Neural networks for classification and pattern recognition of biological signals

M c i a l neural networks have been shown to be very useN and effective alternatives for implementing intelligent systems in Biology and Medicine [1,2,3]. Particularly, A N N s lend themselves very naturally to applications involving biological signal processing and recognition [4]. It bas been proved that they perform better and quicker than conventional methods in situations where noise and uncertainty is present, and that they cao be used to implement several functions, such as data compression (4, digital filters, artifact detection, function optimization, time-series and Fourier analysis, etc. Detection, identification and classification of patterns which may be present in a biosipal record is of great importancc for the development of a variety of biomedical applications, such as closed-loop control [a]; intelligent realtime instruments [7l; non-invasive monitoring [8J; prediction of time-ordered trends (91; automatic interpretation and diagnosis of biosignd recordings [10,11]; adaptive control of bioprostheses [U]; voice control of devices [U]; localization of signal sources [14]; adaptive noise cancellation and signal separation [q; automatic peak detection [16], selection and segmentation [17]; signal decomposition (181; multichannel signal analysis and classification [19]; morphological and template matched filtering [a], etc.

[1]  Gert Pfurtscheller,et al.  Analysis of Sleep Patterns in Babies Using Neural Networks - Preliminary Results , 1991, MIE.

[2]  B Blumenfeld.  A connectionist approach to the recognition of trends in time-ordered medical parameters. , 1990, Computer methods and programs in biomedicine.

[3]  Matthew A. Wilson,et al.  New technical approaches to monitoring and interpreting the dynamics of real neural networks , 1988, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[4]  Russell C. Eberhart,et al.  CaseNet: a neural network tool for EEG waveform classification , 1989, [1989] Proceedings. Second Annual IEEE Symposium on Computer-based Medical Systems.

[5]  D R Westenskow,et al.  Differential features for a neural network based anesthesia alarm system. , 1992, Biomedical sciences instrumentation.

[6]  Y. Nagasaka,et al.  Data compression of the ECG using neural network for digital Holter monitor , 1990, IEEE Engineering in Medicine and Biology Magazine.

[7]  James A. Reggia,et al.  Self-processing networks and their biomedical implications , 1988, Proc. IEEE.

[8]  Daniel Graupe,et al.  Applications of neural networks to medical signal processing , 1988, Proceedings of the 27th IEEE Conference on Decision and Control.

[9]  B. Widrow,et al.  Adaptive noise cancelling: Principles and applications , 1975 .

[10]  W.J. Tompkins,et al.  Neural-network-based adaptive matched filtering for QRS detection , 1992, IEEE Transactions on Biomedical Engineering.

[11]  D T Freeman,et al.  Computer recognition of brain stem auditory evoked potential wave V by a neural network. , 1992, The Annals of otology, rhinology, and laryngology.

[12]  A. V. Sebald,et al.  Use Of Slayrneural Strategies For Closed Loop Control Of Drug Infusion , 1990, [1990] Proceedings of the Twelfth Annual International Conference of the IEEE Engineering in Medicine and Biology Society.