Spatio-Temporal Graph-Based Association Rule Mining Method for Anomaly Node in Internet of Vehicle

Yangmei Zhang; Zixuan Wang

doi:10.54097/tyh36r80

Authors

Yangmei Zhang
Zixuan Wang

DOI:

https://doi.org/10.54097/tyh36r80

Keywords:

Internet of Vehicles, Spatio-Temporal Features, Association Rule, Communication Behavior, Anomaly Node

Abstract

Abnormal behaviors in the Internet of Vehicles often manifest as sudden changes in communication behavior, abnormal fluctuations in communication volume, and other irregular variations. These anomalies may be signs of a cyberattack, such as attackers attempting to disrupt normal commu-nication between vehicles by severing connections, establishing unauthorized communication links, or sending a massive amount of data packets to exhaust resources or isolate specific nodes. Traditional association rule methods struggle to handle the complex spatio-temporal characteristics, large-scale datasets, and the dynamic communication behavior among vehicle nodes that change over temporal and spatial. This study introduces spatio-temporal features to capture the communication behavior of vehicles as they vary across temporal and spatial, proposes an association rule mining algorithm based on spatio-temporal graphs, which deeply combines the spatio-temporal features of the Internet of Vehicles, such as location, time, communication behavior, and communication volume, to precisely track and analyze changes in vehicle node communication with the goal of identifying anomalous behavior nodes. Utilizing spatio-temporal graph-based association rule mining technology reveals nodes with anomalous behaviors characterized by frequent communication and dramatic increases in communication volume. The algorithm is designed in two steps: discovering frequent rules and verifying the credibility of these rules. Thanks to the adoption of connection and elimination strategies, this algorithm demonstrates the efficiency and accuracy in rule mining sought after in the field. Compared to traditional methods, our proposed mining algorithm shows significant improvements in mining time and the accuracy of the number of rules mined, especially displaying a remarkable advantage in handling the complex spatio-temporal characteristics of the Internet of Vehicles.

Downloads

Download data is not yet available.

References

[1] Baofeng Ji, Xueru Zhang, Shahid Mumtaz, Congzheng Han, Chunguo Li, Hong Wen, and Dan Wang. Survey on the internet of vehicles: Network architectures and applications. IEEE Communications Stan- dards Magazine, 4(1):34–41, 2020.

[2] Suvendu Kumar Nayak and Ananta Charan Ojha. Data leakage detection and prevention: Review and research directions. Machine Learning and Information Processing: Proceedings of ICMLIP 2019, pages 203–212, 2020.

[3] Chun-yan Zhang, Lin Zhao, Haotian Zhang, Meng-na Chen, Ru-yao Fang, Ying Yao, Qi-peng Zhang, and Qian Wang. Spatial-temporal characteristics of carbon emissions from land use change in yellow river delta region, china. Ecological Indicators, 136:108623, 2022.

[4] Fei Xiang, Xiaorong Wang, Xinliang He, Zhenghong Peng, Bohan Yang, Jianchu Zhang, Qiong Zhou, Hong Ye, Yanling Ma, Hui Li, et al. Antibody detection and dynamic characteristics in patients with coronavirus disease 2019. Clinical Infectious Diseases, 71(8):1930– 1934, 2020.

[5] Gowtham Atluri, Anuj Karpatne, and Vipin Kumar. Spatio-temporal data mining: A survey of problems and methods. ACM Computing Surveys (CSUR), 51(4):1–41, 2018.

[6] Qiwei Ma, Wei Sun, Junbo Gao, Pengwei Ma, and Mengjie Shi. Spatio-temporal adaptive graph convolutional networks for traffic flow forecasting. IET Intelligent Transport Systems, 17(4): 691–703, 2023.

[7] Zheyi Pan, Songyu Ke, Xiaodu Yang, Yuxuan Liang, Yong Yu, Junbo Zhang, and Yu Zheng. Autostg: Neural architecture search for predictions of spatio-temporal graph. In Proceedings of the Web Conference 2021, pages 1846–1855, 2021.

[8] Lubna Fayez Eliyan and Roberto Di Pietro. Dos and ddos attacks in software defined networks: A survey of existing solutions and research challenges. Future Generation Computer Systems, 122:149– 171, 2021.

[9] HN Lakshmi, Santosh Anand, and Somnath Sinha. Flooding attack in wireless sensor network-analysis and prevention. International Journal of Engineering and Advanced Technology, 8(5):1792–1796, 2019.

[10] Xiaoyan Liu, Feng Feng, Qian Wang, Ronald R Yager, Hamido Fujita, and José Carlos R Alcantud. Mining temporal association rules with temporal soft sets. Journal of Mathematics, 2021:1–17, 2021.

[11] Xubo Du and Fusheng Yu. A fast algorithm for mining temporal association rules in a multi-attributed graph sequence. Expert Systems with Applications, 192:116390, 2022.

[12] Rakesh Agrawal, Tomasz Imieliński, and Arun Swami. Mining asso- ciation rules between sets of items in large databases. In Proceedings of the 1993 ACM SIGMOD international conference on Management of data, pages 207–216, 1993.

[13] Akbar Telikani, Amir H Gandomi, and Asadollah Shahbahrami. A survey of evolutionary computation for association rule mining. Information Sciences, 524:318–352, 2020.

[14] Federico Antonello, Piero Baraldi, Ahmed Shokry, Enrico Zio, Ugo Gentile, and Luigi Serio. A novel association rule mining method for the identification of rare functional dependencies in complex technical infrastructures from alarm data. Expert Systems with Applications, 170:114560, 2021.

[15] Akash Saxena and Vikram Rajpoot. A comparative analysis of asso- ciation rule mining algorithms. In IOP conference series: materials science and engineering, volume 1099, page 012032. IOP Publishing, 2021.

[16] Degan Zhang, Hui Ge, Ting Zhang, Yu-Ya Cui, Xiaohuan Liu, and Guoqiang Mao. New multi-hop clustering algorithm for vehicular ad hoc networks. IEEE Transactions on Intelligent Transportation Systems, 20(4):1517–1530, 2018.

[17] Yi Zhao. Discovery of temporal association rules in multivariate time series, 2017.

[18] Adnan Ozden, F Pelayo García de Arquer, Jianan Erick Huang, Joshua Wicks, Jared Sisler, Rui Kai Miao, Colin P O’Brien, Geonhui Lee, Xue Wang, Alexander H Ip, et al. Carbon-efficient carbon dioxide electrolysers. Nature Sustainability, 5(7):563–573, 2022.

[19] Mahmoud Nasr, Mohamed Hamdy, Doaa Hegazy, and Khaled Bah- nasy. An efficient algorithm for unique class association rule mining. Expert Systems with Applications, 164:113978, 2021.

[20] DongYue Liu, Bin Wu, Chao Gu, Yan Ma, and Bai Wang. A multidi- mensional time-series association rules algorithm based on spark. In 2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), pages 1946–1952. IEEE, 2017.

[21] Li Zhan, Fusheng Yu, and Huixin Zhang. A fast algorithm for mining temporal association rules based on a new definition. In 2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), pages 1548–1553. IEEE, 2017.

[22] Xin Wang, Yang Xu, and Huayi Zhan. Extending association rules with graph patterns. Expert Systems with Applications, 141:112897, 2020.

[23] De-Gan Zhang, Wen-Miao Dong, Ting Zhang, Jie Zhang, Ping Zhang, Gui-Xiang Sun, and Ya-Hui Cao. New computing tasks offloading method for mec based on prospect theory framework. IEEE Transac- tions on Computational Social Systems, 2022.

[24] De-Gan Zhang, Chen-Hao Ni, Jie Zhang, Ting Zhang, and Zhi-Hao Zhang. New method of vehicle cooperative communication based on fuzzy logic and signaling game strategy. Future Generation Computer Systems, 142:131–149, 2023.

[25] Degan Zhang, Wenjing Wang, Jie Zhang, Ting Zhang, Jinyu Du, and Chun Yang. Novel edge caching approach based on multi-agent deep reinforcement learning for internet of vehicles. IEEE Transactions on Intelligent Transportation Systems, 2023.

[26] Degan Zhang, Guang Li, Ke Zheng, Xuechao Ming, and Zhao-Hua Pan. An energy-balanced routing method based on forward-aware factor for wireless sensor networks. IEEE transactions on industrial informatics, 10(1):766–773, 2013.

[27] Vandana Bhatia and Rinkle Rani. Ap-fsm: A parallel algorithm for approximate frequent subgraph mining using pregel. Expert Systems with Applications, 106:217–232, 2018.

[28] Sidali Hocine Farhi and Dalila Boughaci. Two bi-objective hybrid approaches for the frequent subgraph mining problem. Applied Soft Computing, 72:291–297, 2018.

[29] Vijay Ingalalli, Dino Ienco, and Pascal Poncelet. Mining frequent subgraphs in multigraphs. Information Sciences, 451:50–66, 2018.

[30] Mostafa Haghir Chehreghani. Dynamical algorithms for data mining and machine learning over dynamic graphs. Wiley Interdisciplinary Reviews: Data Mining And Knowledge Discovery, 11(2): e1393, 2021.

[31] Sofia Fernandes, Hadi Fanaee-T, and João Gama. Dynamic graph summarization: a tensor decomposition approach. Data Mining and Knowledge Discovery, 32:1397–1420, 2018.

[32] Angelo Impedovo, Corrado Loglisci, Michelangelo Ceci, and Donato Malerba. Condensed representations of changes in dynamic graphs through emerging subgraph mining. Engineering Applications of Artificial Intelligence, 94:103830, 2020.

[33] Sajal Halder, Md Samiullah, and Young-Koo Lee. Supergraph based periodic pattern mining in dynamic social networks. Expert Systems with Applications, 72:430–442, 2017.

[34] Pietro Daverio, Hassan Nazeer Chaudhry, Alessandro Margara, and Matteo Rossi. Temporal pattern recognition in graph data structures. In 2021 IEEE International conference on big data (Big Data), pages 2753–2763. IEEE, 2021.

[35] Yan Li, Shuai Zhang, Lei Guo, Jing Liu, Youxi Wu, and Xindong Wu. Netnmsp: Nonoverlapping maximal sequential pattern mining. Applied Intelligence, pages 1–24, 2022.

[36] Xin Wang and Yang Xu. Mining graph pattern association rules. In International Conference on Database and Expert Systems Applica- tions, pages 223–235. Springer, 2018.

[37] Amol Kapoor, Xue Ben, Luyang Liu, Bryan Perozzi, Matt Barnes, Martin Blais, and Shawn O’Banion. Examining covid-19 forecast- ing using spatio-temporal graph neural networks. arXiv preprint arXiv:2007.03113, 2020.

[38] Xianglong Luo, Wenjuan Gan, Lixin Wang, Yonghong Chen, and Xue Meng. A prediction model of structural settlement based on emd-svr- wnn. Advances in Civil Engineering, 2020: 1–11, 2020.

[39] Bao Huynh, Lam BQ Nguyen, Duc HM Nguyen, Ngoc Thanh Nguyen, Hung-Son Nguyen, Tuyn Pham, Tri Pham, Loan TT Nguyen, Trinh DD Nguyen, and Bay Vo. Mining association rules from a single large graph. Cybernetics and Systems, 55(3):693–707, 2024.

[40] Tongtong Su, Huazhi Sun, Jinqi Zhu, Sheng Wang, and Yabo Li. Bat: Deep learning methods on network intrusion detection using nsl-kdd dataset. IEEE Access, 8:29575–29585, 2020.

[41] De-gan Zhang, Yu-ya Cui, and Ting Zhang. New quantum-genetic based olsr protocol (qg-olsr) for mobile ad hoc network. Applied Soft Computing, 80:285–296, 2019.

[42] Degan Zhang, Zhihao Zhang, Jie Zhang, Ting Zhang, Lei Zhang, and Hongtao Chen. Uav-assisted task offloading system using dung beetle optimization algorithm & deep reinforcement learning. Ad Hoc Networks, page 103434, 2024.

[43] Ting Zhang, De-gan Zhang, Hao-ran Yan, Jian-ning Qiu, and Jin- xin Gao. A new method of data missing estimation with fnn- based tensor heterogeneous ensemble learning for internet of vehicle. Neurocomputing, 420:98–110, 2021.