교통 빅데이터 활용 시 개인 정보 보호를 위한 연합학습 기반의 경로 선택 모델링
Federated Learning-based Route Choice Modeling for Preserving Driver’s Privacy in Transportation Big Data Application
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
본 연구에서는 분산 컴퓨팅 및 개별 디바이스 활용을 통해 개인 정보 보호에 특화된 학습방법인 연합학습 방법론을 기반으로, 모바일 내비게이션 애플리케이션에서 수집된 대규모의운전자 데이터를 이용하여 경로 선택 예측 모델을 수립하는 방법에 대해 고찰한다. 경로 선택모델링에서 활용될 수 있는 운전자 데이터의 전처리 및 분석 방법을 수립하고, 서포트벡터머신(SVM) 및 다층 퍼셉트론(MLP)과 같이 기존에 널리 활용되는 학습 방법과 연합학습 방법의성능과 특성을 비교한다. 분석 결과 연합학습을 통한 모델 성능은 중앙 서버 기반의 모델과의비교에서 예측 정확도 측면의 차이가 거의 없는 것으로 나타났으나, 개별 데이터가 충분히 확보되는 경우 연합학습 모델과 같은 개인화 모델의 성능이 개선될 수 있다는 점을 확인하였다.연합학습 모델은 본 연구의 경로 선택 모델링 사례와 같이 모빌리티 부문의 데이터 프라이버시 문제가 중요한 분야에서 대규모 데이터 처리를 필요로 하는 경우에 그 활용 가치가 매우높을 것으로 기대된다.
Abstract
The use of big data for transportation often involves using data that includes personal information, such as the driver's driving routes and coordinates. This study explores the creation of a route choice prediction model using a large dataset from mobile navigation apps using federated learning. This privacy-focused method used distributed computing and individual device usage. This study established preprocessing and analysis methods for driver data that can be used in route choice modeling and compared the performance and characteristics of widely used learning methods with federated learning methods. The performance of the model through federated learning did not show significantly superior results compared to previous models, but there was no substantial difference in the prediction accuracy. In conclusion, federated learning-based prediction models can be utilized appropriately in areas sensitive to privacy without requiring relatively high predictive accuracy, such as a driver's preferred route choice.
참고문헌 (23)
- Alain, G., "Variance reduction in sgd by distributed importance sampling", arXiv preprint arXiv:1511.06481, ~ (2015)
- Bagdasaryan, E., "How to backdoor federated learning", International Conference on Artificial Intelligence and Statistics, pp.2938~2948 (2020), PMLR
- Brisimi, T. S., "Federated Learning of Predictive Models from Federated Electronic Health Records", International Journal of Medical Informatics, 112, pp.59~67 (2018)
- Chen, M., "Federated learning of out-of-vocabulary words", arXiv preprint arXiv:1903.10635, ~ (2019)
- Hard, A., "Federated learning for mobile keyboard prediction", arXiv preprint arXiv:1811.03604, ~ (2018)
- Kairouz, P., "Advances and open problems in federated learning", arXiv preprint arXiv:1912.04977, ~ (2019)
- Katharopoulos, A., "Not all samples are created equal : Deep learning with importance sampling", International Conference on Machine Learning, pp.2525~2534 (2018)
- Kweon, Y., "Preserving privacy with federated learning in route choice behavior modeling", Transportation Research Record, 2675(10), pp.268~276 (2021)
- Liu, K., "Fine-pruning: Defending against backdooring attacks on deep neural networks", International Symposium on Research in Attacks, Intrusions, and Defenses, pp.273~294 (2018), Springer International Publishing
- Liu, Y., "Privacy-preserving traffic flow prediction : A federated learning approach", IEEE Internet of Things Journal, 7(8), pp.7751~7763 (2020)
- Loshchilov, I., "Online batch selection for faster training of neural networks", arXiv preprint arXiv:1511.06343, ~ (2015)
- Manias, D. M., "Making a case for federated learning in the internet of vehicles and intelligent transportation systems", IEEE Network, 35(3), pp.88~94 (2021)
- McMahan, B., "Federated learning : Collaborative machine learning without centralized training data", Google Research Blog, 3~ (2017)
- McMahan, B., "Communication-Efficient Learning of Deep Networks from Decentralized Data", 20th International Conference on Artificial Intelligence and Statistics, 54, pp.1273~1282 (2017)
- Sarkar, D., "Fed-focal loss for imbalanced data classification in federated learning", arXiv preprint arXiv:2011.06283, ~ (2020)
- Sun, B., "Route choice modeling with support vector machine", Transportation Research Procedia, 25, pp.1806~1814 (2017)
- Sun, B., "A human-centric machine learning based personalized route choice prediction in navigation systems", Journal of Intelligent Transportation Systems, 27(4), pp.523~535 (2023)
- Sun, B., "MT-LinAdapt: A Human Centric Machine Learning Based Individual Drivers’ Route Choice Model for Personalized Route Recommendation", Presented at 99th Annual Meeting of the Transportation Research Board (2020)
- Tian, Y., "Federated vehicular transformers and their federations : Privacy-preserving computing and cooperation for autonomous driving", IEEE Transactions on Intelligent Vehicles, 7(3), pp.456~465 (2022)
- Xu, C., "An efficient and reliable asynchronous federated learning scheme for smart public transportation", IEEE Transactions on Vehicular Technology, 72(5), pp.6584~6598 (2022)
- Yang, L., "Federated Learning: Privacy and Incentive", pp.225~239 (2020), Springer
- Yuksel, A. S., "Driver’s black box : A system for driver risk assessment using machine learning and fuzzy logic", Journal of Intelligent Transportation Systems, 25(5), pp.482~500 (2021)
- Zhang, Y., "Travel mode choice modeling with support vector machines", Transportation Research Record, 2076(1), pp.141~150 (2008)