检索结果-内蒙古大学图书馆

Neighborhood collaborative classifiers

学校读者我要写书评

暂无评论

Neighborhood collaborative classifiers

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Suping Xu Xibei Yang Eric C. C. Tsang Eric A. Mantey Intelligent Information Processing Key Laboratory of Shanxi Province Shanxi University Taiyuan China School of Computer Science and Engineering Jiangsu University of Science and Technology Zhenjiang China Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Zhejiang Ocean University Zhoushan China School of Economics and Management Nanjing University of Science and Technology Nanjing China Faculty of Information Technology Macau University of Science and Technology Macau China

ISBN: (纸本)9781509003914

In neighborhood rough set model, the majority rule based neighborhood classifier (NC) is easy to be misjudged with the increasing of the size of information granules. To remedy this deficiency, we propose a neighborhood collaborative classifier (NCC) based on the idea of collaborative representation based classification (CRC). NCC first performs feature selection with neighborhood rough set, and then instead of solving the classification problem by the majority rule, NCC solves a similar problem with collaborative representation among the neighbors of each unseen sample. Experiments on UCI data sets demonstrate that: 1) Our NCC achieves satisfactory performance in larger neighborhood information granules when compared with NC; 2) NCC reduces the size of dictionary when compared with CRC.

关键词： Collaboration Rough sets Training Cybernetics Numerical models Error analysis Measurement

AdaSemiCD: An Adaptive Semi-supervised Change Detection Method Based on Pseudo Label Evaluation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ran, Lingyan Wen, Dongcheng Zhuo, Tao Zhang, Shizhou Zhang, Xiuwei Zhang, Yanning School of Computer Science Shaanxi Provincial Key Laboratory of Speech and Image Information Processing The National Engineering Laboratory for Integrated Aerospace-GroundOcean Big Data Application Technology The Ningbo Institute of Northwestern Polytechnical University Northwestern Polytechnical University Xi’an710072 China College of Information Engineering Northwest A&F University Yangling712100 China

Change detection(CD) is an essential field in remote sensing, with a primary focus on identifying areas of change in bitemporal image pairs captured at varying intervals of the same region. The data annotation process for CD tasks is both time-consuming and labor-intensive. To better utilize the scarce labeled data and abundant unlabeled data, we introduce an adaptive semi-supervised learning method, AdaSemiCD, to improve pseudo-label usage and optimize the training process. Initially, due to the extreme class imbalance inherent in CD, the model is more inclined to focus on the background class, and it is easy to confuse the boundary of the target object. Considering these two points, we develop a measurable evaluation metric for pseudo-labels that enhances the representation of information entropy by class rebalancing and amplification of ambiguous areas, assigning greater weights to prospective change objects. Subsequently, to enhance the reliability of samplewise pseudo-labels, we introduce the AdaFusion module, to dynamically identifying the most uncertain region and substituting it with more trustworthy content. Lastly, to ensure better training stability, we introduce the AdaEMA module, which updates the teacher model using only batches of trusted samples. Experimental results on ten public CD datasets validate the efficacy and generalizability of our proposed adaptive training framework. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

A new logistic map based chaotic biogeography-based optimization approach for cluster analysis

学校读者我要写书评

暂无评论

A new logistic map based chaotic biogeography-based optimiza...

IEEE International Conference on Progress in Informatics and Computing (PIC)

作者： Shui-Hua Wang Hui-Min Lu Yu-Jie Li Yang Wang Zhi-Min Chen Yu-Min Wei Wen-Juan Jia Fang-Yuan Liu Yu-Dong Zhang Hunan Provincial Key Laboratory of Network Investigational Technology Hunan Policy Academy Changsha Hunan China School of Computer Science and Technology Nanjing Normal University Nanjing Jiangsu China Department of Electrical Engineering CUNY New York NY USA Department of Mechanical and Control Engineering Kyushu Institute of Technology Fukuoka Prefecture Japan School of Information Engineering Yangzhou University Yangzhou Jiangsu China School of Physics and Electronic Engineering Taizhou University Taizhou Zhejiang China School of Electronic Information Shanghai Dianji University Shanghai China School of Energy and Mechanical Engineering Nanjing Normal University Nanjing Jiangsu China Key Laboratory of Intelligent Computing and Information Processing in Fujian Provincial University Quanzhou Normal University Quanzhou Fujian China

ISBN: (纸本)9781509034857

Cluster analysis is important in scientific and industrial fields. In this study, we proposed a novel chaotic biogeography-based optimization (CBBO) method, and applied it in centroid-based clustering methods. The results over three types of simulation data showed that this proposed CBBO method gave better performance than chaotic particle swarm optimization, genetic algorithm, firefly algorithm, and quantum-behaved particle swarm optimization. In all, our CBBO method is effective in centroid-based clustering.

关键词： Genetic algorithms Optimization Clustering algorithms Particle swarm optimization Algorithm design and analysis Logistics Mathematical model

A Shortest Path Query Approach for Encrypted Graphs Based on Padding Dictionary Structure

学校读者我要写书评

暂无评论

A Shortest Path Query Approach for Encrypted Graphs Based on...

Chinese Automation Congress (CAC)

作者： Ming Yang Kaiyang Zhang Chao Mu Xin Wang Yuanlong Liu Heng Zhang Key Laboratory of Computing Power Network and Information Security Shandong Computer Science Center Ministry of Education Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China State Grid Shandong Electric Power Company Jinan China School of Computer Engineering Jiangsu Ocean University Lianyungang China

Hybrid intelligence has emerged as an innovative approach that synergistically combines the strengths of human intelligence and artificial intelligence (AI) to address complex problems. In this paradigm, knowledge graphs play a pivotal role by supplying vital background information and contextual understanding to hybrid intelligence systems. However, due to limitations in local storage capacity, managing large-scale graph data often requires outsourcing to cloud servers. Nevertheless, the use of untrusted cloud servers poses a risk of potential user data leaks. To address these concerns, this paper presents an encryption scheme specifically designed to protect graph data, enabling queries involving intermediate nodes in the shortest path between two nodes within the graph. The proposed scheme ensures the privacy and security of outsourced data by employing a novel method that utilizes padding dictionary structure encryption. This method ensures strict limitations on the cloud server's capabilities, restricting it solely to query operations, it effectively prevents any compromise of user data or unauthorized access to sensitive information, users can securely store and process their graph data on servers, significantly reducing the potential risk of data leakage and unauthorized breaches. To validate the feasibility and effectiveness of the proposed solution, practical experiments were conducted using real-world data.

关键词：

Research on Wireless Channel Modeling for Complex Water Surface Environments

学校读者我要写书评

暂无评论

Research on Wireless Channel Modeling for Complex Water Surf...

Intelligent Communication and Networking (ICN), International Conference on

作者： Xujie Li Tianzhang Ge Baochao Wei Haotian Li Ning Xu College of Information Science and Engineering Hohai University Nanjing China Jiangsu Health Development Research Center Nanjing China NHC Contraceptives Adverse Reaction Surveillance Center Nanjing China Jiangsu Provincial Medical Key Laboratory of Fertility Protection and Health Technology Assessment Nanjing China College of Computer and Information Hohai University Nanjing China

Accurate and efficient channel modeling has always been a critical foundation for the deployment and application of 5G communication technology. To meet the requirements of continuous and extensive coverage in 5G, higher demands have been placed on wireless channel characteristics across various scenarios. However, the propagation of wireless signals over water may involve more complex reflection and scattering phenomena. Additionally, the presence of vegetation on water surface further complicates the channel modeling. Addressing these challenges, we assess relevant theories and representative signal attenuation models, and propose a channel model for complex water-based scenarios based on the open water channel model. To ascertain the precision of the proposed model, we establish an experimental platform and conduct measurements on the attenuation of signals across a water pool populated with various obstacles. The results demonstrate that the suggested model more accurately corresponds to the distinctive patterns of wireless signal attenuation encountered within complex water surface environments.

关键词：

An integrative drug repositioning framework discovered a potential therapeutic agent targeting COVID-19

学校读者我要写书评

暂无评论

Signal Transduction and Targeted Therapy 2021年第5期6卷 1585-1600页

作者： Yiyue Ge Tingzhong Tian Suling Huang Fangping Wan Jingxin Li Shuya Li Xiaoting Wang Hui Yang Lixiang Hong Nian Wu Enming Yuan Yunan Luo Lili Cheng Chengliang Hu Yipin Lei Hantao Shu Xiaolong Feng Ziyuan Jiang Yunfu Wu Ying Chi Xiling Guo Lunbiao Cui Liang Xiao Zeng Li Chunhao Yang Zehong Miao Ligong Chen Haitao Li Hainian Zeng Dan Zhao Fengcai Zhu Xiaokun Shen Jianyang Zeng Institute for Interdisciplinary Information Sciences Tsinghua UniversityBeijingChina NHC Key laboratory of Emeric Pathogenic Microbiology Jiangsu Provincial Center for Diseases Control and PreventionNanjingJiangsu ProvinceChina Shanghai Institute of Materia Medica Chinese Academy of SciencesShanghaiChina Silexon Al Technology Co. Ltd.NanjingJiangsu ProvinceChina Department of Computer Science University of Illinois at Urbana-ChampaignIllinoisILUSA School of Pharmaceutical Sciences Tsinghua UniversityBeijingChina School of Electronic Information and Communications Huazhong University of Science and TechnologyWuhanHubei ProvinceChina Institute of Pathology Tongji HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhanHubei ProvinceChina Department of Automation Tsinghua UniversityBeijingChina Inner Mongolia Alashan League Organization Establishment Committee Office Electronic Support Center AlashanInner MongoliaChina Convalife(Shanghai)Co. Ltd.ShanghaiChina Advanced Innovation Center for Human Brain Protection Beijing Tiantan HospitalCapital Medical UniversityBeijingChina Beijing Advanced Innovation Center for Structural Biology Tsinghua-Peking Joint Center for Life SciencesDepartment of Basic Medical SciencesSchool of MedicineTsinghua UniversityBeijingChina Center for Global Health Nanjing Medical UniversityNanjingJiangsu ProvinceChina

The global spread of severe acute respiratory syndrome coronavirus 2(SARS-CoV-2)requires an urgent need to find effective therapeutics for the treatment of coronavirus disease 2019(COVID-19).In this study,we developed an integrative drug repositioning framework,which fully takes advantage of machine learning and statistical analysis approaches to systematically integrate and mine large-scale knowledge graph,literature and transcriptome data to discover the potential drug candidates against *** in silico screening followed by wet-lab validation indicated that a poly-ADP-ribose polymerase 1(PARP1)inhibitor,CVL218,currently in Phase I clinical trial,may be repurposed to treat *** in vitro assays revealed that CVL218 can exhibit effective inhibitory activity against SARS-CoV-2 replication without obvious cytopathic *** addition,we showed that CVL218 can interact with the nucleocapsid(N)protein of SARS-CoV-2 and is able to suppress the LPS-induced production of several inflammatory cytokines that are highly relevant to the prevention of immunopathology induced by SARS-CoV-2 infection.

关键词： prevention respiratory acute

Privacy-preserving medical treatment system through nondeterministic finite automata

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Yang, Yang Deng, Robert H. Liu, Ximeng Wu, Yongdong Weng, Jian Zheng, Xianghan Rong, Chunming School of Information Systems Singapore Management University Singapore College of Mathematics and Computer Science Fuzhou University Fujian China State Key Laboratory of Integrated Services Networks Xidian University Guangdong Provincial Key Laboratory of Data Security and Privacy Protection Guangzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China School of Information Systems Singapore Management University Singapore Singapore Department of Computer Science Jinan University Guangdong China College of Mathematics and Computer Science Fuzhou University Fujian China Department of Electronic Engineering and Computer Science University of Stavanger Norway MingByte Technology Qingdao China

In this paper, we propose a privacy-preserving medical treatment system using nondeterministic finite automata (NFA), hereafter referred to as P-Med, designed for the remote medical environment. P-Med makes use of the nondeterministic transition characteristic of NFA to flexibly represent the medical model, which includes illness states, treatment methods and state transitions caused by exerting different treatment methods. A medical model is encrypted and outsourced to the cloud to deliver telemedicine services. Using P-Med, patient-centric diagnosis and treatment can be made on-the-fly while protecting the confidentiality of a patient's illness states and treatment recommendation results. Moreover, a new privacy-preserving NFA evaluation method is given in P-Med to get a confidential match result for the evaluation of an encrypted NFA and an encrypted data set, which avoids the cumbersome inner state transition determination. We demonstrate that P-Med realizes treatment procedure recommendation without privacy leakage to unauthorized parties. We conduct extensive experiments and analyses to evaluate efficiency. Copyright © 2020, The Authors. All rights reserved.

关键词： Diseases

Hand Hygiene Assessment via Joint Step Segmentation and key Action Scorer

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Chenglong Zhu, Qiwen Liu, Tubiao Tang, Jin Su, Yu Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Key Lab of Intelligent Computing and Signal Processing of Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China Hefei Normal University Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230061 China

Hand hygiene is a standard six-step hand-washing action proposed by the World Health Organization (WHO). However, there is no good way to supervise medical staff to do hand hygiene, which brings the potential risk of disease spread. Existing action assessment works usually make an overall quality prediction on an entire video. However, the internal structures of hand hygiene action are important in hand hygiene assessment. Therefore, we propose a novel fine-grained learning framework to perform step segmentation and key action scorer in a joint manner for accurate hand hygiene assessment. Existing temporal segmentation methods usually employ multi-stage convolutional network to improve the segmentation robustness, but easily lead to over-segmentation due to the lack of the long-range dependence. To address this issue, we design a multi-stage convolution-transformer network for step segmentation. Based on the observation that each hand-washing step involves several key actions which determine the hand-washing quality, we design a set of key action scorers to evaluate the quality of key actions in each step. In addition, there lacks a unified dataset in hand hygiene assessment. Therefore, under the supervision of medical staff, we contribute a video dataset that contains 300 video sequences with fine-grained annotations. Extensive experiments on the dataset suggest that our method well assesses hand hygiene videos and achieves outstanding performance. Copyright © 2022, The Authors. All rights reserved.

关键词： Convolution

ATASI-Net: An Efficient Sparse Reconstruction Network for Tomographic SAR Imaging with Adaptive Threshold

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Muhan Zhang, Zhe Qiu, Xiaolan Gao, Silin Wang, Yue Suzhou Key Laboratory of Microwave Imaging Processing and Application Technology China Suzhou Aerospace Information Research Institute Jiangsu Suzhou China Aerospace Information Research Institute Chinese Academy of Sciences China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China The Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing China Electrical and Computer Engineering Department George Mason University FairfaxVA United States

Tomographic SAR technique has attracted remarkable interest for its ability of three-dimensional resolving along the elevation direction via a stack of SAR images collected from different cross-track angles. The emerged compressed sensing (CS)-based algorithms have been introduced into TomoSAR considering its super-resolution ability with limited samples. However, the conventional CS-based methods suffer from several drawbacks, including weak noise resistance, high computational complexity, and complex parameter fine-tuning. Aiming at efficient TomoSAR imaging, this paper proposes a novel efficient sparse unfolding network based on the analytic learned iterative shrinkage thresholding algorithm (ALISTA) architecture with adaptive threshold, named Adaptive Threshold ALISTA-based Sparse Imaging Network (ATASI-Net). The weight matrix in each layer of ATASI-Net is pre-computed as the solution of an offline optimization problem, leaving only two scalar parameters to be learned from data, which significantly simplifies the training stage. In addition, adaptive threshold is introduced for each azimuth-range pixel, enabling the threshold shrinkage to be not only layer-varied but also element-wise. Moreover, the final learned thresholds can be visualized and combined with the SAR image semantics for mutual feedback. Finally, extensive experiments on simulated and real data are carried out to demonstrate the effectiveness and efficiency of the proposed method. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics