Acknowledgements
Editor biographies
Irshad Ahmad Ansari
Varun Bajaj
List of contributors
Contributor biographies
Mosabber Uddin Ahmed
Meena Anandan
Zahra Ghanbari
Aakash Kumar Jain
K P Madhavan
Manas Kumar Mishra
Ishrat Jahan Mohima
Mohammad Hassan Moradi
Poorya Moradi
Rohini Palanisamy
Nakul Kishor Pathak
K K Mujeeb Rahman
Mozhdeh Saghalaini
Deepika Sainani
Urvashi Prakash Shukla
Abhishek Kumar Singh
Mahdi Taghaddossi
Pandiyarasan Veluswamy
Chapter 1 Automatic feature extraction using deep learning for automatic modulation classification implemented with Python
1.1 Introduction
1.2 Proposed AMC based on DL framework
1.3 System model for dataset generation
1.4 Generalized feature extraction system using DL
1.4.1 Spatial feature extraction using CNNs
1.4.2 CLDNN-based approach
1.4.3 MCLDNN based approach
1.4.4 Complement of multichannel structure from bimodal information using BMCCLDNN models
1.5 Data preparation
1.5.1 Python code (libraries, file paths)
1.5.2 Python code (random shuffling of data)
1.5.3 Python code (data preparation for training)
1.5.4 Python code (data reshaping)
1.5.5 Python code (model training)
1.5.6 Python code (model evaluation)
1.5.7 Python code (model prediction)
1.6 Conclusion
Acknowledgments
Bibliography
Chapter 2 Applying B-value and empirical equivalence hypothesis testing to intellectual and developmental disabilities electroencephalogram data
2.1 Introduction
2.2 Materials
2.2.1 Dataset
2.2.2 Pre-processing
2.3 Feature extraction
2.3.1 DWT
2.3.2 PSD
2.4 Statistical method
2.4.1 The two-stage hypothesis testing based on EEB
2.4.2 Implementation (Python code)
2.5 Results
2.5.1 Comparison of two groups of IDD and TDC under the same conditions
2.5.2 Comparison of rest-state and music stimuli for each group of IDD and TDC
2.6 Conclusion
Bibliography
Chapter 3 Filter design and denoising technique for ECG signals
3.1 Introduction
3.2 Filter types
3.2.1 Time domain filters
3.2.2 Frequency selective filters
3.3 Python libraries for filter design
3.4 Filter specifications
3.5 Mapping of the digital frequency
3.6 Time domain filters
3.6.1 Moving average window
3.6.2 Derivative filter
3.7 Frequency selective filters
3.7.1 FIR filter
3.7.2 IIR filters
3.7.3 Adaptive filter
3.8 Conclusion
Bibliography
Chapter 4 Electroencephalogram signal processing with Python
4.1 Introduction
4.2 Principal and primary actions in EEG signal processing
4.2.1 Importing EEG signals to Python environment
4.2.2 Saving the details of EEG data on other variables
4.2.3 Modifying the imported EEG data
4.2.4 Extracting data from a raw object
4.2.5 Saving objects
4.2.6 Working with events
4.3 Exposure signals in time and frequency
4.3.1 Displaying data information in time and frequency
4.3.2 Topomap displaying
4.3.3 Saving MNE-produced plots and images
4.4 EEG signals preprocessing
4.4.1 Setting an EEG reference
4.4.2 Removing bad channels and data spans
4.4.3 Filtering the data and resampling
4.4.4 Artifact removal by ICA
4.5 EEG signal processing
4.5.1 Evoke responses analysis
4.5.2 Time-frequency analysis
4.5.3 Source localization
Bibliography
Chapter 5 AG-PSO: prediction of heart diseases for an unbalanced dataset using feature extraction
5.1 Introduction
5.2 Literature survey
5.3 Proposed methodology
5.3.1 Data augmentation and imbalance (SMOTE)
5.3.2 Feature subset selection (BPSO)
5.3.3 Prediction (various ML algorithms)
5.4 Parameter settings for the simulation study
5.4.1 Experimental dataset
5.4.2 Experimentation platform
5.4.3 Evaluation metric
5.5 Results and analysis
5.6 Conclusion
Bibliography
Chapter 6 Python based bio-signal processing: mitigation of baseline wandering in pre-recorded electrooculogram
6.1 Introduction
6.1.1 Baseline wander noise
6.1.2 Muscle tremor noise
6.1.3 Powerline interference
6.1.4 EOGs and their clinical use
6.2 Introduction to Google Colab
6.2.1 How to use Google Colab
6.3 Algorithm for correction of baseline wandering in pre-recorded EOG signals
6.3.1 Steps 1โ3
6.3.2 Step 4
6.3.3 Steps 5โ6
6.3.4 Step 7
6.3.5 Step 8
6.3.6 Step 9
6.3.7 Step 10
6.3.8 Steps 11 and 12
6.4 Conclusion
Bibliography
Chapter 7 Efficient nanoscale device modeling using artificial neural networks with TensorFlow and Keras libraries in Python
7.1 Introduction
7.1.1 Motivation and background
7.1.2 Problem statement and objectives
7.2 Brief literature survey
7.2.1 MuGFETs and their characteristics
7.2.2 ANNs and their application in compact modeling
7.2.3 Previous work using ANNs for modeling MuGFETs
7.3 Methodology
7.3.1 Overview of proposed approach
7.3.2 Implementation details
7.3.3 Hypertuning for optimizing performance
7.3.4 DNN modeling and training
7.4 Results and analysis
7.4.1 Model evaluation and comparison with TCAD simulations
7.4.2 Potential and limitations of the proposed approach
7.5 Conclusion
Bibliography
Chapter 8 A Python-based comparative study of convolutional neural networkโbased approaches for the early detection of breast cancer
8.1 Introduction
8.2 Related works
8.3 Methodology
8.3.1 Dataset
8.3.2 Image preprocessing
8.3.3 Convolutional neural network
8.3.4 Model overview
8.3.5 Evaluation metrics
8.4 Result analysis
8.5 Conclusion
Acknowledgments
Bibliography
Chapter 9 Maximum power point tracking for partially shaded photovoltaic system using advanced signal processing
9.1 Introduction
9.2 Modeling and characteristics of PV systems
9.2.1 Modeling of PV cells
9.2.2 Modeling of PV modules
9.2.3 Characteristics of PV modules
9.2.4 PV system schematics
9.3 MPPT: concept and traditional techniques
9.3.1 Need and concept of MPPT
9.3.2 Traditional MPPT concepts
9.4 Challenges of MPPT
9.4.1 Dynamic changes in temperature and irradiance
9.4.2 PSC and its challenges
9.4.3 MPPT requirements
9.5 Soft computing methods
9.5.1 Fuzzy logic
9.5.2 Artificial neural network
9.5.3 Adaptive neural fuzzy inference system
9.5.4 Extreme learning mechanism
9.5.5 Extremum seeking control
9.5.6 Reinforcement learning
9.5.7 Bayesian network
9.6 Meta-heuristic techniques
9.6.1 Swarm intelligence
9.6.2 Evolutionary algorithms
9.6.3 Mathematics- and physics-based methods
9.6.4 Sociology-based methods
9.7 Exact algorithms
9.7.1 Mathematics-based algorithms
9.7.2 Techniques based on P V array characteristics
9.8 Hardware configurationโbased MPP methods
9.8.1 Array reconfigurationโbased methods
9.8.2 Power electronicsโbased methods
9.9 Analysis and comparison of various techniques
9.10 Challenges and future scope
9.11 Conclusion
Bibliography
Chapter 10 Automating Monte Carlo simulation data analysis using Python in Anaconda environment
10.1 Advanced nodes design
10.1.1 A simple memory design
10.1.2 Monte Carlo simulations
10.1.3 Challenges in Monte Carlo simulation
10.1.4 Fast Monte Carlo simulations
10.1.5 Validation of design for tool evaluation
10.2 Simulation setup and tools overview
10.3 Analysis of simulation results with Python
10.4 Conclusion
10.5 Future scope
Bibliography