Title :
Detection of delayed gastric emptying from electrogastrograms with support vector machine
Author :
Liang, Hualou ; Lin, Zhiyue
Author_Institution :
Center for Complex Syst., Florida Atlantic Univ., Boca Raton, FL, USA
fDate :
5/1/2001 12:00:00 AM
Abstract :
A recent study reported a conventional neural network (NN) approach for the noninvasive diagnosis of delayed gastric emptying from the cutaneous electrogastrograms. Using support vector machine, we show that this relatively new technique can be used for detection of delayed gastric emptying and is in fact able to outdo the conventional NN.
Keywords :
electromyography; generalisation (artificial intelligence); learning (artificial intelligence); medical signal processing; neural nets; pattern classification; signal classification; spectral analysis; cutaneous EGG; delayed gastric emptying; electrogastrograms; feature selection; generalisation error; myoelectric activity; neural network approach; noninvasive diagnosis; pattern classification; quadratic programming; spectral analysis; support vector machine; Abdomen; Delay; Frequency; Neural networks; Noninvasive treatment; Spectral analysis; Stomach; Support vector machine classification; Support vector machines; Testing; Algorithms; Diagnosis, Computer-Assisted; Electrophysiology; Gastric Emptying; Humans; Models, Biological; Neural Networks (Computer); Stomach Diseases;
Journal_Title :
Biomedical Engineering, IEEE Transactions on
