Ram Bilas Pachori - Böcker

Signal Processing Driven Machine Learning Techniques for Cardiovascular Data Processing features recent advances in machine learning coupled with new signal processing-based methods for cardiovascular data analysis. Topics in this book include machine learning methods such as supervised learning, unsupervised learning, semi-supervised learning, and meta-learning combined with different signal processing techniques such as multivariate data analysis, time-frequency analysis, multiscale analysis, and feature extraction techniques for the detection of cardiovascular diseases, heart valve disorders, hypertension, and activity monitoring using ECG, PPG, and PCG signals.In addition, this book also includes the applications of digital signal processing (time-frequency analysis, multiscale decomposition, feature extraction, non-linear analysis, and transform domain methods), machine learning and deep learning (convolutional neural network (CNN), recurrent neural network (RNN), transformer and attention-based models, etc.) techniques for the analysis of cardiac signals. The interpretable machine learning and deep learning models combined with signal processing for cardiovascular data analysis are also covered.Provides details regarding the application of various signal processing and machine learning-based methods for cardiovascular signal analysisCovers methodologies as well as experimental results and studiesHelps readers understand the use of different cardiac signals such as ECG, PCG, and PPG for the automated detection of heart ailments and other related biomedical applications

Non-Stationary and Nonlinear Data Processing for Automated Computer-Aided Medical Diagnosis demonstrates the applications of machine learning and deep learning combined with signal processing techniques for human-machine interface applications using EMG signals. The book includes the analysis and classification of various heart diseases based on bio-signals like electrocardiogram (ECG), photoplethysmography (PPG), and phonocardiogram (PCG) signals. Various machine learning approaches, including advanced algorithms like multivariate signal processing, time-frequency analysis, and nonlinear signal processing are covered for CAD of neural, muscular, and cardiovascular diseases. The methods for CAD of various brain disorders are also included.Presented techniques utilize advanced non-stationary and nonlinear signal processing, along with machine learning and deep learning-based classification processes. CAD methods for diagnosing various neurological diseases are based on bio-signals such as electroencephalogram (EEG) and magnetoencephalogram (MEG), as well as medical images like magnetic resonance imaging (MRI) and computerized tomography (CT). Finally, the book addresses various types of medical signals and images, integrating nonlinear and non-stationary signal processing, machine learning, and deep learning within the CAD framework for diagnosing various diseases.Focuses on various signal analysis techniquesAddresses a wide range of applications, including the analysis and classification of signals related to neural, muscular, and cardiovascular diseasesCovers CAD methods for diagnosing various brain disorders using bio-signals like EEG and medical images like MRI and CT scansExplores advanced algorithms and methodologies, such as multivariate signal processing, time-frequency analysis, and nonlinear signal processing

Most of the real-life signals are non-stationary in nature. The examples of such signals include biomedical signals, communication signals, speech, earthquake signals, vibration signals, etc. Time-frequency analysis plays an important role for extracting the meaningful information from these signals. The book presents time-frequency analysis methods together with their various applications. The basic concepts of signals and different ways of representing signals have been provided. The various time-frequency analysis techniques namely, short-time Fourier transform, wavelet transform, quadratic time-frequency transforms, advanced wavelet transforms, and adaptive time-frequency transforms have been explained. The fundamentals related to these methods are included. The various examples have been included in the book to explain the presented concepts effectively. The recently developed time-frequency analysis techniques such as, Fourier-Bessel series expansion-based methods, synchrosqueezed wavelet transform, tunable-Q wavelet transform, iterative eigenvalue decomposition of Hankel matrix, variational mode decomposition, Fourier decomposition method, etc. have been explained in the book. The numerous applications of time-frequency analysis techniques in various research areas have been demonstrated. This book covers basic concepts of signals, time-frequency analysis, and various conventional and advanced time-frequency analysis methods along with their applications. The set of problems included in the book will be helpful to gain an expertise in time-frequency analysis. The material presented in this book will be useful for students, academicians, and researchers to understand the fundamentals and applications related to time-frequency analysis.

Most of the real-life signals are non-stationary in nature. The examples of such signals include biomedical signals, communication signals, speech, earthquake signals, vibration signals, etc. Time-frequency analysis plays an important role for extracting the meaningful information from these signals. The book presents time-frequency analysis methods together with their various applications. The basic concepts of signals and different ways of representing signals have been provided. The various time-frequency analysis techniques namely, short-time Fourier transform, wavelet transform, quadratic time-frequency transforms, advanced wavelet transforms, and adaptive time-frequency transforms have been explained. The fundamentals related to these methods are included. The various examples have been included in the book to explain the presented concepts effectively. The recently developed time-frequency analysis techniques such as, Fourier-Bessel series expansion-based methods, synchrosqueezed wavelet transform, tunable-Q wavelet transform, iterative eigenvalue decomposition of Hankel matrix, variational mode decomposition, Fourier decomposition method, etc. have been explained in the book. The numerous applications of time-frequency analysis techniques in various research areas have been demonstrated. This book covers basic concepts of signals, time-frequency analysis, and various conventional and advanced time-frequency analysis methods along with their applications. The set of problems included in the book will be helpful to gain an expertise in time-frequency analysis. The material presented in this book will be useful for students, academicians, and researchers to understand the fundamentals and applications related to time-frequency analysis.

The book provides details regarding the application of various signal processing and artificial intelligence-based methods for electroencephalography data analysis. It will help readers in understanding the use of electroencephalography signals for different neural information processing and cognitive neuroscience applications. The book:Covers topics related to the application of signal processing and machine learning-based techniques for the analysis and classification of electroencephalography signalsPresents automated methods for detection of neurological disorders and other applications such as cognitive task recognition, and brain-computer interfaceHighlights the latest machine learning and deep learning methods for neural signal processingDiscusses mathematical details for the signal processing and machine learning algorithms applied for electroencephalography data analysisShowcases the detection of dementia from electroencephalography signals using signal processing and machine learning-based techniquesIt is primarily written for senior undergraduates, graduate students, and researchers in the fields of electrical engineering, electronics and communications engineering, and biomedical engineering.

The book provides details regarding the application of various signal processing and artificial intelligence-based methods for electroencephalography data analysis. It will help readers in understanding the use of electroencephalography signals for different neural information processing and cognitive neuroscience applications. The book:Covers topics related to the application of signal processing and machine learning-based techniques for the analysis and classification of electroencephalography signalsPresents automated methods for detection of neurological disorders and other applications such as cognitive task recognition, and brain-computer interfaceHighlights the latest machine learning and deep learning methods for neural signal processingDiscusses mathematical details for the signal processing and machine learning algorithms applied for electroencephalography data analysisShowcases the detection of dementia from electroencephalography signals using signal processing and machine learning-based techniquesIt is primarily written for senior undergraduates, graduate students, and researchers in the fields of electrical engineering, electronics and communications engineering, and biomedical engineering.

Intelligent data analytics for terror threat prediction is an emerging field of research at the intersection of information science and computer science, bringing with it a new era of tremendous opportunities and challenges due to plenty of easily available criminal data for further analysis.This book provides innovative insights that will help obtain interventions to undertake emerging dynamic scenarios of criminal activities. Furthermore, it presents emerging issues, challenges and management strategies in public safety and crime control development across various domains. The book will play a vital role in improvising human life to a great extent. Researchers and practitioners working in the fields of data mining, machine learning and artificial intelligence will greatly benefit from this book, which will be a good addition to the state-of-the-art approaches collected for intelligent data analytics. It will also be very beneficial for those who are new to the field and need to quickly become acquainted with the best performing methods. With this book they will be able to compare different approaches and carry forward their research in the most important areas of this field, which has a direct impact on the betterment of human life by maintaining the security of our society. No other book is currently on the market which provides such a good collection of state-of-the-art methods for intelligent data analytics-based models for terror threat prediction, as intelligent data analytics is a newly emerging field and research in data mining and machine learning is still in the early stage of development.

This book is a collection of best selected research papers presented at International Conference on Next-Generation Networks and Deployable Artificial Intelligence (NGNDAI-2025) organized by Department of Computer Science and Engineering, Motilal Nehru National Institute of Technology Allahabad, Prayagraj, India, during September 18–20, 2025. The book includes original research by researchers working in the field of artificial intelligence, machine learning, intelligent networks, robotics, and next-generation communication technologies.

The book covers the most recent developments in machine learning, signal analysis, and their applications. It covers the topics of machine intelligence such as: deep learning, soft computing approaches, support vector machines (SVMs), least square SVMs (LSSVMs) and their variants; and covers the topics of signal analysis such as: biomedical signals including electroencephalogram (EEG), magnetoencephalography (MEG), electrocardiogram (ECG) and electromyogram (EMG) as well as other signals such as speech signals, communication signals, vibration signals, image, and video. Further, it analyzes normal and abnormal categories of real-world signals, for example normal and epileptic EEG signals using numerous classification techniques. The book is envisioned for researchers and graduate students in Computer Science and Engineering, Electrical Engineering, Applied Mathematics, and Biomedical Signal Processing.

This book covers latest advancements in the areas of machine learning, computer vision, pattern recognition, computational learning theory, big data analytics, network intelligence, signal processing and their applications in real world.

This book covers latest advancements in the areas of machine learning, computer vision, pattern recognition, computational learning theory, big data analytics, network intelligence, signal processing and their applications in real world. The topics covered in machine learning involves feature extraction, variants of support vector machine (SVM), extreme learning machine (ELM), artificial neural network (ANN) and other areas in machine learning. The mathematical analysis of computer vision and pattern recognition involves the use of geometric techniques, scene understanding and modelling from video, 3D object recognition, localization and tracking, medical image analysis and so on. Computational learning theory involves different kinds of learning like incremental, online, reinforcement, manifold, multi-task, semi-supervised, etc. Further, it covers the real-time challenges involved while processing big data analytics and stream processing with theintegration of smart data computing services and interconnectivity. Additionally, it covers the recent developments to network intelligence for analyzing the network information and thereby adapting the algorithms dynamically to improve the efficiency. In the last, it includes the progress in signal processing to process the normal and abnormal categories of real-world signals, for instance signals generated from IoT devices, smart systems, speech, videos, etc., and involves biomedical signal processing: electrocardiogram (ECG), electroencephalogram (EEG), magnetoencephalography (MEG) and electromyogram (EMG).

It also includes the progress in signal processing to process the normal and abnormal categories of real-world signals such as signals generated from IoT devices, smart systems, speech, and videos and involves biomedical signal processing: electrocardiogram (ECG), electroencephalogram (EEG), magnetoencephalography (MEG), electromyogram (EMG), etc.