A Federated Mixed Logit Model for Personal Mobility Service in Autonomous Transportation Systems
A Federated Mixed Logit Model for Personal Mobility Service in Autonomous Transportation Systems
复制标题
自主交通系统中个人移动服务的联合混合 Logit 模型
DOI：
10.3390/systems10040117
复制
发表时间：
2022-08
期刊：
影响因子：
1.9
通讯作者：
Jiemin Xie
中科院分区：
文献类型：
--
作者：
Linlin You;Junshu He;Juanjuan Zhao;Jiemin Xie
展望未来阶段的自动交通系统（ATS），个人移动服务（PMS）旨在提供基于微观个人出行需求和宏观供给系统目标的推荐出行选择。这样的目标依赖于大量异构数据来解释和预测用户的旅行意图，面临着普遍的集中式方法所带来的挑战，例如云和边缘之间的不平衡利用率以及数据隐私。为了填补这一差距，本文提出了一种联合logit模型（FMXL），用于估计用户偏好，它将离散选择模型--混合logit模型（MXL）与一种新的分散学习范式--联合学习（FL）相结合。FMXL通过以下方式支持PMS：（1）在客户端和服务器端分别进行局部和全局估计以优化负载;（2）通过持续交互机制协同逼近标准混合logit模型的后验;（3）灵活配置两种特定的全局估计方法（采样和聚合）以适应不同的估计场景。此外，在静态和动态估计中，FMXL的预测率比平坦logit模型高约10%。同时，与集中式MXL模型相比，估计时间减少了约40%。该模型不仅可以保护用户隐私，提高边缘资源的利用率，还可以显著提高推荐的准确性和及时性，从而提高ATS中PMS的性能。
Looking ahead to the future-stage autonomous transportation system (ATS), personal mobility service (PMS) aims to provide the recommended travel options based on both microscopic individual travel demand and the macroscopic supply system objectives. Such a goal relies on massive heterogeneous data to interpret and predict user travel intentions, facing the challenges caused by prevalent centralized approaches, such as an unbalanced utilization rate between cloud and edge, and data privacy. To fill the gap, we propose a federated logit model (FMXL), for estimating user preferences, which integrates a discrete choice model—the mixed logit model (MXL), with a novel decentralized learning paradigm—federated learning (FL). FMXL supports PMS by (1) respectively performing local and global estimation at the client and server to optimize the load, (2) collaboratively approximating the posterior of the standard mixed logit model through a continuous interaction mechanism, and (3) flexibly configuring two specific global estimation methods (sampling and aggregation) to accommodate different estimation scenarios. Moreover, the predicted rates of FMXL are about 10% higher compared to a flat logit model in both static and dynamic estimation. Meanwhile, the estimation time has been reduced by about 40% compared to a centralized MXL model. Our model can not only protect user privacy and improve the utilization of edge resources but also significantly improve the accuracy and timeliness of recommendations, thus enhancing the performance of PMS in ATS.
登录
查看更多内容
DOI：
10.1016/j.comnet.2018.11.035
发表时间：
2019-02
期刊：
Comput. Networks
影响因子：
--
作者：
Sadia Din;Anand Paul;A. Rehman
通讯作者：
Sadia Din;Anand Paul;A. Rehman
DOI：
10.1145/2873064
发表时间：
2016-03
期刊：
ACM Transactions on Intelligent Systems and Technology (TIST)
影响因子：
--
作者：
Linlin You;G. Motta;Kaixu Liu;Tianyi Ma
通讯作者：
Linlin You;G. Motta;Kaixu Liu;Tianyi Ma
DOI：
10.3390/urbansci1040036
发表时间：
2017-11
期刊：
--
影响因子：
--
作者：
A. Nikitas;I. Kougias;Elena Alyavina;Eric Njoya Tchouamou
通讯作者：
A. Nikitas;I. Kougias;Elena Alyavina;Eric Njoya Tchouamou
DOI：
10.1145/3292500.3330660
发表时间：
2019-07
期刊：
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
影响因子：
--
作者：
Hao Liu;Yongxin Tong;Panpan Zhang;Xinjiang Lu;Jianguo Duan;Hui Xiong
通讯作者：
Hao Liu;Yongxin Tong;Panpan Zhang;Xinjiang Lu;Jianguo Duan;Hui Xiong
DOI：
10.1007/978-3-030-35543-2_3
发表时间：
2019-09
期刊：
Advances in Intelligent Systems and Computing
影响因子：
--
作者：
W. Lewicki;B. Stankiewicz;Aleksandra Olejarz-Wahba
通讯作者：
W. Lewicki;B. Stankiewicz;Aleksandra Olejarz-Wahba