Nonlinear Biomedical Signal Processing, Volume 1 Fuzzy Logic, Neural Networks, and New Algorithms

by Akay, Metin

• ISBN13: 9780780360112
• ISBN10: 0780360117
• Edition: 1st
• Format: Hardcover
• Copyright: 2000-08-04
• Publisher: Wiley-IEEE Press
• More Book Details

Summary

"Nonlinear Biomedical Signal Processing, Volume I" is a valuable reference tool for medical researchers, medical faculty and advanced graduate students as well as for practicing biomedical engineers. "Nonlinear Biomedical Signal Processing, Volume I" is an excellent companion to "Nonlinear Biomedical Signal Processing, Volume II: Dynamic Analysis and Modeling,"

Author Biography

About the Editor Metin Akay is currently an assistant professor at Dartmouth College. A noted speaker, editor, and author, Dr. Akay has spent several years conducting research in the areas of fuzzy neural networks and signal processing, wavelet transform, and detection and estimation theory. His biomedical research areas include the autonomic nervous system, maturation, respiratory-related evoked response, noninvasive detection of coronary artery disease, and estimation of cardiac output. Dr. Akay is the founding series editor of the IEEE Press Series on Biomedical Engineering. In 1997 he received the prestigious Early Career Achievement Award from the IEEE Engineering in Medicine and Biology Society (EMBS). He is the program chair of both the annual IEEE EMBS Conference and Summer School for 2001. Dr. Akay has published several papers in the field and authored or coauthored eleven books, including Time Frequency and Wavelets in Biomedical Signal Processing (IEEE Press, 1998) and Nonlinear Biomedical Signal Processing, Volume II: Dynamic Analysis and Modeling (IEEE Press, 2000). He holds two U.S. patents.

Table of Contents

Preface	xiii
List of Contributors	xv
Uncertainty Management in Medical Applications	1	(26)
Bernadette Bouchon-Meunier
Introduction	1	(1)
Imperfect Knowledge	1	(3)
Types of Imperfections	1	(1)
Uncertainties	1	(1)
Imprecisions	2	(1)
Incompleteness	2	(1)
Causes of Imperfect Knowledge	2	(1)
Choice of a Method	2	(2)
Fuzzy Set Theory	4	(8)
Introduction to Fuzzy Set Theory	4	(1)
Main Basic Concepts of Fuzzy Set Theory	5	(1)
Definitions	5	(1)
Operations on Fuzzy Sets	6	(2)
The Zadeh Extension Principle	8	(2)
Fuzzy Arithmetic	10	(1)
Fuzzy Relations	11	(1)
Possibility Theory	12	(5)
Possibility Measures	12	(2)
Possibility Distributions	14	(1)
Necessity Measures	15	(2)
Relative Possibility and Necessity of Fuzzy Sets	17	(1)
Approximate Reasoning	17	(6)
Linguistic Variables	17	(2)
Fuzzy Propositions	19	(1)
Possibility Distribution Associated with a Fuzzy Proposition	19	(2)
Fuzzy Implications	21	(1)
Fuzzy Inferences	22	(1)
Examples of Applications of Numerical Methods in Biology	23	(1)
Conclusion	24	(3)
References	25	(2)
Applications of Fuzzy Clustering to Biomedical Signal Processing and Dynamic System Identification	27	(26)
Amir B. Geva
Introduction	27	(3)
Time Series Prediction and System Identification	28	(1)
Fuzzy Clustering	29	(1)
Nonstationary Signal Processing Using Unsupervised Fuzzy Clustering	29	(1)
Methods	30	(10)
State Recognition and Time Series Prediction Using Unsupervised Fuzzy Clustering	31	(1)
Features Extraction and Reduction	32	(1)
Spectrum Estimation	33	(1)
Time-Frequency Analysis	33	(1)
The Hierarchical Unsupervised Fuzzy Clustering (HUFC) Algorithm	34	(2)
The Weighted Unsupervised Optimal Fuzzy Clustering (WUOFC) Algorithm	36	(1)
The Weighted Fuzzy K-Mean (WFKM) Algorithm	37	(2)
The Fuzzy Hypervolume Cluster Validity Criteria	39	(1)
The Dynamic WUOFC Algorithm	40	(1)
Results	40	(8)
State Recognition and Events Detection	41	(3)
Time Series Prediction	44	(4)
Conclusion and Discussion	48	(5)
Acknowledgments	51	(1)
References	51	(2)
Neural Networks: A Guided Tour	53	(16)
Simon Haykin
Some Basic Definitions	53	(1)
Supervised Learning	53	(6)
Multilayer Perceptrons and Back-Propagation Learning	54	(3)
Radial Basis Function (RBF) Networks	57	(1)
Support Vector Machines	58	(1)
Unsupervised Learning	59	(2)
Principal Components Analysis	59	(1)
Self-Organizing Maps	59	(1)
Information-Theoretic Models	60	(1)
Neurodynamic Programming	61	(1)
Temporal Processing Using Feed-Forward Networks	62	(1)
Dynamically Driven Recurrent Networks	63	(4)
Concluding Remarks	67	(2)
References	67	(2)
Neural Networks in Processing and Analysis of Biomedical Signals	69	(29)
Homayoun Nazeran
Khosrow Behbehani
Overview and History of Artificial Neural Networks	69	(8)
What is an Artificial Neural Network?	70	(1)
How Did ANNs Come About?	71	(2)
Attributes of ANNs	73	(1)
Learning in ANNs	74	(1)
Supervised Learning	74	(1)
Unsupervised Learning	75	(1)
Hardware and Software Implementation of ANNs	76	(1)
Application of ANNs in Processing Information	77	(21)
Processing and Analysis of Biomedical Signals	77	(1)
Detection and Classification of Biomedical Signals Using ANNs	77	(1)
Detection and Classification of Electrocardiography Signals	78	(3)
Detection and Classification of Electromyography Signals	81	(2)
Detection and Classification of Electroencephalography Signals	83	(2)
Detection and Classification of Electrogastrography Signals	85	(1)
Detection and Classification of Respiratory Signals	86	(1)
Detection of Goiter-Induced Upper Airway Obstruction	86	(2)
Detection of Pharyngeal Wall Vibration During Sleep	88	(1)
ANNs in Biomedical Signal Enhancement	89	(1)
ANNs in Biomedical Signal Compression	89	(2)
Additional Reading and Related Material	91	(1)
Appendix: Back-Propagation Optimization Algorithm	92	(3)
References	95	(3)
Rare Event Detection in Genomic Sequences by Neural Networks and Sample Stratification	98	(24)
Wooyoung Choe
Okan K. Ersoy
Minou Bina
Introduction	98	(1)
Sample Stratification	98	(1)
Stratifying Coefficients	99	(5)
Derivation of a Modified Back-Propagation Algorithm	100	(2)
Approximation of A Posteriori Probabilities	102	(2)
Bootstrap Stratification	104	(2)
Bootstrap Procedures	104	(1)
Bootstrapping of Rare Events	105	(1)
Subsampling of Common Events	105	(1)
Aggregating of Multiple Neural Networks	105	(1)
The Bootstrap Aggregating Rare Event Neural Networks	105	(1)
Data Set Used in the Experiments	106	(7)
Genomic Sequence Data	106	(1)
Normally Distributed Data 1, 2	107	(6)
Four-Class Synthetic Data	113	(1)
Experimental Results	113	(7)
Experiments with Genomic Sequence Data	113	(2)
Experiments with Normally Distributed Data 1	115	(3)
Experiments with Normally Distributed Data 2	118	(1)
Experiments with Four-Class Synthetic Data	118	(2)
Conclusions	120	(2)
References	120	(2)
An Axiomatic Approach to Reformulating Radial Basis Neural Networks	122	(36)
Nicolaos B. Karayiannis
Introduction	122	(3)
Function Approximation Models and RBF Neural Networks	125	(2)
Reformulating Radial Basis Neural Networks	127	(2)
Admissible Generator Functions	129	(4)
Linear Generator Functions	129	(3)
Exponential Generator Functions	132	(1)
Selecting Generator Functions	133	(8)
The Blind Spot	134	(2)
Criteria for Selecting Generator Functions	136	(1)
Evaluation of Linear and Exponential Generator Functions	137	(1)
Linear Generator Functions	137	(1)
Exponential Generator Functions	138	(3)
Learning Algorithms Based on Gradient Descent	141	(3)
Batch Learning Algorithms	141	(2)
Sequential Learning Algorithms	143	(1)
Generator Functions and Gradient Descent Learning	144	(2)
Experimental Results	146	(8)
Conclusions	154	(4)
References	155	(3)
Soft Learning Vector Quantization and Clustering Algorithms Based on Reformulation	158	(40)
Nicolaos B. Karayiannis
Introduction	158	(1)
Clustering Algorithms	159	(9)
Crisp and Fuzzy Partitions	160	(2)
Crisp c-Means Algorithm	162	(2)
Fuzzy c-Means Algorithm	164	(1)
Entropy-Constrained Fuzzy Clustering	165	(3)
Reformulating Fuzzy Clustering	168	(3)
Reformulating the Fuzzy c-Means Algorithm	168	(2)
Reformulating ECFC Algorithms	170	(1)
Generalized Reformulation Function	171	(3)
Update Equations	171	(2)
Admissible Reformulation Functions	173	(1)
Special Cases	173	(1)
Constructing Reformulation Functions: Generator Functions	174	(1)
Constructing Admissible Generator Functions	175	(3)
Increasing Generator Functions	176	(1)
Decreasing Generator Functions	176	(1)
Duality of Increasing and Decreasing Generator Functions	177	(1)
From Generator Functions to LVQ and Clustering Algorithms	178	(4)
Competition and Membership Functions	178	(2)
Special Cases: Fuzzy LVQ and Clustering Algorithms	180	(1)
Linear Generator Functions	180	(1)
Exponential Generator Functions	181	(1)
Soft LVQ and Clustering Algorithms Based on Nonlinear Generator Functions	182	(4)
Implementation of the Algorithms	185	(1)
Initialization of Soft LVQ and Clustering Algorithms	186	(2)
A Prototype Splitting Procedure	186	(1)
Initialization Schemes	187	(1)
Magnetic Resonance Image Segmentation	188	(6)
Conclusions	194	(4)
Acknowledgments	195	(1)
References	196	(2)
Metastable Associative Network Models of Neuronal Dynamics Transition During Sleep	198	(18)
Mitsuyuki Nakao
Mitsuaki Yamamoto
Dynamics Transition of Neuronal Activities During Sleep	199	(2)
Physiological Substrate of the Global Neuromodulation	201	(1)
Neural Network Model	201	(2)
Spectral Analysis of Neuronal Activities in Neural Network Model	203	(1)
Dynamics of Neural Network in State Space	204	(2)
Metastability of the Network Attractor	206	(4)
Escape Time Distributions in Metastable Equilibrium States	206	(1)
Potential Walls Surrounding Metastable States	207	(3)
Possible Mechanisms of the Neuronal Dynamics Transition	210	(1)
Discussion	211	(5)
Acknowledgments	213	(1)
References	213	(3)
Artificial Neural Networks for Spectroscopic Signal Measurement	216	(17)
Chii-Wann Lin
Tzu-Chien Hsiao
Mang-Ting Zeng
Hui-Hua Kenny Chiang
Introduction	216	(1)
Methods	217	(4)
Partial Least Squares	217	(1)
Back-Propagation Networks	218	(1)
Radial Basis Function Networks	219	(1)
Spectral Data Collection and Preprocessing	220	(1)
Results	221	(1)
PLS	221	(1)
BP	221	(1)
RBF	222	(1)
Discussion	222	(11)
Acknowledgments	231	(1)
References	231	(2)
Applications of Feed-Forward Neural Networks in the Electrogastrogram	233	(24)
Zhiyue Lin
J. D. Z. Chen
Introduction	233	(1)
Measurements and Preprocessing of the EGG	234	(5)
Measurements of the EGG	234	(1)
Preprocessing of the EGG Data	235	(1)
ARMA Modeling Parameters	235	(1)
Running Power Spectra	236	(2)
Amplitude (Power) Spectrum	238	(1)
Applications in the EGG	239	(13)
Detection and Deletion of Motion Artifacts in EGG Recordings	239	(1)
Input Data to the NN	239	(1)
Experimental Results	240	(1)
Identification of Gastric Contractions from the EGG	241	(1)
Experimental Data	241	(2)
Experimental Results	243	(1)
Classification of Normal and Abnormal EGGs	244	(2)
Experimental Data	246	(1)
Structure of the NN Classifier and Performance Indexes	246	(2)
Experimental Results	248	(1)
Feature-Based Detection of Delayed Gastric Emptying from the EGG	249	(1)
Experimental Data	250	(1)
Experimental Results	251	(1)
Discussion and Conclusions	252	(5)
References	253	(4)
Index	257	(2)
About the Editor	259