计算机应用 ›› 2021, Vol. 41 ›› Issue (6): 1557-1565.DOI: 10.11772/j.issn.1001-9081.2020121953

所属专题: 2020年全国开放式分布与并行计算学术年会(DPCS 2020)

• 2020年全国开放式分布与并行计算学术年会(DPCS 2020) • 上一篇    下一篇

基于残差时域注意力神经网络的交通模式识别算法

刘世泽1, 朱奕达2, 陈润泽2, 罗海勇3, 赵方2, 孙艺2, 王宝会1   

  1. 1. 北京航空航天大学 软件学院, 北京 100191;
    2. 北京邮电大学 计算机学院(国家示范性软件学院), 北京 100876;
    3. 中国科学院 计算技术研究所, 北京 100190
  • 收稿日期:2020-11-04 修回日期:2021-03-29 出版日期:2021-06-10 发布日期:2021-06-21
  • 通讯作者: 罗海勇
  • 作者简介:刘世泽(1988-),男,辽宁抚顺人,硕士,主要研究方向:大数据挖掘、智能感知;朱奕达(1996-),男,浙江慈溪人,博士研究生,主要研究方向:城市计算、交通模式识别;陈润泽(1996-),男,甘肃白银人,博士研究生,主要研究方向:城市计算、交通模式识别、位置语义挖掘;罗海勇(1967-),男,湖北麻城人,副研究员,博士,CCF会员,主要研究方向:移动智能、普适计算;赵方(1968-),女,河南开封人,教授,博士,CCF会员,主要研究方向:移动互联网、大数据挖掘;孙艺(1979-),男,山东菏泽人,高级工程师,硕士,主要研究方向:移动互联网、大数据挖掘;王宝会(1973-),男,江苏滨海人,教授级高级工程师,硕士,主要研究方向:软件工程。
  • 基金资助:
    国家重点研发计划项目(2019YFC1511400);国家自然科学基金资助项目(61872046);北京市自然科学基金资助项目(4212024);北京邮电大学提升科技创新能力行动计划项目(2019XD-A06);北京市自然科学基金-海淀原始创新联合基金资助项目(L192004);河北省重点研发计划项目(19210404D);内蒙古自治区关键技术攻关计划项目(2019GG328);移动计算与新型终端北京市重点实验室开放课题。

Traffic mode recognition algorithm based on residual temporal attention neural network

LIU Shize1, ZHU Yida2, CHEN Runze2, LUO Haiyong3, ZHAO Fang2, SUN Yi2, WANG Baohui1   

  1. 1. College of Software, Beihang University, Beijing 100191, China;
    2. School of Computer Science(National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing 100876, China;
    3. Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
  • Received:2020-11-04 Revised:2021-03-29 Online:2021-06-10 Published:2021-06-21
  • Supported by:
    This work is partially supported by the National Key Research and Development Program of China (2019YFC1511400), the National Natural Science Foundation of China (61872046), the Beijing Natural Science Foundation (4212024), the Scientific and Technological Innovation Ability Improvement Action Program of Beijing University of Posts and Telecommunications (2019XD-A06), the Joint Research Fund of Beijing Natural Science Foundation and Haidian Original Innovation (L192004), the Key Research and Development Project of Hebei Province (19210404D), the Key Technology Research Program of Inner Mongolia Autonomous Region (2019GG328), the Open Project of the Beijing Key Laboratory of Mobile Computing and Pervasive Device.

摘要: 交通模式识别是用户行为识别中的一个重要分支,其目的是对用户所处的交通模式进行准确判断。针对现代智慧城市交通系统对在移动设备环境下精准感知用户交通模式的需求,提出了一种基于残差时域注意力神经网络的交通模式识别算法。首先,通过具有较强局部特征提取能力的残差网络提取传感器时序中的局部特征;然后,采用基于通道的注意力机制对不同传感器特征进行重校准,并针对不同传感器的数据异构性进行注意力重校准;最后,利用具有更广感受野的时域卷积网络(TCN)提取传感器时序中的全局特征。采用数据丰富度较高的宏达通讯(HTC)交通模式识别数据集来对已有的交通模式识别算法和所提出的残差时域注意力模型进行评估,实验结果表明,所提出的残差时域注意力模型在对现代移动嵌入式设备的计算开销友好的前提下具有高达96.07%的准确率,且对单一类别均具有高于90%的召回率与精确率,验证了该模型的准确性与鲁棒性。所提模型可以作为一种支持移动智能终端运算的交通模式识别应用于智能交通出行、智慧城市等领域。

关键词: 时域卷积网络, 交通模式识别, 残差网络, 注意力机制, 深度学习

Abstract: Traffic mode recognition is an important branch of user behavior recognition, the purpose of which is to identify the user's current traffic mode. Aiming at the demand of the modern intelligent urban transportation system to accurately perceive the user's traffic mode in the mobile device environment, a traffic mode recognition algorithm based on the residual temporal attention neural network was proposed. Firstly, the local features in the sensor time sequence were extracted through the residual network with strong local feature extraction ability. Then, the channel-based attention mechanism was used to recalibrate the different sensor features, and the attention recalibration was performed by focusing on the data heterogeneity of different sensors. Finally, the Temporal Convolutional Network (TCN) with a wider receptive field was used to extract the global features in the sensor time sequence. The data-rich High Technology Computer (HTC) traffic mode recognition dataset was used to evaluate the existing traffic mode recognition algorithms and the residual temporal attention model. Experimental results show that the proposed residual temporal attention model has the accuracy as high as 96.07% with friendly computational overhead for mobile devices, and has the precision and recall for any single class reached or exceeded 90%, which verify the accuracy and robustness of the proposed model. The proposed model can be applied to intelligent transportation, smart city and other domains as a kind of traffic mode detection for supporting mobile intelligent terminal operation.

Key words: Temporal Convolutional Network (TCN), traffic mode recognition, Residual Network (ResNet), attention mechanism, deep learning

中图分类号: