Machine Learning in Signal Processing : Applications, Challenges, and Road Ahead book cover
1st Edition

Machine Learning in Signal Processing
Applications, Challenges, and Road Ahead

  • Available for pre-order. Item will ship after December 10, 2021
ISBN 9780367618902
December 10, 2021 Forthcoming by Chapman and Hall/CRC
368 Pages 211 B/W Illustrations

SAVE ~ $36.00
was $180.00
USD $144.00

Prices & shipping based on shipping country


Book Description

Machine Learning in Signal Processing: Applications, Challenges and Road Ahead offers a comprehensive approach towards research orientation for familiarising ‘signal processing (SP)’ concepts to machine learning (ML).

Machine Learning (ML), as the driving force of the wave of Artificial Intelligence (AI), provides powerful solutions to many real-world technical and scientific challenges. This book will present the most recent and exciting advances in signal processing for Machine Learning (ML).

The focus is on understanding the contributions of signal processing and ML and its aim to solve some of the Artificial Intelligence (AI) and Machine Learning (ML) challenges.


●       Fully focused on addressing the missing connection between signal processing and ML

●       Provides one-stop guide reference for the readers

●       Oriented towards the material and flow with regard to general introduction, technical aspects

●       Comprehensively elaborates on the material with examples and diagrams


This book is complete outlet and designed exclusively for advanced undergraduate, post graduate students, research scholars, faculties and academicians of Computer Science and Engineering, Computer Science and Applications as well as Electronics & Telecommunication Engineering.

Table of Contents

Machine Learning Espousal in Signal Processing: Applications, Challenges and Road Ahead

Table of Contents


Chapter-1 Introduction to Signal Processing and Machine Learning

Kavita Somraj, Higher Colleges of Technology, Dubai, United Arab Emirates


1.1   Introduction

1.2   Basic Terminologies

1.2.1          Signal Processing Continuous and Discrete Signals Sampling and Quantization Change of Basis    Importance of time domain and frequency domain analysis

1.2.2          Machine Learning

1.3             Distance ased signal classification, Nearest Neighbor Classifier and Hilbert Space

1.3.1          Distance based Signal Classification Metric Space Normal Linear Space Inner Product Space

1.3.2          Nearest Neighbor Classification

1.3.3          Hilbert Space

1.4             Fusion of Machine Learning in Signal Processing

1.5             Benefits of Machine Learning in Signal Processing

1.6             Conclusion



Chapter-2 Learning Theory (Supervised/Unsupervised) for Signal Processing

Ruby Jain, Assistant Professor, Symbiosis Skills and Professional University, Pune

Bhuvan Jain, Assistant Professor, DPU IDL, Pune

Manimala Puri, Director Academics, Symbiosis Open Education Society, Pune



2.1 Introduction

2.2 Machine Learning

2.3 Machine Learning Algorithms

2.4 Supervised Learning

2.5 Unsupervised Learning

2.6 Semi-Supervised Learning

2.7 Reinforcement Learning

2.8 Use case of Signal Processing using Supervised and Unsupervised Learning

2.9 Deep Learning for Signal Data

2.10 Conclusion



Chapter-3 Supervised and Unsupervised Learning Theory for Signal Processing

Sowmya K B, Assistant Professor, Department of ECE, RV College of Engineering, Begaluru, India



3.1 Introduction

3.2 Supervised Learning Method

3.2.1 Classification Problems

3.2.2 Regression Problems

3.2.3 Examples of Supervised Learning

3.3 Unsupervised Learning Method

            3.3.1 Illustrations of Unsupervised Learning

3.4 Semi-Supervised Learning Method

3.5 Binary Classification

3.5.1 Different Classes

3.5.2 Classification in Preparation

3.6 Conclusion



Chapter-4 Applications of Signal Processing

Anuj Kumar Singh, Amity University, Gurugram

Ankit Garg, Amity University, Gurugram


4.1 Introduction

4.2 Audio Signal Processing

            4.2.1 Machine Learning in Audio Signal Processing

               Spectrum and Cepstrum

               Mel Frequency Cepstral Coefficients (MFCC)

               Gammatone Frequency Cepstral Coefficients (GFCC)

               Building the classifier

4.3 Audio Compression

            4.3.1 Modeling and Coding

            4.3.2 Lossless Compression

            4.3.3 Lossy Compression

            4.3.4 Compressed Audio with Machine Learning Algorithms

4.4 Digital Image Processing

4.4.1 Fields Overlapping with Image Processing

4.4.2 Digital Image Signal Processing

4.4.3 Machine Learning with Digital Image Processing

   Image Classification

   Data Labelling

   Location Detection

4.5 Video Compression

            4.5.1 Video Compression Model

            4.5.2 Machine Learning in Video Compression

               Development Savings

               Improving Encoder Density

4.6 Digital Communications

            4.6.1 Machine Learning in Digital Communications

               Communication Networks

               Wireless Communication

               Smart Infrastructure and IoT

               Security and Privacy

               Multimedia Communication

            4.6.2 Healthcare

               Personalized Medical Treatment

               Clinical Research and Trial

               Diagnosis of Disease

               Smart Health Records

               Medical Imaging

               Drug Discovery

               Outbreak Protection

            4.6.3 Seismology

               Interpreting Seismic Observations

               Machine Learning in Seismology

            4.6.4 Speech Recognition

            4.6.5 Computer Vision

            4.6.6 Economic Forecasting

4.7 Conclusion



Chapter-5 Deep Dive in Deep Learning: Computer Vision, Natural Language Processing and Signal Processing

V.Ajantha Devi, Research Head, AP3 Solutions, Chennai, India

Mohd Naved, Assistant Professor, Jagannath University, Delhi, India



5.1 Deep Learning: Introduction

5.2 Past, Present and Future on Deep Learning

5.3 Natural Language Processing

            5.3.1 Word Embeddings

            5.3.2 Global Vectors for Word Representation

            5.3.3 Convolutional Neural Networks

            5.3.4 Feature Selection and Pre-processing

            5.3.5 Named Entity Recognition

5.4 Image Processing

            5.4.1 Introduction to Image Processing and Computer Vision

            5.4.2 Localization

            5.4.3 Smart Cities and Surveillance

            5.4.4 Medical Imaging

            5.4.5 Object Representation

            5.4.6 Object Detection

5.5 Audio Processing and Deep Learning

            5.5.1 Audio Data Handling Using Python

            5.5.2 Spectrogram

            5.5.3 Wavelet-Based Feature Extraction

            5.5.4 Current Methods

5.6 Conclusion



Chapter-6 Brain Computer Interface

Dr. Paras Nath Singh, CMRIT, Bangalore, India


6.1 Introduction to BCI and its Components

6.2 Framework/Architecture of BCI

6.3 Functions of BCI

            6.3.1 Correspondence and Control

            6.3.2 Client state checking

6.4 Applications of BCI

            6.4.1 Healthcare

            6.4.2 Neuro-ergonomic and Smart Environment

            6.4.3 Neuro-Marketing and Advertisement

            6.4.4. Pedagogical and Self-Regulating Oneself

            6.4.5 Games and Entertainment

            6.4.6 Security and Authentication

6.5 Signal Acquisition

            6.5.1 Invasive Techniques


                       ECoG (Electrocorticography) & Cortical Surface

            6.5.2 Non-Invasive Techniques


   fMRI (functional Magnetic Resonance Imaging)

   fNIRS (functional Near-Infrared Spectroscopy)

   EEG (Electroencephalogram)

6.6 Electrical Signal of BCI

            6.6.1 Evoked Potential or Evoked Response (EP)

            6.6.2 Event Related Desynchronization and Synchronization

6.7 Challenges of BCI and Proposed Solutions

            6.7.1 Challenges of Usability

            6.7.2 Technical Issues

            6.7.3 Proposed Solutions

               Noise Removal

               Disconnectedness of Multiple Classes

6.8 Conclusion



Chapter-7 Adaptive Filters

Sowmya K B, Chandana, Anjana Mahaveer Daigond

ECE Department, RV College of Engineering Bengaluru, India



7.1 Introduction

            7.1.1 Adaptive Filtering Problem

7.2 Linear Adaptive Filter Implementation

            7.2.1 Stochastic Gradient Approach

            7.2.2 Least Square Estimation

7.3 Non-Linear Adaptive Filters

            7.3.1 Volterra Based Non-Linear Adaptive Filter

7.4 Applications of Adaptive Filter

            7.4.1 Biomedical Applications

               ECG Power-Line Interference Removal

               Maternal-Foetal ECG Separation

            7.4.2 Speech Processing

               Noise Cancellation

            7.4.3 Communication Systems

               Channel Equalization in Data Transmission Systems

               Multiple Access Interference Mitigation in CDMA

            7.4.4 Adaptive Feedback Cancellation in Hearing Aids

7.5 Neural Network

            7.5.1 Learning Techniques in ANN

7.6 Single and Multi-Layer Neural Net

            7.6.1 Single Layer Neural Networks

            7.6.2 Multi-Layer Neural Net

7.7 Applications of Neural Networks

            7.7.1 ECG Classification

            7.7.2 Speech Recognition

            7.7.3 Communication Systems

               Mobile Station Location Identification using ANN

               ANN Based Call Handoff Management Scheme for Mobile Cellular Network

               A Hybrid Path Loss Prediction Model based on Artificial Neural Networks

               Classification of Primary Radio Signals

               Channel Capacity Estimation using ANN



Chapter-8 Adaptive Decision Feedback Equalizer Based on Wavelet Neural Network



Saikat Majumder,

National Institute of Technology, Raipur, Chhattisgarh, India.

8.1 Introduction

8.2 System Model

            8.2.1 Channel Equalization

            8.2.3 Decision Feedback Equalization

8.3 Wavelet Neural Network

            8.3.1 Wavelet Analysis

            8.3.2 Wavelet Neural Network

8.4 Multidimensional Wavelet Neural Network

8.5 Proposed WNN DFE Architecture

            8.5.1 Equalizer Architecture

            8.5.2 Cuckoo Search Optimization

            8.5.3 CSO-based Training of WNN DFE

            8.5.4 Simulation Results

               MSE Performance

               Effect of EVR

               Effect of Time-varying channel

               BER Performance Evaluation

8.6 Conclusion










Chapter-9 Intelligent Video Surveillance Systems using Deep Learning Methods

Anjanadevi Bondalapati, Department of Information Technology, MVGR College of Engineering, Vizianagaram, India

Manjaiah D H, Department of Computer Science, Mangalore University, India



9.1 Introduction

            9.1.1 Deep Learning

            9.1.2 Deep Learning- Past, Present and Future

            9.1.3 Recent Methodologies

            9.1.4 Concepts used in Deep Learning

               Convolutional Neural Network

9.2 Natural Language Processing Using Deep Learning

            9.2.1 Introduction to Natural Language Processing (NLP)

9.2.2 Word-Vector Representations (Simple Word, Multi Word Prototypes and Global Contexts)

   Word Vector Representation

   Simple Word2VectorRepresentation

   Learning Representation Through Backpropagation

   Natural Language Tasks for Text Classification

   Natural Language Tasks for Image Description Generation

9.3 Machine Translation Using Gated Recurrent Neural Networks (GRNN) and Long Short Time Memory (LSTM)

9.3.1 Gated Recurrent Units (GRUs)

9.3.2 Long Short Term Memory (LSTM)

9.3.3 Results Analysis

9.4 Image Processing Using Deep Learning Algorithms

            9.4.1 Introduction to Image Processing and Computer Vision

            9.4.2 Data preparation for Image processing tasks

            9.4.3 Classification Algorithms with Applications


9.5 Light Weight Deep Convolution Neural Network Architecture (LW-DCNN)

            9.5.1 Introduction

            9.5.2 Architecture

            9.5.3 Results

9.6 Improved Unified Model for Moving Object Detection

            9.6.1 Introduction

            9.6.2 Object Detection Architecture

            9.6.3 Results

            9.6.4 Comparison Analysis

            9.6.5 Applications to Human Action Recognition


9.7 Wavelet Based feature extraction methods and application to audio signals

            9.7.1 Introduction to Discrete Wavelet Transform Techniques

            9.7.2 Wavelet based selection methods

            9.7.3 Hybrid feature extraction method for classification

            9.7.4 Results

            9.7.5 Various applications of Audio Signals




Chapter-10 Stationary Signal, Autocorrelation, Linear and Discriminant Analysis

Dr. Bandana Mahapatra, Symbiosis Skills and Professional University, Pune, India

Kumar Sanjay Bhorekar, Symbiosis Skills and Professional University, Pune, India



10.1 Introduction

10.2 Fundamentals of Linear Algebra and Probability Theory

            10.2.1 What is Linear Algebra?

            10.2.2 Probability Theory

10.3 Basic Concepts of Machine Learning

10.4 Supervised and Unsupervised ML Techniques for Digital Signal Processing

10.5 Applications of Signal Based Identification using Machine Learning Approach

            10.5.1 ML for Audio Classification

            10.5.2 Audio Signals Classification

            10.5.3 ML for Image Processing

10.6 Applications of ML methods in Optical Communications





Chapter-11 Intelligent System for Fault Detection in Rotating Electromechanical Machines

Saad Chakkor

LabTIC, ENSA of Tangier, University of AbdelmalekEssaâdi, Route de Ziaten Km 10,

Tanger Principale, B.P : 1818 – Tangier, Morocco

Pascal Doré

LabTIC, ENSA of Tangier, University of AbdelmalekEssaâdi, Route de Ziaten Km 10,

Tanger Principale, B.P : 1818 – Tangier, Morocco

Ahmed El Oualkad

LabTIC, ENSA of Tangier, University of AbdelmalekEssaâdi, Route de Ziaten Km 10,

Tanger Principale, B.P : 1818 – Tangier, Morocco



11.1 Introduction

11.2 Related works

11.3 Asynchronous Machines

11.4 Electromechanical Defects

            11.4.1 Bearing Faults

            11.4.2 Broken rotar bar faults

            11.4.3 Eccentricity defects

            11.4.4 Misalignment defects

11.5 Methods for detecting anomalies

            11.5.1 Definition

            11.5.2 Importance of anomaly detection

            11.5.3 Some Techniques for anomaly detection

11.6 Frequency Signatures

11.7 The MCSA Measurement Method

            11.7.1 Modeling of the stator current of the asynchronous machine

11.8 Variants of the ESPRIT method    

11.9 MOS (Order Selection Model)

            11.9.1 Principle

            11.9.2 Mathematical expressions

                11.9.3 Results obtained by each of the MOS algorithms

11.10 Intelligent defect classification algorithms

            11.10.1 Artificial Neuronal Networks and Genetic Algorithms (ANN-AG)

               Artificial neural networks      

               Genetic Algorithms (GA)

                           Chromosome coding   Generation of the initial population   Calculation of the evaluation function (fitness)

   Selection of individuals for reproduction



            11.10.2 Fusion ANN et AG

            11.10.3Association of two architectures

            11.10.4 Support Vectors Machine (SVM)

               How it works

            11.10.5 K-Nearest Neighbors (K-NN)

            11.10.6 Extrem Learning Machines

               Principle or algorithm

11.11 Simulation and analysis of results

            11.11.1 High-resolution estimation methods

               Preparation of simulation data

               Frequency error analysis

               Amplitude error analysis

               Interpretations on frequency analysis

               Interpretations on amplitude analysis

               Interpretations on frequency and amplitude analysis

               Interpretation of algorithm execution times

            11.11.2 Fault Classification Algorithms

               Artificial Neural Networks and Genetic Algorithms

                           Preparation of the simulation data

                           Simulation in the time domain        

                           Simulation in the frequency domain

                           Simulation in the frequency domain

            11.11.3 Vector machine supports

               Simulation in the time domain

               Simulation in the frequency domain

            11.11.4 K-Nearest neighbors

               in the time domain

               Simulation in the frequency domain

            11.11.5 Exterm Learning Machine

               Simulation in the time domain

               Simulation in the frequency domain

            11.11.6 Comparative table of the different algorithms developed in time and frequency

               Comparison of intelligent fault classification algorithms in the time and frequency domain

                           In the time domain

                           In the frequency domain




Chapter-12 Wavelet Transformation and Machine Learning Techniques for Digital Signal Analysis in IoT Systems

Rajalakshmi Krishnamurthy, Jaypee Institute of Information Technology, Noida, India

Dhanalekshmi Gopinathan, Jaypee Institute of Information Technology, Noida, India


12.1 Introduction

12.2 Digital Signal processing techniques for IoT Devices

            12.2.1 Fourier Transform

            12.2.2 Wavelet Transform

               Continuous Wavelet Transform

               Discrete Wavelet Transformation DWT

               Computation of Discrete wavelet transform (DWT)

12.3. Machine learning and Deep Learning techniques for time series analysis in IoT

            12.3.1. Time series classification algorithms

            12.3.2. Time series classification using deep learning

12.4 Comparison for Morlet, Mexican Hat, Frequency B-spline wavelet towards the classification of ECG signal.

                12.4.1 Mexican wavelet transform

                12.4.2 Morlet Wavelet transform

            12.4.3 Frequency B-spline wavelet transform












View More



Sudeep Tanwar (M’15, SM’21) is currently working as a Professor of the Computer Science and Engineering Department at the Institute of Technology, Nirma University, India. Dr Tanwar was a visiting Professor at Jan Wyzykowski University in Polkowice, Poland and the University of Pitesti in Pitesti, Romania. Dr Tanwar’s research interests include Blockchain Technology, Wireless Sensor Networks, Fog Computing, Smart Grid, and IoT. He has authored 02 books and edited 13 books, more than 200 technical papers, including top journals and top conferences, such as IEEE TNSE, TVT, TII, WCM, Networks, ICC, GLOBECOM, and INFOCOM. He is a Senior Member of IEEE, CSI, IAENG, ISTE, CSTA, and the member of the Technical Committee on Tactile Internet of IEEE Communication Society. He is leading the ST research lab where group members are working on the latest cutting-edge technologies.

Anand Nayyar received Ph.D (Computer Science) from Desh Bhagat University in 2017 in the area of Wireless Sensor Networks and Swarm Intelligence. He is currently working in Graduate School, Duy Tan University, Da Nang, Vietnam. A Certified Professional with 75+ Professional certificates from CISCO, Microsoft, Oracle, Google, Beingcert, EXIN, GAQM, Cyberoam and many more. Published 100+ Research Papers in various National International Journals (Scopus/SCI/SCIE/SSCI Indexed) with High Impact Factor. Member of more than 50+ Associations as Senior and Life Member. He is acting as Editor-in-Chief of IGI-Global, USA Journal titled “International Journal of Smart Vehicles and Smart Transportation (IJSVST)”.

Rudra Rameshwar (Ph.D. – IIT Roorkee, M.Tech. – IIT Roorkee, D.B.E. – EDII Ahmedabad, B.Tech. (Elect. Engg.) – DEI Agra, B.Sc. – DEI Agra) is full-time management faculty working in LMTSOM, Thapar Institute of Engineering & Technology (Deemed-to-be-University) Patiala (Punjab State), India. He is associated with core MBA specializations working in the area of “Operations, Energy & Sustainability, and Analytics”. Additionally, he is working in the area of Industry 4.0, Education 4.0, Business Analytics, HR Analytics, CSR, Service Operations Management, Sustainable Development, Warehouse Management, Sustainable Business Strategies, Industrial Marketing, Technology & Innovation, Research Methodology, Data Analytics, International Management, Business Statistics, Research Design and Statistical Tools – Techniques, - Data Analysis, Interpretation – SPSS/EViews/Minitab Training, Meta-Analysis, Advanced Regression Analysis, Qualitative & Quantitative Research, Academic Publishing and Integrity. He is a Life member of Thomason Alumni Association (IIT Roorkee), Indian Science Congress Association (ISCA) Kolkata, Confederation of Indian Industry (CII) Chandigarh.