检索结果-内蒙古大学图书馆

Multiview Subspace clustering via Co-Training Robust Data Representation

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2022年第10期33卷 5177-5189页

作者： Liu, Jiyuan Liu, Xinwang Yang, Yuexiang Guo, Xifeng Kloft, Marius He, Liangzhong Natl Univ Def Technol Coll Comp Sci Changsha 410072 Peoples R China Tech Univ Kaiserslautern Dept Comp Sci D-67653 Kaiserslautern Germany China Mobile Su Zhou Software Technol Co Ltd Suzhou 215009 Peoples R China

Taking the assumption that data samples are able to be reconstructed with the dictionary formed by themselves, recent multiview subspace clustering (MSC) algorithms aim to find a consensus reconstruction matrix via exploring complementary information across multiple views. Most of them directly operate on the original data observations without preprocessing, while others operate on the corresponding kernel matrices. However, they both ignore that the collected features may be designed arbitrarily and hard guaranteed to be independent and nonoverlapping. As a result, original data observations and kernel matrices would contain a large number of redundant details. To address this issue, we propose an MSC algorithm that groups samples and removes data redundancy concurrently. In specific, eigendecomposition is employed to obtain the robust data representation of low redundancy for later clustering. By utilizing the two processes into a unified model, clustering results will guide eigendecomposition to generate more discriminative data representation, which, as feedback, helps obtain better clustering results. In addition, an alternate and convergent algorithm is designed to solve the optimization problem. Extensive experiments are conducted on eight benchmarks, and the proposed algorithm outperforms comparative ones in recent literature by a large margin, verifying its superiority. At the same time, its effectiveness, computational efficiency, and robustness to noise are validated experimentally.

关键词： Kernel Eigenvalues and eigenfunctions clustering algorithms Redundancy Machine learning algorithms Robustness Dermatology Eigendecomposition multiview clustering robust representation subspace clustering

来源：评论

学校读者我要写书评

暂无评论

Short-Term Power Load Dynamic Scheduling Based on GWO-TCN-GRU Optimization Algorithm

引用

IEEE ACCESS 2024年 12卷 144919-144931页

作者： Hu, Yuyang Pan, Lianrong Yang, Xiao Wei, Xin Xie, Daiyu Guangxi Power Grid Co Ltd Elect Power Dispatching & Control Ctr Nanning 530023 Peoples R China

With the continuous increase of global energy demand and the transformation and upgrading of energy structure, the stability and efficiency of the power system are facing unprecedented challenges. A short-term power load dynamic scheduling model on the basis of temporal convolutional neural network and gated recurrent neural network is designed, and improved through grey wolf optimization algorithm. It simulates the hunting behavior of grey wolf populations, conducts global parameter searches, and finds the optimal temporal convolutional neural network and gated recurrent neural network structures and their hyper-parameter configurations. Subsequently, based on the optimized model, short-term electricity loads are predicted to obtain high-precision load forecasting results. On this basis, combined with dynamic scheduling strategies, real-time scheduling and management of power loads are achieved to ensure the stable operation of the power system. From the results, the designed model converged with an accuracy of 0.98. The root mean square error value was 0.21 when the iteration reached 100. In dataset A, when the iteration was 40, the proposed model had a scheduling time of 2.3s, and its loss function value, accuracy, F1-value, and Micro F1 were 0.203, 0.897, 0.626, and 0.971, respectively. In dataset B, the proposed model had a scheduling time of 2.6s. Therefore, the proposed optimized artificial bee colony algorithm can effectively predict and schedule power loads, providing a solution for scheduling problems in power systems.

关键词： Predictive models Load modeling Optimization clustering algorithms Dynamic scheduling Accuracy Heuristic algorithms Prediction algorithms Power system stability Adaptation models Power network load forecasting dynamic scheduling GWO TCN

来源：评论

学校读者我要写书评

暂无评论

Optimal EVs Charge Station Allocation Considering Residents Dispersion Using a Genetic Algorithm and Weighted K-Means

引用

IEEE ACCESS 2024年 12卷 191071-191085页

作者： Monteagudo, Rafael Castronuovo, Edgardo D. Barber, Ramon FCC Madrid 28050 Spain Univ Carlos III Madrid Elect Engn Dept Leganes 28911 Spain Univ Carlos III Madrid Syst Engn & Automat Leganes 28911 Spain

In this work, an innovative methodology for the strategic placement of electric vehicle (EV) charging stations is presented, considering both population density and proximity to the stations, in order to optimize accessibility. This approach synergistic leverages the advantages of genetic algorithms (GAs) and weighted K-means clustering, creating a phased process that circumvents the typical constraints presented by the two methods in developing efficient EV charging infrastructures. Initially, a GA is used to obtain a spectrum of potential locations, setting a preliminary distribution of charging stations. Then, a K-means clustering method is used to refine this distribution and obtain the most advantageous sites. The number of charging stations is modulated by variable alpha, which adjusts the influence of the GA and K-means in the final solution. The outcome is a more effective and realistic distribution of EV charging stations that can adapt to the actual patterns of urban population distribution, the economy of resources and EV demand. The proposed methodology is applied to an urban environment in two Spanish cities. The solution decreases between 60.60 and 95 % the number of the charging stations relative to those obtained by using k-mean and between 38.09 and 70 % those obtained using GAs, resulting in an economic and efficient grid of charging stations.

关键词： Charging stations Genetic algorithms Electric vehicle charging Resource management clustering algorithms Dispersion Costs Buildings Partitioning algorithms Investment weighted K-means clustering EV charging stations placement optimization

来源：评论

学校读者我要写书评

暂无评论

Efficient algorithms for Personalized PageRank Computation: A Survey

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2024年第9期36卷 4582-4602页

作者： Yang, Mingji Wang, Hanzhi Wei, Zhewei Wang, Sibo Wen, Ji-Rong Renmin Univ China Beijing 100872 Peoples R China Pazhou Lab Huangpu Gaoling Sch Artificial Intelligence Beijing Key Lab Big Data Management & Anal Methods MOE Key Lab Data Engn & Knowledge Engn Guangzhou 510555 Guangdong Peoples R China Chinese Univ Hong Kong Sha Tin Hong Kong Peoples R China

Personalized PageRank (PPR) is a traditional measure for node proximity on large graphs. For a pair of nodes s and t, the PPR value pi(s)(t)equals the probability that an alpha-discounted random walk from s terminates at t and reflects the importance between s and tin a bidirectional way. As a generalization of Google's celebrated PageRank centrality, PPR has been extensively studied and has found multifaceted applications in many fields, such as network analysis, graph mining, and graph machine learning. Despite numerous studies devoted to PPR over the decades, efficient computation of PPR remains a challenging problem, and there is a dearth of systematic summaries and comparisons of existing algorithms. In this paper, we recap several frequently used techniques for PPR computation and conduct a comprehensive survey of various recent PPR algorithms from an algorithmic perspective. We classify these approaches based on the types of queries they address and review their methodologies and contributions. We also discuss some representative algorithms for computing PPR on dynamic graphs and in parallel or distributed environments.

关键词： Vectors Surveys clustering algorithms Heuristic algorithms Classification algorithms Reviews Measurement uncertainty Graphs and networks graph algorithms PageRank personalized PageRank

来源：评论

学校读者我要写书评

暂无评论

Nonagriculturalization Detection Based on Vector Polygons and Contrastive Learning With High-Resolution Remote Sensing Images

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2024年 17卷 18474-18488页

作者： Zhang, Hui Liu, Wei Zhu, Changming Niu, Hao Yin, Pengcheng Dong, Shiling Wu, Jialin Li, Erzhu Zhang, Lianpeng Jiangsu Normal Univ Sch Geog Geomat & Planning Xuzhou 221116 Peoples R China Bur Nat Resources & Planning Xuzhou Xuzhou 221006 Peoples R China

The conversion of agricultural lands, termed "nonagriculturalization," poses profound threats to food security and ecological stability. Remote sensing image change detection offers an invaluable tool for monitoring this phenomenon. However, most change detection techniques prioritize image comparison over exploiting accumulated vector datasets. Additionally, many current methods are not readily applicable in practical scenarios due to inadequate model generalization capabilities and a scarcity of samples, resulting in a continued reliance on manual intervention for nonagriculturalization detection. In response, this article introduces a novel change detection approach for nonagriculturalization based on the vector data and contrastive learning. Initially, the boundary-constrained simple noniterative clustering algorithm is applied to segment two-phase images under vector data guidance. Samples are then generated using an adaptive cropping method. For early phase image samples, a collaborative validation-based sample annotation framework is employed to optimize and annotate the samples, with the purified high-quality samples serving as the training set for subsequent classification. For later-phase image samples, only those within the cropland vector polygons are retained for prediction. Building on this, a semi-supervised cross-domain contrastive learning framework is proposed for remote sensing scene classification. Ultimately, by integrating nonagriculturalization rules and postprocessing techniques, areas undergoing nonagriculturalization are further detected. Validating our methodology on Wuxi and Yangzhou datasets yielded precision rates of 91.57% and 89.21%, with recall rates of 93.68% and 90.51%, respectively. These outcomes affirm the effectiveness of our method in nonagriculturalization detection, offering robust technical support for research in this domain.

关键词： Vectors Image segmentation Feature extraction Monitoring Deep learning clustering algorithms Training Annotations Change detection contrastive learning (CL) cropland remote sensing vector polygons remote sensing vector polygons

来源：评论

学校读者我要写书评

暂无评论

FGRBC: A Novel Fuzzy Granular Rule-Based Classifier Using the Justifiable Granularity Principle and a Fusion Strategy

引用

IEEE TRANSACTIONS ON FUZZY SYSTEMS 2024年第12期32卷 7096-7108页

作者： Zhang, Xiao Liu, Yijing Li, Jinhai Mei, Changlin Xian Univ Technol Dept Appl Math Xian 710054 Peoples R China Kunming Univ Sci & Technol Fac Sci Kunming 650093 Peoples R China Xian Polytech Univ Dept Finance & Stat Xian 710048 Peoples R China

As a powerful tool for the representation of classifying knowledge, fuzzy classification rules can not only effectively deal with imprecise and uncertain data, but also possess readability and interpretability. Fuzzy granular rules, also to be a kind of fuzzy classification rules, can be induced by fuzzy information granules. It has been acknowledged that one of the important criteria for evaluating the quality of information granules comes from the principle of justifiable granularity. Unfortunately, the existing methods for extracting fuzzy granular rules fail to take into account the principle of justifiable granularity. In view of the advantages of the justifiable granularity principle in classifying knowledge, we propose in this article a new method of extracting fuzzy granular rules using the justifiable granularity principle and a fusion strategy and establish a fuzzy granular rule-based classifier (FGRBC). Specifically, the justifiability of fuzzy granules is first presented according to both coverage and specificity of fuzzy granules, on which a rule extraction method is formulated to obtain a set of fuzzy granular rules. Furthermore, a fusion strategy is put forward to generate a set of fused rules. Then, the two sets of rules are combined and attribute reduction is performed on the combined rule set. Finally, the reduced combined rule set is employed to construct FGRBC. Moreover, performance of FGRBC is evaluated by numerical experiments and the results show that FGRBC is of satisfactory classification ability.

关键词： Classification algorithms Data mining Feature extraction Rough sets Information systems Granular computing Fuzzy systems Fuzzy set theory Data models clustering algorithms Attribute reduction fuzzy decision system (FDS) fuzzy granular rule fuzzy rough set (FRS) rule-based classifier

来源：评论

学校读者我要写书评

暂无评论

A Data-Driven Framework for Operational Analysis and Traffic Pattern Identification in Multi-Airport Terminals

引用

IEEE ACCESS 2024年 12卷 140681-140698页

作者： Ouyang, Yuxiang Li, Guiyi Linlong, Siyu Nanjing Univ Aeronaut & Astronaut Coll Civil Aviat Nanjing 210016 Peoples R China

The terminal airspace is considered the most complex area within the air traffic system, as it encompasses multiple nearby airports whose operations are interdependent, thereby increasing the complexity of management. A thorough understanding of airspace traffic patterns and operational characteristics is crucial for ensuring the safety and stability of air traffic. The paper proposes a data-driven analysis framework for traffic patterns in multi-airport terminal airspace. This framework utilizes machine learning methods applied to airport arrival and departure trajectory data to explore the operational characteristics within the terminal airspace. The framework comprises (i) a trajectory pattern identification module, which identifies trajectory patterns from a large volume of trajectories and analyzes the characteristics of these patterns, and (ii) a traffic flow pattern identification module, which utilizes the trajectory pattern to identify traffic flow patterns within the terminal airspace, thereby characterizing the operational structure of airspace traffic flows and the spatiotemporal dependency between trajectory patterns. This framework can analyze the operational characteristics of trajectory patterns, route intersections, and traffic flow patterns within the airport terminal area. It helps managers better understand aircraft behavior in the terminal area, identify risk locations at intersections in the airspace, and reveal typical traffic flow structures. This supports the optimization of terminal area airspace structure and provides decision-making tools. By analyzing the terminal airspace operations of two airports in Shanghai (ZSPD and ZSSS), the framework's outcomes and capabilities are demonstrated. The study found that the airspace design of ZSPD is relatively complex, identifying multiple prevalent trajectory patterns. It also revealed that the airspace traffic flow structure exhibits certain temporal regularities, which aids in predicting the airs

关键词： Trajectory clustering algorithms Airports Aircraft Traffic control Air traffic control Signal processing algorithms Safety Feature extraction Data mining Flight trajectory data mining terminal maneuvering area multi-airport system trajectory clustering air traffic pattern identification

来源：评论

学校读者我要写书评

暂无评论

Optimizing the Number of Clusters for Billion-Scale Quantization-Based Nearest Neighbor Search

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2024年第11期36卷 6786-6800页

作者： Fu, Yujian Chen, Cheng Chen, Xiaohui Wong, Weng-Fai He, Bingsheng Natl Univ Singapore Sch Comp Singapore 119077 Singapore ByteDance Inc Beijing 100086 Peoples R China

Approximate nearest neighbor search (ANNS) is crucial in various real-world applications, including recommendation systems, data mining, and image retrieval. To date, quantization-based algorithms have emerged as one of the most efficient solutions for ANNS on billion-scale datasets. However, the determination of the optimal number of clusters, a critical factor for peak data performance in quantization-based systems, remains inadequately explored. Previous works often propose numbers of clusters that are not optimal, and the absence of effective methodologies for tuning this parameter leads to suboptimal search performance due to the vast configuration space. In response to this challenge, this paper introduces a novel algorithm that automatically identifies the optimal number of clusters for billion-scale, quantization-based ANNS systems to maximize search efficiency. We propose an analytical model for evaluating retrieval performance, serving as the benchmark for optimizing cluster numbers in quantization-based indexes. Our algorithm applies iterative local adjustments to the ANNS index being constructed, progressively refining the number of clusters. We demonstrate the efficacy of our approach using the popular inverted index structure in quantization-based ANNS systems. Our findings indicate that: (1) By optimizing the number of clusters, the vanilla inverted index exhibits improved retrieval performance on billion-scale datasets when compared to existing state-of-the-art quantization-based methods;and (2) The additional computational overhead introduced by our optimization algorithm is minimal, even when applied to billion-scale datasets.

关键词： Indexes Vectors Costs clustering algorithms Optimization Databases Task analysis Inverted index billion-scale approximate nearest neighbor search parameter optimization vector quantization

来源：评论

学校读者我要写书评

暂无评论

Online Neural Speaker Diarization With Target Speaker Tracking

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2024年 32卷 5078-5091页

作者： Wang, Weiqing Li, Ming Duke Univ Dept Elect & Comp Engn Durham NC 27708 USA Duke Kunshan Univ Suzhou Municipal Key Lab Multimodal Intelligent Sy Kunshan 215306 Peoples R China

This paper proposes an online target speaker voice activity detection (TS-VAD) system for speaker diarization tasks that does not rely on prior knowledge from clustering-based diarization systems to obtain target speaker embeddings. By adapting conventional TS-VAD for real-time operation, our framework identifies speaker activities using self-generated embeddings, ensuring consistent performance and avoiding permutation inconsistencies during inference. In the inference phase, we employ a front-end model to extract frame-level speaker embeddings for each incoming signal block. Subsequently, we predict each speaker's detection state based on these frame-level embeddings and the previously estimated target speaker embeddings. The target speaker embeddings are then updated by aggregating the frame-level embeddings according to the current block's predictions. Our model predicts results block-by-block and iteratively updates target speaker embeddings until reaching the end of the signal. Experimental results demonstrate that the proposed method outperforms offline clustering-based diarization systems on the DIHARD III and AliMeeting datasets. Additionally, this approach is extended to multi-channel data, achieving comparable performance to state-of-the-art offline diarization systems.

关键词： Voice activity detection clustering algorithms Acoustics Real-time systems Vectors Speech enhancement Training Target tracking Low latency communication Automatic speech recognition Speaker diarization online speaker diarization target speaker voice activity detection

来源：评论

学校读者我要写书评

暂无评论

BiG-Fed: Bilevel Optimization Enhanced Graph-Aided Federated Learning

引用

IEEE TRANSACTIONS ON BIG DATA 2024年第6期10卷 903-914页

作者： Xing, Pengwei Lu, Songtao Wu, Lingfei Yu, Han Nanyang Technol Univ Sch Comp Sci & Engn Singapore 639798 Singapore IBM Thomas J Watson Res Ctr Yorktown Hts NY 10562 USA JD Silicon Valley Res Ctr Mountain View CA 94043 USA

In federated learning (FL), due to the non-i.i.d. nature of distributedly owned local datasets, personalization is an important design goal. In this paper, we investigate FL scenarios in which data owners are related by a network topology (e.g., traffic prediction based on sensor networks). Existing personalized FL approaches cannot take this information into account. To address this limitation, we propose the Bilevel Optimization enhanced Graph-aided Federated Learning (BiG-Fed) approach. The inner weights enable local tasks to evolve towards personalization, and the outer shared weights on the server side target the non-i.i.d problem enabling individual tasks to evolve towards a global constraint space. To the best of our knowledge, BiG-Fed is the first bilevel optimization technique to enable FL approaches to cope with two nested optimization tasks at the FL server and FL clients simultaneously. Theoretical analysis shows that BiG-Fed is guaranteed to converge in an efficient manner. Extensive experiments on both synthetic and real-world data demonstrate significant superior performance of BiG-Fed over seven state-of-the-art methods.

关键词： Task analysis Optimization Servers Collaborative work Jacobian matrices Data models clustering algorithms Bilevel optimization federated learning graph neural networks

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：