A comprehensive review of the most recent applications of intelligent multi-modal data processing Intelligent Multi-Modal Data Processing contains a review of the most recent applications of data processing. The Editors and contributors ? noted experts on the topic ? offer a review of the new and challenging areas of multimedia data processing as well as state-of-the-art algorithms to solve the problems in an intelligent manner. The text provides a clear understanding of the real-life implementation of different statistical theories and explains how to implement various statistical theories. Intelligent Multi-Modal Data Processing is an authoritative guide for developing innovative research ideas for interdisciplinary research practices. Designed as a practical resource, the book contains tables to compare statistical analysis results of a novel technique to that of the state-of-the-art techniques and illustrations in the form of algorithms to establish a pre-processing and/or post-processing technique for model building. The book also contains images that show the efficiency of the algorithm on standard data set. This important book: Includes an in-depth analysis of the state-of-the-art applications of signal and data processing Contains contributions from noted experts in the field Offers information on hybrid differential evolution for optimal multilevel image thresholding Presents a fuzzy decision based multi-objective evolutionary method for video summarisation Written for students of technology and management, computer scientists and professionals in information technology, Intelligent Multi-Modal Data Processing brings together in one volume the range of multi-modal data processing.

Table of Contents:
List of contributors xv Series Preface xix Preface xxi About the Companion Website xxv 1 Introduction 1 Soham Sarkar, Abhishek Basu, and Siddhartha Bhattacharyya 1.1 Areas of Application for Multimodal Signal 1 1.1.1 Implementation of the Copyright Protection Scheme 1 1.1.2 Saliency Map Inspired Digital Video Watermarking 1 1.1.3 Saliency Map Generation Using an Intelligent Algorithm 2 1.1.4 Brain Tumor Detection Using Multi-Objective Optimization 2 1.1.5 Hyperspectral Image Classification Using CNN 2 1.1.6 Object Detection for Self-Driving Cars 2 1.1.7 Cognitive Radio 2 1.2 Recent Challenges 2 References 3 2 Progressive Performance of Watermarking Using Spread Spectrum Modulation 5 Arunothpol Debnath, Anirban Saha, Tirtha Sankar Das, Abhishek Basu, and Avik Chattopadhyay 2.1 Introduction 5 2.2 Types of Watermarking Schemes 9 2.3 Performance Evaluation Parameters of a Digital Watermarking Scheme 10 2.4 Strategies for Designing the Watermarking Algorithm 11 2.4.1 Balance of Performance Evaluation Parameters and Choice of Mathematical Tool 11 2.4.2 Importance of the Key in the Algorithm 13 2.4.3 Spread Spectrum Watermarking 13 2.4.4 Choice of Sub-band 14 2.5 Embedding and Detection of a Watermark Using the Spread Spectrum Technique 15 2.5.1 General Model of Spread Spectrum Watermarking 15 2.5.2 Watermark Embedding 17 2.5.3 Watermark Extraction 18 2.6 Results and Discussion 18 2.6.1 Imperceptibility Results for Standard Test Images 20 2.6.2 Robustness Results for Standard Test Images 20 2.6.3 Imperceptibility Results for Randomly Chosen Test Images 22 2.6.4 Robustness Results for Randomly Chosen Test Images 22 2.6.5 Discussion of Security and the key 24 2.7 Conclusion 31 References 36 3 Secured Digital Watermarking Technique and FPGA Implementation 41 Ranit Karmakar, Zinia Haque, Tirtha Sankar Das, and Rajeev Kamal 3.1 Introduction 41 3.1.1 Steganography 41 3.1.2 Cryptography 42 3.1.3 Difference between Steganography and Cryptography 43 3.1.4 Covert Channels 43 3.1.5 Fingerprinting 43 3.1.6 Digital Watermarking 43 3.1.6.1 Categories of Digital Watermarking 44 3.1.6.2 Watermarking Techniques 45 3.1.6.3 Characteristics of Digital Watermarking 47 3.1.6.4 Different Types of Watermarking Applications 48 3.1.6.5 Types of Signal Processing Attacks 48 3.1.6.6 Performance Evaluation Metrics 49 3.2 Summary 50 3.3 Literary Survey 50 3.4 System Implementation 51 3.4.1 Encoder 52 3.4.2 Decoder 53 3.4.3 Hardware Realization 53 3.5 Results and Discussion 55 3.6 Conclusion 57 References 64 4 Intelligent Image Watermarking for Copyright Protection 69 Subhrajit Sinha Roy, Abhishek Basu, and Avik Chattopadhyay 4.1 Introduction 69 4.2 Literature Survey 72 4.3 Intelligent Techniques for Image Watermarking 75 4.3.1 Saliency Map Generation 75 4.3.2 Image Clustering 77 4.4 Proposed Methodology 78 4.4.1 Watermark Insertion 78 4.4.2 Watermark Detection 81 4.5 Results and Discussion 82 4.5.1 System Response for Watermark Insertion and Extraction 83 4.5.2 Quantitative Analysis of the Proposed Watermarking Scheme 85 4.6 Conclusion 90 References 92 5 Video Summarization Using a Dense Captioning (DenseCap) Model 97 Sourav Das, Anup Kumar Kolya, and Arindam Kundu 5.1 Introduction 97 5.2 Literature Review 98 5.3 Our Approach 101 5.4 Implementation 102 5.5 Implementation Details 108 5.6 Result 110 5.7 Limitations 127 5.8 Conclusions and Future Work 127 References 127 6 A Method of Fully Autonomous Driving in Self-Driving Cars Based on Machine Learning and Deep Learning 131 Harinandan Tunga, Rounak Saha, and Samarjit Kar 6.1 Introduction 131 6.2 Models of Self-Driving Cars 131 6.2.1 Prior Models and Concepts 132 6.2.2 Concept of the Self-Driving Car 133 6.2.3 Structural Mechanism 134 6.2.4 Algorithm for theWorking Procedure 134 6.3 Machine Learning Algorithms 135 6.3.1 Decision Matrix Algorithms 135 6.3.2 Regression Algorithms 135 6.3.3 Pattern Recognition Algorithms 135 6.3.4 Clustering Algorithms 137 6.3.5 Support Vector Machines 137 6.3.6 Adaptive Boosting 138 6.3.7 TextonBoost 139 6.3.8 Scale-Invariant Feature Transform 140 6.3.9 Simultaneous Localization and Mapping 140 6.3.10 Algorithmic Implementation Model 141 6.4 Implementing a Neural Network in a Self-Driving Car 142 6.5 Training and Testing 142 6.6 Working Procedure and Corresponding Result Analysis 143 6.6.1 Detection of Lanes 143 6.7 Preparation-Level Decision Making 146 6.8 Using the Convolutional Neural Network 147 6.9 Reinforcement Learning Stage 147 6.10 Hardware Used in Self-Driving Cars 148 6.10.1 LIDAR 148 6.10.2 Vision-Based Cameras 149 6.10.3 Radar 150 6.10.4 Ultrasonic Sensors 150 6.10.5 Multi-Domain Controller (MDC) 150 6.10.6 Wheel-Speed Sensors 150 6.10.7 Graphics Processing Unit (GPU) 151 6.11 Problems and Solutions for SDC 151 6.11.1 Sensor Disjoining 151 6.11.2 Perception Call Failure 152 6.11.3 Component and Sensor Failure 152 6.11.4 Snow 152 6.11.5 Solutions 152 6.12 Future Developments in Self-Driving Cars 153 6.12.1 Safer Transportation 153 6.12.2 Safer Transportation Provided by the Car 153 6.12.3 Eliminating Traffic Jams 153 6.12.4 Fuel Efficiency and the Environment 154 6.12.5 Economic Development 154 6.13 Future Evolution of Autonomous Vehicles 154 6.14 Conclusion 155 References 155 7 The Problem of Interoperability of Fusion Sensory Data from the Internet of Things 157 Doaa Mohey Eldin, Aboul Ella Hassanien, and Ehab E. Hassanein 7.1 Introduction 157 7.2 Internet of Things 158 7.2.1 Advantages of the IoT 159 7.2.2 Challenges Facing Automated Adoption of Smart Sensors in the IoT 159 7.3 Data Fusion for IoT Devices 160 7.3.1 The Data Fusion Architecture 160 7.3.2 Data Fusion Models 161 7.3.3 Data Fusion Challenges 161 7.4 Multi-Modal Data Fusion for IoT Devices 161 7.4.1 Data Mining in Sensor Fusion 162 7.4.2 Sensor Fusion Algorithms 163 7.4.2.1 Central Limit Theorem 163 7.4.2.2 Kalman Filter 163 7.4.2.3 Bayesian Networks 164 7.4.2.4 Dempster-Shafer 164 7.4.2.5 Deep Learning Algorithms 165 7.4.2.6 A Comparative Study of Sensor Fusion Algorithms 168 7.5 A Comparative Study of Sensor Fusion Algorithms 170 7.6 The Proposed Multimodal Architecture for Data Fusion 175 7.7 Conclusion and Research Trends 176 References 177 8 Implementation of Fast, Adaptive, Optimized Blind Channel Estimation for Multimodal MIMO-OFDM Systems Using MFPA 183 Shovon Nandi, Narendra Nath Pathak, and Arnab Nandi 8.1 Introduction 183 8.2 Literature Survey 185 8.3 STBC-MIMO-OFDM Systems for Fast Blind Channel Estimation 187 8.3.1 Proposed Methodology 187 8.3.2 OFDM-Based MIMO 188 8.3.3 STBC-OFDM Coding 188 8.3.4 Signal Detection 189 8.3.5 Multicarrier Modulation (MCM) 189 8.3.6 Cyclic Prefix (CP) 190 8.3.7 Multiple Carrier-Code Division Multiple Access (MC-CDMA) 191 8.3.8 Modified Flower Pollination Algorithm (MFPA) 192 8.3.9 Steps in the Modified Flower Pollination Algorithm 192 8.4 Characterization of Blind Channel Estimation 193 8.5 Performance Metrics and Methods 195 8.5.1 Normalized Mean Square Error (NMSE) 195 8.5.2 Mean Square Error (MSE) 196 8.6 Results and Discussion 196 8.7 Relative Study of Performance Parameters 198 8.8 Future Work 201 References 201 9 Spectrum Sensing for Cognitive Radio Using a Filter Bank Approach 205 Srijibendu Bagchi and Jawad Yaseen Siddiqui 9.1 Introduction 205 9.1.1 Dynamic Exclusive Use Model 206 9.1.2 Open Sharing Model 206 9.1.3 Hierarchical Access Model 206 9.2 Cognitive Radio 207 9.3 Some Applications of Cognitive Radio 208 9.4 Cognitive Spectrum Access Models 209 9.5 Functions of Cognitive Radio 210 9.6 Cognitive Cycle 211 9.7 Spectrum Sensing and Related Issues 211 9.8 Spectrum Sensing Techniques 213 9.9 Spectrum Sensing in Wireless Standards 216 9.10 Proposed Detection Technique 218 9.11 Numerical Results 221 9.12 Discussion 222 9.13 Conclusion 223 References 223 10 Singularity Expansion Method in Radar Multimodal Signal Processing and Antenna Characterization 231 Nandan Bhattacharyya and Jawad Y. Siddiqui 10.1 Introduction 231 10.2 Singularities in Radar Echo Signals 232 10.3 Extraction of Natural Frequencies 233 10.3.1 Cauchy Method 233 10.3.2 Matrix Pencil Method 233 10.4 SEM for Target Identification in Radar 234 10.5 Case Studies 236 10.5.1 Singularity Extraction from the Scattering Response of a Circular Loop 236 10.5.2 Singularity Extraction from the Scattering Response of a Sphere 237 10.5.3 Singularity Extraction from the Response of a Disc 238 10.5.4 Result Comparison with Existing Work 239 10.6 Singularity Expansion Method in Antennas 239 10.6.1 Use of SEM in UWB Antenna Characterization 240 10.6.2 SEM for Determining Printed Circuit Antenna Propagation Characteristics 241 10.6.3 Method of Extracting the Physical Poles from Antenna Responses 241 10.6.3.1 Optimal Time Window for Physical Pole Extraction 241 10.6.3.2 Discarding Low-Energy Singularities 242 10.6.3.3 Robustness to Signal-to-Noise Ratio (SNR) 243 10.7 Other Applications 243 10.8 Conclusion 243 References 243 11 Conclusion 249 Soham Sarkar, Abhishek Basu, and Siddhartha Bhattacharyya References 250 Index 253