[1]赵嘉,李辉,肖人彬,等.相对密度和马氏距离的时空密度峰值聚类算法[J].智能系统学报,2026,21(5):1335-1347.[doi:10.11992/tis.202511002]
ZHAO Jia,LI Hui,XIAO Renbin,et al.Spatial-temporal density peaks clustering algorithm with relative density and mahalanobis distance[J].CAAI transactions on intelligent systems,2026,21(5):1335-1347.[doi:10.11992/tis.202511002]
点击复制
ZHAO Jia,LI Hui,XIAO Renbin,et al.Spatial-temporal density peaks clustering algorithm with relative density and mahalanobis distance[J].CAAI transactions on intelligent systems,2026,21(5):1335-1347.[doi:10.11992/tis.202511002]
相对密度和马氏距离的时空密度峰值聚类算法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
21
期数:
2026年第5期
页码:
1335-1347
栏目:
学术论文—智能系统
出版日期:
2026-09-05
- Title:
- Spatial-temporal density peaks clustering algorithm with relative density and mahalanobis distance
- Keywords:
- spatial-temporal clustering; density peak; clustering algorithm; spatial-temporal nearest neighbors; relative density; Mahalanobis distance; local density; relative distance
- 分类号:
- TP181
- 摘要:
- 快速搜索密度峰值的时空聚类(spatial-temporal clustering by fast search and find of density peaks, ST-CFSFDP)算法在处理时空数据时未充分考虑样本间密度差异，导致样本的局部密度不能正确反映样本的密度分布；通过欧氏距离计算样本的相对距离，无法将时间邻近的簇进行区分。针对以上问题，提出相对密度和马氏距离的时空密度峰值聚类(spatial-temporal density peaks clustering algorithm with relative density and mahalanobis distance, ST-DPC-RDMD)算法。ST-DPC-RDMD算法在局部密度中引入时空近邻概念，并结合相对密度思想重新定义样本局部密度，提高近邻样本的影响程度；使用空间与时间属性的马氏距离替代欧氏距离，综合分析各维度的协方差关系实现空间与时间距离权重的合理分配，以准确识别具有特征差异的簇。在模拟数据集和真实地震数据集上的实验结果表明，ST-DPC-RDMD算法的聚类效果优势显著。
- Abstract:
- The spatial-temporal clustering by fast search and find of density peaks (ST-CFSFDP) fails to fully consider density differences among samples when processing spatial-temporal data, resulting in the inability of sample local density to accurately reflect density distribution. Additionally, using Euclidean distance to calculate relative distances between samples prevents the differentiation of clusters that are temporally adjacent but spatially distinct. To address these issues, a spatial-temporal density peaks clustering algorithm with relative density and Mahalanobis distance (ST-DPC-RDMD) is proposed. The ST-DPC-RDMD algorithm introduces the concept of spatial-temporal nearest neighbors into local density and redefines sample local density by incorporating the idea of relative density, thereby enhancing the influence of neighboring samples, amplifying the local density of samples in sparse clusters, and reducing the impact of inter-cluster density heterogeneity. It replaces Euclidean distance with Mahalanobis distance for spatial and temporal attributes, comprehensively analyzing covariance relationships across various dimensions to achieve a reasonable allocation of weights between spatial and temporal distances, thus accurately identifying clusters with characteristic differences. Experimental results on simulated datasets and real earthquake datasets demonstrate that the ST-DPC-RDMD algorithm exhibits significant advantages in clustering performance.
- 参考文献/References:
-
[1] SCHWYCK M E, DU Meng, LI Yuchen, et al. Similarity among friends serves as a social prior: the assumption that “birds of a feather flock together” shapes social decisions and relationship beliefs[J]. Personality & social psychology bulletin, 2024, 50(6): 823-840
[2] 张远鹏, 周洁, 邓赵红, 等. 代表点一致性约束的多视角模糊聚类算法[J]. 软件学报, 2019, 30(2): 282-301 ZHANG Yuanpeng, ZHOU Jie, DENG Zhaohong, et al. Multi-view fuzzy clustering approach based on medoid invariant constraint[J]. Journal of software, 2019, 30(2): 282-301
[3] 吕莉, 朱梅子, 康平, 等. 面向密度分布不均数据的混合近邻密度峰值聚类算法[J]. 控制理论与应用, 2024, 41(10): 1821-1830 L? Li, ZHU Meizi, KANG Ping, et al. Multiplex neighbor density peaks clustering for uneven density data sets[J]. Control theory & applications, 2024, 41(10): 1821-1830
[4] 李智冈, 吕莉, 谭德坤, 等. 基于加权核密度估计与微簇合并的密度峰值聚类算法[J]. 信息与控制, 2024, 53(3): 302-314 LI Zhigang, L? Li, TAN Dekun, et al. Density peaks clustering algorithm based on weighted kernel density estimation and micro-cluster merging[J]. Information and control, 2024, 53(3): 302-314
[5] JAIN A K. Data clustering: 50 years beyond K-means[J]. Pattern recognition letters, 2010, 31(8): 651-666
[6] SINGH J, SINGH D. A comprehensive review of clustering techniques in artificial intelligence for knowledge discovery: Taxonomy, challenges, applications and future prospects[J]. Advanced engineering informatics, 2024, 62: 102799
[7] AHMED U, NAZIR M, SARWAR A, et al. Signature-based intrusion detection using machine learning and deep learning approaches empowered with fuzzy clustering[J]. Scientific reports, 2025, 15: 1726
[8] WANG Nian, CUI Zhigao, LI Aihua, et al. Structured doubly stochastic graph-based clustering[J]. IEEE transactions on neural networks and learning systems, 2025, 36(6): 11064-11077
[9] THAKUR J, KUSHWAHA B P. Artificial intelligence in marketing research and future research directions: Science mapping and research clustering using bibliometric analysis[J]. Global business and organizational excellence, 2024, 43(3): 139-155
[10] RODRIGUEZ A, LAIO A. Clustering by fast search and find of density peaks[J]. Science, 2014, 344(6191): 1492-1496
[11] ZHAO Jia, WANG Gang, PAN J S, et al. Density peaks clustering algorithm based on fuzzy and weighted shared neighbor for uneven density datasets[J]. Pattern recognition, 2023, 139: 109406
[12] LI Qingpeng, HU Xinyue, ZHAO Jia, et al. Density peak clustering algorithm based on shared neighbors and natural neighbors and analysis of electricity consumption patterns[J]. Concurrency and computation: practice and experience, 2025, 37(3): e8387
[13] 陈芳淼, 黄慧萍, 贾坤. 时空大数据在城市群建设与管理中的应用研究进展[J]. 地球信息科学学报, 2020, 22(6): 1307-1319 CHEN Fangmiao, HUANG Huiping, JIA Kun. Study on the administration and construction of urban agglomeration with spatiotemporal big data: a progress review[J]. Journal of geo-information science, 2020, 22(6): 1307-1319
[14] YOO M, KOO H. Exploring the impact of spatial autocorrelation on optimistic bias in cross-validation and assessing the effectiveness of spatial cross-validation[J]. Cartography and geographic information science, 2025, 52(5): 596-609
[15] HUANG Ruixi, LONG Yin, ZIA T. A physical-enhanced spatio-temporal graph convolutional network for river flow prediction[J]. Applied sciences, 2025, 15(16): 9054
[16] TANTOUSH M, SENGUPTA U, HAN Liangxiu. Exploring city dynamics through tweets: a framework for capturing urban activities as complex spatiotemporal patterns[J]. Cities, 2025, 162: 105894
[17] GAETAN C, GIRARDI P, MUSAU V M. Spatial quantile clustering of climate data[J]. Advances in data analysis and classification, 2025, 19(1): 147-175
[18] BUCHDADI A D. Temporal crime pattern analysis using seasonal decomposition and k-means clustering[J]. Journal of cyber law, 2025, 1(1): 65-87
[19] SPERNA WEILAND R, VAN DER WIEL K, SELTEN F, et al. Spatiotemporal clustering of preferred trajectories of the euro-Atlantic summer circulation[J]. Journal of climate, 2025, 38(10): 2435-2459
[20] ANSARI M Y, AHMAD A, KHAN S S, et al. Spatiotemporal clustering: a review[J]. Artificial intelligence review, 2020, 53(4): 2381-2423
[21] CHOI C, HONG S Y. MDST-DBSCAN: a density-based clustering method for multidimensional spatiotemporal data[J]. ISPRS international journal of geo-information, 2021, 10(6): 391
[22] YOU G. Spatiotemporal data-adaptive clustering algorithm: an intelligent computational technique for city big data[J]. Annals of the American association of geographers, 2022, 112(2): 602-619
[23] BIRANT D, KUT A. ST-DBSCAN: an algorithm for clustering spatial–temporal data[J]. Data & knowledge engineering, 2007, 60(1): 208-221
[24] AGRAWAL K P, GARG S, SHARMA S, et al. Development and validation of OPTICS based spatio-temporal clustering technique[J]. Information sciences, 2016, 369: 388-401
[25] ESTER M, KRIEGEL H P, SANDER J, et al. A density-based algorithm for discovering clusters in large spatial databases with noise[C]//Knowledge Discovery and Data Mining. Portland: AAAI Press, 1996: 226-231.
[26] ANKERST M, BREUNIG M M, KRIEGEL H P, et al. OPTICS: ordering points to identify the clustering structure[J]. ACM SIGMOD record, 1999, 28(2): 49-60
[27] 吴文浩, 吴升. 多时间尺度密度聚类算法的案事件分析应用[J]. 地球信息科学学报, 2015, 17(7): 837-845 WU Wenhao, WU Sheng. Application of density-based clustering algorithm in crime cases analysis considering multiple time scale[J]. Journal of geo-information science, 2015, 17(7): 837-845
[28] 王培晓, 张恒才, 王海波, 等. ST-CFSFDP: 快速搜索密度峰值的时空聚类算法[J]. 测绘学报, 2019, 48(11): 1380-1390 WANG Peixiao, ZHANG Hengcai, WANG Haibo, et al. Spatial-temporal clustering by fast search and find of density peaks[J]. Acta geodaetica et cartographica sinica, 2019, 48(11): 1380-1390
[29] 赵嘉, 姚占峰, 吕莉, 等. 基于相互邻近度的密度峰值聚类算法[J]. 控制与决策, 2021, 36(3): 543-552 ZHAO Jia, YAO Zhanfeng, L? Li, et al. Density peaks clustering based on mutual neighbor degree[J]. Control and decision, 2021, 36(3): 543-552
[30] WANG Min, WANG Aiping, LI Anbo. Mining spatial-temporal clusters from geo-databases[C]//Advanced Data Mining and Applications. Berlin: Springer, 2006: 263-270.
[31] 沈江飞, 李怀洲, 黄立军, 等. 基于局部离群因子和神经网络模型的设备状态在线监测方法研究[J]. 核动力工程, 2021, 42(3): 160-165 SHEN Jiangfei, LI Huaizhou, HUANG Lijun, et al. Study on online monitoring of equipment condition based on local outlier factor and artificial neural networks model[J]. Nuclear power engineering, 2021, 42(3): 160-165
[32] 王培晓, 王海波, 傅梦颖, 等. 室内用户语义位置预测研究[J]. 地球信息科学学报, 2018, 20(12): 1689-1698 WANG Peixiao, WANG Haibo, FU Mengying, et al. Research on semantic location prediction of indoor users[J]. Journal of geo-information science, 2018, 20(12): 1689-1698
[33] ZHANG Fengling, HUANG Shengqiang, ZHANG Haiyan, et al. STSNN-DPC: spatio-temporal shared nearest neighbors and density peaks based clustering method[EB/OL]. (2024-11-25)[2026-01-07]. https://doi.org/10.21203/rs.3.rs-5381784/v1.
[34] NGUYEN X V, EPPS J, BAILEY J. Information theoretic measures for clusterings comparison: variants, properties, normalization and correction for chance[J]. J Mach learn res, 2010, 11: 2837-2854
[35] FOWLKES E B, MALLOWS C L. A method for comparing two hierarchical clusterings[J]. Journal of the American statistical association, 1983, 78(383): 553-569
[36] 赵嘉, 王刚, 吕莉, 等. 面向流形数据的测地距离与余弦互逆近邻密度峰值聚类算法[J]. 电子学报, 2022, 50(11): 2730-2737 ZHAO Jia, WANG Gang, L? Li, et al. Density peaks clustering algorithm based on geodesic distance and cosine mutual reverse nearest neighbors for manifold datasets[J]. Acta electronica sinica, 2022, 50(11): 2730-2737
[37] 张建勇, 王新, 陈凌, 等. 2022—2023年四川泸定MS6.8、MS5.0和MS5.6地震序列的发震构造及成因[J]. 地球物理学报, 2024, 67(4): 1471-1486 ZHANG Jianyong, WANG Xin, CHEN Ling, et al. Seismotectonics and seismogenesis of the 2022-2023 Sichuan Luding MS 6.8, MS5.0 and MS5.6 earthquake sequences[J]. Chinese journal of geophysics, 2024, 67(4): 1471-1486
[38] ZHANG Zhe, FANG Lihua, XU Lisheng. Primary source characteristics of the 2022 Sichuan Luding MS 6.8 Earthquake[J]. Chinese journal of geophysics, 2023, 66(4): 1397-1408
- 相似文献/References:
-
[1]赵嘉,马清,肖人彬,等.面向流形数据的共享近邻密度峰值聚类算法[J].智能系统学报,2023,18(4):719.[doi:10.11992/tis.202209026]
ZHAO Jia,MA Qing,XIAO Renbin,et al.Density peaks clustering based on shared nearest neighbor for manifold datasets[J].CAAI transactions on intelligent systems,2023,18():719.[doi:10.11992/tis.202209026]
备注/Memo
收稿日期:2025-11-3。
基金项目:国家自然科学基金项目(62066037).
作者简介:赵嘉，教授，博士生导师，博士，主要研究方向为智能计算与计算智能、模式识别与大数据挖掘。主持国家自然科学基金项目3项，发表学术论文100余篇，出版专著1部。E-mail：zhaojia925@163.com。;李辉，硕士研究生，主要研究方向为数据挖掘。E-mail：lihui66688@126.com。;肖人彬，博士生导师，主要研究方向为群体智能、大规模个性化定制、复杂系统与复杂性科学。主持并承担国家自然科学基金项目11项，作为第一完成人获得教育部自然科学奖1项和湖北省自然科学奖及科技进步奖4项。发表学术论文300余篇，出版学术专著和教材10余部。E-mail：rbxiao@hust.edu.cn。
通讯作者:赵嘉. E-mail：zhaojia925@163.com
更新日期/Last Update:
2026-09-05