Context- and cost-aware feature selection in ultra-low-power sensor interfaces
作者： Steven Lauwereins , Komail M. H. Badami , Wannes Meert , Marian Verhelst
DOI:
关键词:
摘要: This paper introduces the use of machine learning to improve efficiency ultra-low-power sensor interfaces. Adaptive feature extrac- tion circuits are assisted by hardware embedded dynamically activate only most relevant features. selection is done in a context and power cost-aware way, through modification C4.5 algorithm. Furthermore, dependence different sets explained. As proof-of-principle, Voice Activity Detector expanded with pro- posed context- cost-dependent voice/noise classifier, resulting an average circuit savings 75%, negligible accuracy loss.
kuleuven.be 参考文章(8)
Yifei Jiang, Kun Li, Ricardo Piedrahita, Xiang Yun, Lei Tian, Omkar M. Mansata, Qin Lv, Robert P. Dick, Michael Hannigan, Li Shang, User-Centric Indoor Air Quality Monitoring on Mobile Devices Ai Magazine. ,vol. 34, pp. 11- 30 ,(2013) , 10.1609/AIMAG.V34I2.2472
Charles X. Ling, Qiang Yang, Jianning Wang, Shichao Zhang, Decision trees with minimal costs Twenty-first international conference on Machine learning - ICML '04. pp. 69- ,(2004) , 10.1145/1015330.1015369
Benton H Calhoun, John Lach, John Stankovic, David D Wentzloff, Kamin Whitehouse, Adam T Barth, Jonathan K Brown, Qiang Li, Seunghyun Oh, Nathan E Roberts, Yanqing Zhang, None, Body Sensor Networks: A Holistic Approach From Silicon to Users Proceedings of the IEEE. ,vol. 100, pp. 91- 106 ,(2012) , 10.1109/JPROC.2011.2161240
Kilian Weinberger, Matt Kusner, Zhixiang Xu, Minmin Chen, Cost-Sensitive Tree of Classifiers international conference on machine learning. pp. 133- 141 ,(2013)
Yi Hu, Philipos C. Loizou, Subjective comparison and evaluation of speech enhancement algorithms Speech Communication. ,vol. 49, pp. 588- 601 ,(2007) , 10.1016/J.SPECOM.2006.12.006
D. Siewiorek, A. Smailagic, J. Furukawa, A. Krause, N. Moraveji, K. Reiger, J. Shaffer, Fei Lung Wong, SenSay: a context-aware mobile phone international symposium on wearable computers. pp. 248- 249 ,(2003) , 10.1109/ISWC.2003.1241422
Pei-Yu Hsu, Yuhwai Tseng, Chien-Ying Yu, Po-Yao Chang, Tze-Zheng Yang, Chauchin Su, Yingchieh Ho, Ten-Fang Yang, Shu-Yu Hsu, Ray-Jade Chen, Chen-Yi Lee, A 48.6-to-105.2µW machine-learning assisted cardiac sensor SoC for mobile healthcare monitoring symposium on vlsi circuits. pp. 6578683- ,(2013)
Verhelst, Dehaene, Gielen, Van Helleputte, [IEEE 2009 IEEE International Solid-State Circuits Conference (ISSCC 2009) - San Francisco, CA (2009.02.8-2009.02.12)] 2009 IEEE International Solid-State Circuits Conference - Digest of Technical Papers - A reconfigurable, 0.13µm CMOS 110pJ/pulse, fully integrated IR-UWB receiver for communication and sub-cm ranging ,(2009)