Title :
A comparative evaluation of various methods for detection of small spikes in data
Author :
Das, M. ; Hunt, T.
Author_Institution :
Dept. of Electr. & Syst. Eng., Oakland Univ., Rochester, MI, USA
Abstract :
The detection of relatively large spikes in data can be easily handled using common outlier detection techniques, but that of the smaller ones becomes a non-trivial task because of their inconspicuous nature. One has to utilize various signal enhancement, processing, and thresholding techniques in order achieve a 100% detection accuracy and a low false alarm rate. Seven different spike detection techniques are studied and compared here. Experimental results are presented in details
Keywords :
signal detection; time-domain analysis; detection accuracy; false alarm rate; inconspicuous nature; signal enhancement; spike detection; thresholding techniques; Data engineering; Data mining; Filtering algorithms; Finite impulse response filter; Frequency; Matched filters; Signal processing; Signal processing algorithms; Systems engineering and theory; Time domain analysis;
Conference_Titel :
Circuits and Systems, 1998. Proceedings. 1998 Midwest Symposium on
Conference_Location :
Notre Dame, IN
Print_ISBN :
0-8186-8914-5
DOI :
10.1109/MWSCAS.1998.759542
