Abstract
Activity recognition from mobile device sensors and wearables is attracting more attention from the research community due to the widespread adoption of these devices and the unique opportunity they provide for understanding user’s behavior leading to novel services and improvements in the delivery of existing ones. Approaches to tackle this problem either rely on predefined statistical features of sensor data streams or feature learning with the latter providing higher accuracies in most cases. Deep learning methods proved more effective than traditional approaches to feature learning in multiple studies. This paper presents a novel end-to-end trainable deep architecture that utilizes multiple convolutional neural networks (CNN), late fusion and extensive layer bypassing. The proposed method can easily accommodate multiple sensors and signal representations. The proposed approach is validated on eight publicly available datasets using a variety of evaluation conditions showing that it outperforms state-of-the-art methods in six of them.
Similar content being viewed by others
Notes
The authors would like to thank M. Alsheikh for providing us with the source code of their method enabling the comparative experiment reported here
References
Abdallah ZS, Gaber MM, Srinivasan B, Krishnaswamy S (2015) Adaptive mobile activity recognition system with evolving data streams. Neurocomputing 150(Part A):304–317
Alsheikh MA, Selim A, Niyato D, Doyle L, Lin S, Tan HP (2016) Deep activity recognition models with triaxial accelerometers. In: The workshops of the thirtieth AAAI conference on artificial intelligence, pp 1–8
Altun K, Barshan B (2010) Human activity recognition using inertial/magnetic sensor units. In: International workshop on human behavior understanding. Springer, pp 38–51
Anderez DO, Appiah K, Lotfi A, Langesiepen C (2017) A hierarchical approach towards activity recognition. In: Proceedings of the 10th international conference on PErvasive technologies related to assistive environments. ACM, pp 269–274
Anguita D, Ghio A, Oneto L, Parra X, Reyes-Ortiz JL (2013) A public domain dataset for human activity recognition using smartphones. In: European symposium on artificial neural networks, computational intelligence and machine learning, pp 24–26
Anwar S, Hwang K, Sung W (2017) Structured pruning of deep convolutional neural networks. ACM J Emerg Technol Comput Syst (JETC) 13(3):32
Barshan B, Yüksek MC (2014) Recognizing daily and sports activities in two open source machine learning environments using body-worn sensor units. Comput J 57(11):1649–1667
Borazio M, Van Laerhoven K (2013) Using time use with mobile sensor data: a road to practical mobile activity recognition?. In: Proceedings of the 12th international conference on mobile and ubiquitous multimedia, MUM ’13. ACM, New York, pp 20:1–20:10
Catal C, Tufekci S, Pirmit E, Kocabag G (2015) On the use of ensemble of classifiers for accelerometer-based activity recognition. Applied Soft Computing Journal 37:1018–1022
Chen L, Hoey J, Nugent CD, Cook DJ, Yu Z (2012) Sensor-based activity recognition. IEEE Trans Syst Man Cybern Part C (Appl Rev) 42(6):790–808
Cornwell BR, Carver FW, Coppola R, Johnson L, Alvarez R, Grillon C (2008) Evoked amygdala responses to negative faces revealed by adaptive meg beamformers. Brain Res 1244:103–112
Dharia S, Jain V, Patel J, Vora J, Chawla S, Eirinaki M (2016) PRO-Fit: a personalized fitness assistant framework. Int J Softw Eng Knowl Eng 26(9):386–389
Forster K, Roggen D, Troster G (2009) Unsupervised classifier self-calibration through repeated context occurences: is there robustness against sensor displacement to gain?. In: 2009 international symposium on wearable computers, pp 77–84
Garvert MM, Friston KJ, Dolan RJ, Garrido MI (2014) Subcortical amygdala pathways enable rapid face processing. Neuroimage 102:309–316
Guan Y, Plötz T (2017) Ensembles of deep lstm learners for activity recognition using wearables. Proc ACM Interact Mob Wearable Ubiquitous Technol 1(2):11:1–11:28
Hammerla NY, Halloran S, Plötz T (2016) Deep, convolutional, and recurrent models for human activity recognition using wearables. In: Proceedings of the twenty-fifth international joint conference on artificial intelligence, IJCAI’16, pp 1533–1540
Hasan M, Roy-Chowdhury AK (2015) A continuous learning framework for activity recognition using deep hybrid feature models. IEEE Trans Multimedia 17(11):1909–1922
Karantonis DM, Narayanan MR, Mathie M, Lovell NH, Celler BG (2006) Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring. IEEE Trans Inf Technol Biomed 10(1):156–167
Kingma D, Ba J (2014) Adam: a method for stochastic optimization. arXiv:1412.6980
Kreil M, Sick B, Lukowicz P (2016) Coping with variability in motion based activity recognition. In: Proceedings of the 3rd international workshop on sensor-based activity recognition and interaction, iWOAR ’16. ACM, New York, pp 4:1–4:8
Kwapisz JR, Weiss GM, Moore SA (2011) Activity recognition using cell phone accelerometers. ACM SigKDD Explorations Newsletter 12(2):74–82
Liu S, Deng W (2015) Very deep convolutional neural network based image classification using small training sample size. In: 2015 3rd IAPR Asian conference on pattern recognition (ACPR), pp 730–734
Lockhart JW, Pulickal T, Weiss GM (2012) Applications of mobile activity recognition. In: Proceedings of the 2012 ACM conference on ubiquitous computing. ACM, pp 1054–1058
Lu DN, Nguyen TT, Ngo TTT, Nguyen TH, Nguyen HN (2017) Mobile online activity recognition system based on smartphone sensors. Springer International Publishing, Cham, pp 357–366
Mizell D (2003) Using gravity to estimate accelerometer orientation. In: Seventh IEEE international symposium on wearable computers, 2003. Proceedings. IEEE, pp 252–253
Ordóñez FJ, Roggen D (2016) Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition. Sensors 16(1):115
Plötz T, Hammerla NY, Olivier P (2011) Feature learning for activity recognition in ubiquitous computing. In: Proceeding IJCAI’11 proceedings of the twenty-second international joint conference on artificial intelligence, vol 2, pp 1729–1734
Raman N, Maybank SJ (2016) Activity recognition using a supervised non-parametric hierarchical hmm. Neurocomputing 199:163–177
Roggen D, Calatroni A, Rossi M, Holleczek T, Forster K, Troster G, Lukowicz P, Bannach D, Pirkl G, Ferscha A, Doppler J, Holzmann C, Kurz M, Holl G, Chavarriaga R, Sagha H, Bayati H, Creatura M, Millan JDR (2010) Collecting complex activity datasets in highly rich networked sensor environments. In: 2010 Seventh international conference on networked sensing systems (INSS), July 2010. IEEE, pp 233–240
Ronao CA, Cho SB (2016) Human activity recognition with smartphone sensors using deep learning neural networks. Expert Syst Appl 59:235–244
Sagha H, Digumarti ST, Millán JDR, Chavarriaga R, Calatroni A, Roggen D, Tröster G (2011) Benchmarking classification techniques using the opportunity human activity dataset. In: 2011 IEEE international conference on systems, man, and cybernetics (SMC). IEEE, pp 36–40
San-Segundo R, Montero JM, Barra-Chicote R, Fernández F, Pardo JM (2016) Feature extraction from smartphone inertial signals for human activity segmentation. Signal Process 120:359–372
Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. In: Advances in neural information processing systems, pp 568–576
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: International conference on learning representations (ICLR)
Urban G, Geras KJ, Kahou SE, Aslan O, Wang S, Caruana R, Mohamed A, Philipose M, Richardson M (2016) Do deep convolutional nets really need to be deep and convolutional? arXiv:1603.05691
Veenendaal A, Daly E, Jones E, Gang Z, Vartak S, Patwardhan RS (2016) Sensor tracked points and HMM based classifier for human action recognition. Computer Science and Emerging Research Journal 5:4–8
Weiss GM, Lockhart JW (2011) Identifying user traits by mining smart phone accelerometer data. In: Proceedings of the fifth international workshop on knowledge discovery from sensor data, SensorKDD2011, pp 61–69
Weiss GM, Lockhart JW (2012) The impact of personalization on smartphone-based activity recognition. In: AAAI workshop on activity context representation: techniques and languages, pp 98–104
Weiss GM, Lockhart JW, Pulickal TT, McHugh PT, Ronan IH, Timko JL (2016) Actitracker: a smartphone-based activity recognition system for improving health and well-being. In: 2016 IEEE international conference on data science and advanced analytics (DSAA). IEEE, pp 682–688
Yu J, Lukefahr A, Palframan D, Dasika G, Das R, Mahlke S (2017) Scalpel: customizing dnn pruning to the underlying hardware parallelism. In: Proceedings of the 44th annual international symposium on computer architecture. ACM, pp 548–560
Zagoruyko S, Lerer A, Lin TY, Pinheiro PO, Gross S, Chintala S, Dollár P (2016) A multipath network for object detection. In: British machine vision conference. New York, pp 15.1–15.12
Zappi P, Lombriser C, Stiefmeier T, Farella E, Roggen D, Benini L, Troster G (2008) Activity recognition from on-body sensors: accuracy-power trade-off by dynamic sensor selection. Lect Notes Comput Sci 4913:17
Zappi P, Stiefmeier T, Farella E, Roggen D, Benini L, Troster G (2007) Activity recognition from on-body sensors by classifier fusion: sensor scalability and robustness. In: 2007 3rd international conference on intelligent sensors, sensor networks and information, pp 281–286
Zeng M, Nguyen LT, Yu B, Mengshoel OJ, Zhu J, Wu P, Zhang J (2014) Convolutional neural networks for human activity recognition using mobile sensors. In: Proceedings of the 6th international conference on mobile computing, applications and services, ICST, vol 6, pp 197–205
Zhu Z, Blanke U, Calatroni A, Tröster G (2013) Human activity recognition using social media data. In: Proceedings of the 12th international conference on mobile and ubiquitous multimedia, MUM ’13. ACM, New York, pp 21:1–21:10
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mohammad, Y., Matsumoto, K. & Hoashi, K. Primitive activity recognition from short sequences of sensory data. Appl Intell 48, 3748–3761 (2018). https://doi.org/10.1007/s10489-018-1166-6
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-018-1166-6