Title :
Hybrid fuzzy-neural committee networks for recognition of swallow acceleration signals
Author :
Reddy, Narender P. ; Das, Amitava ; Simcox, Denise
Author_Institution :
Dept. of Biomed. Eng., Akron Univ., OH, USA
fDate :
29 Oct-1 Nov 1998
Abstract :
Swallowing gives rise to characteristic patterns of acceleration in normal and dysphagic individuals. Usually, there are several artifacts present in the signal due to speech, coughing, etc. In the present study, two sets of fuzzy-neural committee networks were developed and trained to recognized acceleration signals due to swallowing. Evaluation showed that the networks well recognized the swallow signals and artifacts
Keywords :
acceleration measurement; biomedical measurement; feature extraction; fuzzy neural nets; medical expert systems; medical signal processing; pattern classification; signal classification; artifacts recognition; characteristic patterns of acceleration; dysphagic individuals; feature extraction; fuzzified parameters; hybrid fuzzy-neural committee networks; hybrid intelligent system; signal classification; swallow acceleration signals recognition; swallowing patterns; Acceleration; Accelerometers; Character recognition; Fuzzy logic; Hospitals; Liquids; Neural networks; Pattern recognition; Signal processing; Testing;
Conference_Titel :
Engineering in Medicine and Biology Society, 1998. Proceedings of the 20th Annual International Conference of the IEEE
Conference_Location :
Hong Kong
Print_ISBN :
0-7803-5164-9
DOI :
10.1109/IEMBS.1998.747136
