Automated classification pipeline tuning under mobile device resource constraints
作者： Feng Zhao , Nicholas D. Lane , David Chiyuan Chu , Jing Zhao
DOI:
关键词: Resource constraints 、 Mobile device 、 Data classification 、 Pipeline (computing) 、 Latency (audio) 、 Energy (signal processing) 、 Engineering 、 Real-time computing
摘要: An architecture and techniques to enable a mobile device efficiently classify raw sensor data into useful high level inferred is discussed. Classification efficiency achieved by tuning the device's classification pipeline attain balance of accuracy, latency energy suitable for devices. The accomplished via multi-pipeline approach that uses Statistical Machine Learning Tools (SMLTs) cost modeler.
google.de 参考文章(18)
Joseph S. Rosen, Multistage machine learning process ,(1999)
Mathias Stager, Nagendra B. Bharatula, Empirical Study of Design Choices in Multi-Sensor Context Recognition Systems ,(2005)
Aloak Kapoor, Russell Greiner, Learning and Classifying Under Hard Budgets Machine Learning: ECML 2005. pp. 170- 181 ,(2005) , 10.1007/11564096_20
Yi Wang, Bhaskar Krishnamachari, Qing Zhao, Murali Annavaram, The Tradeoff between Energy Efficiency and User State Estimation Accuracy in Mobile Sensing mobile computing, applications, and services. pp. 42- 58 ,(2009) , 10.1007/978-3-642-12607-9_4
John Cleary, Automated learning system ,(2002)
Ying Yang, Geoff Webb, Kevin Korb, Kai Ming Ting, Classifying under computational resource constraints: anytime classification using probabilistic estimators Machine Learning. ,vol. 69, pp. 35- 53 ,(2007) , 10.1007/S10994-007-5020-Z
Shahaf Abileah, Shyamalan Pather, Niranjan Nilakantan, Holly Knight, Robert H. Gerber, Murali M. Krishna, System and method for preference application installation and execution ,(2004)
Arnd Christian König, Eric Brill, Reducing the human overhead in text categorization knowledge discovery and data mining. pp. 598- 603 ,(2006) , 10.1145/1150402.1150474
S Blom, Matthias Book, Volker Gruhn, Ruslan Hrushchak, Andr K, Write Once, Run Anywhere A Survey of Mobile Runtime Environments grid and pervasive computing. pp. 132- 137 ,(2008) , 10.1109/GPC.WORKSHOPS.2008.19
Min Mun, Sasank Reddy, Katie Shilton, Nathan Yau, Jeff Burke, Deborah Estrin, Mark Hansen, Eric Howard, Ruth West, Péter Boda, None, PEIR, the personal environmental impact report, as a platform for participatory sensing systems research Proceedings of the 7th international conference on Mobile systems, applications, and services - Mobisys '09. pp. 55- 68 ,(2009) , 10.1145/1555816.1555823