universiteti Luarasi University of Rijeka Tirana Albania Department of Software Engineering Canadian Institute of Technology Tirana Albania

ISBN: (纸本)9798331516390

Urban traffic congestion is an issue that metropolitan regions face throughout the world. It has a substantial negative influence on the levels of pollution in the environment and lowers the standard of living in urban areas. This study examines the efficacy of three different traffic control methods in the urban environment of Tirana, Albania: conventional static, actuated, and delay-based. The study assesses how effective they are in controlling traffic flow and reducing emissions by using simulation approaches. Using the Simulation of Urban Mobility (SUMO) tool, the investigation compares the performance of these systems, focusing on key indicators such as time spent in traffic, fuel consumption, and emission levels. Contrary to initial assumptions, the simulations reveal the actuated system as the most efficient, showcasing its superior adaptability to real-time traffic conditions at multiple consecutive intersections. This adaptability optimizes traffic flow and contributes to a reduction in environmental impact. This discovery emphasizes the significance of implementing dynamic traffic management solutions tailored to the specific dynamics of urban environments. Based on these findings, the study advocates for the adoption of actuated traffic management systems in cities struggling with similar traffic challenges, highlighting their potential to bolster urban mobility and sustainability. The research also advocates for further exploration into the scalability of these systems and their integration into broader smart city frameworks. By contributing to the ongoing discourse on urban traffic management, this study provides valuable insights that can inform policy-making and the deployment of intelligent traffic solutions. ©2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

An improved pulse coupled neural networks model for semantic IoT

引用

Digital Communications and Networks 2024年第3期10卷 557-567页

作者： Rong Ma Zhen Zhang Yide Ma Xiping Hu Edith C.H.Ngai Victor C.M.Leung School of Information Science and Engineering Lanzhou UniversityLanzhou 730000China School of Medical Technology Beijing Institute of TechnologyBeijing100081China Department of Electrical and Electronic Engineer The University of Hong KongHong Kong 999077China College of Computer Science and Software Engineering Shenzhen UniversityShenzhen 518060China Department of Electrical and Computer Engineering the University of British ColumbiaVancouverBC V6T 1Z4Canada

In recent years,the Internet of Things(IoT)has gradually developed applications such as collecting sensory data and building intelligent services,which has led to an explosion in mobile data ***,with the rapid development of artificial intelligence,semantic communication has attracted great attention as a new communication ***,for IoT devices,however,processing image information efficiently in real time is an essential task for the rapid transmission of semantic *** the increase of model parameters in deep learning methods,the model inference time in sensor devices continues to *** contrast,the Pulse Coupled Neural Network(PCNN)has fewer parameters,making it more suitable for processing real-time scene tasks such as image segmentation,which lays the foundation for real-time,effective,and accurate image ***,the parameters of PCNN are determined by trial and error,which limits its *** overcome this limitation,an Improved Pulse Coupled Neural Networks(IPCNN)model is proposed in this *** IPCNN constructs the connection between the static properties of the input image and the dynamic properties of the neurons,and all its parameters are set adaptively,which avoids the inconvenience of manual setting in traditional methods and improves the adaptability of parameters to different types of *** segmentation results demonstrate the validity and efficiency of the proposed self-adaptive parameter setting method of IPCNN on the gray images and natural images from the Matlab and Berkeley Segmentation *** IPCNN method achieves a better segmentation result without training,providing a new solution for the real-time transmission of image semantic information.

关键词： Internet of things(IoT) Semantic information Real-time application Improved pulse coupled neural network Image segmentation

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：