Mining Fuzzy Relationship Between Malignant Tumors and Industrial Pollution

doi:10.3778/j.issn.1673-9418.1912024

Abstract

Abstract:

Malignant tumors are one of the serious diseases that endanger human health. The use of data mining techniques to mine the relationship between malignant tumors and various pathogenic factors has been attracted more and more attention. In practice, the relationship between tumor diseases and pathogenic factors is often fuzzy, and the occurrence of tumor diseases is not only affected by a single factor. However, there is no research to address the above problem. For this reason, the concept of fuzzy co-location patterns is proposed that combines the spatial co-location pattern mining with fuzzy theory, and pollution sources are fuzzified by the clustering method. Then, the method of extracting rules from the decision table is adopted to extract rules, and the corresponding confidence calculation algorithm is designed. As a result, a novel method which can discover the fuzzy relationships between tumor diseases and pathogenic factors is proposed. The effectiveness of the proposed method is verified on the actual case, and the effects of different parameters on the running time of the algorithm are analyzed by conducting experiments on synthetic datasets. At last, the theoretical analysis of the time complexity of the proposed algorithm is presented.

Key words: spatial data mining, spatial co-location pattern, fuzzy theory, clustering analysis, rule extraction

摘要：

恶性肿瘤是危害人类健康的重要疾病之一，运用数据挖掘技术挖掘恶性肿瘤与各种致病因素之间的关系受到越来越多的关注。在实际中，肿瘤疾病与致病因素之间的关系往往是模糊的，肿瘤疾病的发生也不只受单一因素的影响，但目前还没有针对上述问题的研究。为此，基于空间共存模式挖掘技术，结合模糊理论，提出了模糊共存模式的概念；运用聚类方法对污染源进行了模糊化处理；在进行规则提取时采用了决策表提取规则的方法，并设计了相应的置信度计算算法；最终提出了一种能够挖掘出多种肿瘤疾病与多种污染源之间模糊关系的新方法。通过在实际案例上的应用验证了提出算法的有效性，通过在合成数据集上的实验分析了不同参数对算法运行时间的影响，并对算法的时间效率进行了理论分析。

关键词: 空间数据挖掘, 空间共存模式, 模糊理论, 聚类分析, 规则提取

CHU Chuanxin, WANG Lizhen, ZHOU Lihua, LI Xuyang. Mining Fuzzy Relationship Between Malignant Tumors and Industrial Pollution[J]. Journal of Frontiers of Computer Science and Technology, 2020, 14(12): 2061-2071.

储传鑫，王丽珍，周丽华，李旭阳. 恶性肿瘤与工业污染之间的模糊关系挖掘[J]. 计算机科学与探索, 2020, 14(12): 2061-2071.

References

[1] Bai H X, Ge Y, Wang J F, et al. Using rough set theory to identify villages affected by birth defects: the example of Heshun, Shanxi, China[J]. International Journal of Geogra-phical Information Science, 2010, 24(4): 559-576.
[2] Bai H X, Ge Y, Wang J F, et al. A method for extracting rules from spatial data based on rough fuzzy sets[J]. Knowledge-Based Systems, 2014, 57(12): 28-40.
[3] Park J V, Park S J, Yoo J S. Finding characteristics of excep-tional breast cancer subpopulations using subgroup mining and statistical test[J]. Expert Systems with Applications, 2019, 118(10): 553-562.
[4] Delgado M, Marin N, Sanches D, et al. Fuzzy association rules general model and applications[J]. IEEE Transactions on Fuzzy Systems, 2003, 11(2): 214-225.
[5] Hong T P, Kuo C S, Chi S C, et al. A fuzzy AprioriTid mining algorithm[J]. International Journal of Mathematics, 2002, 2(11): 1089-1117.
[6] Weng C H, Chen Y L. Mining fuzzy association rules from uncertain data[J]. Knowledge and Information Systems, 2010, 23(2): 129-152.
[7] Rizkallah L W, Hamouda S, Darwish N. FDG-SD: a new hybrid technique for solving subgroup discovery problem[C]//Proceedings of the 5th International Conference on Fuzzy Systems and Data Mining, Kitakyushu City, Oct 18-21, 2019. Amsterdam: IOS Press, 2019: 191-197.
[8] Ouyang Z P, Wang L Z, Wu P P. Spatial co-location pattern discovery from fuzzy objects[J]. International Journal on Artificial Intelligence Tools, 2017, 26(2): 1750003.
[9] Lei L, Wang L Z, Wang X X. Mining spatial co-location pat-terns by fuzzy technology[C]//Proceedings of the 2019 IEEE International Conference on Big Knowledge, Beijing, Nov 10-11, 2019. Piscataway: IEEE, 2019: 129-136.
[10] Wang M J, Wang L Z, Zhao L H. Spatial co-location pattern mining based on fuzzy neighbor relationship[J]. Journal of Information Science and Engineering, 2019, 35(6): 1343-1363.
[11] Wang L Z, Chen H M. Spatial pattern mining[M]. Beijing: Science Press, 2014. 王丽珍, 陈红梅. 空间模式挖掘理论与方法[M]. 北京: 科学出版社, 2014.
[12] Huang Y, Shekhar S, Xiong H. Discovering colocation patterns from spatial data sets: a general approach[J]. IEEE Transactions on Knowledge and Data Engineering, 2004, 16(12): 1472-1485.
[13] Yoo J S, Shekhar S, Smith J, et al. A partial join approach for mining co-location patterns[C]//Proceedings of the 12th ACM International Workshop on Geographic Information Systems, Washington, Nov 12-13, 2004. New York: ACM, 2004: 241-249.
[14] Yoo J S, Shekhar S. A join-less approach for mining spatial co-location patterns[J]. IEEE Transactions on Knowledge and Data Engineering, 2006, 18(10): 1323-1337.
[15] Li J D, Adilmagambetov A, Mohomed Jabbar M S, et al. On discovering co-location patterns in datasets: a case study of pollutants and child cancers[J]. GeoInformatica, 2016, 20(4): 651-692.