ABSTRACT
Mobile devices such as smart phones, tablet computers, and music players are ubiquitous. These devices typically contain many sensors, such as vision sensors (cameras), audio sensors (microphones), acceleration sensors (accelerometers) and location sensors (e.g., GPS), and also have some capability to send and receive data wirelessly. Sensor arrays on these mobile devices make innovative applications possible, especially when data mining is applied to the sensor data. But a key design decision is how best to distribute the responsibilities between the client (e.g., smartphone) and any servers. In this paper we investigate alternative architectures, ranging from a "dumb" client, where virtually all processing takes place on the server, to a "smart" client, where no server is needed. We describe the advantages and disadvantages of these alternative architectures and describe under what circumstances each is most appropriate. We use our own WISDM (WIreless Sensor Data Mining) architecture to provide concrete examples of the various alternatives.
- Actitracker. http://actitracker.comGoogle Scholar
- Android, Google. http://www.android.comGoogle Scholar
- Kwapisz, J., Weiss, G. M., and Moore, S. A. Activity recognition using cell phone accelerometers. ACM SIGKDD Explorations, 12(2):74--82. Google ScholarDigital Library
- Lane, N. D., Miluzzo, E., Hong Lu, Peebles, D., Choudhury, T., and Campbell, A. T. A survey of mobile phone sensing. Communications Magazine, IEEE Vol.48, 9 (Sept. 2010): 140--150. Google ScholarDigital Library
- Lockhart, J. W., Weiss, G. M., Xue, J. C., Gallagher, S. T. Grosner, A. B., and Pulickal, T. T. Design considerations for the WISDM smart phone-based sensor mining architecture. Proc. 5th International Workshop on Knowledge Discovery from Sensor Data, San Diego, CA (at KDD-2011): 25--33. Google ScholarDigital Library
- Menn, J. Smartphone shipments surpass PCs. February 8, 2011. Retrieved from http://www.ft.com/cms/s/2/d96e3bd8-33ca-11e0-b1ed-00144feabdc0.htmlGoogle Scholar
- Ravindranath, L., Thiagarajan, A., Balakrishnan, H., and Madden S. Code in the air: simplifying sensing and coordination tasks on smartphones. Proc. HotMobile'12 San Diego, CA. Google ScholarDigital Library
- Weiss, G. M., Lockhart, J. W. The impact of personalization on smartphone-based activity recognition. Proc. of the Activity Context Representation Workshop, Toronto, Canada (at AAAI-2012).Google Scholar
- WIreless Sensor Data Mining (WISDM) Lab. http://www.cis.fordham.edu/wisdmGoogle Scholar
- Witten, I. H. and Frank, E. Data Mining: Practical Machine Learning Tools and Techniques. 2nd Ed. 2005. Google ScholarDigital Library
Recommendations
Design considerations for the WISDM smart phone-based sensor mining architecture
SensorKDD '11: Proceedings of the Fifth International Workshop on Knowledge Discovery from Sensor DataSmart phones comprise a large and rapidly growing market. These devices provide unprecedented opportunities for sensor mining since they include a large variety of sensors, including an: acceleration sensor (accelerometer), location sensor (GPS), ...
Sensor-enhanced mobile web clients: an XForms approach
WWW '03: Proceedings of the 12th international conference on World Wide WebThis paper describes methods for service selection and service access for mobile, sensor-enhanced web clients such as wireless cameras or wireless PDAs with sensor devices attached. The clients announce their data-creating capabilities in "Produce" ...
A Ubiquitous Model for Wireless Sensor Networks Monitoring
IMIS '12: Proceedings of the 2012 Sixth International Conference on Innovative Mobile and Internet Services in Ubiquitous ComputingWireless sensor networks (WSNs) belong to emerging technologies where network devices can interact with the surrounding environment by sensing physical parameters. Recently, with the dissemination of mobile devices to Internet connectivity, users can ...
Comments