检索结果-内蒙古大学图书馆

Dual-Graph Contrastive Learning for Unsupervised Person Reidentification

IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS 2024年第4期16卷 1352-1363页

作者： Zhang, Lin Song, Ran Wang, Yifan Zhang, Qian Zhang, Wei Shandong Univ Sch Control Sci & Engn Jinan 250012 Shandong Peoples R China

Unsupervised person reidentification (re-ID) aims to perform person retrieval in an unsupervised manner across multiple cameras. Most recent works usually adopted contrastive learning with clustering strategy to guide learning process. However, the domain gap between cameras easily causes the high intraclass variance and prohibits an effective contrastive learning. To overcome this problem, we propose dual-graph contrastive learning (Dual-GCL) to fully utilize the structures between the instances as well as the relationship between the instances and the centroids generated by the clustering strategy. First, a dual-graph is constructed by utilizing the affinities of instances in the feature space and the pseudolabel space derived from clustering strategy with the node-to-node contrastive learning. Then, to capture the relations between the dual-graph and the centroids, we perform Dual-GCL at both the node level and the super-node level. The contrastive learning based on the two levels can encode multilevel structural representations between the instances corresponding to the nodes in dual-graph and align the centroids between different cameras in the shared embedding space. Moreover, a camera-aware augmentation scheme that exploits the semantic relationship is proposed to alleviate the domain discrepancy between cameras. Experimental results demonstrate that our approach outperforms the state-of-the-art methods.

关键词： Cameras Semantics Heuristic algorithms Reliability Noise measurement Feature extraction clustering algorithms Contrastive learning person reidentification (re-ID) unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

An Efficient Secure and Adaptive Routing Protocol Based on GMM-HMM-LSTM for Internet of Underwater Things

引用

IEEE INTERNET OF THINGS JOURNAL 2024年第9期11卷 16491-16504页

作者： Zhu, Rongxin Boukerche, Azzedine Yang, Qiuling Hainan Univ Sch Cyberspace Secur Haikou 570228 Peoples R China Univ Ottawa Paradise Res Lab Ottawa ON K1N 6N5 Canada Hainan Univ Sch Comp Sci & Technol Haikou 570228 Peoples R China Hainan Univ Innovat Platform Academicians Hainan Prov Haikou 570228 Peoples R China

The growing significance of marine information in the context of increased human oceanic activities has fostered interest in marine exploration. However, the specific nature of underwater acoustic communication, characterized by propagation delays and fluctuating link quality, presents multifaceted challenges to Internet of Underwater Things (IoUT). The vast openness of the underwater environment further amplifies security vulnerabilities, emphasizing the imperative for secure network routing. This article introduces GHL-SAR, a fortified routing paradigm to address these challenges. Central to GHL-SAR's design is its ability to evaluate node trustworthiness based on energy, communication, and node trust. Within this model, the Gaussian mixture model-hidden Markov model (GMM-HMM) serves as a predictor of potential hidden state sequences, while the long short-term memory (LSTM) elucidates the relationship between these states and trust levels. Moreover, GHL-SAR deploys an adaptive routing mechanism rooted in the particle swarm optimization algorithm (PSOA), judiciously weighing link quality for routing decisions. The protocol further advances a density-based spatial clustering method for effective trust evidence aggregation. The simulation results demonstrate that GHL-SAR significantly reduces packet loss and energy consumption, while ensuring detection accuracy and network security compared to other existing routing protocols.

关键词： Routing Security clustering algorithms Routing protocols Internet of Things Adaptation models Underwater acoustics Internet of Underwater Things (IoUT) link quality routing protocol trust model underwater acoustic communication

来源：评论

学校读者我要写书评

暂无评论

AdaDC: Adaptive Deep clustering for Unsupervised Domain Adaptation in Person Re-Identification

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2022年第6期32卷 3825-3838页

作者： Li, Shihua Yuan, Mingkuan Chen, Jie Hu, Zhilan Chinese Acad Sci Inst Microelect Beijing 100029 Peoples R China Univ Chinese Acad Sci Sch Microelect Beijing 100049 Peoples R China Cent Med Technol Inst Huawei Beijing 100085 Peoples R China

Unsupervised domain adaptation (UDA) in person re-identification (re-ID) is a challenging task, aiming to learn a model with labeled source data and unlabeled target data to recognize the same person in the target domain across different cameras. Recently, a lot of popular and promising methods based on clustering are proposed for this task and achieve a sizable progress. However, in those methods, without target labels, the clustering algorithms will inevitably produce noisy pseudo-labels. Overfitting on these noisy labels is severely harmful to the performance and generalization of models. In order to address the above issues, we propose a novel framework, Adaptive Deep clustering (AdaDC), to reduce the negative impact of noisy pseudo-labels. On one hand, the proposed approach employs different clustering methods adaptively and alternately to fully exploit their complementary information and avoid overfitting noisy pseudo-labels. On the other hand, there is a progressive sample selection strategy for reducing noisy label ratio in pseudo-labels, which is achieved by integrating different clustering results. Experiments present that the proposed approach can achieve state-of-the-art performance compared to the other recent UDA person re-ID methods on widely-used datasets. Moreover, there are some other analysis experiments conducted for verifying the effectiveness of the proposed approach.

关键词： Noise measurement clustering algorithms Task analysis Adaptation models Training Supervised learning Robustness Unsupervised domain adaptation person re-identification

来源：评论

学校读者我要写书评

暂无评论

TARIS: Scalable Incremental Processing of Time-Respecting algorithms on Streaming Graphs

引用

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 2024年第12期35卷 2527-2544页

作者： Bhoot, Ruchi Ghanmode, Suved Sanjay Simmhan, Yogesh Indian Inst Sci Bangalore 560012 India

Temporal graphs change with time and have a lifespan associated with each vertex and edge. These graphs are suitable to process time-respecting algorithms where the traversed edges must have monotonic timestamps. Interval-centric Computing Model (ICM) is a distributed programming abstraction to design such temporal algorithms. There has been little work on supporting time-respecting algorithms at large scales for streaming graphs, which are updated continuously at high rates (Millions/s), such as in financial and social networks. In this article, we extend the windowed-variant of ICM for incremental computing over streaming graph updates. We formalize the properties of temporal graph algorithms and prove that our model of incremental computing over streaming updates is equivalent to batch execution of ICM. We design TARIS, a novel distributed graph platform that implements these incremental computing features. We use efficient data structures to reduce memory access and enhance locality during graph updates. We also propose scheduling strategies to interleave updates with computing, and streaming strategies to adapt the execution window for incremental computing to the variable input rates. Our detailed and rigorous evaluation of temporal algorithms on large-scale graphs with up to 2B edges show that TARIS out-performs contemporary baselines, Tink and Gradoop, by 3-4 orders of magnitude, and handles a high input rate of 83k-587 M Mutations/s with latencies in the order of seconds-minutes.

关键词： Social networking (online) Heuristic algorithms Topology Computational modeling Network topology Data structures clustering algorithms Space exploration Roads COVID-19 Discrete Mathematics distributed programming distributed systems general graph algorithms graph theory information storage and retrieval information technology and systems mathematics of computing numerical analysis programming techniques parallel algorithms systems and software software/software engineering

来源：评论

学校读者我要写书评

暂无评论

A Multi-Sources DOA Localization Method Based on UAV Cluster Systems

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2024年第6期73卷 8681-8692页

作者： Zhang, Chenhao Wang, Wenjie Hong, Xi Zhou, Jianwei Xi An Jiao Tong Univ Sch Informat & Commun Engn Xian 710049 Shaanxi Peoples R China Shaanxi Key Lab Deep Space Explorat Intelligent In Xian 710049 Shaanxi Peoples R China INSPUR Commun Technol Co Ltd Stand R&D Dept Jinan 250000 Peoples R China

Multi-sources Direction of Arrival (DOA) localization by Unmanned-Aerial-Vehicle (UAV) cluster systems has gained significant attention due to its flexibility and high precision. The key technology lies in high-resolution multi-sources DOA estimation. UAV cluster systems with traditional element-space structure often suffer the extreme demands of Radio Frequency (RF) chains, resulting in high hardware complexity and computation burden. Additionally, the unknown phase differences among all the UAV units caused by asynchronous crystal oscillators and imprecise unit locations further complicates this problem. To address these issues, a beamspace ESPRIT based multi-sources DOA localization method is proposed in this paper. The beamspace pre-processing with the hybrid structure is used to handle the RF chain number problem, while the rotation invariance between beam clusters is built to solve the unknown phase difference problem in DOA estimation. The performance analysis is also provided to show the contributions of some key physical parameters on DOA estimation performance. The simulation results show that the DOA localization precision depends on the DOA estimation performance and Geometric Dilution of Precision (GDOP). The proposed method achieves a similar performance to the existing methods, but both the RF chain number and the computation complexity are significantly decreased.

关键词： Autonomous aerial vehicles Direction-of-arrival estimation Location awareness Estimation clustering algorithms Radio frequency Antenna arrays Beamspace pre-processing DOA localization ESPRIT first-order perturbation analysis UAV cluster system

来源：评论

学校读者我要写书评

暂无评论

A Cooperative Caching System in Heterogeneous Edge Networks

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2024年第7期23卷 7635-7649页

作者： Peng, Junkun Li, Qing Tang, Xun Zhao, Dan Hu, Chuang Jiang, Yong Tsinghua Univ Shenzhen Int Grad Sch Shenzhen 518055 Guangdong Peoples R China Peng Cheng Lab Shenzhen 518055 Guangdong Peoples R China Sun Yat Sen Univ Shenzhen 518107 Guangdong Peoples R China Wuhan Univ Wuhan 430072 Hubei Peoples R China

Recently, the rapid growth of video content and the increasing demand for high Quality of Experience (QoE) have significantly strained the backbone network. Edge caching is a promising approach to alleviate the strain by caching content closer to users. However, it confronts challenges stemming from the low capability of individual edge nodes and the high density of their distribution, resulting in low hit ratios and unbalanced workloads. In this paper, we conduct in-depth analyses of these challenges and formulate a typical cooperative edge caching problem. Based on the insights, we introduce MagNet, a cooperative edge caching system featuring two key mechanisms: Automatic Content Congregating (ACC) and Mutual Assistance Group (MAG). ACC improves hit ratios by intelligently guiding requests to their optimal edges, thereby facilitating content aggregation. Complementing this, Quick Cache is implemented to accelerate this congregation process by prefetching content and optimizing cache space, effectively boosting hit ratios. MAG, on the other hand, achieves workload balance by dynamically forming groups to augment edge capabilities and redistribute requests on overloaded edges. To elucidate the design principles of MagNet, we conduct detailed component-level comparisons and quantitative analyses. To validate the overall performance, we compare it with various caching solutions using real-world datasets, demonstrating significant performance improvements.

关键词： Mobile computing Quality of experience clustering algorithms IP networks Streaming media Prefetching Magnetic confinement Edge computing cache cooperative workload balance embedding

来源：评论

学校读者我要写书评

暂无评论

A Sector-Based Energy-Efficient Lightweight clustering Algorithm

引用

IEEE ACCESS 2022年 10卷 108285-108295页

作者： Zeng, Bo Zhao, Chaofeng Zhang, Yongxin Sun, Jie Gao, Xiaofeng Luoyang Normal Univ Coll Informat Technol Luoyang 471934 Peoples R China Henan Univ Sci & Technol Network Informat & Modern Educ Technol Ctr Luoyang 471000 Peoples R China

Wireless sensor networks consist of a large number of nodes with constrained energy supply. Energy efficiency is hot and challenging issue in wireless sensor networks. Existing studies have shown that clustering is one of the efficient techniques to improve energy efficiency. An easy-to-implement and flexible method for even clustering and cluster head selection is beneficial to optimize network stability and energy efficiency. In this study, a sector-based lightweight and flexible clustering algorithm is developed to reduce node energy dissipation and optimize energy efficiency. Our proposal divides the area into virtual sectors. In the meanwhile, an even sector cluster is created using the sector decomposition approach. Based on the total communication distance, residual energy, and local node density, each node in the cluster calculates its own priority. The node with the highest priority is selected as the cluster head. Our proposal is compared with TSC,MH-TSC,SEECP,DREEP and LEACH. Experimental results show that the proposed algorithm outperforms these algorithms in terms of network stability and network lifetime.

关键词： clustering algorithms Energy efficiency Wireless sensor networks Energy consumption Proposals Energy dissipation Routing Wireless sensor networks sectors energy efficiency clustering

来源：评论

学校读者我要写书评

暂无评论

Joint Topology Reconstruction and Resource Allocation for UAV-IoT Networks

引用

IEEE INTERNET OF THINGS JOURNAL 2024年第22期11卷 36452-36464页

作者： Sun, Wen-Bin Zhao, Lei Yang, Xin Wang, Ling Meng, Wei-Xiao Northwestern Polytech Univ Sch Elect & Informat Xian 710072 Peoples R China Harbin Inst Technol Commun Res Ctr Harbin 150001 Peoples R China

Due to high-flexible deployment and enhanced transmission capabilities, unmanned aerial vehicle (UAV) has attracted significant attention in recent years. UAV can serve as base station to provide communication coverage for emerging Internet of Things (IoT) in hot-spot areas. Stable topology plays an important role in improving connection and efficiency of UAV-IoT networks. However, when UAV-IoT nodes fail, network topology is destroyed and reconstruction becomes a formidable challenge, particularly in extremely harsh scenarios. Traditional topology reconstruction schemes predominantly rely on node movement to restore network connectivity, which neglect the performances of UAV-IoT networks. To remain stability and promote performances simultaneously, this article proposes a distributed resource scheduling topology reconstruction (DRSTR) scheme, where both connectivity and throuphput of UAV nodes are jointly considered. Then, an optimization problem combining topology reconstruction and resource allocation is presented under the constraints of UAV-IoT nodes' Quality of Service (QoS) requirements. Since the difficulty in solving the problem, the original problem is divided into three suboptimal issues and an iterative approach is introduced to approximate the global optimal solution. Numerical results show that the proposed scheme achieves higher performances in UAV-IoT networks, compared to the traditional topology reconstruction schemes.

关键词： Autonomous aerial vehicles Network topology Internet of Things Topology clustering algorithms Resource management Throughput Internet of Things (IoT) networks joint iteration resource allocation topology reconstruction unmanned aerial vehicle (UAV)

来源：评论

学校读者我要写书评

暂无评论

Learning Consistency and Specificity of Cells From Single-Cell Multi-Omic Data

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2024年第5期28卷 3134-3145页

作者： Wang, Haiyue Liu, Zaiyi Ma, Xiaoke Xidian Univ Sch Comp Sci & Technol Xian 710071 Peoples R China Guangdong Acad Med Sci Guangdong Gen Hosp Dept Radiol Guangzhou 510080 Peoples R China Guangdong Prov Key Lab Artificial Intelligence Med Guangzhou 510080 Peoples R China

Advancements in single-cell technologies concomitantly develop the epigenomic and transcriptomic profiles at the cell levels, providing opportunities to explore the potential biological mechanisms. Even though significant efforts have been dedicated to them, it remains challenging for the integration analysis of multi-omic data of single-cell because of the heterogeneity, complicated coupling and interpretability of data. To handle these issues, we propose a novel self-representation Learning-based Multi-omics data Integrative clustering algorithm (sLMIC) for the integration of single-cell epigenomic profiles (DNA methylation or scATAC-seq) and transcriptomic (scRNA-seq), which the consistent and specific features of cells are explicitly extracted facilitating the cell clustering. Specifically, sLMIC constructs a graph for each type of single-cell data, thereby transforming omics data into multi-layer networks, which effectively removes heterogeneity of omic data. Then, sLMIC employs the low-rank and exclusivity constraints to separate the self-representation of cells into two parts, i.e., the shared and specific features, which explicitly characterize the consistency and diversity of omic data, providing an effective strategy to model the structure of cell types. Feature extraction and cell clustering are jointly formulated as an overall objective function, where latent features of data are obtained under the guidance of cell clustering. The extensive experimental results on 13 multi-omics datasets of single-cell from diverse organisms and tissues indicate that sLMIC observably exceeds the advanced algorithms regarding various measurements.

关键词： clustering algorithms Feature extraction Bioinformatics Transcriptomics Biomedical measurement Cells (biology) Representation learning Single-cell multi-omic data self-representation learning cell type graph learning integrative analysis

来源：评论

学校读者我要写书评

暂无评论

Towards More Precise Coincidental Correctness Detection With Deep Semantic Learning

引用

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING 2024年第12期50卷 3265-3289页

作者： Xie, Huan Lei, Yan Yan, Meng Li, Shanshan Mao, Xiaoguang Yu, Yue Lo, David Chongqing Univ Sch Big Data & Software Engn Chongqing 401331 Peoples R China Peng Cheng Lab Shenzhen 518055 Peoples R China Natl Univ Def Technol Coll Comp Changsha 410003 Peoples R China Singapore Management Univ Sch Comp & Informat Syst Singapore 178902 Singapore

Coincidental correctness (CC) is a situation during the execution of a test case, the buggy entity is executed, but the program behaves correctly as expected. Many automated fault localization (FL) techniques use runtime information to discover the underlying connection between the executed buggy entity and the failing test result. The existence of CC will weaken such connection, mislead the FL algorithms to build inaccurate models, and consequently, decrease the localization accuracy. To alleviate the adverse effect of CC on FL, CC detection techniques have been proposed to identify the possible CC tests via heuristic or machine learning algorithms. However, their performance on precision is not satisfactory since they overestimate the possible CC tests and are insufficient in learning the deep semantic features. In this work, we propose a novel Triplet network-based Coincidental Correctness detection technique (i.e., TriCoCo) to overcome the limitations of the prior works. TriCoCo narrows the possible CC tests by designing three features to identify genuine passing tests. Instead of using all tests as inputs by existing techniques, TriCoCo takes the identified genuine passing tests and failing ones to train a triplet model that can evaluate their relative distance. Finally, TriCoCo infers the probability of being a CC test of the test in the rest of the passing tests by using the trained triplet model. We conduct large-scale experiments to evaluate TriCoCo based on the widely-used Defects4J benchmark. The results demonstrate that TriCoCo can improve not only the precision of CC detection but also the effectiveness of FL techniques, e.g., the precision of TriCoCo is 80.33% on average, and TriCoCo boosts the efficacy of DStar by 18%-74% in terms of MFR metric when compared to seven state-of-the-art CC detection baselines.

关键词： Feature extraction Semantics Machine learning algorithms Location awareness Deep learning clustering algorithms Prediction algorithms Benchmark testing Accuracy Partitioning algorithms Coincidental correctness fault localization deep semantic learning

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：