基于模糊邻近关系挖掘含主导特征的空间并置模式
Mining Spatial Collocation Patterns with Dominant Features Based on Fuzzy Neighborhood Relationship
摘要: 空间并置(co-location)模式挖掘旨在发现空间中频繁在一起出现的空间特征的子集。空间并置模式中有一类模式其特征的地位是不平等，发现含主导特征的并置模式可以为实际应用提供更为精准的决策支持。由于单一的邻近距离阈值判定两个空间实例间的邻近性会导致邻近关系的缺失，因此，本文首先定义空间实例间的模糊邻近关系，然后定义模式中特征的模糊影响度和模糊影响比识别含主导特征的并置模式；其次，提出基于模糊邻近关系的含主导特征的并置模式挖掘算法及算法优化策略；最后，在合成数据集和真实数据集上验证了算法的正确性和有效性，并在真实数据集上对挖掘结果的实用性进行了比较和分析。
Abstract: Spatial colocation pattern mining aims at mining the collection of spatial features that are frequently occurring together in a space. There is a kind of pattern in spatial colocation patterns whose feature position is inequality. Finding colocation patterns with dominant features can provide more accurate decision support for practical applications. A single distance threshold determines the neighborhood relationship between two spatial instances could lead to a lack of the neighborhood relationship. So, firstly, a fuzzy neighbor relation between spatial instances is defined, and then the fuzzy influence degree and influence ratio of the features in a colocation pattern are defined to identify the colocation pattern with dominant features. Secondly, based on fuzzy neighborhood relationship, a mining algorithm and an optimization strategy of colocation patterns with dominant features are proposed. Finally, the correctness and effectiveness of the algorithm are verified on the synthetic and real data sets, and the practicability of mining results on the real data sets is compared and analyzed.
文章引用：冯时, 王丽珍, 方圆. 基于模糊邻近关系挖掘含主导特征的空间并置模式[J]. 计算机科学与应用, 2021, 11(1): 176-194. https://doi.org/10.12677/CSA.2021.111019

参考文献

[1] Akbari, M., Samadzadegan, F. and Weibel, R. (2015) A Generic Regional Spatio-Temporal Co-Occurrence Pattern Min-ing Model: A Case Study for Air Pollution. Journal of Geographical Systems, 17, 249-274. [Google Scholar] [CrossRef] 
[2] Yu, W., Ai, T., He, Y., et al. (2017) Spatial Co-Location Pattern Mining of Facility Points-of-Interest Improved by Network Neighborhood and Distance Decay Effects. International Journal of Geographical Information Science, 31, 280-296. [Google Scholar] [CrossRef] 
[3] An, S., Yang, H.Q., Wang, J., et al. (2016) Mining Urban Recurrent Congestion Evolution Patterns from GPS Equipped Vehicle Mobility Data. Information Sciences, 373, 515-526. [Google Scholar] [CrossRef] 
[4] Wang, L.Z. and Chen, H.M. (2014) Spatial Pattern Mining Theory and Methods. Science Press, Beijing, 2-4.
[5] Fang, Y., Wang, L.Z., Wang, X.X., et al. (2017) Mining Co-Location Patterns with Dominant Features. In: International Conference on Web Information Systems Engineering, Springer, Cham, 183-198. [Google Scholar] [CrossRef] 
[6] Wang, L.Z., Bao, X.G., Zhou, L.H., et al. (2017) Maximal Sub Prevalent Co-Location Patterns and Efficient Mining Algorithms. In: International Conference on Web Information Systems Engineering, Springer, Cham, 199-214. [Google Scholar] [CrossRef] 
[7] Wang, L.Z., Bao, X.G., Zhou, L.H., et al. (2019) Mining Maximal Sub Prevalent Co-Location Patterns. World Wide Web, 22, 1971-1997. [Google Scholar] [CrossRef] 
[8] Huang, Y., Shekhar, S. and Xiong, H. (2004) Discovering Co-Location Patterns from Spatial Data Sets: A General Approach. IEEE Transaction s on Knowledge and Data Engi-neering, 16, 1472-1485. [Google Scholar] [CrossRef] 
[9] Yoo, J.S., Shekhar, S., Smith, J., et al. (2004) A Partial Join Approach for Mining Co-Location Patterns. Proceedings of the 12th Annual ACM International Workshop on Geographic Infor-mation Systems, Arlington, 12-13 November 2004, 241-249. [Google Scholar] [CrossRef] 
[10] Yoo, J.S., Shekhar, S. and Celik, M. (2005) A Join-Less Approach for Co-Location Pattern Mining: A Summary of Results. Proceedings of the 5th IEEE International Conference on Data Mining (ICDM), Houston, 27-30 November 2005, 813-816.
[11] Wang, L.Z., Bao, Y., Lu, J.L., et al. (2008) A New Join-Less Approach for Co-Location Pattern Mining. 2008 8th IEEE International Conference on Computer and Information Technology, Sydney, 8-11 July 2008, 197-202.
[12] Wang, L.Z., Bao, Y. and Lu, Z. (2009) Efficient Discovery of Spatial Co-Location Patterns Using the ICPI-Tree. The Open Information Systems Journal, 3, 69-80. [Google Scholar] [CrossRef] 
[13] Wang, L.Z., Zhou, L.H., Lu, J.L., et al. (2009) An Or-der-Clique-Based Approach for Mining Maximal Co-Locations. Information Sciences, 179, 3370-3382. [Google Scholar] [CrossRef] 
[14] Wang, L.Z., Chen, H.M., Zhao, L., et al. (2010) Efficiently Mining Co-Location Rules on Interval Data. In: International Conference on Advanced Data Mining and Applications, Springer, Berlin, 477-488. [Google Scholar] [CrossRef] 
[15] Lu, Y., Wang, L.Z. and Zhang, X.F. (2009) Mining Frequent Co-Location Patterns from Uncertain Data. Journal of Frontiers of Computer Science and Technology, 3, 656-664.
[16] Wang, L.Z., Wu, P. and Chen, H.M. (2013) Finding Probabilistic Prevalent Co-Locations in Spatially Uncertain Data Sets. IEEE Transactions on Knowledge and Data Engineering, 25, 790-804. [Google Scholar] [CrossRef] 
[17] Huang, Y., Pei, J. and Xiong, H. (2006) Mining Co-Location Pat-terns with Rare Events from Spatial Data Sets. Geoinformatica, 10, 239-260. [Google Scholar] [CrossRef] 
[18] Feng, L., Wang, L.Z. and Gao, S.J. (2012) A New Approach of Mining Co-Location Patterns in Spatial Datasets with Rare Features. Journal of Nanjing University (Natural Sciences), 48, 99-107.
[19] Ouyang, Z.P., Wang, L.Z. and Chen, H.M. (2011) Mining Spatial Co-Location Patterns for Fuzzy Ob-jects. Chinese Journal of Computers, 34, 1947-1955. [Google Scholar] [CrossRef] 
[20] Fang, Y., Wang, L.Z. and Hu, T. (2018) Spatial Co-Location Pattern Mining Based on Density Peaks Clustering and Fuzzy Theory. In: Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data, Springer, Cham, 298-305. [Google Scholar] [CrossRef] 
[21] Fang, Y., Wang, L.Z. and Zhou, L.H. (2016) Research on Mining Significant Co-Location Pattern with Key Features. Data Acquisition and Processing, 33, 692-703.
[22] Ma, D., Chen, H.M., Wang, L.Z. and Xiao, Q. (2020) Dominant Feature Mining of Spa-tial Sub-Prevalent Co-Location Patterns. Journal of Computer Applications, 40, 465-472.
[23] Lei, L., Wang, L.Z. and Xiao, Q. (2019) Study on Fuzzy Mining Technology in Spatial Co-Location Pattern Mining. CEA, 55, 158-166.
[24] Wang, X.X., Wang, L.Z. and Wang, J.L. (2020) Mining Spatio-Temporal Co-Location Fuzzy Congestion Patterns from Traffic Datasets. Journal of Tsinghua University (Science and Technology), 60, 683-692.
[25] Lei, L., Wang, L.Z. and Wang, X.X. (2019) Mining Spatial Co-Location Patterns by Fuzzy Technology. Proceedings of the 2019 IEEE International Conference on Big Knowledge (ICBK), Beijing, 10-11 November 2019, 129-136. [Google Scholar] [CrossRef]