Journal of IKEEE (전기전자학회논문지)

Institute of Korean Electrical and Electronics Engineers (한국전기전자학회)
권호 표지
DOI QR코드

DOI QR Code

Anomaly Data Detection Using Machine Learning in Crowdsensing System

크라우드센싱 시스템에서 머신러닝을 이용한 이상데이터 탐지

  • Kim, Mihui (School of Comp. Eng. & Applied Math., Computer System Institute, Hankyong National University) ;
  • Lee, Gihun (School of Comp. Eng. & Applied Math., Computer System Institute, Hankyong National University)
  • Received : 2020.06.01
  • Accepted : 2020.06.23
  • Published : 2020.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, a crowdsensing system that provides a new sensing service with real-time sensing data provided from a user's device including a sensor without installing a separate sensor has attracted attention. In the crowdsensing system, meaningless data may be provided due to a user's operation error or communication problem, or false data may be provided to obtain compensation. Therefore, the detection and removal of the abnormal data determines the quality of the crowdsensing service. The proposed methods in the past to detect these anomalies are not efficient for the fast-changing environment of crowdsensing. This paper proposes an anomaly data detection method by extracting the characteristics of continuously and rapidly changing sensing data environment by using machine learning technology and modeling it with an appropriate algorithm. We show the performance and feasibility of the proposed system using deep learning binary classification model of supervised learning and autoencoder model of unsupervised learning.

최근, 별도의 센서를 설치하지 않고 센서가 포함된 사용자의 기기로부터 제공되는 실시간 센싱 데이터를 가지고 새로운 센싱 서비스를 제공하는 크라우드센싱(Crowdsensing) 시스템이 주목받고 있다. 크라우드센싱 시스템에서는 사용자의 조작실수나 통신 문제로 인해 의미 없는 데이터가 제공되거나 보상을 얻기 위해 거짓 데이터를 제공할 수 있어 해당 이상 데이터의 탐지 및 제거가 크라우드센싱 서비스의 질을 결정짓는다. 이러한 이상데이터를 탐지하기 위해 제안되었던 방법들은 크라우드센싱의 빠른 변화 환경에 효율적이지 않다. 본 논문은 머신러닝 기술을 활용하여 지속적이고 빠르게 변화하는 센싱 데이터의 특징을 추출하고 적절한 알고리즘을 통해 모델링하여 이상데이터를 탐지하는 방법을 제안한다. 지도학습의 딥러닝 이진 분류 모델과 비지도학습의 오토인코더 모델을 사용하여 제안 시스템의 성능 및 실현 가능성을 보인다.

Keywords

References

  1. R. Ganti, F. Ye and H. Lei, "Mobile Crowdsensing-Current State and Future Challenges," IEEE Communications Magazine, vo.49, no.11, pp.32-39, Nov. 2011. https://doi.org/10.1109/MCOM.2011.6069707
  2. B. Guo, Z. Yu, X. Zhou and D. Zhang, "From Participatory Sensing to Mobile Crowd Sensing," in Proc. of the 2014 IEEE International Conference on Pervasive Computing and Communication Workshops (PERCOM WORKSHOPS), pp.593-598, 2014.
  3. Y. J. Kim, Y. Y. He and J. K. Park, "Efficient Anomaly Detection Through Confidence Interval Estimation Based on Time Series Analysis," The Journal of Korean Institute of Communications and Information Sciences, vo.39, no.1, pp.708-715, Aug. 2014.
  4. S. Suthaharan, C. Leckie, M. Moshtaghi and S. Karunasekera, "Sensor data boundary estimation for anomaly detection in wireless sensor networks," in Proc. of the IEEE International Conference on Mobile Ad-hoc and Sensor Systems (IEEE MASS), 2010, pp.546-551.
  5. A. Chirayil, R. Maharjan and C. Sehwu "Survey on Anomaly Detection in Wireless Sensor Networks (WSNs)," in Proc. of the IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD), 2019, pp.150-157.
  6. M. Musthag, A. Raij, D. Ganesan, S. Kumar and S. Shiffman, "Exploring micro-incentive strategies for participant compensation in high-burden studies," in Proc. of the Proceedings of the 13th international conference on Ubiquitous computing, 2011, pp.435-444.
  7. D. Chatzopoulos, S. Gujar, B. Faltings and P. Hui, "Privacy Preserving and Cost Optimal Mobile Crowdsensing Using Smart Contracts on Blockchain," in Proc. of the 2018 IEEE 15th International Conference on Mobile Ad Hoc and Sensor Systems (MASS), 2018, pp.442-450.
  8. S. H. Kwan, M. J. Ahnn and H. C. Lee, "Fault Detection and Classification of Process Cycle Signals using Density-based Clustering and Deep Learning," Korean Institute of Industrial Engineers, vo.44, no.6, pp.475-482, Dec. 2018. https://doi.org/10.7232/JKIIE.2018.44.6.475
  9. A. Truong, A. Walters and J. Goodsitt, "Towards Automated Machine Learning: Evaluation and Comparison of AutoML Approaches and Tools," in Proc. of the IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI), 2019, pp.1471-1479.
  10. L. Klopfenstein, S. Delpriori, P. Polidori and A. Sergiacomi, "Mobile crowdsensing for road sustainability: exploitability of publicly-sourced data," International Review of Applied Economics, vo.0, no.0, pp.1-22, Jul. 2019.
  11. L. Buczak and E. Guven, "A Survey of Data Mining and Machine Learning Methods for Cyber Security Intrusion Detection," IEEE Communications Surveys & Tutorials, vo.18, no.0, pp.1153-1176, Oct. 2015. https://doi.org/10.1109/COMST.2015.2494502
  12. D. Bui, D. K. Nguyen and T. D. Ngo, "Supervising an Unsupervised Neural Network," in Proc. of the First Asian Conference on Intelligent Information and Database Systems, 2019, pp.307-312.
  13. Y. Sani, A. Mohamedou and K. Ali, "An overview of neural networks use in anomaly Intrusion Detection Systems," in Proc. of the IEEE Student Conference on Research and Development (SCOReD), 2009, pp.89-92.
  14. B. K. Ko and J. G. Back, "Anomaly Detection With Variational Autoencoder To Prevent System Malfunctions," Korean Institute of Industrial Engineers, vo.0, no.6, pp.537-557, Nov. 2018.
  15. H. Cai, J. Lin, Y. Lin and Z. Liu, "AutoML for Architecting Efficient and Specialized Neural Networks," IEEE Micro, vo.40, no.1, pp.75-82, Jan. 2020. https://doi.org/10.1109/mm.2019.2953153
  16. C. Wendl, D. Marcos and D. Tuia, "Novelty detection in very high resolution urban scenes with Density Forests", Joint Urban Remote Sensing Event (JURSE), vo.0, no.0, pp.1-4, Aug. 2019.
  17. A. Goldbloom, "Kaggle", https://www.kaggle.com/