Biomedical Signal Processing and Artificial Intelligence in Healthcare (Developments in Biomedical Engineering and Bioelectronics)

__Biomedical Signal Processing with Artificial Intelligence__, a new volume in the __Developments in Biomedical Engineering and Bioelectronics__ series, covers the basics of analog and digital data and data acquisition. The book explains the role of smart sensors, smart materials and wearables in relation to biomedical signals. It also provides background to statistical analysis in biomedical systems. Several types of biomedical signals are introduced and analyzed, including ECG and EEG signals. The role of Machine Learning, including Deep Learning, Neural Networks, and the implications of the expansion of artificial intelligence is also covered, as are biomedical images and their segmentation, classification and detection. This book covers all aspects of signals, from acquisition, the use of hardware and software, analyzing signals, and making use of AI in problem-solving. __Developments in Biomedical Engineering and Bioelectronics__ is a 10-volume series which covers recent developments, trends and advances in this field. Edited by leading academics in the field, and taking a multidisciplinary approach, this series is a forum for cutting-edge, contemporary review articles and contributions from key ‘up-and-coming’ academics across the full subject area. Cover Biomedical Signal Processing and Artificial Intelligence in Healthcare Copyright Dedication Contributors Foreword Preface Book chapters Introduction to biomedical signal processing and artificial intelligence Introduction to signal processing Biomedical signals Electrocardiogram Electroencephalogram Noise Thermal noise Flicker noise Power-line interference Filters FIR filters Frequency domain filters Computer-aided diagnosis (CAD): Why? Artificial intelligence (AI): An overview Fuzzy logic in artificial intelligence Questions and answers Describe other types of biomedical signals such as EMG and ERG State any two difficulties encountered in biomedical signal acquisition and analysis Provide a comparison between stationary and nonstationary processes. Are biosignals such EEG and ECG stationary or nonstati ... References Characterization of biomedical signals: Feature engineering and extraction Introduction Feature engineering Discrete Fourier transform Time-frequency analysis Statistical features Local binary patterns Feature ranking Variance threshold Correlation measures Information measures Class separability measures Feature selection Filter methods for feature selection Wrapper methods: Feature subset search Embedded methods Feature extraction Principal component analysis Fisher linear discriminant Summary Further reading Supervised and unsupervised learning Introduction Density estimation Maximum likelihood, maximum a posteriori, and Bayesian parameter estimation Estimating parameters for individual densities Nonparametric and Kernel density estimation Kernel density estimation Nearest neighbor density estimation Classification analysis Bayes classifier MVN discriminant functions Naive Bayes classifier Nonparametric Bayes classifier Discriminant functions Linear discriminants Perceptron discriminant Least squares methods Fishers linear discriminant Generalized discriminants Logistic regression Logistic regression Kernel discriminants Constrained discriminant functions Support vector machines Kernel support vector machines Training and generalization performance Evaluating performance Summary Further reading Machine learning in biomedical signal processing with ECG applications Introduction Automated ECG signal analysis The electrocardiogram Standard bipolar limb leads Augmented unipolar limb leads Precordial (chest) leads Clinical ECG features Cardiac arrhythmia Life-threatening arrhythmias The AAMI standard ECG heartbeat classifier ECG signal descriptor Intra- and interpatient paradigms Feature generation Ranking individual feature subsets Training and testing the final model Conclusions References Further reading Deep EEG: Deep learning in biomedical signal processing with EEG applications EEG data basics Fundamentals of deep convolutional neural networks (DCNNs) Why deep learning Basics of deep convolutional neural networks The perceptron CNN architecture Convolutions and the convolutional layer Padding Strided convolutions Loss and optimization: Updated weights and biases Optimization algorithms Minibatch gradient descent and stochastic gradient descent (SGD) Gradient descent with momentum Root mean square prop (RMSprop) Adam optimization (adaptive moment estimation) TensorFlow and keras for deep convolutional neural networks Deep learning frameworks Setting up a deep learning application Bias versus variance Regularization L2 regularization Dropout regularization Data augmentation Normalizing data input Data collection workflow (step-by-step) with a BCI device Preprocessing and training using tensorflow and keras Deployment and real-time applications with embedded systems Conclusion, challenges and future research Appendix A. Working with Pandas References Fuzzy logic in medicine Introduction to fuzzy logic Fuzzy sets The mathematical definition of fuzzy sets Representation of fuzzy sets Basic operations on fuzzy sets Properties of fuzzy sets Membership function Fuzzification Defuzzification An overview of the algebraic operations for fuzzy sets Application of fuzzy logic in medicine Fuzzy linear programming in medicine Fuzzy linear programming models Fuzzy multiple-criteria decision analysis in medicine Preference ranking organization method for enrichment evaluations (PROMETHEE) Fuzzy PROMETHEE (F-PROMETHEE) The technique for order of preference by similarity to ideal solution (TOPSIS) Challenges and opportunities Future direction Summary References Neural network applications in medicine Introduction to artificial neural networks Artificial neural network architectures Multilayer perceptron and neural networks Back propagation neural network Convolutional neural networks Applications on neurological and neuropsychiatric diseases Alzheimers disease Parkinsons disease Attention-deficit/hyperactivity disorder Autism spectrum disorder Challenges and opportunities Future directions Summary Acknowledgments References Analysis and management of sleep data Introduction Evolution of sleep medicine Sleep disorders Structure of sleep Macrostructure, sleep phases Microstructure, cyclic alternating patterns Sleep-related events Diagnostic standards for sleep data analysis Polysomnography Physiological parameters measured during polysomnography Automated analysis of polysomnographic data Ambulatory cardiorespiratory screening Actigraphy Body temperature Multichannel pressure measurement Drug-induced sleep endoscopy Acoustic analysis of breathing-related noise Conclusion Acknowledgments References Index Back Cover Biomedical Signal Processing and Artificial Intelligence in Healthcare is a new volume in the Developments in Biomedical Engineering and Bioelectronics series. This volume covers the basics of biomedical signal processing and artificial intelligence. It explains the role of machine learning in relation to processing biomedical signals and the applications in medicine and healthcare. The book provides background to statistical analysis in biomedical systems. Several types of biomedical signals are introduced and analyzed, including ECG and EEG signals. The role of Deep Learning, Neural Networks, and the implications of the expansion of artificial intelligence is covered. Biomedical Images are also introduced and processed, including segmentation, classification, and detection. This book covers different aspects of signals, from the use of hardware and software, and making use of artificial intelligence in problem solving.Dr Zgallai's book has up to date coverage where readers can find the latest information, easily explained, with clear examples and illustrations. The book includes examples on the application of signal and image processing employing artificial intelligence to Alzheimer, Parkinson, ADHD, autism, and sleep disorders, as well as ECG and EEG signals. Developments in Biomedical Engineering and Bioelectronics is a 10-volume series which covers recent developments, trends and advances in this field. Edited by leading academics in the field, and taking a multidisciplinary approach, this series is a forum for cutting-edge, contemporary review articles and contributions from key ‘up-and-coming'academics across the full subject area. The series serves a wide audience of university faculty, researchers and students, as well as industry practitioners. Coverage of the subject area and the latest advances and applications in biomedical signal processing and Artificial Intelligence Contributions by recognized researchers and field leaders On-line presentations, tutorials, application and algorithm examples Biomedical Signal Processing With Artificial Intelligence, A New Volume In The Developments In Biomedical Engineering And Bioelectronics Series, Covers The Basics Of Analog And Digital Data And Data Acquisition. The Book Explains The Role Of Smart Sensors, Smart Materials And Wearables In Relation To Biomedical Signals. It Also Provides Background To Statistical Analysis In Biomedical Systems. Several Types Of Biomedical Signals Are Introduced And Analyzed, Including Ecg And Eeg Signals. The Role Of Machine Learning, Including Deep Learning, Neural Networks, And The Implications Of The Expansion Of Artificial Intelligence Is Also Covered, As Are Biomedical Images And Their Segmentation, Classification And Detection. This Book Covers All Aspects Of Signals, From Acquisition, The Use Of Hardware And Software, Analyzing Signals, And Making Use Of Ai In Problem-solving. Developments In Biomedical Engineering And Bioelectronics Is A 10-volume Series Which Covers Recent Developments, Trends And Advances In This Field. Edited By Leading Academics In The Field, And Taking A Multidisciplinary Approach, This Series Is A Forum For Cutting-edge, Contemporary Review Articles And Contributions From Key 'up-and-coming' Academics Across The Full Subject Area. Presents Comprehensive Coverage And The Latest Advances And Applications In Biomedical Signal Processing Contains Contributions From Recognized Researchers And Field Leaders Includes Online Presentations, Tutorials, Applications And Algorithm Examples