Collaborative cloud-edge computation for personalized driving behavior modeling

Driving behavior modeling is an essential component of Advanced Driver Assistance Systems (ADAS). Existing methods usually analyze driving behaviors based on generic driving data, which do not consider personalization and user privacy. In this paper, we propose pBEAM, a collaborative cloud-edge computation system for personalized driving behavior modeling. The driving behavior model is built on top of Generative Adversarial Recurrent Neural Networks (GARNN), which adapts to the dynamic change of normal driving. Transfer learning from cloud to edge improves the model performance and robustness on the edge. We prune the deep neural networks in the cloud in order to minimize the model transferring load while maximally preserve the original model performance. A personalized edge model is trained on top of the pruned model using CGARNN-Edge (Conditional GARNN), which considers drivers' personal or contextual information as additional conditions. User privacy is well protected as no personal data needs to be uploaded to the cloud. Experimental results on driving data from both real world and driving simulator show that the proposed CGARNN-Edge achieves the best performance among all the methods.

[1]  Bryan Reimer,et al.  MIT Autonomous Vehicle Technology Study: Large-Scale Deep Learning Based Analysis of Driver Behavior and Interaction with Automation , 2017 .

[2]  Yiran Chen,et al.  Learning Structured Sparsity in Deep Neural Networks , 2016, NIPS.

[3]  Hui Jiang,et al.  Generating images with recurrent adversarial networks , 2016, ArXiv.

[4]  Song Han,et al.  Learning both Weights and Connections for Efficient Neural Network , 2015, NIPS.

[5]  Hans-Peter Kriegel,et al.  LOF: identifying density-based local outliers , 2000, SIGMOD '00.

[6]  Fengyuan Xu,et al.  Learning from Differentially Private Neural Activations with Edge Computing , 2018, 2018 IEEE/ACM Symposium on Edge Computing (SEC).

[7]  Weisong Shi,et al.  Edge Computing: Vision and Challenges , 2016, IEEE Internet of Things Journal.

[8]  Mahadev Satyanarayanan,et al.  Edge-Based Discovery of Training Data for Machine Learning , 2018, 2018 IEEE/ACM Symposium on Edge Computing (SEC).

[9]  Mykel J. Kochenderfer,et al.  Imitating driver behavior with generative adversarial networks , 2017, 2017 IEEE Intelligent Vehicles Symposium (IV).

[10]  Weisong Shi,et al.  SafeShareRide: Edge-Based Attack Detection in Ridesharing Services , 2018, 2018 IEEE/ACM Symposium on Edge Computing (SEC).

[11]  Peter Richtárik,et al.  Federated Learning: Strategies for Improving Communication Efficiency , 2016, ArXiv.

[12]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[13]  Olof Mogren,et al.  C-RNN-GAN: Continuous recurrent neural networks with adversarial training , 2016, ArXiv.

[14]  Anna-Sara Lind.  General Data Protection Regulation – final result , 2016 .

[15]  H. T. Kung,et al.  Distributed Deep Neural Networks Over the Cloud, the Edge and End Devices , 2017, 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS).

[16]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[17]  Charu C. Aggarwal,et al.  You Are How You Drive: Peer and Temporal-Aware Representation Learning for Driving Behavior Analysis , 2018, KDD.

[18]  Xiaopei Wu,et al.  OpenVDAP: An Open Vehicular Data Analytics Platform for CAVs , 2018, 2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS).

[19]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[20]  I. Pavlidis,et al.  Dissecting Driver Behaviors Under Cognitive, Emotional, Sensorimotor, and Mixed Stressors , 2016, Scientific Reports.

[21]  Yifan Wang,et al.  pCAMP: Performance Comparison of Machine Learning Packages on the Edges , 2019, HotEdge.

[22]  Guangzhong Sun,et al.  Driving with knowledge from the physical world , 2011, KDD.

[23]  Zhenming Liu,et al.  DeepDecision: A Mobile Deep Learning Framework for Edge Video Analytics , 2018, IEEE INFOCOM 2018 - IEEE Conference on Computer Communications.

[24]  Rob Fergus,et al.  Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks , 2015, NIPS.

[25]  M. Amaç Güvensan,et al.  Driver Behavior Analysis for Safe Driving: A Survey , 2015, IEEE Transactions on Intelligent Transportation Systems.

[26]  Xiaopei Wu,et al.  CAVBench: A Benchmark Suite for Connected and Autonomous Vehicles , 2018, 2018 IEEE/ACM Symposium on Edge Computing (SEC).

[27]  Mahadev Satyanarayanan,et al.  The Emergence of Edge Computing , 2017, Computer.

[28]  Fanglin Chen,et al.  CarSafe app: alerting drowsy and distracted drivers using dual cameras on smartphones , 2013, MobiSys.

[29]  Sheng Tang,et al.  Auto-Balanced Filter Pruning for Efficient Convolutional Neural Networks , 2018, AAAI.

[30]  Suyog Gupta,et al.  To prune, or not to prune: exploring the efficacy of pruning for model compression , 2017, ICLR.

[31]  Bin Yu,et al.  Structural Compression of Convolutional Neural Networks Based on Greedy Filter Pruning , 2017, ArXiv.

[32]  Jin-Hyuk Hong,et al.  A smartphone-based sensing platform to model aggressive driving behaviors , 2014, CHI.

[33]  Weisong Shi,et al.  Collaborative Learning on the Edges: A Case Study on Connected Vehicles , 2019, HotEdge.

[34]  Nianbo Liu,et al.  DrivingSense: Dangerous Driving Behavior Identification Based on Smartphone Autocalibration , 2017, Mob. Inf. Syst..