ABSTRACT
Sliding window based activity recognition chains represent the state-of-the-art for many mobile and embedded scenarios as they are common in wearable computing. The length of the analysis frames is a crucial system parameter that directly influences the effectiveness of the overall approach. In this paper we present a method that optimizes the window length - individually for each target activity. Instead of employing a single, multi-class recognition system that is based on a generic window length, we combine individually optimized activity detectors into an Ensemble based recognition approach. We demonstrate the effectiveness of the approach through an experimental evaluation on eight benchmark datasets. The proposed method leads to significant improvements across a range of activity recognition application domains.
Supplemental Material
Available for Download
Supplemental material.
- O. Banos, J Galvez, M Damas, H Pomares, and I Rojas. 2014. Window size impact in human activity recognition. Sensors 14, 4 (2014), 6474--6499.Google ScholarCross Ref
- A. Bulling, U. Blanke, and B. Schiele. 2014. A Tutorial on Human Activity Recognition Using Body-worn Inertial Sensors. ACM Comput. Surv. 46, 3 (Jan. 2014). Google ScholarDigital Library
- R. Chavarriaga, H. Sagha, A. Calatroni, S. Digumarti, G. Troester, J. del R Millan, and D. Roggen. 2013. The Opportunity challenge: A benchmark database for on-body sensor-based activity recognition. PRL 34, 15 (2013), 2033--2042. Google ScholarDigital Library
- L. Cheng, Y. Yu, X. Liu, J. Su, and Y. Guan. 2017. Recognition of Human Activities Using Fast and Adaptive Sparse Representation Based on Wearable Sensors. In Proc. ICMLA.Google Scholar
- A. Chowdhury, D. Tjondronegoro, V. Chandran, and S. Trost. 2017. Physical activity recognition using posterior-adapted class-based fusion of multi-accelerometers data. J. Biomed Health Inform (2017).Google Scholar
- K. Forster, D. Roggen, and G. Troester. 2009. Unsupervised classifier self-calibration through repeated context occurences: Is there robustness against sensor displacement to gain?. In Proc. ISWC. Google ScholarDigital Library
- M. Galar, A. Fernández, E. Barrenechea, H. Bustince, and F. Herrera. 2011. An overview of ensemble methods for binary classifiers in multi-class problems: Experimental study on one-vs-one and one-vs-all schemes. Pattern Recognition 44, 8 (2011), 1761--1776. Google ScholarDigital Library
- Y. Guan and T. Plötz. 2017. Ensembles of deep lstm learners for activity recognition using wearables. PACM IMWUT 1, 2 (2017), 11. Google ScholarDigital Library
- H. Guo, L. Chen, L. Peng, and G. Chen. Wearable sensor based multimodal human activity recognition exploiting the diversity of classifier ensemble. In Proc. Ubicomp. Google ScholarDigital Library
- S. Ha, J. Yun, and S. Choi. 2015. Multi-modal convolutional neural networks for activity recognition. In Proc. SMC. 3017--3022.Google Scholar
- N. Hammerla, S. Halloran, and T. Plötz. 2016. Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearables. Proc. IJCAI (2016). Google ScholarDigital Library
- N. Hammerla, R. Kirkham, P. Andras, and T. Plötz. 2013. On preserving statistical characteristics of accelerometry data using their empirical cumulative distribution. In Proc. ISWC. Google ScholarDigital Library
- W. He, Y. Guo, C. Gao, andX. Li. 2012. Recognition of human activities with wearable sensors. EURASIP 2012, 1 (2012), 108.Google ScholarCross Ref
- T. Huynh and B. Schiele. 2005. Analyzing features for activity recognition. In Proc. SOAI. Google ScholarDigital Library
- A. Khan, N. Hammerla, S. Mellor, and T. Plötz. 2016. Optimising sampling rates for accelerometer-based human activity recognition. PRL 73 (2016), 33--40. Google ScholarDigital Library
- T. Miu, P. Missier, and T. Plötz. 2015. Bootstrapping personalised human activity recognition models using online active learning. In Proc. IUCC.Google Scholar
- S. Münzner, P. Schmidt, A. Reiss, M. Hanselmann, R. Stiefelhagen, and R. Dürichen. 2017. CNN-based sensor fusion techniques for multimodal human activity recognition. In Proc. ISWC. Google ScholarDigital Library
- L. Nguyen, M. Zeng, P. Tague, and J. Zhang. 2015. Recognizing new activities with limited training data. In Proc. ISWC. Google ScholarDigital Library
- F. Ordóñez and D. Roggen. 2016. Deep convolutional and lstm recurrent neural networks for multimodal wearable activity recognition. Sensors 16, 1 (2016), 115.Google ScholarCross Ref
- A. Reiss and D. Stricker. 2012. Creating and benchmarking a new dataset for physical activity monitoring. In Proc. ICPTRAE. Google ScholarDigital Library
- S. Savvaki, G. Tsagkatakis, A. Panousopoulou, and P. Tsakalides. 2017. Matrix and Tensor Completion on a Human Activity Recognition Framework. J Biomed Health Inform 21, 6 (2017), 1554--1561.Google ScholarCross Ref
- B. Su, J. Jiang, Q. Tang, and M. Sheng. 2016. Human periodic activity recognition based on functional features. In Proc. SIGGRAPH. Google ScholarDigital Library
- J. Wu, J. Wang, Y. Ling, and H. Xu. 2017. AnAdvanced Hybrid Technique of DCS and JSRC for Telemonitoring of Multi-Sensor Gait Pattern. Sensors 17, 12 (2017).Google Scholar
- J. Wu and H. Xu. 2016. An advanced scheme of compressed sensing of acceleration data for telemonintoring of human gait. Biomedical engineering online 15, 1 (2016), 27.Google Scholar
Recommendations
Activity recognition with hand-worn magnetic sensors
Activity recognition is a key technology for realizing ambient assisted living applications such as care of the elderly and home automation. This paper proposes a new activity recognition method that employs hand-worn magnetic sensors to recognize a ...
Adaptive sliding window based activity recognition for assisted livings
Highlights- This work addresses recognition of human activities with different time duration.
AbstractThe incessant diffusion of smart wearable devices and Body Area Networks (BANs) systems is pushing more and more researches on human activity recognition. Previous studies usually adopted fixed time window or chose an optimal window ...
Artificial intelligence in human activity recognition: a review
The various activities of human movements have been discussed for several years, such as sports activities, daily life activities, and so on. Their detection and classification have given crucial information about a person's behaviour and health status. ...
Comments