检索结果-内蒙古大学图书馆

Brain Functional Networks with Dynamic Hypergraph Manifold Regularization for Classification of End-Stage Renal Disease Associated with Mild Cognitive Impairment

引用

computer Modeling in engineering & Sciences 2023年第6期135卷 2243-2266页

作者： Zhengtao Xi Chaofan Song Jiahui Zheng Haifeng Shi Zhuqing Jiao School of Microelectronics and Control Engineering Changzhou UniversityChangzhou213164China School of Computer Science and Artificial Intelligence Changzhou UniversityChangzhou213164China Department of Radiology Changzhou Second People’s Hospital Affiliated to Nanjing Medical UniversityChangzhou213003China

The structure and function of brain networks have been altered in patients with end-stage renal disease(ESRD).Manifold regularization(MR)only considers the pairing relationship between two brain regions and cannot represent functional interactions or higher-order relationships between multiple brain *** solve this issue,we developed a method to construct a dynamic brain functional network(DBFN)based on dynamic hypergraph MR(DHMR)and applied it to the classification of ESRD associated with mild cognitive impairment(ESRDaMCI).The construction of DBFN with Pearson’s correlation(PC)was transformed into an optimization *** convolution and hyperedge convolution superposition were adopted to dynamically modify the hypergraph structure,and then got the dynamic hypergraph to form the manifold regular terms of the dynamic *** DHMR and L_(1) norm regularization were introduced into the PC-based optimization model to obtain the final DHMR-based DBFN(DDBFN).Experiment results demonstrated the validity of the DDBFN method by comparing the classification results with several related brain functional network construction *** work not only improves better classification performance but also reveals the discriminative regions of ESRDaMCI,providing a reference for clinical research and auxiliary diagnosis of concomitant cognitive impairments.

关键词： End-stage renal disease mild cognitive impairment brain functional network dynamic hypergraph manifold regularization classification

来源：评论

学校读者我要写书评

暂无评论

Renewable integration and energy reduction in multiple stage evaporator

引用

Materials Today: Proceedings 2023年 80卷 24-31页

作者： Pati, Smitarani Kumar Sharma, Tarun Kumar Goyal, Kapil Prakash Verma, Om Department of Instrumentation and Control Engineering Dr B R Ambedkar National Institute of Technology Jalandhar Punjab Jalandhar 144011 India Department of Computer Science and Engineering Shobhit University UP Saharanpur-247341 India Department of Industrial and Production Engineering Dr B R Ambedkar National Institute of Technology Jalandhar Punjab Jalandhar 144011 India

Multiple Effect Evaporator (MEE) is an imperative part of the paper industry. It is used to process the waste byproduct named Black Liquor to enhance its solid concentration that may be further utilized to produce biomass-based energy. This process accounts very high energy consumption which leads to the energy intensiveness of this unit. A substantial amount of energy-saving may be accumulated by integrating various Energy Reduction Schemes (ERSs) with the MEE. Steam splitting, feed splitting, feed liquor preheating, thermo-vapor compressor, etc. are the well-known ERSs that may be incorporated with the MEE to reduce energy utilization. Hence, this study investigates the hybrid ERSs incorporated with MEE to observe their energy efficiency in an optimal manner. The prime focus of this investigation is to achieve enhanced energy efficiency in teams of maximum steam efficiency which is computed by formulating the nonlinear mathematical models of the MEE. To achieve the maximized energy efficiency, an optimization function has been developed under a constraint environment and solved by using metaheuristic-based approach named Flow Direction Algorithm. Another ERSs named flash tanks can also be integrated with this system to encourage waste heat re-utilization and ensures an increase in energy efficiency with constant steam consumption. This work also deals with the incorporation of the Linear Fresnel Reflector with ERSs integrated MEE which is capable of reducing the conventional energy load. The overall integrated MEE model achieves an energy-efficient and renewably operated MEE unit that may enhance the self-sustainability of the industry. © 2022

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Research on the Expert Database System of Characteristic Species in Wuling Mountain Area 21

Research on the Expert Database System of Characteristic Spe...

引用

21st International computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2024

作者： Yujun, Yang Yimei, Yang Wang, Zhou Liyun, Li Ling, Peng Jin, Xiang Huixia, Shu College of Computer and Artificial Intelligence Software College Huaihua University Huaihua418008 China Hunan Provincial Key Laboratory of Ecological Agriculture Intelligent Control Technology Huaihua418008 China School of Computer and Software Engineering Xihua University Chengdu610039 China

ISBN: (纸本)9798331519254

The Wuling Mountains Area(WMA) is one of the important ecological protection areas in central China, known for its rich biodiversity and unique ecological environment. To effectively protect the species resources in this area and strengthen ecological monitoring and research, this paper proposes and designs the 'Wuling Mountains Region Characteristic Species Expert Database System.' By integrating expert resources, species data, ecological environment information, and modern information technologies, an intelligent system has been developed that combines data management, expert support, species identification, and research analysis. This paper discusses in detail the system's requirements analysis, design concept, implementation technologies, and potential applications, aiming to provide technological support for biodiversity conservation and sustainable ecological development in the region. © 2024 IEEE.

关键词： Characteristic species Expert database system Intelligent system Species data Wuling Mountain Area

来源：评论

学校读者我要写书评

暂无评论

On-Device Learning with Raspberry Pi for GCN-Based Epilepsy EEG Classification

On-Device Learning with Raspberry Pi for GCN-Based Epilepsy ...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： He, Zhuoli Wang, Chuansheng Huang, Jiayan Grau, Antoni Guerra, Edmundo Yan, Jiaquan Fuzhou University College of Computer and Big Data Fuzhou China Polytechnic University of Catalonia Department of Automatic Control Barcelona Spain Putian University College of New Engineering Industry Putian China Minjiang University School of Computer and Big Data Fuzhou China

ISBN: (纸本)9798350386226

Epilepsy is a chronic brain disease characterized by recurrent and transient seizures, which is accompanied by super-synchronous abnormal discharge of electroencephalogram (EEG) signals. As a non-invasive auxiliary diagnostic technique, EEG is currently important means of seizure detection. However, due to ignoring the spatial topological relationship between electrodes, existing data-driver methods fail to fully reflect the interaction between signals. Meanwhile, their models usually be designed with a large number of redundant parameters, making it difficult to deploy to micro-embedded devices with limited-resources. In this paper, we propose a on-device learning with edge device for epilepsy EEG classification network based on GCN (oDLGCN-EEG). Specifically, to analyze the spatial relationships between various electrodes and their temporal dependencies, we design a Brain Topology Network (BTN) for the spatiotemporal dependency feature map construction. To capture the internal activity during epilepsy seizures, we design a Neural Feature Extraction Module (NFEM) for the neural activity feature map construction. Besides, we propose a pruning scheme to optimize the model, which successfully deploys the optimized oDLGCN-EEG on the embedded Raspberry Pi device for efficient and low-power consumption intelligent epilepsy classification. Experiments in comparison with state-of-the-art methods show that oDLGCN-EEG achieves the best classification accuracy and with the smallest parameter number on baseline EEG dataset. The code is available at https://***/cathnat/Epileptic-Classification. © 2024 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Cascading Delays for the High-Speed Rail Network Under Different Emergencies:A Double Layer Network Approach

引用

IEEE/CAA Journal of Automatica Sinica 2023年第10期10卷 2014-2025页

作者： Xingtang Wu Mingkun Yang Wenbo Lian Min Zhou Hongwei Wang Hairong Dong School of Automation Science and Electrical Engineering Beihang UniversityBeijing 100191China School of Control and Computer Engineering North China Electric Power UniversityBeijing 100096China State Key Laboratory of Advanced Rail Autonomous Operation Beijing Jiaotong UniversityBeijing 100044China National Research Center of Railway Safety Assessment Beijing Jiaotong UniversityBeijing 100044China

High-speed rail(HSR) has formed a networked operational scale in China. Any internal or external disturbance may deviate trains’ operation from the planned schedules, resulting in primary delays or even cascading delays on a network scale. Studying the delay propagation mechanism could help to improve the timetable resilience in the planning stage and realize cooperative rescheduling for dispatchers. To quickly and effectively predict the spatial-temporal range of cascading delays, this paper proposes a max-plus algebra based delay propagation model considering trains’ operation strategy and the systems’ constraints. A double-layer network based breadth-first search algorithm based on the constraint network and the timetable network is further proposed to solve the delay propagation process for different kinds of emergencies. The proposed model could deal with the delay propagation problem when emergencies occur in sections or stations and is suitable for static emergencies and dynamic emergencies. Case studies show that the proposed algorithm can significantly improve the computational efficiency of the large-scale HSR network. Moreover, the real operational data of China HSR is adopted to verify the proposed model, and the results show that the cascading delays can be timely and accurately inferred, and the delay propagation characteristics under three kinds of emergencies are unfolded.

关键词： Delay propagation double layer network high speed rail network max-plus algebra

来源：评论

学校读者我要写书评

暂无评论

Enhancing standardization in the electricity industry: an intelligent analysis of standard discrepancy 3

Enhancing standardization in the electricity industry: an in...

引用

3rd International Conference on Electronic Information engineering, Big Data, and computer Technology, EIBDCT 2024

作者： Ni, Wenshu Fang, Zhijian Fu, Jie Jiang, Xin Cai, Yuxiang Guan, Wangning State Grid Fujian Electric Power CO. LTD. Fujian350000 China North China Electric Power University School of Control and Computer Engineering Beijing100000 China

ISBN: (纸本)9781510680449

This paper proposes an intelligent discrepancy analysis method based on natural language processing to address the issue of standard discrepancy in the electricity industry. The objective of this method is to identify discrepancies between standards and pinpoint their distinguishing factors, in order to achieve better standardization, regulation, and consistency. This will enhance the safety and reliability of electricity equipment and systems, while reducing production, operation, and management costs. The paper first builds an electricity standard discrepancy dataset using the open-world assumption theory. Then, it uses a noisy method to fine-tune the SBERT model for identifying discrepancies in electricity standard clauses. Finally, by optimizing the SimCSE model with relaxed optimal transport distance, the interpretability of the model is improved and a text similarity matrix is obtained, enabling the visualization of discrepancies in clause text. The precision and recall rates of standard discrepancy identification achieved by this method are 81.54% and 82.78%, respectively. This method not only helps to improve the sustainable development of the electricity industry, but also provides more data support and decision-making references for electricity enterprises to better address issues related to standard management and implementation. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

BOAformer: Object Detection Network Based on Background-Object Attention Transformer 6

BOAformer: Object Detection Network Based on Background-Obje...

引用

6th International Conference on Communications, Information System and computer engineering, CISCE 2024

作者： Yang, Yong Liang, Chenbin Huang, Shuying Wang, Xiaozheng School of Computer Science and Technology Tiangong University Tianjin China School of Electronics and Information Engineering Tiangong University Tianjin China School of Software Tiangong University Tianjin China School of Control Science and Engineering Tiangong University Tianjin China

ISBN: (纸本)9798350353174

At present, deep learning has achieved great success in the field of object detection. To ensure that positive samples in the image are not missed, most deep-learning object detection methods set many prediction boxes and use the same prediction operation on them. Although these methods can obtain higher predictive values for high certainty objects, they may identify objects with lower certainty, such as small or fuzzy objects, as negative samples or miss them. To address this issue, this paper presents an object detection network based on background-object attention transformer (BOAformer), which improves the accuracy of object detection by establishing the relationship between background and object features. Firstly, the existing classification model is employed to obtain scores of object prediction boxes. On this basis, a scoring mechanism is designed to filter out high scoring object prediction boxes to reduce the computational complexity of the later network. Then, to improve the accuracy of object detection, BOAformer is constructed, which obtains auxiliary classification values of objects by learning the relationship between background and object features, and adds them to the initial detection results. Finally, many experiments are conducted to verify the effectiveness of BOAformer. The experimental results show that the designed network improves the accuracy of object detection and can detect small or lost objects in the background. © 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 Personality Detection Method Based on Semantic and Psycholinguistic of Social Texts

A Personality Detection Method Based on Semantic and Psychol...

引用

computer Information Science and Application Technology (CISAT), International Conference on

作者： Chundong Wang Yuhan Yang Hao Lin Lu Han School of Computer Science and Engineering National Engineering Laboratory for Computer Virus Prevention and Control Technology Tianjin University of Technology Tianjin China

ISBN: (数字)9798350375107

ISBN: (纸本)9798350375114

At the intersection of personality psychology, computer science, and linguistics, more and more researchers are paying attention to personality detection based on content analysis of texts on social media. However, existing social text-based personality detection methods rely heavily on pre-trained language models, overlook multi-dimensional sentiment in social texts, and lack of effective feature selection of psycholinguistic features. To address these limitations, we propose a method for Myers-Briggs type indicator (MBTI) personality detection. Our approach extracts and selects high-dimensional psycholinguistic feature, utilizes an optimal intermediate layer output from pre-trained language models for semantic representation, and fuses these features to enhance detection accuracy. The experiment results indicate that our proposed method improves the state-of-art results for MBTI personality traits by 1.65% on average on Kaggle MBTI dataset.

关键词： computer science Information science Social networking (online) Fuses Computational modeling Semantics Psychology Linguistics Media Feature extraction

来源：评论

学校读者我要写书评

暂无评论

H-STEP: Heuristic Stable Edge Service Entity Placement for Mobile Virtual Reality Systems

引用

IEEE Transactions on Mobile Computing 2025年

作者： Chi, Xuejian Chen, Honglong Ni, Zhichen Sun, Haiyang Sun, Peng Yu, Dongxiao Shandong Provincial Engineering Research Center of Intelligent Sensing and Measurement and Control Technology College of Control Science and Engineering Qingdao266580 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Shandong University School of Computer Science and Technology Qingdao266237 China

Virtual reality (VR) technology, as a latency-sensitive application, can achieve real-time response to enhance the user's quality of experience (QoE) on edge devices. However, edge servers, unlike internally managed cloud servers, are prone to hardware failures, software abnormalities, and network attacks. Most prior studies have focused on reducing service delay and improving user coverage through service entity (SE) placement, often neglecting the critical impact of edge server malfunctions on user QoE. In this work, we design a stable service entity placement framework that connects users on faulty servers to collaborative edge servers, ensuring seamless task completion. This framework presents two primary challenges: determining the grouping of collaborative edge services and the placement of SEs. To address these challenges, we introduce a heuristic stable service entity placement (H-STEP) scheme. This scheme first determines the grouping of collaborative edge servers using an iterative search algorithm and then places SEs on suitable edge servers via a fast non-dominated sorting genetic placement algorithm. This approach balances stability benefits with total cost, enhancing the system's economic benefits. We theoretically analyze the performance of H-STEP and derive the performance gap between H-STEP and the optimal scheme. Extensive real-data-driven simulations demonstrate that H-STEP's performance closely approximates that of the optimal scheme and surpasses existing schemes. © 2002-2012 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Learning with Nearest-Neighbor Label and Consistency Regularization 1

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Zheng, Guolin Li, Zuoyong Hu, Wenkai Fan, Haoyi Ching, Fum Yew Yu, Zhaochai Chen, Kaizhi College of Computer and Data Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou350121 China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou450001 China School of Computer Sciences Universiti Sains Malaysia Penang11800 Malaysia Minjiang University Fuzhou350121 China

ISBN: (数字)9783031200991

ISBN: (纸本)9783031200984

Semi-supervised learning, a system dedicated to making networks less dependent on labeled data, has become a popular paradigm due to its strong performance. A common approach is to use pseudo-labels with unlabeled data for training, however, pseudo-labels cannot correct their own errors. In this paper, we propose a semi-supervised method that uses nearest neighbor samples to obtain pseudo-labels and combines consistency regularization for image classification. Our method obtains pseudo-labels by computing the similarity of the data distribution between the weakly-augmented version of the unlabeled data and the labeled data stored in the support set and combines the consistency of the strongly-augmented version and the weakly-augmented version of the unlabeled data. We compared with several standard semi-supervised learning benchmarks and achieved a competitive performance. For example, we achieved an accuracy of 94.02 % on CIFAR-10 with 250 labels and 97.50 % on SVNH with 250 labels. It even achieved 91.59 % accuracy with only 40 labels data in the CIFAR-10. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Benchmarking

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：