基于特征自学习的交通模式识别研究
|
摘要
针对目前交通模式识别以人工设计特征为主,特征设计主观性强、区分度不高的问题,本文依据深度学习理论,建立了基于卷积神经网络的特征自动学习模型。该模型利用卷积神经网络自动学习深度特征,然后与人工特征共同用于交通模式识别。模型基于微软Geo Life数据,针对不同特征组合与分类方法设计实验,实验结果表明模型能学习到高区分度深度特征、有效提高交通模式识别准确率。
At present,transportation mode detection is mainly based on artificial design features that have strong subjective design characteristics and low differentiation degree. To solve this problem,a feature self-learning model is established based on convolutional neural network( CNN). Through the CNN' s self-learning of deep features,the model is combined with artificial features before the transportation mode detection is applied. Based on Microsoft's GeoLife data,the model is designed and tested according to different feature combinations and classification methods. The experiments show that this model can learn deep features with high differentiation degree,thereby effectively improving the accuracy of transportation mode detection.
At present,transportation mode detection is mainly based on artificial design features that have strong subjective design characteristics and low differentiation degree. To solve this problem,a feature self-learning model is established based on convolutional neural network( CNN). Through the CNN' s self-learning of deep features,the model is combined with artificial features before the transportation mode detection is applied. Based on Microsoft's GeoLife data,the model is designed and tested according to different feature combinations and classification methods. The experiments show that this model can learn deep features with high differentiation degree,thereby effectively improving the accuracy of transportation mode detection.
引文
[1]陈娜.基于位置信息的北京市出行模式研究[D].北京:北京交通大学,2016.CHEN Na. Position-based resident travel pattern of BeiJing[D]. Beijing:Beijing Jiaotong University,2016.
[2]隋雪芹.基于社会媒体的用户移动轨迹挖掘及其在朋友推荐中的应用研究[D].济南:山东大学,2016.SUI Xueqin. Research on movement trajectory detection and application in friend recommendation based on social media[D]. Ji'nan:Shandong University,2016.
[3]PATTERSON D J,LIAO lin,FOX D,et al. Inferring high-level behavior from low-level sensors[C]//Proceedings of the 5th International Conference on Ubiquitous Computing. Seattle,WA,USA,2003:73-89.
[4]ZHENG Yu,LI Quannan,CHEN Yukun,et al. Understanding mobility based on GPS data[C]//Proceedings of the 10th International Conference on Ubiquitous Computing. Seoul,Korea,2008:312-321.
[5]REDDY S,MUN M,BURKE J,et al. Using mobile phones to determine transportation modes[J]. ACM transactions on sensor networks(TOSN),2010,6(2):13.
[6]ZHENG Yu,LIU Like,WANG Longhao,et al. Learning transportation mode from raw gps data for geographic applications on the web[C]//Proceedings of the 17th International Conference on World Wide Web. Beijing,2008:247-256.
[7]ZHENG Yu. Trajectory data mining:an overview[J].ACM transactions on intelligent systems and technology,2015,6(3):29.
[8]LIAO Lin,PATTERSON D J,FOX D,et al. Learning and inferring transportation routines[J]. Artificial intelligence,2007,171(5):311-331.
[9]SHAH R C,WAN C Y,LU Hong,et al. Classifying the mode of transportation on mobile phones using GIS information[C]//Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Seattle,Washington,2014:225-229.
[10]ZHENG Yu,CHEN Yukun,LI Quannan,et al. Understanding transportation modes based on GPS data for web applications[J]. ACM transactions on the web(TWEB),2010,4(1):1.
[11]VINCENT P,LAROCHELLE H,BENGIO Y,et al. Extracting and composing robust features with denoising autoencoders[C]//Proceedings of the 25th International Conference on Machine Learning. Helsinki, Finland,2008:1096-1103.
[12]VINCENT P, LAROCHELLE H, LAJOIE I, et al.Stacked denoising autoencoders:Learning useful representations in a deep network with a local denoising criterion[J]. The journal of machine learning research,2010,11:3371-3408.
[13]HINTON G E,SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science,2006,313(5786):504-507.
[14]KRIZHEVSKY A,SUTSKEVER I,HINTON G E. ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe,Nevada,2012:1097-1105.
[15]毕晓君,冯雪赟.基于改进深度学习模型C-GRBM的人体行为识别[J].哈尔滨工程大学学报,2018,39(1):156-162.BI Xiaojun,FENG Xueyun. Human action recognition based on improved depth learning model C-GRBM[J].Journal of Harbin Engineering University,2018,39(1):156-162.
[16]ZHENG Yu,ZHANG Lizhu,XIE Xing,et al. Mining interesting locations and travel sequences from GPS trajectories[C]//Proceedings of the 18th International Conference on World Wide Web. Madrid,Spain,2009:791-800.
[17]ZHENG Yu,XIE Xing,MA Weiying. GeoLife:A collaborative social networking service among user,location and trajectory[J]. IEEE data(base)engineering bulletin,2010,32(2):32-39.
[2]隋雪芹.基于社会媒体的用户移动轨迹挖掘及其在朋友推荐中的应用研究[D].济南:山东大学,2016.SUI Xueqin. Research on movement trajectory detection and application in friend recommendation based on social media[D]. Ji'nan:Shandong University,2016.
[3]PATTERSON D J,LIAO lin,FOX D,et al. Inferring high-level behavior from low-level sensors[C]//Proceedings of the 5th International Conference on Ubiquitous Computing. Seattle,WA,USA,2003:73-89.
[4]ZHENG Yu,LI Quannan,CHEN Yukun,et al. Understanding mobility based on GPS data[C]//Proceedings of the 10th International Conference on Ubiquitous Computing. Seoul,Korea,2008:312-321.
[5]REDDY S,MUN M,BURKE J,et al. Using mobile phones to determine transportation modes[J]. ACM transactions on sensor networks(TOSN),2010,6(2):13.
[6]ZHENG Yu,LIU Like,WANG Longhao,et al. Learning transportation mode from raw gps data for geographic applications on the web[C]//Proceedings of the 17th International Conference on World Wide Web. Beijing,2008:247-256.
[7]ZHENG Yu. Trajectory data mining:an overview[J].ACM transactions on intelligent systems and technology,2015,6(3):29.
[8]LIAO Lin,PATTERSON D J,FOX D,et al. Learning and inferring transportation routines[J]. Artificial intelligence,2007,171(5):311-331.
[9]SHAH R C,WAN C Y,LU Hong,et al. Classifying the mode of transportation on mobile phones using GIS information[C]//Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Seattle,Washington,2014:225-229.
[10]ZHENG Yu,CHEN Yukun,LI Quannan,et al. Understanding transportation modes based on GPS data for web applications[J]. ACM transactions on the web(TWEB),2010,4(1):1.
[11]VINCENT P,LAROCHELLE H,BENGIO Y,et al. Extracting and composing robust features with denoising autoencoders[C]//Proceedings of the 25th International Conference on Machine Learning. Helsinki, Finland,2008:1096-1103.
[12]VINCENT P, LAROCHELLE H, LAJOIE I, et al.Stacked denoising autoencoders:Learning useful representations in a deep network with a local denoising criterion[J]. The journal of machine learning research,2010,11:3371-3408.
[13]HINTON G E,SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science,2006,313(5786):504-507.
[14]KRIZHEVSKY A,SUTSKEVER I,HINTON G E. ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe,Nevada,2012:1097-1105.
[15]毕晓君,冯雪赟.基于改进深度学习模型C-GRBM的人体行为识别[J].哈尔滨工程大学学报,2018,39(1):156-162.BI Xiaojun,FENG Xueyun. Human action recognition based on improved depth learning model C-GRBM[J].Journal of Harbin Engineering University,2018,39(1):156-162.
[16]ZHENG Yu,ZHANG Lizhu,XIE Xing,et al. Mining interesting locations and travel sequences from GPS trajectories[C]//Proceedings of the 18th International Conference on World Wide Web. Madrid,Spain,2009:791-800.
[17]ZHENG Yu,XIE Xing,MA Weiying. GeoLife:A collaborative social networking service among user,location and trajectory[J]. IEEE data(base)engineering bulletin,2010,32(2):32-39.