检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Mei, Huawei Liu, Yanping Cao, Wangbin Yu, Yang North China Electric Power University Baoding071003 China Engineering Research Center of Intelligent Computing for Complex Energy Systems Ministry of Education Baoding071003 China Hebei Key Laboratory of Power Internet of Things Technology North China Electric Power University Baoding071003 China State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power University Baoding071003 China

This paper proposes a mother-son model (MSM) to address the challenges of missing data, complex models, and limited transfer capabilities in non-intrusive load monitoring (NILM). The MSM model designs a novel transfer method based on feature inheritance to dynamically decompose multiple appliances (including unknown appliances). The mother model incorporates a six-parallel feature extraction structure to extract comprehensive features, which are then inherited by the son model. The features inherited from the mother model integrate information from multiple dimensions in the spatial domain and focus on local fine features in the temporal domain. The son model offers the capability to adjust the number of appliances and decompose unknown appliances, catering to the requirements of practical applications of NILM. Furthermore, a novel statistical metric, Ratio Squared Error (RSE), is designed to quantify the proportion of squared error in energy consumption. The experiments are carried out on five households and statistically evaluated using five statistical indicators. The results indicate that the son model exhibits superior decomposition performance and greater resilience compared to the state-of-the-art model. © 2023, The Authors. All rights reserved.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

A MEC Offloading Strategy Based on Improved DQN and Simulated Annealing for Internet of Behavior

引用

ACM Transactions on Sensor Networks 2022年第2期19卷 28-28页

作者： Yuan, Xiaoming Tian, Hansen Zhang, Zedan Zhao, Zheyu Liu, Lei Sangaiah, Arun Kumar Yu, Keping Qinghuangdao Branch Campus Northeastern University Qinhuangdao066004 China State Key Laboratory of Integrated Service Networks Xidian University Xian710071 China Xidian Guangzhou Institute of Technology Guangzhou510555 China School of Computing Science and Engineering Vellore Institute of Technology Vellore632014 India National Yunlin University of Science and Technology Douliou64002 Taiwan K. Yu Graduate School of Science and Engineering Hosei University Tokyo184-8584 Japan

The Internet of Medical Things (IoMT) and Artificial Intelligence (AI) have brought unprecedented opportunities to meet massive behavioral data access and personalization requirements for Internet of Behavior (IoB). They facilitate the communication and computing resource allocation to guarantee low delay and energy consumption demands in healthcare. This article presents an improved offloading algorithm for Mobile Edge computing (MEC) based on Deep Q Network (DQN) and Simulated Annealing (SA) for IoB. Firstly, we analyze the network model and establish a task cost function based on processing delay and energy consumption. Secondly, we define a Distributed Optimization Problem (DOP) to maximize individual utilities and system utility, which is proved to be a potential countermeasure. Thirdly, we conduct Markov modeling for the current offloading strategy-making scheme and define the objectives and constraints of the optimization function. At the same time, the SA is introduced into the DQN Algorithm, which improves the capacity of the algorithm by focusing on the exploration in the early stage and following the experience value in the later stage. From the simulation results, we can see that compared with the traditional scheme, the proposed strategy can maximize the utilization of the system and reduce processing delay and energy consumption. © 2022 Association for computing Machinery.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Coordinate Attention Based 3D-CNN Using Ghost Multi-Scale for Diagnosing Alzheimer’s Disease

Coordinate Attention Based 3D-CNN Using Ghost Multi-Scale fo...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xiaolu Lin Pinya Lu Jie Pan Hongqin Yang Xuemei Ding Fujian Provincial Engineering Research Center for Public Service Big Data Mining and Application Fujian Provincial University Engineering Research Center for Big Data Analysis and Application Fujian Normal University Fuzhou China Xiamen Jingyi Zhikang Technology Co. Ltd Xiamen China Fujian Provincial Key Laboratory for Photonics Technology Key Laboratory of OptoElectronic Science and Technology for Medicine of Ministry of Education Fujian Normal University Fuzhou China School of Computing Engineering and Intelligent Systems Ulster University Derry-Londonderry NI UK

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Alzheimer's disease (AD) is a neurodegenerative disease and mild cognitive impairment (MCI) is the early stage of AD. Previous studies have predominantly focused on binary classification using 3 dimensional - convolutional neural network (3D-CNN) for AD diagnosis, with limited progress in multi-classification. Moreover, the current 3D-CNNs often adopt a single-scale architecture with massive parameters growth. Additionally, obtaining precise location information of brain imaging data is crucial for improving the classification accuracy with 3D-CNN. Hence, we propose a multi-scale 3D-CNN based on coordinate attention mechanism to marvelously capture and integrate 3D features with fewer parameters, improving the accuracy of AD diagnosis. A total of 447 cognitively normal (CN), 512 MCI, and 358 AD sMRI images from the Alzheimer's Disease Neuroimaging Initiative datasets are used for multi-class classification task, yielding a classification accuracy of 92.8%. The model merely involves 2.41 M parameters and achieves the best classification results with the least number of parameters when compared to other representative CNN architectures including ResNet 18, ResNet 34, ConvNeXt tiny, and VGG 11. Through the ablation experiment, the addition of attention mechanism and the multi-scale classification enhances the classification performance by 4.5% and 1.5%, respectively. Furthermore, our model outperforms the other six existing studies in terms of accuracy for classifying AD vs. MCI vs. CN. Overall, this study underscores the efficacy of our approach for AD diagnosis, showcasing its utility in diagnosing AD patients and providing novel insights for diagnosing other neurological disorder diseases.

关键词： Neuroimaging Accuracy Attention mechanisms Three-dimensional displays Resonance Convolutional neural networks Alzheimer's disease

来源：评论

学校读者我要写书评

暂无评论

Dynamic Simulation Test for Traveling Wave Fault Positioning system in Distribution Network

Dynamic Simulation Test for Traveling Wave Fault Positioning...

引用

China International Electrical and Energy Conference (CIEEC)

作者： Chao Zhuo Yanru Ni Xiangjun Zeng Yang Leng Yunkun Xiang Guangxi Key Laboratory of Power System Optimization and Energy Technology Guangxi University Nanning Guangxi Zhuang Autonomous Region China Collaborative Innovation Center of Clean Energy and Electric Power Technology Changsha University of Science and Technology Changsha Hunan Province China State Grid Hunan Energy Conservation Service Company State Grid Hunan Electric Power Company Changsha Hunan Province China

ISBN: (纸本)9781538653937

Fault positioning system based on traveling wave has been widely used in engineering application, but the test technology still needs further study. The research status of test methods was introduced in this paper, and the reason of existing test technology is not suitable for fault location system was researched. Then the idea of dynamic simulation test system was put forward, including simulation methods of distribution lines, fault signal and traveling wave signal acquisition. Thus, a 10kV distribution network dynamic simulation test model was built, and dynamic simulation test scheme for fault positioning system was designed, introducing the fault setting method and the system function test project in detail. The experimental results showed that the dynamic simulation test platform is close to the actual operation environment of the distribution network, which can effectively estimate technical indicators of the voltage traveling wave positioning system into operation.

关键词： Power system dynamics Fault location Power cables Transient analysis Circuit faults

来源：评论

学校读者我要写书评

暂无评论

Distributed Transactive Energy Control of Electric Vehicles Based on Blockchain and Oracle technology

Distributed Transactive Energy Control of Electric Vehicles ...

引用

IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC)

作者： Meiqin Mao Rui Xu Chen Yang Yuanyue Wang Yan Du Zhang Wei Minglei Zhu Hongwei Liu Research Center for Photovoltaic System Engineering.MOE Hefei University of Technology Hefei China Anhui Province Key Laboratory of Semiconductor Packaging and Reliability Hefei University of Technology Hefei China State Grid Anhui Electric Power Co. Ltd Hefei China State Grid Anhui Electric Vehcile Service Co. Ltd Hefei China

ISBN: (数字)9798350386127

ISBN: (纸本)9798350386134

The traditional centralized scheduling control of large-scale electric vehicles (EVs) has problems such as high scheduling costs, low reliability, and difficulty in making scheduling data open and transparent. To address the problems, based on blockchain and oracle technology, this paper proposes a distributed transactive energy control (DTEC) method for electric vehicle aggregators (EVAs) to participate in ancillary services in power system. Firstly, the framework of the proposed DTEC for EVAs is proposed using blockchain technology. Secondly, considering the execution requirements of smart contracts, a secure and fast on-chain and off-chain data interconnection module based on oracle technology is proposed for off-chain intelligent optimal dispatching decision model (ODDM), real time charging data of EVs, and on-chain electric vehicle control smart contract (EVCSC). Thirdly, an off-chain ODDM that considers multiple parties' interests is designed. Finally, taking the scenario of EVs participating in peak shaving and valley filling in the ADN as an example, the proposed method is verified based on the blockchain test platform built through Ethereum and Chainlink.

关键词： Transactive energy Smart contracts Tariffs Electric vehicles Real-time systems Filling Dispatching Blockchains Power system reliability Reliability

来源：评论

学校读者我要写书评

暂无评论

Size-invariance matters: rethinking metrics and losses for imbalanced multi-object salient object detection 24

Size-invariance matters: rethinking metrics and losses for i...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Feiran Li Qianqian Xu Shilong Bao Zhiyong Yang Runmin Cong Xiaochun Cao Qingming Huang Institute of Information Engineering Chinese Academy of Sciences Beijing China and School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China and School of Control Science and Engineering Shandong University Jinan China and Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Shenzhen Campus Sun Yat-sen University School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China and Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China and Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sample hardness based gradient loss for long-tailed cervical cell detection

arXiv

引用

arXiv 2022年

作者： Liu, Minmin Li, Xuechen Gao, Xiangbo Chen, Junliang Shen, Linlin Wu, Huisi Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence of Robotics of Society Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China University of California Irvine United States

Due to the difficulty of cancer samples collection and annotation, cervical cancer datasets usually exhibit a long-tailed data distribution. When training a detector to detect the cancer cells in a WSI (Whole Slice Image) image captured from the TCT (Thinprep Cytology Test) specimen, head categories (e.g. normal cells and inflammatory cells) typically have a much larger number of samples than tail categories (e.g. cancer cells). Most existing state-of-the-art long-tailed learning methods in object detection focus on category distribution statistics to solve the problem in the long-tailed scenario, without considering the "hardness" of each sample. To address this problem, in this work we propose a Grad-Libra Loss that leverages the gradients to dynamically calibrate the degree of hardness of each sample for different categories, and re-balance the gradients of positive and negative samples. Our loss can thus help the detector to put more emphasis on those hard samples in both head and tail categories. Extensive experiments on a long-tailed TCT WSI image dataset show that the mainstream detectors, e.g. RepPoints, FCOS, ATSS, YOLOF, etc. trained using our proposed Gradient-Libra Loss, achieved much higher (7.8%) mAP than that trained using cross-entropy classification loss. Copyright © 2022, The Authors. All rights reserved.

关键词： Cytology

来源：评论

学校读者我要写书评

暂无评论

An interval-based Bayesian generative model for human complex activity recognition

arXiv

引用

arXiv 2017年

作者： Liu, Li Yang, Yongzhong Govindarajan, Lakshmi N. Wang, Shu Hu, Bin Cheng, Li Rosenblum, David S. Ministry of Education Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing400044 China School of Software Engineering Chongqing University Chongqing400044 China School of Computing National University of Singapore 117417 Singapore Bioinformatics Institute A*STAR 138671 Singapore College of Material Science and Engineering Lanzhou University of Technology Lanzhou730050 China School of Information Science and Engineering Lanzhou University 730000 China

Complex activity recognition is challenging due to the inherent uncertainty and diversity of performing a complex activity. Normally, each instance of a complex activity has its own configuration of atomic actions and their temporal dependencies. We propose in this paper an atomic action-based Bayesian model that constructs Allen's interval relation networks to characterize complex activities with structural varieties in a probabilistic generative way: By introducing latent variables from the Chinese restaurant process, our approach is able to capture all possible styles of a particular complex activity as a unique set of distributions over atomic actions and relations. We also show that local temporal dependencies can be retained and are globally consistent in the resulting interval network. Moreover, network structure can be learned from empirical data. A new dataset of complex hand activities has been constructed and made publicly available, which is much larger in size than any existing datasets. Empirical evaluations on benchmark datasets as well as our in-house dataset demonstrate the competitiveness of our approach. Copyright © 2017, The Authors. All rights reserved.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

An improved PSO algorithm with simulated annealing for constrained function optimization

引用

Zhongnan Daxue Xuebao (Ziran Kexue Ban)/Journal of Central South University (Science and technology) 2011年第SUPPL. 1期42卷 175-179页

作者： Si, Cheng-Yong Yang, Dong-Sheng Tian, Hong-Jun Wang, Lei Wu, Qi-Di College of Electronics and Information Engineering Tongji University Shanghai 201804 China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 200092 China Shanghai Economic and Information Committee Shanghai 200040 China

To solve the problem of infeasible solutions in the constrained function optimization, a constraint-handling technique based on simulated annealing is proposed. The improved particle swarm optimization is also used to verify the effectiveness of this technique. The experimental results show that the proposed algorithm is suitable for solving such problems.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Virtual Storage Image Implementation in a SAN system to Improve Storage Capacity, Fault Tolerance and Bandwidth

Virtual Storage Image Implementation in a SAN System to Impr...

引用

Intermag 2006 (INTERMAG 2006), vol.2

作者： Y. Deng F. Wang K. Zhou S. Wu Center for Grid Computing Cambridge-Cranfield High Performance Computing Facility Cranfield Bedfordshire UK Key Laboratory of Data Storage System Ministry of Education School of Computer Huazhong University of Science and Technology Wuhan China

With a SAN (Storage Area Network), large-capacity storage can be shared among multiple hosts at high speed. The potential market for SAN is enormous, but the technology won't become ubiquitous overnight. The complex administration is indicated by many researches as a key barrier to adopt SAN solutions. This paper designs and implements a virtual storage image (VSI) that aggregates storage space located on heterogeneous storage nodes (see Fig.1)in a Fibre Channel point-to-point (FC-P2P) SAN.

关键词： Image storage Storage area networks Fault tolerant systems Bandwidth File systems Space technology Aggregates Linux Fault tolerance Load management

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：