基于残差时域注意力神经网络的交通模式识别算法

doi:10.11772/j.issn.1001-9081.2020121953

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. 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. 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/Abstract

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:

TP183

刘世泽, 朱奕达, 陈润泽, 罗海勇, 赵方, 孙艺, 王宝会. 基于残差时域注意力神经网络的交通模式识别算法[J]. 计算机应用, 2021, 41(6): 1557-1565.

LIU Shize, ZHU Yida, CHEN Runze, LUO Haiyong, ZHAO Fang, SUN Yi, WANG Baohui. Traffic mode recognition algorithm based on residual temporal attention neural network[J]. Journal of Computer Applications, 2021, 41(6): 1557-1565.

参考文献

[1] YU M C,YU T,WANG S C,et al. Big data small footprint:the design of a low-power classifier for detecting transportation modes[J]. Proceedings of the VLDB Endowment,2014,7(13):1429-1440.
[2] WANG L, GJORESKI H, CILIBERTO M, et al. Enabling reproducible research in sensor-based transportation mode recognition with the Sussex-Huawei dataset[J]. IEEE Access, 2019,7:10870-10891.
[3] ZHENG Y, XIE X, MA W. GeoLife:a collaborative social networking service among user,location and trajectory[EB/OL].[2020-03-30]. http://sites.computer.org/debull/A10june/geolife.pdf.
[4] YANG H F,DILLON T S,CHEN Y P P. Optimized structure of the traffic flow forecasting model with a deep learning approach[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017,28(10):2371-2381.
[5] LV Y,DUAN Y,KANG W,et al. Traffic flow prediction with big data:a deep learning approach[J]. IEEE Transactions on Intelligent Transportation Systems,2015,16(2):865-873.
[6] 汪磊, 左忠义, 傅军豪. 基于SVM的出行方式特征分析和识别研究[J]. 交通运输系统工程与信息, 2014, 14(3):70-75, 84. (WANG L,ZUO Z Y,FU J H. Travel mode character analysis and recognition based on SVM[J]. Journal of Transportation Systems Engineering and Information Technology, 2014, 14(3):70-75,84.)
[7] ZHENG Y,ZHANG L,XIE X,et al. Mining correlation between locations using human location history[C]//Proceedings of the 2009 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. New York:ACM, 2009:472-475.
[8] GHOSE A,LI B,LIU S. Mobile targeting using customer trajectory patterns[J]. Management Science,2019,65(11):4951-5448.
[9] 熊苏生. 基于改进LightGBM的交通模式识别算法[J]. 计算机与现代化,2018(10):68-73,126. (XIONG S S. Identifying transportation mode based on improved LightGBM algorithm[J]. Computer and Modernization,2018(10):68-73,126.)
[10] ZHENG L,LI S,ZHU C,et al. Application of IndRNN for human activity recognition:the Sussex-Huawei locomotion-transportation challenge[C]//Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing/2019 ACM International Symposium on Wearable Computers. New York:ACM,2019:869-872.
[11] ZHU Y,ZHAO F,CHEN R. Applying 1D sensor DenseNet to Sussex-Huawei locomotion-transportation recognition challenge[C]//Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing/2019 ACM International Symposium on Wearable Computers. New York:ACM,2019:873-877.
[12] CHOI J H,LEE J S. EmbraceNet for activity:a deep multimodal fusion architecture for activity recognition[C]//Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing/2019 ACM International Symposium on Wearable Computers. New York:ACM,2019:693-698.
[13] BALABKA D. Semi-supervised learning for human activity recognition using adversarial autoencoders[C]//Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing/2019 ACM International Symposium on Wearable Computers. New York:ACM,2019:685-688.
[14] FRIEDRICH B,CAUCHI B,HEIN A,et al. Transportation mode classification from smartphone sensors via a long-short-termmemory network[C]//Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing/2019 ACM International Symposium on Wearable Computers. New York:ACM,2019:709-713.
[15] CARPINETI C,LOMONACO V,BEDOGNI L,et al. Custom dual transportation mode detection by smartphone devices exploiting sensor diversity[C]//Proceedings of the 2018 IEEE International Conference on Pervasive Computing and Communications Workshops. Piscataway:IEEE,2018:367-372.
[16] WIDHALM P,LEODOLTER M,BRÄNDLE N. Ensemble-based domain adaptation for transport mode recognition with mobile sensors[C]//Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing/2019 ACM International Symposium on Wearable Computers. New York:ACM. 2019:857-861.
[17] LU H,PINAROC M,LV M,et al. Locomotion recognition using XGBoost and neural network ensemble[C]//Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing/2019 ACM International Symposium on Wearable Computers. New York:ACM,2019:757-760.
[18] AHMED M,ANTAR A D,HOSSAIN T,et al. POIDEN:position and orientation independent deep ensemble network for the classification of locomotion and transportation modes[C]//Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing/2019 ACM International Symposium on Wearable Computers. New York:ACM,2019:674-679.
[19] COROAMĂ V C, TÜRK C, MATTERN F. Exploring the usefulness of Bluetooth and WiFi proximity for transportation mode recognition[C]//Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing/2019 ACM International Symposium on Wearable Computers. New York:ACM,2019:37-40.
[20] STENNETH L,WOLFSON O,YU P S,et al. Transportation mode detection using mobile phones and GIS information[C]//Proceedings of the 2011 19th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. New York:ACM,2011:54-63.
[21] ALWAN A,FREY V,LAN G L. Orange labs contribution to the Sussex-Huawei locomotion-transportation recognition challenge[C]//Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing/2019 ACM International Symposium on Wearable Computers. New York:ACM,2019:680-684.
[22] SU X, CACERES H, TONG H, et al. Online travel mode identification using smartphones with battery saving considerations[J]. IEEE Transactions on Intelligent Transportation Systems, 2016,17(10):2921-2934.
[23] GJORESKI H,CILIBERTO M,WANG L,et al. The university of Sussex-Huawei locomotion and transportation dataset for multimodal analytics with mobile devices[J]. IEEE Access, 2018,6:42592-42604.
[24] REDDY S,MUN M,BURKE J,et al. Using mobile phones to determine transportation modes[J]. ACM Transactions on Sensor Networks,2010,6(2):No. 13.
[25] HUANG G,LIU Z,MAATEN L V D,et al. Densely connected convolutional networks[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2017:2261-2269.
[26] BAI S,KOLTER J Z,KOLTUN V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling[EB/OL].[2021-03-12]. http://arxiv.org/pdf/1803.01271.pdf.
[27] HU J,SHEN L,SUN G. Squeeze-and-excitation networks[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE,2018:7132-7141.
[28] REDDI S J,KALE S,KUMAR S. On the convergence of ADAM and beyond[EB/OL].[2021-03-12]. http://www.sanjivk.com/AdamConvergence_ICLR.pdf.

基于残差时域注意力神经网络的交通模式识别算法

Traffic mode recognition algorithm based on residual temporal attention neural network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	谢德峰, 吉建民. 融入句法感知表示进行句法增强的语义解析[J]. 计算机应用, 2021, 41(9): 2489-2495.
[2]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[3]	刘雅璇, 钟勇. 基于头实体注意力的实体关系联合抽取方法[J]. 计算机应用, 2021, 41(9): 2517-2522.
[4]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[5]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[6]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[7]	陈成瑞, 孙宁, 何世彪, 廖勇. 面向C-V2X通信的基于深度学习的联合信道估计与均衡算法[J]. 计算机应用, 2021, 41(9): 2687-2693.
[8]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[9]	郑志强, 胡鑫, 翁智, 王雨禾, 程曦. 基于改进DenseNet的牛眼图像特征提取方法[J]. 计算机应用, 2021, 41(9): 2780-2784.
[10]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[11]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[12]	党伟超, 李涛, 白尚旺, 高改梅, 刘春霞. 基于自注意力长短期记忆网络的Web软件系统实时剩余寿命预测方法[J]. 计算机应用, 2021, 41(8): 2346-2351.
[13]	何正海, 线岩团, 王蒙, 余正涛. 融合句法指导与字符注意力机制的案情阅读理解方法[J]. 计算机应用, 2021, 41(8): 2427-2431.
[14]	李扬志, 袁家政, 刘宏哲. 基于时空注意力图卷积网络模型的人体骨架动作识别算法[J]. 计算机应用, 2021, 41(7): 1915-1921.
[15]	张洋, 江铭虎. 基于注意力机制的文本作者识别[J]. 计算机应用, 2021, 41(7): 1897-1901.