Applications of Computational Intelligence in Multi-Disciplinary Research

Description

Front Cover Applications of Computational Intelligence in Multi-Disciplinary Research Copyright Page Contents List of contributors 1 Iris feature extraction using three-level Haar wavelet transform and modified local binary pattern Abbreviations 1.1 Introduction 1.2 Related works 1.3 Iris localization 1.4 Iris normalization 1.5 The proposed feature extraction scheme 1.6 Matching results 1.7 Performance evaluation 1.8 Conclusion References 2 A novel crypt-intelligent cryptosystem 2.1 Introduction 2.2 Related work 2.2.1 Machine learning contributions in cryptology 2.2.1.1 Analogy between machine learning and cryptography 2.2.1.2 Application of machine learning in cryptography 2.2.1.3 Application of machine learning in cryptanalysis 2.2.1.4 Analysis of existing contributions of machine learning in cryptology 2.2.2 Genetic algorithm contributions in cryptology 2.2.2.1 Applications of genetic algorithm in Cryptography 2.2.2.2 Applications of genetic algorithm in cryptanalysis 2.2.2.3 Analysis of existing contributions of genetic algorithms in cryptology 2.2.3 Neural network contributions in cryptology 2.2.3.1 Applications of neural networks in cryptography 2.2.3.2 Applications of neural networks in cryptanalysis 2.2.3.3 Analysis of contribution of neural network in cryptology 2.2.4 Background of DNA cryptography 2.2.4.1 Analysis of existing work in DNA cryptography 2.3 Proposed methodology 2.3.1 Proposed encryption scheme 2.3.2 Proposed decryption scheme 2.4 Discussion 2.5 Conclusion and future work References 3 Behavioral malware detection and classification using deep learning approaches 3.1 Introduction 3.1.1 Digital forensics—malware detection 3.1.2 Malware evolution and its taxonomy 3.1.3 Machine learning techniques for malware analysis 3.1.4 Behavioral analysis of malware detection 3.2 Deep learning strategies for malware detection 3.2.1 Feature extraction and data representation 3.2.2 Static Analysis 3.2.2.1 Byte code n-gram features 3.2.2.2 Opcode n-gram features 3.2.2.3 Portable executables 3.2.2.4 String feature 3.2.3 Dynamic analysis 3.2.4 Hybrid analysis 3.2.5 Image processing techniques 3.3 Architecture of CNNs for malware detection 3.3.1 Preprocessing 3.3.2 Classification using CNNs 3.3.3 Evaluation 3.4 Comparative analysis of CNN approaches 3.5 Challenges and future research directions 3.6 Conclusion References 4 Optimization techniques and computational intelligence with emerging trends in cloud computing and Internet of Things 4.1 Introduction 4.1.1 Introduction to optimization 4.1.2 Introduction to cloud computing with emphasis on fog/edge computing 4.2 Optimization techniques 4.2.1 An optimization problem 4.2.1.1 Defining an optimization problem 4.2.1.2 Elements of an optimization problem 4.2.1.3 Classification of the optimization problem 4.2.1.3.1 On the basis of types of constraints 4.2.1.3.2 On the basis of the physical structure of the problem 4.2.1.3.3 On the basis of the nature of the design variables 4.2.1.3.4 On the basis of the nature of the equations (constraints and objective functions) 4.2.1.3.5 On the basis of the separable nature of the variables 4.2.1.3.6 On the basis of the deterministic nature of the variables 4.2.1.3.7 On the basis of the permissible values of the decision variables 4.2.1.3.8 On the basis of the number of objectives 4.2.2 Solution to the optimization problem 4.2.2.1 Classical optimization techniques 4.2.2.2 Advanced optimization techniques 4.3 Understanding fog/edge computing 4.3.1 What is fog? 4.3.2 Prelude to our framework 4.3.3 Our goal 4.3.4 Framework for fog computing 4.4 Optimizing fog resources 4.4.1 Defining optimization problem for fog layer resources 4.4.2 Optimization techniques used 4.5 Case studies 4.5.1 Case study I: floorplan optimization 4.5.2 Case study II: Gondwana—optimization of drinking water distribution system 4.6 Scope of advancements and future research 4.7 Conclusion References 5 Bluetooth security architecture cryptography based on genetic codons 5.1 Introduction 5.1.1 Bluetooth 5.1.2 Bluetooth security architecture 5.2 Survey of literature 5.3 Plaintext-to-ciphertext conversion process 5.3.1 Basic workflow 5.3.1.1 Encryption 5.3.1.2 Decryption 5.3.2 Algorithm 5.3.2.1 Encryption 5.3.2.1.1 Plaintext to DNA/RNA codon conversion 5.3.2.2 Promoter addition 5.3.2.2.1 Generation of promoters 5.3.2.2.2 Promoter addition 5.3.2.3 Intron addition 5.3.2.3.1 Intron number generation 5.3.2.3.2 Position to place the introns 5.3.2.3.3 Placing the introns at their positions 5.3.2.4 Masking of the ciphertext 5.3.2.5 Extra data 5.3.2.6 Decryption 5.3.2.6.1 Removal of the mask 5.3.2.6.2 Removal of the introns 5.3.2.6.3 Removal of the promoter 5.3.2.6.4 Conversion of the ciphertext without the intron and promoter to plaintext 5.3.3 Analysis and discussion 5.4 Conclusion 5.5 Future work References 6 Estimation of the satellite bandwidth required for the transmission of information in supervisory control and data acquis... Abbreviations 6.1 Introduction 6.2 Supervisory control and data acquisition systems 6.3 The very small aperture terminal networks 6.3.1 The satellite communication systems 6.3.2 Architecture very small aperture terminal networks 6.3.3 Connectivity 6.3.4 Multiple access 6.4 Algorithm for estimating the satellite bandwidth 6.4.1 Determining the bandwidth required for data transmission 6.4.2 Case study 6.4.3 Overview of some recent algorithms in detail 6.4.4 Validation of bandwidth calculations 6.5 Challenges and future work 6.6 Conclusions References 7 Using artificial intelligence search in solving the camera placement problem Nomenclature 7.1 Introduction 7.1.1 The roles of visual surveillance systems 7.1.2 The camera placement problem from an artificial intelligence perspective 7.1.3 Chapter description 7.2 Background 7.3 Modeling the visual sensors 7.3.1 The sensor space modeling 7.3.2 The camera coverage modeling 7.3.3 The analysis of camera visibility 7.4 Solving the camera placement problem using artificial intelligence search 7.4.1 Generate and test algorithm 7.4.2 Uninformed search 7.4.3 Hill climbing strategy 7.5 Further discussion 7.5.1 The efficiency of the algorithms 7.5.2 The performance of the algorithms 7.6 Conclusion References 8 Nanotechnology and applications 8.1 Introduction 8.2 Nanoscience and nanotechnology 8.3 Computational nanotechnology 8.3.1 Molecular modeling 8.3.1.1 Molecular mechanics 8.3.1.2 Quantum methods 8.3.1.3 Semiempirical 8.3.1.4 Molecular dynamics 8.3.2 Nanodevice simulation 8.3.3 Nanoinformatics 8.3.4 High-performance computing 8.3.5 Computational intelligence 8.3.5.1 Genetic algorithms 8.3.5.2 Artificial neural networks 8.3.5.3 Fuzzy system 8.4 Applications of computational nanotechnology 8.4.1 Nanotube-based sensors and actuators 8.4.2 Nanoinformatics for drugs 8.4.3 Molecular docking 8.4.4 Nanotoxicology 8.4.5 Other applications 8.5 Conclusion References 9 Advances of nanotechnology in plant development and crop protection 9.1 Introduction 9.2 Agriculture’s nanofarming: a modern frontier 9.3 Synthesis of green nanoparticles and its sources 9.4 Good distribution possibilities allowed by nanoparticles: a modern sustainable agriculture portal 9.5 Nanofertilizers: a good food supply for crops 9.6 Germination, field production, and efficiency enhancement of seed nanomaterials 9.7 Plant sensory systems and responses to radical climate change influences nanomaterials 9.8 Nanosensors and nanomaterials: perturbation detection and control 9.9 Pesticide-based plant safety nanomaterials 9.10 Nanotechnology in pesticides and fertilizers 9.11 Control of plant pests 9.12 Concluding remarks Consent for publication Conflict of interest References 10 A methodology for designing knowledge-based systems and applications 10.1 Introduction 10.2 Related work 10.3 Design the knowledge-based system 10.3.1 The architecture of a knowledge-based system 10.3.2 The process for designing the knowledge-based system 10.4 Knowledge base and inference engine of a knowledge-based system 10.4.1 Design the knowledge base 10.4.1.1 Organize the knowledge base 10.4.1.2 Basic knowledge manipulations 10.4.1.2.1 Updating the knowledge base 10.4.1.2.2 Checking the consistency of the knowledge base 10.4.1.2.3 Unification of facts 10.4.2 Design the Inference engine 10.4.2.1 The process for designing the inference engine 10.4.2.1.1 The principles of an inference engine 10.4.2.1.2 Criteria of an inference engine 10.4.2.1.3 The process for designing an inference engine 10.4.2.2 The reasoning methods 10.4.2.2.1 Forward chaining 10.4.2.2.2 Backward chaining 10.4.2.2.3 Reasoning with pattern problems and sample problems 10.5 Applications 10.5.1 Design an intelligent problem solver for solving solid geometry at high school 10.5.1.1 Collect the knowledge domain 10.5.1.2 Build the knowledge model 10.5.1.3 Organize the knowledge base 10.5.1.4 Design the inference engine 10.5.1.5 Testing 10.5.2 Consultancy system for designing housing architecture 10.5.2.1 Organize the knowledge base of the consultancy system 10.5.2.2 Design the inference engine of the consultancy system 10.5.2.3 Testing 10.6 Conclusion and Future work References 11 IoT in healthcare ecosystem 11.1 Introduction 11.2 Applications of  Internet of Things in healthcare 11.2.1 Patient-centric IoT 11.2.1.1 Remote patient care 11.2.1.2 Pathology and fatal viral/bacterial diseases 11.2.1.3 Critical and emergency patient care 11.2.1.4 Food and workout monitoring 11.2.1.5 Affective computing 11.2.2 Hospital-centric IoT applications 11.2.2.1 Real-time location of medical equipment 11.2.2.2 Deployment of medical staff 11.2.2.3 Drugs management 11.2.2.4 Reducing the charting time 11.2.3 IoT benefitting health insurance companies 11.2.4 Pharmaceutical governance 11.3 Implementation methodologies 11.3.1 Fog computing 11.3.1.1 Architecture 11.3.1.1.1 Smart IoT devices/applications 11.3.1.1.2 Fog nodes 11.3.1.1.3 Cloud 11.3.1.2 Advantages 11.3.2 Edge computing 11.3.2.1 Architecture 11.3.2.1.1 IoT nodes/applications 11.3.2.1.2 Edge nodes 11.3.2.1.3 Cloud 11.3.2.2 Advantages 11.3.2.3 Empowering edge computing 11.4 Implementation models 11.4.1 Heart disease prediction 11.4.2 Healthcare IoT-based affective state mining using deep convolutional neural networks 11.4.2.1 Electrodermal activity 11.4.2.2 Electromyography 11.4.2.3 Electrocardiogram 11.5 Challenges in healthcare IoT 11.5.1 Technology-oriented challenges 11.5.1.1 Risking the patient’s life 11.5.1.2 Incorrect results 11.5.1.3 No planned downtime 11.5.1.4 Need for a specialized tool to handle diversified protocols 11.5.1.5 Remote places with a lack of infrastructure and connectivity 11.5.2 Adapting to remote healthcare and telehealth 11.5.3 Data security 11.6 Security issues and defense mechanisms and IoT 11.6.1 Security requirements in healthcare IoT 11.6.1.1 Confidentiality 11.6.1.2 Integrity 11.6.1.3 Authentication 11.6.2 Attacks on IoT devices 11.6.2.1 Sinkhole attack 11.6.2.2 Blackhole attack 11.6.2.3 Selecting forwarding attack (grayhole attack) 11.6.2.4 Wormhole attack 11.6.2.5 Sybil attack 11.6.2.6 Denial-of-service attack 11.6.3 Defensive mechanism 11.6.3.1 Key management 11.6.3.2 User/device authentication and authorization 11.6.3.3 Intrusion detection 11.6.3.4 Fault tolerance 11.6.3.5 Blockchain technology 11.7 Covid 19—how IoT rose to the global pandemic 11.7.1 About Covid 19 11.7.2 Decoding the outbreak and identifying patient zero 11.7.3 Quarantined patient care 11.7.4 Public surveillance 11.7.5 Safeguarding hygiene 11.7.6 IoT and robotics 11.7.7 Smart disinfection and sanitation tunnel 11.7.8 Smart masks and smart medical equipment 11.8 Future of IoT in healthcare 11.8.1 IoT and 5G 11.8.2 IoT and artificial intelligence 11.9 Conclusion References Index Back Cover