The Journal of The Korea Institute of Intelligent Transport Systems (한국ITS학회 논문지)

The Korea Institute of Intelligent Transport Systems (한국ITS학회)
권호 표지
DOI QR코드

DOI QR Code

Research on Driving Pattern Analysis Techniques Using Contrastive Learning Methods

대조학습 방법을 이용한 주행패턴 분석 기법 연구

  • 정회준 (인하대학교 전기컴퓨터공학과) ;
  • 김승하 (인하대학교 컴퓨터공학과) ;
  • 김준희 (인하대학교 통계학과) ;
  • 권장우 (인하대학교 컴퓨터공학과 )
  • Received : 2024.01.10
  • Accepted : 2024.01.22
  • Published : 2024.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

This study introduces driving pattern analysis and change detection methods using smartphone sensors, based on contrastive learning. These methods characterize driving patterns without labeled data, allowing accurate classification with minimal labeling. In addition, they are robust to domain changes, such as different vehicle types. The study also examined the applicability of these methods to smartphones by comparing them with six lightweight deep-learning models. This comparison supported the development of smartphone-based driving pattern analysis and assistance systems, utilizing smartphone sensors and contrastive learning to enhance driving safety and efficiency while reducing the need for extensive labeled data. This research offers a promising avenue for addressing contemporary transportation challenges and advancing intelligent transportation systems.

자동차 보급과 교통 시설 발달로 인한 문제에 대응하여, ADAS와 같은 운전 보조 기술이 주목받고 있다. 최근에는 스마트폰 내장 센서를 사용한 운전패턴 분석 방법론이 개발되었다. 이 연구에서는 레이블 없이 대조학습을 통해 운전패턴의 특징을 학습하고 변화점을 감지하는 새로운 방법을 제안한다. 이 방법은 운전패턴 분류에도 확장 가능하여, 매우 적은 레이블링 데이터만으로 높은 분류 성능을 달성할 수 있음은 물론 적용 차량이 달라지는 도메인 변화 문제에 민감하게 반응하지 않아 일반화된 성능을 달성할 수 있다는 장점을 가지고 있다. 또한 본 연구에서는 추후 스마트폰 적용성을 고려하여 6가지 대표적인 경량화 딥러닝 모델에 대해 제안하는 방법을 적용하고 비교분석하여 추후 스마트폰 기반의 시스템 개발에 활용할 수 있도록 하였다.

Keywords

Acknowledgement

이 논문은 2023년도 정부(산업통상자원부)의 재원으로 한국에너지기술평가원의 지원을 받아 수행된 연구임(20224B10100060, 회전설비 인공지능형 진동 감시 시스템 개발)

References

  1. Adams, R. P. and MacKay, D. J.(2007), Bayesian online changepoint detection, arXiv preprint arXiv:0710.3742.
  2. Bayat, A., Pomplun, M. and Tran, D. A.(2014), "A Study on Human Activity Recognition Using Accelerometer Data from Smartphones", Procedia Computer Science, vol. 34, pp.450-457. https://doi.org/10.1016/j.procs.2014.07.009
  3. Carvalho, E., Ferreira, B. V., Ferreira, J., De Souza, C., Carvalho, H. V., Suhara, Y., Pentland, A. S. and Pessin, G.(2017), "Exploiting the use of recurrent neural networks for driver behavior profiling", 2017 International Joint Conference on Neural Networks(IJCNN), IEEE, pp.3016-3021.
  4. Chen, T., Kornblith, S., Norouzi, M. and Hinton, G.(2020), "A simple framework for contrastive learning of visual representations", International Conference on Machine Learning, PMLR, pp.1597-1607.
  5. Fazeen, M., Gozick, B., Dantu, R., Bhukhiya, M. and Gonzlez, M. C.(2012), "Safe driving using mobile phones", IEEE Transactions on Intelligent Transportation Systems, vol. 13, no. 3, pp.1462-1468. https://doi.org/10.1109/TITS.2012.2187640
  6. Ferreira, J., Carvalho, E., Ferreira, B. V., De Souza, C., Suhara, Y., Pentland, A. and Pessin, G.(2017), "Driver behavior profiling: An investigation with different smartphone sensors and machine learning", PLoS One, vol. 12, no. 4, e0174959.
  7. Grill, J. B., Strub, F., Altch, F., Tallec, C., Richemond, P., Buchatskaya, E., Doersch, C., Pires, B. A., Guo, Z. D., Azar, M. G., Piot, B., Kavukcuoglo, K., Munos, R. and Valko, M.(2020), "Bootstrap your own latent-a new approach to self-supervised learning", Advances in Neural Information Processing Systems, vol. 33, pp.21271-21284.
  8. He, K., Fan, H., Wu, Y., Xie, S. and Girshick, R.(2020) "Momentum contrast for unsupervised visual representation learning", Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.9729-9738.
  9. Hjelm, R. D., Fedorov, A., Lavoie-Marchildon, S., Grewal, K., Bachman, P., Trischler, A. and Bengio, Y.(2018), Learning deep representations by mutual information estimation and maximization, arXiv preprint arXiv:1808.06670.
  10. Johnson, D. A. and Trivedi, M. M.(2011), "Driving style recognition using a smartphone as a sensor platform", Proc 14th International IEEE Conference on Intelligent Transportation Systems(ITSC), Washington, DC, USA, pp.1609-1615.
  11. Kim, D. H., Jang, B. T. and Shine, S. W.(2018), "Trends on Personalization in Advanced Driver Assistance Systems", ETRI Electronics and Telecommunications Trends, vol. 34, no. 4, pp.61-69.
  12. Kim, H. S., Hwang, Y. S., Yoon, D. S., Choi, W. G. and Park, C. H.(2014), "Driver workload characteristics analysis using EEG data from an urban road", IEEE Transactions on Intelligent Transportation Systems, vol. 15, no. 4, pp.1844-1849. https://doi.org/10.1109/TITS.2014.2333750
  13. Lee, S. K.(2012), "Driving Pattern Recognition System Using Smartphone Sensor Stream", Journal of Advanced Information Technology, vol. 17, no. 3, pp.35-42.
  14. Lindow, F., Kaiser, C., Kashevnik, A. and Stocker, A.(2020), "AI-Based Driving Data Analysis for Behavior Recognition in Vehicle Cabin", 2020 27th Conference of Open Innovations Association(FRUCT), Trento, Italy, pp.116-125.
  15. Lu, D. N., Nguyen, D. N., Nguyen, T. H. and Nguyen, H. N.(2018), "Vehicle Mode and Driving Activity Detection Based on Analyzing Sensor Data of Smartphones", Sensors, vol. 18, no. 4, p.1036. doi: 10.3390/s18041036
  16. Malhotra, P., Vig, L., Shroff, G. and Agarwal, P.(2015), "Long Short Term Memory Networks for Anomaly Detection in Time Series", InEsann, vol. 2015, p.89.
  17. Nickel, C., Busch, C., Rangarajan, S. and Mobius, M.(2011), "Using Hidden Markov Models foraccelerometer-based biometric gait recognition", IEEE 7th International Colloquium on Signal Processing and its Applications(CSPA), pp.58-63.
  18. Oord, A. V. D., Li, Y. and Vinyals, O.(2018), Representation learning with contrastive predictive coding, arXiv preprint arXiv:1807.03748.
  19. Page, E. S.(1954), "Continuous inspection schemes", Biometrika, vol. 41, no. 1/2, pp.100-115. https://doi.org/10.1093/biomet/41.1-2.100
  20. Salinas, D., Flunkert, V., Gasthaus, J. and Januschowski, T.(2020), "DeepAR: Probabilistic forecasting with autoregressive recurrent networks", International Journal of Forecasting, vol. 36, no. 3, pp.1181-1191. https://doi.org/10.1016/j.ijforecast.2019.07.001
  21. Schneider, S., Baevski, A., Collobert, R. and Auli, M.(2019), Wav2vec: Unsupervised pre-training for speech recognition, arXiv preprint arXiv:1904.05862.
  22. Song, C. W., Nam, K. W. and Lee, C. W.(2012), "Driving Pattern Recognition System Using Smartphone sensor stream", Journal of the Korea Industrial Information Systems Research, vol. 17, no. 3, pp.35-42. https://doi.org/10.9723/JKSIIS.2012.17.3.035
  23. Wang, Q., Gu, Y., Liu, J. and Kamijo, S.(2017), "DeepSpeedometer: Vehiclespeed estimation from accelerometer and gyroscope using LSTMmodel", Proc IEEE 20th International Conference on Intelligent Transportation Systems(ITSC), Yokohama, Japan, pp.214-219.
  24. Xie, Y., Li, F., Wu, Y., Yang, S. and Wang, Y.(2019), "D3-guard: Acoustic-baseddrowsy driving detection using smartphones", Proc IEEE Conference on Computer Communications, Paris, France, pp.1225-1233.
  25. Xu, L., Li, S., Bian, K., Zhao, T. and Yan, W.(2014), "Sober-drive:A smartphone-assisted drowsy driving detection system", International Conference on Computing, Networking and Communications(ICNC), Honolulu, pp.398-402.