Abstract
Wearable gesture recognition enables context aware applications and unobtrusive HCI. It is realized by applying machine learning techniques to data from on-body sensor nodes. We present an gesture recognition system minimizing power while maintaining a run-time application defined performance target through dynamic sensor selection.
Compared to the non managed approach optimized for recognition accuracy (95% accuracy), our technique can extend network lifetime by 4 times with accuracy >90% and by 9 times with accuracy >70%. We characterize the approach and outline its applicability to other scenarios.
- Abrams, Z., Goel, A., and Plotkin, S. 2004. Set k-cover algorithms for energy efficient monitoring in wireless sensor networks. In Proceedings of the International Symposium on Information Processing in Sensor Networks. 424--432. Google Scholar
Digital Library
- Bannach, D., Amft, O., and Lukowicz, P. 2008. Rapid prototyping of activity recognition applications. IEEE Pervasive Comput. 7, 2, 22--31. Google Scholar
Digital Library
- Bao, L. and Intille, S. S. 2004. Activity recognition from user-annotated acceleration data. In Pervasive Computing 2004, 1--17.Google Scholar
- Benbasat, A. and Paradiso, J. 2007. A framework for the automated generation of power-efficient classifiers for embedded sensor nodes. In Proceedings of the International Conference on Embedded Networked Sensor Systems. 219--232. Google Scholar
Digital Library
- Benini, L., Farella, E., and Guiducci, C. 2006. Wireless sensor networks: Enabling technology for ambient intelligence. Microelectron. J. 37, 12, 1639--1649. Google Scholar
Digital Library
- Benocci, M., Farella, E., Benini, L., and Vanzago, L. 2009. Optimizing zigbee for data streaming in body-area bio-feedback applications. In Proceedings of the 3rd International Workshop on Advances in Sensors and Interfaces (IWASI’09). 150--155.Google Scholar
- Bharatula, N., Lukowicz, P., and Tröster, G. 2008. Functionality-power-packaging considerations in context aware wearable systems. Personal Ubiquitous Comput. 12, 2, 123--141. Google Scholar
Digital Library
- Calatroni, A., Roggen, D., and Tröster, G. 2010. A methodology to use unknown new sensors for activity recognition by leveraging sporadic interactions with primitive sensors and behavioral assumptions. In Proceedings of the Opportunistic Ubiquitous Systems Workshop, Part of 12th ACM International Conference on Ubiquitous Computing.Google Scholar
- Chambers, G., Venkatesh, S., West, G., and Bui, H. 2002. Hierarchical recognition of intentional human gestures for sports video annotation. In Proceedings of the 16th IEEE Conference on Pattern Recognition. Vol. 2. IEEE, 1082--1085.Google Scholar
- Chen, H., Wu, H., and Tzeng, N.-F. 2004. Grid-based approach for working node selection in wireless sensor networks. In Proceedings of the IEEE International Conference on Communications. 3673--3678.Google Scholar
- Chen, X., Zhao, Q., and Guan, X. 2007. Energy-efficient sensing coverage and communication for wireless sensor networks. J. Syst. Sci. Complexity 20, 225--234.Google Scholar
Cross Ref
- Chen, S. D., Monga, V., and Moulin, P. 2009. Meta-classifiers for multimodal document classification. In Proceedings of the IEEE International Workshop on Multimedia Signal Processing (MMSP’09). 1--6.Google Scholar
- Commuri, S. and Tadigotla, V. 1-3 Oct. 2007. Dynamic data aggregation in wireless sensor networks. In Proceedings of the IEEE 22nd International Symposium on Intelligent Control. 1--6.Google Scholar
- Dai, L. and Basu, P. 2006. Energy and delivery capacity of wireless sensor networks with random duty-cycles. In Proceedings of the IEEE International Conference on Communications (ICC’06). 3503--3510.Google Scholar
- Davies, N., Siewiorek, D. P., and Sukthankar, R. 2008. Activity-based computing. IEEE Pervasive Comput. 7, 2, 20--21. Google Scholar
Digital Library
- Dey, A. K. 2001. Understanding and using context. Personal Ubiquitous Comput. J. 5, 1, 4--7. Google Scholar
Digital Library
- Dubarry, M., Vuillaume, N., and Liaw, B. Y. 2009. From single cell model to battery pack simulation for li-ion batteries. J. Power Sources 186, 2, 500--507.Google Scholar
Cross Ref
- Dutta, P., Grimmer, M., Arora, A., Bibyk, S., and Culler, D. 2005. Design of a wireless sensor network platform for detecting rare, random, and ephemeral events. In Proceedings of the 4th International Symposium on Information Processing in Sensor Networks. 497--502. Google Scholar
Digital Library
- Fortino, G., Guerrieri, A., Bellifemine, F. L., and Giannantonio, R. 2009. SPINE2: Developing BSN applications on heterogeneous sensor nodes. In Proceedings of the IEEE Symposium on Industrial Embedded Systems.Google Scholar
- Gu, L., Jia, D., et al. 2005. Lightweight detection and classification for wireless sensor networks in realistic environments. In Proceedings of the International Conference on Embedded Networked Sensor Systems. 205--217. Google Scholar
Digital Library
- He, T., Krishnamurthy, S., et al. 2006. Vigilnet: An integrated sensor network system for energy-efficient surveillance. ACM Trans. Sens. Netw. 2, 1, 1--38. Google Scholar
Digital Library
- Healey, J., Patel, S., Bonato, P., Mancinelli, C., and Moy, M. 2009. Using wearable sensors to monitor physical activities of patients with copd: A comparison of classifier performance. In Proceedings of the 6th International Workshop on Wearable and Implantable Body Sensor Networks (BSN’09). 234--239. Google Scholar
Digital Library
- Hernandez-Rebollar, J. L. 2005. Gesture-driven American Sign Language phraselator. In Proceedings of the 7th International Conference on Multimodal Interfaces (ICMI’05). ACM Press, New York, NY, 288--292. Google Scholar
Digital Library
- Hill, J. and Culler, D. 2002. Mica: A wireless platform for deeply embedded networks. IEEEMicro 22, 6, 12--24. Google Scholar
Digital Library
- Hsin, C. and Liu, M. 2004. Network coverage using low duty-cycled sensors; random and coordinated sleep algorithms. In Proceedings of the International Symposium on Information Processing in Sensor Networks. Google Scholar
Digital Library
- Isler, V. and Bajcsy, R. 2005. The sensor selection problem for bounded uncertainty sensing models. In Proceedings of the International Symposium on Information Processing in Sensor Networks. 151--158. Google Scholar
Digital Library
- Junker, H., Lukowicz, P., and Tröster, G. 2004. Sampling frequency, signal resolution and the accuracy of wearable context recognition systems. In Proceedings of the 8th International Symposium on Wearable Computers (ISWC’04). 176--177. Google Scholar
Digital Library
- Kallio, S., Kela, J., Korpipää, P., and Mäntyjärvi, J. 2006. User independent gesture interaction for small handheld devices. Int. J. Pattern Recog. Artif. Intell. 20, 4, 505--524.Google Scholar
Cross Ref
- Keally, M., Zhou, G., and Xing, G. 2010. Watchdog: Confident event detection in heterogeneous sensor networks. In Proceedings of the 16th IEEE Real-Time and Embedded Technology and Applications Symposium. IEEE Computer Society, 279--288. Google Scholar
Digital Library
- Kittler, J., Hatef, M., Duin, R. P. W., and Matas, J. 1998. On combining classifiers. IEEE Trans. Pattern Anal. Mach. Intell. 20, 3, 226--239. Google Scholar
Digital Library
- Krause, A., Ihmig, M., Rankin, E., Leong, D., Gupta, S., Siewiorek, D. P., Smailagic, A., Deisher, M., and Sengupta, U. 2005. Trading off prediction accuracy and power consumption for context-aware wearable computing. In Proceedings of the 9th International Symposium on Wearable Computers. IEEE, 20--26. Google Scholar
Digital Library
- Kukkonen, J., Lagerspetz, E., Nurmi, P., and Andersson, M. 2009. Betelgeuse: A platform for gathering and processing situational data. IEEE Pervasive Comput. 8, 2, 49--56. Google Scholar
Digital Library
- Kuncheva, L. I. and Whitaker, C. J. 2003. Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy. Mach. Learn. 51, 181--207. Google Scholar
Digital Library
- Lombriser, C., Roggen, D., Stäger, M., and Tröster, G. 2007. Titan: A tiny task network for dynamically reconfigurable heterogeneous sensor networks. In 15. Fachtagung Kommunikation in Verteilten Systemen. 127--138.Google Scholar
- Macii, D., Boni, A., De Cecco, M., and Petri, D. 2008. Tutorial 14: Multisensor data fusion. IEEE Instrum. Meas. Mag. 11, 3, 24--33.Google Scholar
Cross Ref
- Mann, S. 1996. Smart clothing: The shift to wearable computing. Commun. ACM 39, 8, 23--24. Google Scholar
Digital Library
- Meng, Y., Dunham, M. H., Marchetti, F., and Huang, J. 2006. Rare event detection in a spatiotemporal environment. In Proceedings of the IEEE International Conference on Granular Computing. 629--634.Google Scholar
- Murao, K., Terada, T., Takegawa, Y., and Nishio, S. 2008. A context-aware system that changes sensor combinations considering energy consumption. In Proceedings of the 6th International Conference on Pervasive Computing, J. Indulska, D. J. Patterson, T. Rodden, and M. Ott, Eds. Lecture Notes in Computer Science, vol. 5013. Springer, 197--212. Google Scholar
Digital Library
- Pattem, S., Poduri, S., and Krishnamachari, B. 2003. Energy-quality tradeoffs for target tracking in wireless sensor networks. In Proceedings of the 2nd International Conference on Information Processing in Sensor Networks. 32--46. Google Scholar
Digital Library
- Polikar, R. 2006. Ensemble based systems in decision making. IEEE Circ. Syst. Mag. 6, 3, 21--45.Google Scholar
Cross Ref
- Rabiner, L. R. 1989. A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 77, 2, 257--285.Google Scholar
Cross Ref
- Radunovic, B. and Le Boudec, J.-Y. 2004. Optimal power control, scheduling, and routing in uwb networks. IEEE J. Select. Areas Commun. 22, 7, 1252--1270. Google Scholar
Digital Library
- Rakhmatov, D. and Vrudhula, S. 2003. Energy management for battery-powered embedded systems. ACM Trans. Embed. Comput. Syst. 2, 3, 277--324. Google Scholar
Digital Library
- Rao, N. S. 2001. On fusers that perform better than best sensor. IEEE Trans Pattern Anal. Mach. Intell. 23, 8, 904--909. Google Scholar
Digital Library
- Roggen, D., Bharatula, N. B., Stäger, M., Lukowicz, P., and Tröster, G. 2006. From sensors to miniature networked sensorbuttons. In Proceedings of the 3rd International Conference on Networked Sensing Systems (INSS’06). 119--122.Google Scholar
- Roggen, D., Förster, K., et al. 2009. Opportunity: Towards opportunistic activity and context recognition systems. In Proceedings of the 3rd IEEE WoWMoM Workshop on Autonomic and Opportunistic Communications.Google Scholar
Cross Ref
- Roggen, D., Calatroni, A., et al. 2010. Collecting complex activity data sets in highly rich networked sensor environments. In Proceedings of the 7th International Conference on Networked Sensing Systems. IEEE Press, 233--240.Google Scholar
- Roggen, D., Lombriser, C., Rossi, M., and Tröster, G. 2011. Titan: An enabling framework for activity-aware “pervasive apps” in opportunistic personal area networks. EURASIP J. on Wireless Commun. Netw. Google Scholar
Digital Library
- Santini, S. and Römer, K. 2006. An adaptive strategy for quality-based data reduction in wireless sensor networks. In Proceedings of the 3rd International Conference on Networked Sensing Systems (INSS’06). 29--36.Google Scholar
- Sharma, R. 1998. Toward multimodal human-computer interface. Proc. IEEE 86, 5, 853--869.Google Scholar
Cross Ref
- ST Microelectronics. 2009. Motionbee(tm) modules. Tech. rep.Google Scholar
- Stäger, M., Lukowicz, P., and Tröster, G. 2007. Power and accuracy trade-offs in sound-based context recognition systems. Pervasive Mobile Comput. 3, 300--327. Google Scholar
Digital Library
- Stiefmeier, T., Roggen, D., and Tröster, G. 2007. Fusion of string-matched templates for continuous activity recognition. In Proceedings of the 11th IEEE International Symposium on Wearable Computers. IEEE, 41--44. Google Scholar
Digital Library
- Stiefmeier, T., Roggen, D., Ogris, G., Lukowicz, P., and Tröster, G. 2008. Wearable activity tracking in car manufacturing. IEEE Pervasive Comput. 7, 2, 42--50. Google Scholar
Digital Library
- Stojmenovic, I. and Lin, X. 2001. Power-aware localized routing in wireless networks. IEEE Trans. Parall. Distrib. Syst. 12, 11, 1122--1133. Google Scholar
Digital Library
- Tognetti, A., Carbonaro, N., Zupone, G., and De Rossi, D. 2006. Characterization of a novel data glove based on textile integrated sensors. In Proceedings of the 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS’06). 2510--2513.Google Scholar
Cross Ref
- Toshiba. 2009. Toshiba TG01 smartphone. Toshiba, https://www.toshibaeurope.com/mobilerevolution/default.aspx.Google Scholar
- van Dam, T. and Langendoen, K. 2003. An adaptive energy-efficient mac protocol for wireless sensor networks. In Proceedings of the International Conference on Embedded Networked Sensor Systems. ACM Press, New York, NY, 171--180. Google Scholar
Digital Library
- Villalonga, C., Roggen, D., Lombriser, C., Zappi, P., and Tröster, G. 2009. Bringing quality of context into wearable human activity recognition systems. In Proceedings of the 1st International Workshop on Quality of Context. Google Scholar
Digital Library
- Viswanathan, R. and Varshney, P. K. 1997. Distributed detection with multiple sensors: Part i and ii. Proc. IEEE 85, 1, 54--79.Google Scholar
Cross Ref
- Wang, D. 2007. A power-balancing scheme for clustered wireless sensor networks. In Proceedings of the International Conference on Future Generation Communication and Networking, 231--236. Google Scholar
Digital Library
- Want, R. 2009. When cell phones become computers. IEEE Pervasive Comput. 8, 2, 2--5. Google Scholar
Digital Library
- Ward, J., Lukowicz, P., Tröster, G., and Starner, T. 2006. Activity recognition of assembly tasks using body-worn microphones and accelerometers. IEEE Trans. Pattern Analysis Mach. Intell. 28, 10, 1553--1567. Google Scholar
Digital Library
- Wenzl, H., Baring-Gould, I., Kaiser, R., Liaw, B. Y., Lundsager, P., Manwell, J., Ruddell, A., and Svoboda, V. 2005. Life prediction of batteries for selecting the technically most suitable and cost effective battery. J. Power Sources 144, 2, 373--384.Google Scholar
Cross Ref
- Xipower Ltd. 2009. Active cell balancing increases effective battery capacity and reduces capacity variance. Tech. rep.Google Scholar
- Zappi, P., Lombriser, C., Farella, E., Roggen, D., Benini, L., and Tröster, G. 2008. Activity recognition from on-body sensors: Accuracy-power trade-off by dynamic sensor selection. In Proceedings of the 5th European Conference on Wireless Sensor Networks (EWSN’08), R. Verdone Ed., Springer, 17--33. Google Scholar
Digital Library
- Zappi, P., Milosevic, B., Farella, E., and Benini, L. 2009. Hidden markov model based gesture recognition on low-cost, low-power tangible user interfaces. Entertainment Comput. 1, 2, 75--84.Google Scholar
Cross Ref
- Zappi, P., Lombriser, C., Farella, E., Benini, L., and Tröster, G. 2009. Experiences with experiments in ambient intelligence environments. In Proceedings of the IADIS International Conference on Wireless Applications and Computing. 171--174.Google Scholar
- Zhang, W., Liang, Z., Hou, Z., and Tan, M. 2007. A power efficient routing protocol for wireless sensor network. In Proceedings of the IEEE International Conference on Networking, Sensing and Control. IEEE, 20--25.Google Scholar
- Zigbee Alliance. 2006. Zigbee specification. http://www.zigbee.org.Google Scholar
Index Terms
Network-Level Power-Performance Trade-Off in Wearable Activity Recognition: A Dynamic Sensor Selection Approach
Recommendations
Human Activity Recognition Using Wearable Sensors by Deep Convolutional Neural Networks
MM '15: Proceedings of the 23rd ACM international conference on MultimediaHuman physical activity recognition based on wearable sensors has applications relevant to our daily life such as healthcare. How to achieve high recognition accuracy with low computational cost is an important issue in the ubiquitous computing. Rather ...
A tutorial on human activity recognition using body-worn inertial sensors
The last 20 years have seen ever-increasing research activity in the field of human activity recognition. With activity recognition having considerably matured, so has the number of challenges in designing, implementing, and evaluating activity ...
Real-time activity classification using ambient and wearable sensors
Special section on body sensor networksNew approaches to chronic disease management within a home or community setting offer patients the prospect of more individually focused care and improved quality of life. This paper investigates the use of a light-weight ear worn activity recognition ...






Comments