Learning to detect subway arrivals for passengers on a train

Abstract

The use of traditional positioning technologies, such as GPS and wireless local positioning, rely on underlying infrastructure. However, in a subway environment, such positioning systems are not available for the positioning tasks, such as the detection of the train arrivals for the passengers in the train. An alternative approach is to exploit the contextual information available in the mobile devices of subway riders to detect train arrivals. To this end, we propose to exploit multiple contextual features extracted from the mobile devices of subway riders to precisely detecting train arrivals. Following this line, we first investigate potential contextual features which may be effective to detect train arrivals according to the observations from 3D accelerometers and GSM radio. Furthermore, we propose to explore the maximum entropy (MaxEnt) model for training a train arrival detector by learning the correlation between contextual features and train arrivals. Finally, we perform extensive experiments on several real-world data sets collected from two major subway lines in the Beijing subway system. Experimental results validate both the effectiveness and efficiency of the proposed approach.

Keywords

subway arrival detection / mobile users / smart cities / information storage and retrieval / experimentation

References

[1] Yu K, Zhu H, Cao H, Zhang B, Chen E, Tian J, Rao J. Learning to detect the subway station arrival for mobile users. In: Proceedings of the 14th Intelligent Data Engineering and Automated Learning. 2013, 49−57

[2] Han L, Jyri S, Ma J, Yu K. Research on context-aware mobile computing. In: Proceedings of the 22nd International Conference on Advanced Information Networking and Applications Workshops. 2008, 24−30

[3] Yu C C, Chang H P. Towards context-aware recommendation for personalized mobile travel planning. In: Proceedings of the 2013 Context-Aware Systems and Applications. 2013, 121−130

[4] Huang C M, Lin S Y, Hsieh T H. The personalized context-aware mobile advertisement system using a novel approaching detection method over cellular networks. Software: Practice and Experience, 2013

[5] Yu K, Zhang B, Zhu H, Cao H, Tian J. Towards personalized context aware recommendation by mining context logs through topic models. In: Proceedings of the 1st Pacific Asia Knowledge Discovery and Data Mining. 2012, 431−443

[6] Zhu H, Chen E, Yu K, Cao H, Xiong H, Tian J. Mining personal context-aware preferences for mobile users. In: Zaki M J, Siebes A, Yu J X, Goethals B, Webb G I, Wu X, eds. Proceedings of the IEEE International Conference on Data Mining. 2012, 1212−1217

[7] Zhu H, Cao H, Chen E, Xiong H. Mobile App Classification with Enriched Contextual Information. IEEE Transactions on Mobile Computing, Pre-print,2013, 113

[8] Reddy S, Burke J, Estrin D, Hansen M, Srivastava M. Determining transportation mode on mobile phones. In: Proceeding of the 12th IEEE International Symposium on Wearable Computers. 2008, 25−28

[9] Reddy S, Mun M, Burke J, Estrin D, Hansen M, Srivastava M. Using mobile phones to determine transportation modes. ACM Transactions on Sensor Networks, 2010, 6(2): 13

[10] Zhang L, Qiang M, Yang G. Mobility transportation mode detection based on trajectory segment? Journal of Computational Information Systems, 2013, 9(8): 3279−3286

[11] Mantyjarvi J, Himberg J, Huuskonen P. Collaborative context recognition for handheld devices. In: Proceedings of the 1st IEEE International Conference on Pervasive Computing and Communications. 2003, 161−168

[12] Mayrhofer R, Radi H, Ferscha A. Recognizing and predicting context by learning from user behavior. In: Proceedings of the 2003 International Conference on Advances in Mobile Multimedia. 2003, 25−35

[13] Brezmes T, Gorricho J L, Cotrina J. Activity recognition from accelerometer data on a mobile phone. Distributed Computing, Artificial Intelligence, Bioinformatics, Soft Computing, and Ambient Assisted Living. Berlin: Springer, 2009, 796−799

[14] Hu D H, Yang Q. Transfer learning for activity recognition via sensor mapping. In: Proceedings of the 22nd International Joint Conference on Artificial Intelligence. 2011, 3: 1962−1967

[15] Kwapisz J R, Weiss G M, Moore S A. Activity recognition using cell phone accelerometers. ACM SIGKDD Explorations Newsletter, 2011, 12(2): 74−82

[16] Thiemjarus S. A device-orientation independent method for activity recognition. In: Proceedings of the 2010 International Conference on Body Sensor Networks. 2010, 19−23

[17] Deblauwe N, Ruppel P. Combining gps and gsm cell-id positioning for proactive location-based services. In: Proceedings of the 4th Annual International Conference on Mobile and Ubiquitous Systems: Networking& Services. 2007, 1−7

[18] Yang J, Varshavsky A, Liu H, Chen Y, Gruteser M. Accuracy characterization of cell tower localization. In: Proceedings of the 12th ACM International Conference on Ubiquitous Computing. 2010, 223−226

[19] Paek J, Kim K H, Singh J P, Govindan R. Energy-efficient positioning for smartphones using cell-ID sequence matching. In: Proceedings of the 9th International Conference on Mobile Systems, Applications, and Services. 2011, 293−306

[20] 4G—Wikipedia, the free encyclopedia. 2013. Online; accessed on 2013-June-22

[21] Liu H, Darabi H, Banerjee P, Liu J. Survey of wireless indoor positioning techniques and systems. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, 2007, 37(6): 1067−1080

[22] Lee J Y, Yoon C H, Park H, So J. Analysis of location estimation algorithms for wifi fingerprint-based indoor localization. American Society of Transportation and Logistics, 2013, 19: 89−92

[23] Arai K, Tolle H. Color radiomap interpolation for efficient fingerprint wifi-based indoor location estimation. International Journal of Advanced Research in Artificial Intelligence, 2013, 2(3): 10−15

[24] Rojas F M. Transit Transparency: Effective Disclosure through Open Data. Transparency Policy Project, 2012

[25] Zheng Y, Wong W K, Guan X, Trost S. Physical activity recognition from accelerometer data using a multi-scale ensemble method. In: Proceedings of the 25th Innovative Applications of Artificial Intelligence Conference. 2013, 1575−1581

[26] Received signal strength indication—Wikipedia, the free encyclopedia. Online; accessed on 2013-June-22

[27] Responsiveness—Wikipedia, the free encyclopedia. Responsiveness. Online; accessed on 2013-Nov-18

[28] Nielsen J. Response times: the 3 important limits.

[29] Phan X H, Nguyen L M, Horiguchi S. Learning to classify short and sparse text & web with hidden topics from large-scale data collections. In: Proceedings of the 17th International Conference on World Wide Web. 2008, 91−100

[30] Zhu H, Cao H, Chen E, Xiong H, Tian J. Exploiting enriched contextual information for mobile app classification. In: Proceedings of the 21st ACM International Conference on Information and Knowledge Management. 2012, 1617−1621

[31] Della Pietra S, Della Pietra V, Lafferty J. Inducing features of random fields. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(4): 380−393

[32] Malouf R, Groningen R. A comparison of algorithms for maximum entropy parameter estimation. In: Proceedings of the 6th Conference on Natural Language Learning. 2002, 49−55

[33] Maloof M A. Learning when data sets are imbalanced and when costs are unequal and unknown. In: Proceedings of the 2003 International Conference on Machine Learning Workshop on Learning from Imbalanced Data Sets II. 2003, 1−8

[34] Sun Y, Kamel M S, Wong A K, Wang Y. Cost-sensitive boosting for classification of imbalanced data. Pattern Recognition, 2007, 40(12): 3358−3378

[35] Weiss G M. Mining with rarity: a unifying framework. ACM SIGKDD Explorations Newsletter, 2004, 6(1): 7−19

[36] Chawla N V. Data mining for imbalanced datasets: an overview. Data Mining and Knowledge Discovery Handbook. Berlin: Springer, 2010, 875−886

[37] Android APIs. Online; accessed on 2013-June-22

[38] Beijing Subway—Wikipedia, the free encyclopedia. Beijing_Subway. Online; accessed on 2013-June-22

[39] Nigam K, Lafferty J, McCallum A. Using maximum entropy for text classification. In: Proceedings of the 16th International Joint Conference on Artificial Intelligence Workshop on Machine Learning for Information Filtering. 1999, 61−67

[40] Biagioni J, Gerlich T, Merrifield T, Eriksson J. Easytracker: automatic transit tracking, mapping, and arrival time prediction using smartphones. In: Proceedings of the 9th ACM Conference on Embedded Networked Sensor Systems. 2011, 68−81

RIGHTS & PERMISSIONS

Higher Education Press and Springer-Verlag Berlin Heidelberg