检索结果-内蒙古大学图书馆

Multi-modal data information alignment based SOH estimation for lithium-ion batteries using a local–global parallel CNN-Transformer Network

引用

Journal of Energy Storage 2025年 129卷

作者： Xuanang Gui Junrong Du Qianlong Wang Huan Zhao Yuheng Cheng Junhua Zhao School of Science and Engineering The Chinese University of Hong Kong Shenzhen 518172 China National Computer System Engineering Research Institute of China Beijing 100083 China Business School Nankai University Tianjin 300071 China Department of Building Environment and Energy Engineering The Hong Kong Polytechnic University Hong Kong China

Accurate State of Health (SOH) estimation of lithium-ion batteries is crucial for safe and reliable operation. However, real-world applications often lack comprehensive labeled data across diverse operating conditions, hindering data-driven methods’ performance in unseen scenarios. To address this, we propose a novel Multi-Modal Data Information Alignment Local–Global Parallel CNN-Transformer Network (MM-LG-CNNT) for cross-domain SOH estimation. MM-LG-CNNT leverages abundant labeled data from source domain to improve accuracy in target domain with limited unlabeled data. Unlike traditional methods relying solely on raw sequential data, our framework incorporates multi-modal data: raw degradation sequences and their corresponding image representations from recurrence plots to capture both the local and global degradation information. A multi-information alignment strategy, combining Maximum Mean Discrepancy (MMD), Correlation Alignment (CORAL), and adversarial learning, aligns both data structure and domain label information to improve the estimation accuracy. A parallel CNN-Transformer architecture efficiently extracts local degradation patterns and long-range dependencies. Extensive experiments demonstrate the effectiveness and superiority of MM-LG-CNNT for SOH estimation. The proposed framework offers a promising solution for practical, accurate, and robust SOH estimation under limited data availability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AI-based Fog and Edge Computing: A Systematic Review, Taxonomy and Future Directions

arXiv

引用

arXiv 2022年

作者： Iftikhar, Sundas Gill, Sukhpal Singh Song, Chenghao Xu, Minxian Aslanpour, Mohammad Sadegh Toosi, Adel N. Du, Junhui Wu, Huaming Ghosh, Shreya Chowdhury, Deepraj Golec, Muhammed Kumar, Mohit Abdelmoniem, Ahmed M. Cuadrado, Felix Varghese, Blesson Rana, Omer Dustdar, Schahram Uhlig, Steve School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom University of Kotli Azad Jammu & Kashmir Azad Kashmir Kotli Pakistan Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Department of Software Systems and Cybersecurity Faculty of Information Technology Monash University Australia Csiro DATA61 Australia Center for Applied Mathematics Tianjin University Tianjin China The Pennsylvania State University PA United States Naya Raipur India Abdullah Gül University Kayseri Turkey Department of Information Technology National Institute of Technology Jalandhar India Spain School of Computer Science University of St Andrews United Kingdom School of Computer Science and Informatics Cardiff University Cardiff United Kingdom Distributed Systems Group Vienna University of Technology Vienna Austria

Resource management in computing is a very challenging problem that involves making sequential decisions. Resource limitations, resource heterogeneity, dynamic and diverse nature of workload, and the unpredictability of fog/edge computing environments have made resource management even more challenging to be considered in the fog landscape. Recently Artificial Intelligence (AI) and Machine Learning (ML) based solutions are adopted to solve this problem. AI/ML methods with the capability to make sequential decisions like reinforcement learning seem most promising for these type of problems. But these algorithms come with their own challenges such as high variance, explainability, and online training. The continuously changing fog/edge environment dynamics require solutions that learn online, adopting changing computing environment. In this paper, we used standard review methodology to conduct this Systematic Literature Review (SLR) to analyze the role of AI/ML algorithms and the challenges in the applicability of these algorithms for resource management in fog/edge computing environments. Further, various machine learning, deep learning and reinforcement learning techniques for edge AI management have been discussed. Furthermore, we have presented the background and current status of AI/ML-based Fog/Edge Computing. Moreover, a taxonomy of AI/ML-based resource management techniques for fog/edge computing has been proposed and compared the existing techniques based on the proposed taxonomy. Finally, open challenges and promising future research directions have been identified and discussed in the area of AI/ML-based fog/edge computing. Copyright © 2022, The Authors. All rights reserved.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Dual Representation Learning for One-Step Clustering of Multi-View Data

arXiv

引用

arXiv 2022年

作者： Zhang, Wei Deng, Zhaohong Choi, Kup-Sze Wang, Jun Wang, Shitong The School of Artificial Intelligence and Computer Science Jiangnan University Jiangsu Key Laboratory of Media Design and Software Technology Wuxi214122 China The School of Artificial Intelligence and Computer Science Jiangnan University Wuxi214122 China ZJLab Shanghai200433 China The Centre for Smart Health The Hong Kong Polytechnic University Hong Kong The Key laboratory of Specialty Fiber Optics and Optical Access Networks Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication Shanghai Institute for Advanced Communication and Data Science School of Communication and Information Engineering Shanghai University Shanghai200444 China

Multi-view data are commonly encountered in data mining applications. Effective extraction of information from multi-view data requires specific design of clustering methods to cater for data with multiple views, which is non-trivial and challenging. In this paper, we propose a novel one-step multi-view clustering method by exploiting the dual representation of both the common and specific information of different views. The motivation originates from the rationale that multi-view data contain not only the consistent knowledge between views but also the unique knowledge of each view. Meanwhile, to make the representation learning more specific to the clustering task, a one-step learning framework is proposed to integrate representation learning and clustering partition as a whole. With this framework, the representation learning and clustering partition mutually benefit each other, which effectively improves the clustering performance. Results from extensive experiments conducted on benchmark multi-view datasets clearly demonstrate the superiority of the proposed method. Copyright © 2022, The Authors. All rights reserved.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Culturally-embedded visual literacy: A study of impression management via emoticon, emoji, sticker, and meme on social media in China

引用

Proceedings of the ACM on Human-computer Interaction 2019年第CSCW期3卷 1-24页

作者： Wang, Yuan Li, Yukun Gui, Xinning Kou, Yubo Liu, Fenglian School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin300384 China Penn State State CollegePA United States

Social media is often analyzed as a "front stage" where social media users perform their identities and manage impressions through various forms of user-generated content: text, picture, video, as well as visual expression such as emoticon, emoji, sticker, and meme. Previous scholarship has suggested various functions of visual expression in supporting computer-mediated communication. In this study, we move beyond the utility perspective to ask what constitutes the literacy to utilize visual expression for impression management. Towards this goal, we conducted an interview study with 30 social media users in China. We found that visual literacy intersects with its cultural context. Our interviewees used text and visual expressions in sophisticated, skillful ways and tailored for different audiences in order to construct desired images. They also interacted with audience memory in order to perform their uniqueness and creativity. Lastly, we discuss culturally-embedded visual literacy and provide implications for design. Copyright is held by the owner/author(s).

关键词： Goffman backstage emoji emoticon front stage impression management meme performance social media sticker visual expression

来源：评论

学校读者我要写书评

暂无评论

Nanoscale control of grain boundary potential barrier, dopant density and filled trap state density for higher efficiency perovskite solar cells

引用

InfoMat 2020年第2期2卷 409-423页

作者： Behzad Bahrami Sally Mabrouk Nirmal Adhikari Hytham Elbohy Ashim Gurung Khan M.Reza Rajesh Pathak Ashraful H.Chowdhury Gopalan Saianand Wenjin Yue Jiantao Zai Xuefeng Qian Mao Liang Qiquan Qiao Department of Electrical Engineering and Computer Science Center for Advanced Photovoltaics and Sustainable EnergySouth Dakota State UniversityBrookingsSouth Dakota Physics Department Damietta UniversityNew Damietta CityEgypt Global Innovative Center for Advanced Nanomaterials Faculty of EngineeringThe University of NewcastleCallaghanNew South WalesAustralia College of Biochemical Engineering Anhui Polytechnic UniversityWuhuChina Shanghai Electrochemical Energy Devices Research Center School of Chemistry and Chemical EngineeringState Key Laboratory of Metal Matrix CompositesShanghai Jiao Tong UniversityShanghaiChina Tianjin Key Laboratory of Organic Solar Cells and Photochemical Conversion Department of Applied ChemistryTianjin University of TechnologyTianjinChina

In this work,grain boundary(GB)potential barrier(ΔφGB),dopant density(Pnet),and filled trap state density(PGB,trap)were manipulated at the nanoscale by exposing the fabricated perovskite films to various relative humidity(RH)*** mapping of surface potential in the perovskite film revealed higher positive potential at GBs than inside the *** averageΔφGB,Pnet,and PGB,trap in the perovskite films decreased from 0%RH to 25%RH exposure,but increased when the RH increased to 35%RH and 45%*** clearly indicated that perovskite solar cells fabricated at 25%RH led to the lowest average GB potential,smallest dopant density,and least filled trap states *** is consistent with the highest photovoltaic efficiency of 18.16%at 25%RH among the different relative humidities from 0%to 45%RH.

关键词： dopant density filled trap state density grain boundary potential barrier perovskite solar cells relative humidity

来源：评论

学校读者我要写书评

暂无评论

A Feature Subset Selection Method Based on the Combination of PCA and Improved GA

A Feature Subset Selection Method Based on the Combination o...

引用

International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI)

作者： Yinghao Li Kai Shi Fuqiang Qiao Hongyu Luo School of Computer Science and Engineering Tianjin University of Technology China College of Software and Communication Tianjin Sino-German University of Applied Sciences China

ISBN: (数字)9781728196381

ISBN: (纸本)9781728196398

Nowadays, intrusion detection data has redundant features, which leads to unsatisfactory detection results. This paper proposes a feature selection method based on the combination of principal component analysis (PCA) and improved Genetic algorithm(GA). First, PCA is used to reduce the dimensionality of the intrusion data, and the cosine similarity is used to calculate angles between the principal component and the original feature; the feature with high cosine similarity to the principal component is selected and the genetic algorithm is input, and the improved inter-group crossover strategy is adopted to reduce the probability of entering the local optimum. The fitness function of the genetic algorithm is the detection rate, and the optimal feature subset is selected as the intrusion detection data feature. Experimental results show that this method can improve the efficiency of intrusion detection and improve the classification ability of the classifier.

关键词： Machine learning algorithms Diversity reception Intrusion detection Probability Feature extraction Principal component analysis Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

ATVHUNTER: Reliable version detection of third-party libraries for vulnerability identification in android applications

arXiv

引用

arXiv 2021年

作者： Zhan, Xian Fan, Lingling Chen, Sen Wu, Feng Liu, Tianming Luo, Xiapu Liu, Yang Department of Computing The Hong Kong Polytechnic University Hong Kong College of Cyber Science Nankai Univerisity China College of Intelligence and Computing Tianjin University China School of Computer Science and Engineering Nanyang Technological University Singapore Faculty of Information Technology Monash University Australia

Third-party libraries (TPLs) as essential parts in the mobile ecosystem have become one of the most significant contributors to the huge success of Android, which facilitate the fast development of Android applications. Detecting TPLs in Android apps is also important for downstream tasks, such as malware and repackaged apps identification. To identify in-app TPLs, we need to solve several challenges, such as TPL dependency, code obfuscation, precise version representation. Unfortunately, existing TPL detection tools have been proved that they have not solved these challenges very well, let alone specify the exact TPL versions. To this end, we propose a system, named ATVHUNTER, which can pinpoint the precise vulnerable in-app TPL versions and provide detailed information about the vulnerabilities and TPLs. We propose a two-phase detection approach to identify specific TPL versions. Specifically, we extract the Control Flow Graphs as the coarse-grained feature to match potential TPLs in the predefined TPL database, and then extract opcode in each basic block of CFG as the fine-grained feature to identify the exact TPL versions. We build a comprehensive TPL database (189,545 unique TPLs with 3,006,676 versions) as the reference database. Meanwhile, to identify the vulnerable in-app TPL versions, we also construct a comprehensive and known vulnerable TPL database containing 1,180 CVEs and 224 security bugs. Experimental results show ATVHUNTER outperforms state-of-the-art TPL detection tools, achieving 90.55% precision and 88.79% recall with high efficiency, and is also resilient to widely-used obfuscation techniques and scalable for large-scale TPL detection. Furthermore, to investigate the ecosystem of the vulnerable TPLs used by apps, we exploit ATVHUNTER to conduct a large-scale analysis on 104,446 apps and find that 9,050 apps include vulnerable TPL versions with 53,337 vulnerabilities and 7,480 security bugs, most of which are with high risks and are not recognize

关键词： Libraries

来源：评论

学校读者我要写书评

暂无评论

Scenario referring expression comprehension via attributes of vision and language 1

引用

2nd Chinese Conference on Pattern Recognition and computer Vision, PRCV 2019

作者： Wei, Shaonan Wang, Jianming Sun, Yukuan Jin, Guanghao Liang, Jiayu Liu, Kunliang School of Electronics and Information Engineering Tianjin Polytechnic University Tianjin China School of Computer Science and Technology Tianjin Polytechnic University Tianjin China Tianjin International Joint Research and Development Center of Autonomous Intelligence Technology and Systems Tianjin Polytechnic University Tianjin China Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems Tianjin Polytechnic University Tianjin China Center for Engineering Internship and Training Tianjin Polytechnic University Tianjin China

ISBN: (数字)9783030317263

ISBN: (纸本)9783030317256

Referring Expression Comprehension (REC) is a task that requires to indicate particular objects within an image by natural language expressions. Previous studies on this task have assumed that the language expression and the image are one-to-one correspondence, that is, the language refers to the target region must exist in the current image and then the region with the highest score will be located, no matter whether they match or not. However, in practical applications, REC is required to locate the reference target region from a series of matched, semi-matched and mismatched scene image sequences. It is the 3D version of this challenge that refers to as Scenario Referring Expression Comprehension (SREC) in this paper. To accomplish such a task, we made a testset based on the existing real-scenario dataset enhancement, constructed a Dual Attributes Recursive Retrieve Reasoning Model (DA3R) for the first time with the Attributes of both images and expressions, and finally verified the feasibility of the method on the testset by assess with three different types of enhanced expression. © Springer Nature Switzerland AG 2019.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

One-shot video object segmentation initialized with referring expression 1

引用

2nd Chinese Conference on Pattern Recognition and computer Vision, PRCV 2019

作者： Bu, Xiaoqing Wang, Jianming Liang, Jiayu Liu, Kunliang Sun, Yukuan Jin, Guanghao School of Electronic and Information Engineering Tianjin Polytechnic University Tianjin China School of Computer Science and Technology Tianjin Polytechnic University Tianjin China Tianjin International Joint Research and Development Center of Autonomous Intelligence Technology and Systems Tianjin Polytechnic University Tianjin China Center for Engineering Internship and Training Tianjin China Tianjin Key Laboratory of Autonomous Intelligence Technology and Systems Tianjin Polytechnic University Tianjin China

ISBN: (数字)9783030317232

ISBN: (纸本)9783030317225

One-Shot Video Object Segmentation (OSVOS) is a CNN architecture to tackle the problem of semi-supervised video object segmentation, which performs the separation of an object from the background in a frame-independent way with the aid of one manually-segmented frame. However, in the scenarios of real applications, the requirement of one manually-segmented frame would do harm to user-friendliness of a system. To tackle the problem above, we propose a video object segmentation based on referring expression (named as REVOS), which obtains the segmented frame by a referring expression (a noun phrase whose function is to identify on specific object). The main task of our method is to select the target from all candidate objects which have the highest matching score with the referring expression by using the language analysis module. Then generate the annotation of the first frame and continue to segment all the remaining frames with OSVOS. The results of experiment show that our method can achieve similar accuracy to OSVOS and more convenient and flexible for system design. © Springer Nature Switzerland AG 2019.

关键词： Motion compensation

来源：评论

学校读者我要写书评

暂无评论

Task Offloading for End-Edge-Cloud Orchestrated Computing in Mobile Networks

Task Offloading for End-Edge-Cloud Orchestrated Computing in...

引用

IEEE Conference on Wireless Communications and Networking

作者： Chuan Sun L. Hui Xiuhua Li Junhao We Qingyu Xiongl Xiaofei Wang Victor C.M. Leun School of Big Data Software Engineering Chongqing University Chongqing China TKLAN College of Intelligence & Computing Tianjin University Tianjin China College of Computer Science Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9781728131061

ISBN: (纸本)9781728131078

Recently, mobile edge computing has received widespread attention, which provides computing infrastructure via pushing cloud computing, network control, and storage to the network edges. To improve the resource utilization and Quality of Service, we investigate the issue of task offloading for End-EdgeCloud orchestrated computing in mobile networks. Particularly, we jointly optimize the server selection and resource allocation to minimize the weighted sum of the average cost. A cost minimization problem is formulated underjoint the constraints of cache resource and communication/computation resource of edge servers. The resultant problem is a Mixed-Integer Non-linear Programming, which is NP-hard. To tackle this problem, we decompose it into simpler subproblems for server selection and resource allocation, respectively. We propose a low-complexity hierarchical heuristic approach to achieve server selection, and a Cauchy-Schwards Inequality based closed-form approach to efficiently determine resource allocation. Finally, simulation results demonstrate the superior performance of the proposed scheme on reducing the weighted sum of the average cost in the network.

关键词：

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：