ABSTRACT
Despite the active research into, and the development of, human activity recognition over the decades, existing techniques still have several limitations, in particular, poor performance due to insufficient ground-truth data and little support of intra-class variability of activities (i.e., the same activity may be performed in different ways by different individuals, or even by the same individuals with different time frames). Aiming to tackle these two issues, in this paper, we present a robust activity recognition approach by extracting the intrinsic shared structures from activities to handle intra-class variability, and the approach is embedded into a semi-supervised learning framework by utilizing the learned correlations from both labeled and easily-obtained unlabeled data simultaneously. We use l2,1 minimization on both loss function and regularizations to effectively resist outliers in noisy sensor data and improve recognition accuracy by discerning underlying commonalities from activities. Extensive experimental evaluations on four community-contributed public datasets indicate that with little training samples, our proposed approach outperforms a set of classical supervised learning methods as well as those recently proposed semi-supervised approaches.
- Ryan Aipperspach, Elliot Cohen, and John Canny. 2006. Modeling human behavior from simple sensors in the home. In Pervasive Computing. Springer, 337--348. Google ScholarDigital Library
- Rie Kubota Ando and Tong Zhang. 2005. A framework for learning predictive structures from multiple tasks and unlabeled data. The Journal of Machine Learning Research 6 (2005), 1817--1853. Google ScholarDigital Library
- Davide Anguita, Alessandro Ghio, Luca Oneto, Xavier Parra, and Jorge L Reyes-Ortiz. 2013. A public domain dataset for human activity recognition using smartphones. In European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN.Google Scholar
- Ling Bao and Stephen S Intille. 2004. Activity recognition from user-annotated acceleration data. In Pervasive computing. Springer, 1--17.Google Scholar
- Mikhail Belkin, Partha Niyogi, and Vikas Sindhwani. 2006. Manifold regularization: A geometric framework for learning from labeled and unlabeled examples. The Journal of Machine Learning Research 7 (2006), 2399--2434. Google ScholarDigital Library
- Sourav Bhattacharya, Petteri Nurmi, Nils Hammerla, and Thomas Plötz. 2014. Using unlabeled data in a sparse-coding framework for human activity recognition. Pervasive and Mobile Computing 15 (2014), 242--262. Google ScholarDigital Library
- Ulf Blanke, Bernt Schiele, Matthias Kreil, Paul Lukowicz, Bernhard Sick, and Thiemo Gruber. 2010. All for one or one for all? Combining Heterogeneous Features for Activity Spotting. In Pervasive Computing and Communications Workshops (PERCOM Workshops), 2010 8th IEEE International Conference on. IEEE, 18--24.Google Scholar
- David M Blei, Michael I Jordan, and others. 2006. Variational inference for Dirichlet process mixtures. Bayesian analysis 1, 1 (2006), 121--143.Google Scholar
- Avrim Blum and Tom Mitchell. 1998. Combining labeled and unlabeled data with co-training. In Proceedings of the eleventh annual conference on Computational learning theory. ACM, 92--100. Google ScholarDigital Library
- Andreas Bulling, Ulf Blanke, and Bernt Schiele. 2014. A tutorial on human activity recognition using body-worn inertial sensors. ACM Computing Surveys (CSUR) 46, 3 (2014), 33. Google ScholarDigital Library
- Liming Chen, Jesse Hoey, Chris D Nugent, Diane J Cook, and Zhiwen Yu. 2012. Sensor-based activity recognition. Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on 42, 6 (2012), 790--808. Google ScholarDigital Library
- B. Clarkson and A. Pentland. 1999. Unsupervised clustering of ambulatory audio and video. In Acoustics, Speech, and Signal Processing, 1999. Proceedings., 1999 IEEE International Conference on, Vol. 6. IEEE, 3037--3040. Google ScholarDigital Library
- Gene H Golub and Charles F Van Loan. 2012. Matrix computations. Vol. 3. JHU Press.Google Scholar
- Enamul Hoque and John Stankovic. 2012. AALO: Activity recognition in smart homes using Active Learning in the presence of Overlapped activities. In Pervasive Computing Technologies for Healthcare (PervasiveHealth), 2012 6th International Conference on. IEEE, 139--146.Google ScholarCross Ref
- Harold Hotelling. 1936. Relations between two sets of variates. Biometrika (1936), 321--377.Google Scholar
- Tâm Hunh, Ulf Blanke, and Bernt Schiele. 2007. Scalable recognition of daily activities with wearable sensors. In Location-and context-awareness. Springer, 50--67. Google ScholarDigital Library
- Nicky Kern, Bernt Schiele, Holger Junker, Paul Lukowicz, and Gerhard Tröster. 2003. Wearable sensing to annotate meeting recordings. Personal and Ubiquitous Computing 7, 5 (2003), 263--274. Google ScholarDigital Library
- Jennifer R Kwapisz, Gary M Weiss, and Samuel A Moore. 2011. Activity recognition using cell phone accelerometers. ACM SigKDD Explorations Newsletter 12, 2 (2011), 74--82. Google ScholarDigital Library
- Jason J Liu, Wenyao Xu, Ming-Chun Huang, Nabil Alshurafa, Majid Sarrafzadeh, Nitin Raut, and Behrooz Yadegar. 2013. A dense pressure sensitive bedsheet design for unobtrusive sleep posture monitoring. In Pervasive Computing and Communications (PerCom), 2013 IEEE International Conference on. IEEE, 207--215.Google ScholarCross Ref
- Beth Logan, Jennifer Healey, Matthai Philipose, Emmanuel Munguia Tapia, and Stephen Intille. 2007. A long-term evaluation of sensing modalities for activity recognition. Springer.Google Scholar
- Brent Longstaff, Sasank Reddy, and Deborah Estrin. 2010. Improving activity classification for health applications on mobile devices using active and semi-supervised learning. In 2010 4th International Conference on Pervasive Computing Technologies for Healthcare. IEEE, 1--7.Google ScholarCross Ref
- Paul Lukowicz, Jamie A Ward, Holger Junker, Mathias Stäger, Gerhard Tröster, Amin Atrash, and Thad Starner. 2004. Recognizing workshop activity using body worn microphones and accelerometers. In Pervasive Computing. Springer, 18--32.Google Scholar
- Ryunosuke Matsushige, Koh Kakusho, and Takeshi Okadome. 2015. Semi-supervised learning based activity recognition from sensor data. In 2015 IEEE 4th Global Conference on Consumer Electronics (GCCE). IEEE, 106--107.Google ScholarCross Ref
- Uwe Maurer, Asim Smailagic, Daniel P Siewiorek, and Michael Deisher. 2006. Activity recognition and monitoring using multiple sensors on different body positions. In Wearable and Implantable Body Sensor Networks, 2006. BSN 2006. International Workshop on. IEEE, 4--pp. Google ScholarDigital Library
- Alfredo Nazabal, Pablo Garcia-Moreno, Antonio Artes-Rodriguez, and Zoubin Ghahramani. 2015. Human activity recognition by combining a small number of classifiers. (2015).Google Scholar
- Long-Van Nguyen-Dinh, Mirco Rossi, Ulf Blanke, and Gerhard Tröster. 2013. Combining crowd-generated media and personal data: semi-supervised learning for context recognition. In Proceedings of the 1st ACM international workshop on Personal data meets distributed multimedia. ACM, 35--38. Google ScholarDigital Library
- Feiping Nie, Heng Huang, Xiao Cai, and Chris H Ding. 2010. Efficient and robust feature selection via joint l2, 1-norms minimization. In Proc. of the 24th Annual Conference on Neural Information Processing Systems (NIPS). 1813--1821. Google ScholarDigital Library
- Kaare Brandt Petersen, Michael Syskind Pedersen, and others. 2008. The matrix cookbook. Technical University of Denmark 7 (2008), 15.Google Scholar
- Nishkam Ravi, Nikhil Dandekar, Preetham Mysore, and Michael L Littman. 2005. Activity recognition from accelerometer data. In AAAI, Vol. 5. 1541--1546. Google ScholarDigital Library
- Daniele Riboni, Claudio Bettini, Gabriele Civitarese, Zaffar Haider Janjua, and Rim Helaoui. 2015. Fine-grained recognition of abnormal behaviors for early detection of mild cognitive impairment. In Pervasive Computing and Communications (PerCom), 2015 IEEE International Conference on. IEEE, 149--154.Google ScholarCross Ref
- Julia Seiter, Walon Wei-Chen Chiu, Mario Fritz, Oliver Amft, and Gerhard Tröster. 2015. Joint Segmentation and Activity Discovery Using Semantic and Temporal Priors. In Proc. of the 2015 IEEE International Conference on Pervasive Computing and Communications (PerCom 2015). St. Louis, MO, USA.Google ScholarCross Ref
- Gina Sprint, Douglas Weeks, Vladimir Borisov, and Diane Cook. 2014. Wearable sensors in ecological rehabilitation environments. In Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct Publication. ACM, 163--166. Google ScholarDigital Library
- Maja Stikic, Diane Larlus, Sandra Ebert, and Bernt Schiele. 2011. Weakly supervised recognition of daily life activities with wearable sensors. Pattern Analysis and Machine Intelligence, IEEE Transactions on 33, 12 (2011), 2521--2537. Google ScholarDigital Library
- Maja Stikic, Diane Larlus, and Bernt Schiele. 2009. Multi-graph based semi-supervised learning for activity recognition. In Wearable Computers, 2009. ISWC'09. International Symposium on. IEEE, 85--92. Google ScholarDigital Library
- Maja Stikic, Kristof Van Laerhoven, and Bernt Schiele. 2008. Exploring semi-supervised and active learning for activity recognition. In Wearable computers, 2008. ISWC 2008. 12th IEEE international symposium on. IEEE, 81--88. Google ScholarDigital Library
- Emmanuel Munguia Tapia, Stephen S Intille, and Kent Larson. 2004. Activity recognition in the home using simple and ubiquitous sensors. Springer.Google Scholar
- TLM Van Kasteren, Gwenn Englebienne, and Ben JA Kröse. 2010. Transferring knowledge of activity recognition across sensor networks. In Pervasive computing. Springer, 283--300. Google ScholarDigital Library
- Tim Van Kasteren, Athanasios Noulas, Gwenn Englebienne, and Ben Kröse. 2008. Accurate activity recognition in a home setting. In Proceedings of the 10th international conference on Ubiquitous computing. ACM, 1--9. Google ScholarDigital Library
- Kristof Van Laerhoven, David Kilian, and Bernt Schiele. 2008. Using rhythm awareness in long-term activity recognition. In Wearable Computers, 2008. ISWC 2008. 12th IEEE International Symposium on. IEEE, 63--66. Google ScholarDigital Library
- Yi Yang, Heng Tao Shen, Zhigang Ma, Zi Huang, and Xiaofang Zhou. 2011. l2, 1-norm regularized discriminative feature selection for unsupervised learning. In IJCAI Proceedings-International Joint Conference on Artificial Intelligence, Vol. 22. Citeseer, 1589. Google ScholarDigital Library
- Yi Yang, Fei Wu, Feiping Nie, Heng Tao Shen, Yueting Zhuang, and Alexander G Hauptmann. 2012. Web and personal image annotation by mining label correlation with relaxed visual graph embedding. Image Processing, IEEE Transactions on 21, 3 (2012), 1339--1351. Google ScholarDigital Library
- Lina Yao, Quan Z Sheng, Xue Li, Sen Wang, Tao Gu, Wenjie Ruan, and Wan Zou. 2015a. Freedom: Online Activity Recognition via Dictionary-based Sparse Representation of RFID Sensing Data. In Proceedings of the IEEE International Conference on Data Mining (ICDM). IEEE. Google ScholarDigital Library
- Lina Yao, Quan Z. Sheng, Wenjie Ruan, Tao Gu, Nickolas Falkner, Xue Li, and Zhi Yang. 2015b. RF-Care: Device-Free Posture Monitoring of Elderly People Using a Passive RFID Tag Array. In Proc. of the 12th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (MobiQuitous 2015). Coimbra, Portugal. Google ScholarDigital Library
- Mi Zhang and Alexander A Sawchuk. 2012. Usc-had: a daily activity dataset for ubiquitous activity recognition using wearable sensors. In Proceedings of the 2012 ACM Conference on Ubiquitous Computing. ACM, 1036--1043. Google ScholarDigital Library
- Dengyong Zhou, Olivier Bousquet, Thomas Navin Lal, Jason Weston, and Bernhard Schölkopf. 2004. Learning with local and global consistency. Advances in neural information processing systems 16, 16 (2004), 321--328. Google ScholarDigital Library
- Xiaojin Zhu, Zoubin Ghahramani, John Lafferty, and others. 2003. Semi-supervised learning using gaussian fields and harmonic functions. In ICML, Vol. 3. 912--919.Google ScholarDigital Library
Index Terms
Learning from less for better: semi-supervised activity recognition via shared structure discovery
Recommendations
Transductive Multilabel Learning via Label Set Propagation
The problem of multilabel classification has attracted great interest in the last decade, where each instance can be assigned with a set of multiple class labels simultaneously. It has a wide variety of real-world applications, e.g., automatic image ...
Inductive Semi-supervised Multi-Label Learning with Co-Training
KDD '17: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningIn multi-label learning, each training example is associated with multiple class labels and the task is to learn a mapping from the feature space to the power set of label space. It is generally demanding and time-consuming to obtain labels for training ...
Towards making co-training suffer less from insufficient views
Co-training is a famous semi-supervised learning algorithm which can exploit unlabeled data to improve learning performance. Generally it works under a two-view setting (the input examples have two disjoint feature sets in nature), with the assumption ...
Comments