ARTIFICIAL INTELLIGENCE : models, algorithms and applications

Artificial Intelligence: Models, Algorithms and Applications presents focused information about applications of artificial intelligence (AI) in different areas to solve complex problems. The book presents 8 chapters that demonstrate AI based systems for vessel tracking, mental health assessment, radiology, instrumentation, business intelligence, education and criminology. The book concludes with a chapter on mathematical models of neural networks. The book serves as an introductory book about AI applications at undergraduate and graduate levels and as a reference for industry professionals working with AI based systems. CONTENTS PREFACE List of Contributors From AIS Data to Vessel Destination Through Prediction with Machine Learning Techniques Wells Wang1, Chengkai Zhang1, Fabien Guillaume2, Richard Halldearn3, Terje Solsvik Kristensen4 and Zheng Liu1,* INTRODUCTION AIS DATA PREPROCESSING APPROACH Trajectory Extraction Trajectory Resampling Noise Filtering Trajectory Segmentation VESSEL DESTINATION PREDICTION APPROACHES Sequence Prediction Approach Classification Approach Classification of Ports Classification of Trajectories CONCLUDING REMARKS CONSENT FOR PUBLICATION CONFLICT OF INTEREST ACKNOWLEDGEMENTS REFERENCES Artificial Intelligence in Mental Health Suresh Kumar Mukhiya1,*, Amin Aminifar1, Fazle Rabbi1,3, Violet Ka I. Pun1,2 and Yngve Lamo1 INTRODUCTION MENTAL HEALTH TREATMENT MOTIVATION Adaptiveness and Adherence Automation of the Treatment Process Scalability Personal Stigma (Self-aware Treatment Systems) AI for A Personalized Recommendation DATA COLLECTION AND PREPARATION Challenges in Data Collection MENTAL HEALTH AND AI Natural Language Processing (NLP) Virtual Reality (VR) and Augmented Reality (AR) Affective Computing Robotics Brain Computer Interface (BCI) Machine Perception and Ambient Intelligence CHALLENGES Technical Issues Security and Privacy Issues Ethical Issues Design Issues DISCUSSION ABOUT FUTURE DEVELOPMENT CONCLUSION NOTES CONSENT FOR PUBLICATION CONFLICT OF INTEREST ACKNOWLEDGEMENTS REFERENCES Deep Learning in Radiology Madhura Ingalhalikar1,* INTRODUCTION MOTIVATION DEEP LEARNING IN RADIOLOGY Diagnostic Predictions Detecting Abnormalities on Chest X-rays Screening for Lung Cancer on Low Dose CT Genotype Detection in Gliomas on Multi-Modal MRI Prostrate Cancer Detection Segmentation 2d and 3d Cnns U-Nets Registration Image Generation Other Applications LIMITATIONS AND WAYS FORWARD CONCLUSION CONSENT FOR PUBLICATION CONFLICT OF INTEREST ACKNOWLEDGEMENTS REFERENCES AI in Instrumentation Industry Ajay V. Deshmukh1,* INTRODUCTION A SYSTEMATIC APPROACH TO APPLIED AI ARTIFICIAL INTELLIGENCE AND ITS NEED AI IN CHEMICAL PROCESS INDUSTRY AI IN MANUFACTURING PROCESS INDUSTRY AI for Quality Control AI in Process Monitoring AI in Plant Safety CONCLUSION CONSENT FOR PUBLICATION CONFLICT OF INTEREST ACKNOWLEDGEMENTS REFERENCES AI in Business and Education Tarjei Alvær Heggernes1,* INTRODUCTION THE INDUSTRIAL REVOLUTION AND THE LONG ECONOMIC WAVES ARTIFICIAL INTELLIGENCE AND INDUSTRY 4.0 What can AI do? DEFINITIONS Machine Learning Sense, Understand and Act How Do Systems Learn? Deep Learning and Neural Networks Generative Adversary Networks AI IN BUSINESS OPERATIONS AI IN BUSINESS MANAGEMENT AI IN MARKETING Use of Reinforcement Learning in Real-Time Auctions for Online Advertising AI IN EDUCATION Systems for Intelligent Tutoring and Adaptive Learning Evaluation of Assignments with Neural Networks CONCLUSION CONSENT FOR PUBLICATION CONFLICT OF INTEREST ACKNOWLEDGEMENTS REFERENCES Extreme Randomized Trees for Real Estate Appraisal with Housing and Crime Data Junchi Bin1, Bryan Gardiner2, Eric Li3 and Zheng Liu1,* INTRODUCTION RELATED WORKS Machine Learning in Real Estate Appraisal Real Estate Appraisal beyond House Attributes METHODOLOGY Overall Architecture of Proposed Method Data Collection and Description House Attributes Comprehensive Crime Intensity Extremely Randomized Trees EXPERIMENTS Experimental Setup Evaluation Metrics Performance Comparison CONCLUSIONS CONSENT FOR PUBLICATION CONFLICT OF INTEREST ACKNOWLEDGEMENTS REFERENCES The Knowledge-based Firm and AI Ove Rustung Hjelmervik1 and Terje Solsvik Kristensen1,2,* INTRODUCTION AI - A CREATIVE DESTRUCTION TECHNOLOGY Schumpeter’s Disruptive Technology and Radical Innovation IT and The Productivity Paradox ALAN TURING’S DISRUPTIVE RESEARCH AND INNOVATION Turing Machine Turing Test Problem Solving Turing’s Connectionism Gødel and AI THE KNOWLEDGE-BASED ORGANIZATION The Resource-Based View of The Firm Organizational Learning Bounded Rationality DISCUSSION CONCLUSION NOTES CONSENT FOR PUBLICATION CONFLICT OF INTEREST ACKNOWLEDGEMENTS REFERENCES A Mathematical Description of Artificial Neural Networks Hans Birger Drange1,* INTRODUCTION ARTIFICIAL NEURAL NETWORKS, ANN Neurons in the Brain A Mathematical Model The Synapse A Mathematical Structure The Network as a Function Description of the Weights Turning to the Matrices Themselves The Functions of the Network The Details of what the Functions fk do to their Arguments Study of the Function f of the whole Network Determination of the Correct Weight Matrices The Actual Mathematical Objects that we Manipulate PERCEPTRON A Special Notation for Two Layers and an Output Layer of only One Neuron Training of the Network About the Threshold b Not all Logic Functions can be defined by a Simple Perceptron Solving Pattern Classification with a Simple Perceptron A Geometric Criterion for the Solution of the Classification Problem REGRESSION AS A NEURAL NETWORK Solving by Standard Linear Regression Solving by Using the Perceptron A Little More about the Learning Rate and Finding the Minimum MULTILAYER PERCEPTRONS, MLP BACKPROPAGATION Computation of the Weight Updates Updates for the Weights in the First Layer of Connections Definition of the Local Error Signals Updates of the Weights in the Second Layer of Connections THE FINAL CONCLUSION PROPAGATION OF THE ERROR SIGNALS Updating the Weights for all Layers of Weights Using Number Indices Finding the Weights Themselves CONCLUSION NOTES CONSENT FOR PUBLICATION CONFLICT OF INTEREST ACKNOWLEDGEMENTS REFERENCES Subject index