book

Cognitive Machine Intelligence

Name: Cognitive Machine Intelligence
ISBN: 9781040097106

by Inam Ullah Khan, Salma El Hajjami, Mariya Ouaissa, Salwa Belaqziz, Tarandeep Kaur Bhatia

August 2024

Intermediate to advanced

372 pages

11h 44m

English

CRC Press

Read now

Unlock full access

Cover Page
Half Title page
Series Page
Title Page
Copyright Page
Contents
Editors
Contributors
Preface
Part I AI trends and challenges

Chapter 1 AI-based computing applications in future communication
1.1 Introduction1.2 Artificial Intelligence1.2.1 Why is artificial intelligence important?1.3 Artificial and social networks1.3.1 Network theory1.3.2 Network analysis1.4 Scholarly investigation into social network intelligence1.5 AI as it is portrayed in the media1.5.1 2013: AlexNet and variational autoencoders1.5.2 In 20181.5.3 Last three year’s review1.6 Latest developments in AI1.6.1 Computer vision1.6.2 Features of computer vision1.6.3 AI in education1.6.4 AI-optimized hardware1.7 Definition of artificial superintelligence (ASI)1.7.1 The state of artificial intelligence at the moment1.8 The future of digital communications using AI1.9 The benefits of AI-powered automation for digital communication1.9.1 Increased efficiency1.9.2 Improved accuracy1.9.3 Enhanced personalization1.9.4 Increased security1.10 How does AI impact digital communications?1.10.1 Artificial Intelligence’s effect on communication1.11 What’s next for AI in digital communications?1.11.1 Source1.11.2 Input transducer1.11.3 Encoder of source1.11.4 Encoder of channels1.12 Prediction for the future of digital communications1.12.1 In-app messaging becomes dominant1.12.2 VR adoption: Make or break1.12.3 The need for human contact and validation1.13 What will the future of AI look like?1.14 Few predictions for AI1.14.1 In 20301.14.2 In 20501.15 Predictions on future technologies1.15.1 Robotics1.15.2 Augmented reality and virtual reality1.15.3 Nanotech1.15.4 Space exploration1.15.5 Superconductors1.15.6 3D printing1.15.7 Autonomous vehicle1.16 ConclusionReferences
Chapter 2 Advances of deep learning and related applications
2.1 Introduction2.2 Deep learning techniques2.3 Multilayer perceptron2.4 Convolutional neural network2.5 Recurrent neural network2.6 Long-term short-term memory2.7 GRU2.8 Autoencoders2.9 Attention mechanism2.10 Deep generative models2.11 Restricted Boltzmann machine2.12 Deep belief network2.13 Modern deep learning platforms2.13.1 PyTorch2.13.2 TensorFlow2.13.3 Keras2.13.4 Caffe (Convolutional architecture for fast feature embedding) and Caffe22.13.5 Deeplearning4j2.13.6 Theano2.13.7 Microsoft cognitive toolkit (CNTK)2.14 Challenges of deep learning2.15 Applications of deep learning2.16 ConclusionReferences
Chapter 3 Machine learning for big data and neural networks
3.1 Introduction3.2 Machine learning and fundamentals3.2.1 Supervised learning3.2.2 Decision trees3.2.3 Linear regression3.2.4 Naive Bayes3.2.5 Logistic regression3.3 Unsupervised learning3.3.1 K-Means algorithm3.3.2 Principal component analysis3.4 Reinforcement learning3.5 Machine learning in large-scale data3.6 Data analysis in big data3.7 Predictive modelling3.7.1 Understanding customer behavior and preferences3.7.2 The role of supply chain and performance management in organizational success3.7.3 Management of quality and enhancement3.7.4 Risk mitigation and detection of fraud3.8 Neural networks3.8.1 Artificial neural network3.8.2 RNN3.8.3 CNN3.8.4 Deep learning using convolutional neural networks to find building defects3.9 Data generation and manipulation3.9.1 Generative Adversarial Networks3.9.2 Domains of real-world applications3.9.3 Financial applications3.9.4 Medical and data science3.9.5 Internet of Things3.10 ConclusionReferences
Part II Machine intelligence in network technologies
Chapter 4 Deformation prediction and monitoring using real-time WSN and machine learning algorithms: A review
4.1 Introduction4.2 Causes of landslides4.2.1 Climate changes4.2.2 Earthquake4.2.3 Deforestation4.3 Early warning system4.3.1 Risk Knowledge4.3.2 Monitoring and warning services4.3.3 Dissemination and communication4.3.4 Response capability4.3.5 Classification of early warning system4.4 Landslide monitoring techniques4.4.1 Multi-antenna GPS deformation monitoring systems4.4.2 Monitoring landslide deformation using InSAR Technique4.4.3 Electro-Mechanical System (MEMS) tilt sensor4.4.4 Low-cost vibration sensor network4.4.5 Extensometer4.4.6 Rain gauge4.5 Landside prediction modeling and forecasting using machine learning and statistical analysis4.6 ConclusionAcknowledgmentsReferences
Chapter 5 Unmanned aerial vehicle: Integration in healthcare sector for transforming interplay among smart cities
5.1 Introduction5.1.1 Objectives of the chapter5.1.2 Significance of study5.2 UAVs in healthcare: Applications and benefits5.2.1 Specific applications of UAVs in healthcare sector5.2.1.1 Transportation5.2.1.2 Livestock monitoring5.2.1.3 Disaster relief5.2.1.4 Public health surveillance and medical research5.2.2 Benefits of UAVs in healthcare sector5.3 Communication protocols for UAVs in healthcare5.3.1 Diverse communication protocols suitable for UAVs in healthcare settings5.3.2 Addressing challenges and requirements of real-time data transmission5.4 Deployment strategies and logistics5.4.1 Different deployment strategies for UAVs in healthcare5.4.2 Logistical considerations5.5 Security challenges and solutions5.5.1 Security challenges associated with UAVs in healthcare5.5.2 Potential solutions and mitigation strategies5.5.3 Importance of regulatory compliance and adherence to safety standards5.6 Regulatory and legal framework5.6.1 Need for standardized regulations and guidelines to ensure safe and ethical use of UAVs5.7 Conclusion and future scopeReferences
Chapter 6 Blockchain technologies using machine learning
6.1 Introduction6.2 Understanding blockchain technologies6.2.1 Introduction to blockchain6.2.2 Key components of a blockchain network6.2.3 Consensus mechanisms and their impact6.2.4 Benefits and limitations of BCT6.2.4.1 Benefits of BCT6.2.4.2 Limitations of BCT6.3 ML fundamentals6.3.1 Overview of ML6.3.2 Types of ML algorithms6.3.2.1 Supervised learning algorithms6.3.2.2 Unsupervised learning algorithms6.3.2.3 Semi-supervised learning algorithms6.3.2.4 Reinforcement learning algorithms6.3.2.5 Deep learning algorithms6.3.3 Data pre-processing and feature engineering6.3.3.1 Data pre-processing6.3.3.2 Feature engineering6.4 Evaluating ML models6.4.1 Common evaluation metrics6.5 Synergies between blockchain and ML6.5.1 Combining ML models on the blockchain6.6 Applications of blockchain and ML integration6.7 Challenges and limitations in BCT and ML integration6.7.1 Scalability issues6.7.2 Data availability and quality6.7.3 Regulatory and legal challenges6.7.4 Trusted oracles and data feeds6.7.5 Energy efficiency concerns6.8 Future prospects and research directions6.8.1 Federated learning on blockchain networks6.8.2 Integration of privacy-preserving techniques6.8.3 AI-driven smart contracts6.9 ConclusionReferences
Chapter 7 Q-learning and deep Q networks for securing IoT networks, challenges, and solution
7.1 Introduction7.2 Methodology7.2.1 Proposed algorithm for training DQNs as agents in IoT networks for security7.2.1.1 The algorithm7.2.1.2 Program7.2.1.3 Various security actions7.2.2 Algorithm for applying security actions using a DQN in IoT network security7.2.2.1 Program7.3 Result and conclusionReferences
Chapter 8 The application of artificial intelligence and machine learning in network security using a bibliometric study
8.1 Introduction8.2 Analysis of state-of-art network security AI/ML models8.2.1 Performance comparison of support vector machine, random forest, and extreme learning machine for intrusion detection8.2.2 A novel online incremental and decremental learning algorithm based on variable support vector machine8.2.3 An effective intrusion detection framework based on SVM with feature augmentation, knowledge-based systems8.2.4 A novel hybrid KPCA and SVM with GA model for intrusion detection8.2.5 A novel SVM-KNN-PSO ensemble method for intrusion detection system8.2.6 SVM-DT-based adaptive and collaborative intrusion detection8.2.7 Random forest modeling for network intrusion detection system8.3 Analysis of the state-of-art malware detection AL/ML models8.3.1 Malware detection classification using machine learning8.3.2 A review of Android malware detection approaches based on machine learning8.3.3 A two-layer deep learning method for Android malware detection using network traffic8.3.4 A lightweight network-based Android malware detection system8.3.5 Phishing website classification and detection using machine learning8.3.6 Static and dynamic malware analysis using machine learning8.4 Research findings in AI/ML-based network security models8.5 Research findings in AL/ML-based malware detection systems8.6 ConclusionReferences
Chapter 9 Machine learning approaches for intrusion detection: Enhancing cybersecurity and threat mitigation
9.1 Introduction9.2 Traditional intrusion detection methods9.3 Machine learning algorithms for intrusion detection9.4 Related works9.5 Addressing the research gap: Adaptive intrusion detection9.6 Challenges of integrating machine learning in IDS9.7 Feature engineering for intrusion detection9.8 Enhancing robustness with ensemble learning9.9 Future research directions9.10 ConclusionReferences
Part III Cognitive machine intelligence applications
Chapter 10 The rise of AI in the field of healthcare
10.1 Introduction10.2 2 Types of AI10.2.1 AI type 1: skill base10.2.1.1 Weak AI or narrow AI10.2.1.2 General-purpose AI10.2.1.3 Super AI10.2.2 AI Type: function-based10.2.2.1 Reactive apparatus10.2.2.2 Memory machines with limited memory10.2.2.3 Mind theory10.2.2.4 Confidence10.3 Features of artificial intelligence10.3.1 Eliminate monotonous and tedious tasks10.3.2 Data acquisition10.3.3 A copy of human cognition10.3.4 Avoid natural disaster10.3.5 Chatbots and facial recognition10.4 Artificial intelligence: unraveling the shade of innovation10.4.1 Machine learning: the art of adaptation10.4.2 Neural networks: mirroring the human brain10.4.3 Deep learning: navigating complexity10.4.4 Natural language processing10.4.5 Computer vision: seeing the unseen10.4.6 Reinforcement learning: learning from experience10.4.7 Generative adversarial networks: fostering creativity10.4.8 Explainable AI: illuminating the black box10.4.9 Ethics and bias in AI: navigating a moral compass10.4.10 Artificial general intelligence: the quest for human-level AI10.4.11 Quantum AI: bridging new realities10.4.12 AI in creativity: collaborating with machines10.4.13 AI in finance: predicting the economic future10.4.14 AI and climate change: a greener tomorrow10.5 Revolutionizing healthcare through technology: a comprehensive overview10.5.1 Introduction: healthcare in the digital age10.5.2 AI in diagnostics: enhancing precision and early detection10.5.3 Personalized medicine: tailoring treatment to individuals10.5.4 Drug discovery and development: accelerating breakthroughs10.5.5 Electronic health records and AI: enabling informed decision-making10.5.6 Telemedicine and virtual health assistants: expanding access to care10.5.7 Robotics in surgery: advancing precision and minimally invasive procedures10.5.8 Mental health and AI: revolutionizing approaches10.5.9 Ethical considerations: balancing progress and privacy10.5.10 The human touch: AI as a collaborator10.6 ConclusionReferences
Chapter 11 A comprehensive survey of machine learning applications in healthcare
11.1 Introduction11.2 Machine learning in healthcare11.2.1 Machine learning algorithms in healthcare11.2.2 Supervised, unsupervised, and reinforcement learning techniques11.2.2.1 Supervised learning11.2.2.2 Unsupervised learning11.2.2.3 Reinforcement learning11.3 Medical imaging and diagnostic applications11.3.1 Image classification and segmentation11.3.2 Computer-aided detection and diagnosis11.3.3 Radiomics and radiogenomics in cancer diagnosis11.3.4 Neuroimaging for brain disorder diagnosis11.4 Clinical decision support systems11.4.1 ML-driven risk prediction models11.4.2 Decision support for treatment planning11.4.3 Early warning systems for patient deterioration11.5 Electronic Health Records analysis11.5.1 Predictive modelling using EHR data11.5.2 Natural Language Processing for extracting medical information11.5.3 Clinical data integration and interoperability11.6 Disease prediction and prevention11.6.1 ML-based models for disease risk assessment11.6.2 Predictive analytics for patient outcomes11.6.3 Population health management using ML11.7 Personalised medicine and treatment11.7.1 Pharmacogenomics and drug response prediction11.7.2 Precision oncology and targeted therapies11.7.3 Individualised treatment recommendations11.8 Drug discovery and development11.8.1 AI-driven drug screening and design11.8.2 ML in clinical trials and drug efficacy evaluation11.8.3 Repurposing existing drugs with ML11.9 Ethical, legal, and privacy considerations11.9.1 Ethical challenges in using ML in healthcare11.9.1.1 Fairness and bias11.9.1.2 Transparency and explainability11.9.1.3 Informed consent11.9.1.4 Data security and privacy11.9.1.5 Clinical validation11.9.1.6 AI can assist in making medical decisions11.9.2 Legal implications and regulatory frameworks11.9.3 Privacy-preserving ML techniques for healthcare data11.10 Challenges and future directions11.10.1 Data quality, quantity, and interoperability11.10.2 Interpretability and explainability of ML models11.10.3 Integration of ML algorithms into clinical workflows11.10.4 Addressing bias and fairness in healthcare AI11.11 ConclusionReferences
Chapter 12 A deep learning approach for the early diagnosis of melanoma cancer: Study and analysis
12.1 Introduction12.2 Relevant work12.3 Theoretical framework12.4 Proposed methodology12.5 Results12.5.1 Results of identification of melanoma cancer using dermatoscopy by physicians12.5.2 Results of identification of melanoma cancer by CNN12.6 ConclusionReferences
Chapter 13 A study and analysis on nowcasting: Forms of precipitation using improvised random forest classifier
13.1 Introduction13.2 Relevant work13.3 IRFC model for weather forecasting13.3.1 Dataset used13.3.2 Data preprocessing13.3.3 Training set13.3.4 Testing set13.3.5 Proposed model: Random forest13.3.6 Model evaluation13.4 Results and discussion13.5 ConclusionReferences
Chapter 14 A study and comparative analysis on prediction of tsunami using convolutional neural network
14.1 Introduction14.2 Relevant work14.3 Proposed methodology14.3.1 Architecture14.3.2 Dataset description14.3.3 Data preprocessing14.3.4 Training dataset14.3.5 Testing dataset14.3.6 CNN model14.3.7 Model evaluation14.4 Results and discussions14.4.1 Accuracy14.4.2 Sensitivity14.4.3 Specificity14.4.4 Precision14.5 ConclusionReferences
Chapter 15 Towards smarter Chatbots: Unravelling the capabilities of ChatGPT
15.1 Introduction15.2 ChatGPT summary compilation15.2.1 Background of ChatGPT15.3 Architecture of ChatGPT15.4 Training ChatGPT15.4.1 Data sources used in training ChatGPT15.5 Applications of ChatGPT15.5.1 Advantages15.5.2 Disadvantages15.6 ConclusionReferences
Index

Content preview from Cognitive Machine Intelligence

Chapter 3 Machine learning for big data and neural networks

Anuraag Ramineni, J. Jayashree, J. Vijayashree, and Rishita Konda

Vellore Institute of Technology, Vellore, India

DOI: 10.1201/9781003500865-4

3.1 Introduction

In the contemporary era, commonly referred to as the age of data, there exists an interconnectedness between various elements of our surroundings and their corresponding data sources. Consequently, nearly every facet of our existence is subject to digital recording. The contemporary digital landscape encompasses a diverse array of data types, including but not limited to Internet of Things (IoT) data, cybersecurity data, smart city data [1], corporate data, smartphone data, social media data, health data, COVID-19 data, and ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

The Human Factor in AI-Based Decision-Making

Publisher Resources

ISBN: 9781040097106

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Cognitive Machine Intelligence

by Inam Ullah Khan, Salma El Hajjami, Mariya Ouaissa, Salwa Belaqziz, Tarandeep Kaur Bhatia

Chapter 3 Machine learning for big data and neural networks

3.1 Introduction

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.