Machine Learning and Data Science: Fundamentals and Applications

Description

MACHINE LEARNING AND DATA SCIENCE Written and edited by a team of experts in the field, this collection of papers reflects the most up-to-date and comprehensive current state of machine learning and data science for industry, government, and academia. Machine learning (ML) and data science (DS) are very active topics with an extensive scope, both in terms of theory and applications. They have been established as an important emergent scientific field and paradigm driving research evolution in such disciplines as statistics, computing science and intelligence science, and practical transformation in such domains as science, engineering, the public sector, business, social science, and lifestyle. Simultaneously, their applications provide important challenges that can often be addressed only with innovative machine learning and data science algorithms. These algorithms encompass the larger areas of artificial intelligence, data analytics, machine learning, pattern recognition, natural language understanding, and big data manipulation. They also tackle related new scientific challenges, ranging from data capture, creation, storage, retrieval, sharing, analysis, optimization, and visualization, to integrative analysis across heterogeneous and interdependent complex resources for better decision-making, collaboration, and, ultimately, value creation. Cover Half-Title Page Title Page Copyright Page Contents Preface Book Description 1 Machine Learning: An Introduction to Reinforcement Learning 1.1 Introduction 1.1.1 Motivation 1.1.2 Machine Learning 1.1.3 How Machines Learn 1.1.4 Analogy 1.1.5 Reinforcement Learning Process 1.1.6 Reinforcement Learning Definitions: Basic Terminologies 1.1.7 Reinforcement Learning Concepts 1.2 Reinforcement Learning Paradigm: Characteristics 1.3 Reinforcement Learning Problem 1.4 Applications of Reinforcement Learning Conclusion References 2 Data Analysis Using Machine Learning: An Experimental Study on UFC 2.1 Introduction 2.2 Proposed Methodology 2.2.1 Data Extraction: Preliminary 2.2.2 Pre-Processing Dataset 2.3 Experimental Evaluation and Visualization 2.4 Conclusion References 3 Dawn of Big Data with Hadoop and Machine Learning 3.1 Introduction 3.2 Big Data 3.2.1 The Life Cycle of Big Data 3.2.2 Challenges in Big Data 3.2.3 Scaling in Big Data Platforms 3.2.4 Factors to Understand Big Data Platforms and Their Selection Criteria 3.2.5 Current Trends in Big Data 3.2.6 Big Data Use Cases 3.3 Machine Learning 3.3.1 Machine Learning Algorithms 3.4 Hadoop 3.4.1 Components of the Hadoop Ecosystem 3.4.2 Other Important Components of the Hadoop Ecosystem for Machine Learning 3.4.3 Benefits of Hadoop with Machine Learning 3.5 Studies Representing Applications of Machine Learning Techniques with Hadoop 3.6 Conclusion References 4 Industry 4.0: Smart Manufacturing in Industries The Future 4.1 Introduction Challenges or Responses Shared Infrastructure Security Costs or Profitability Future Proofing Conclusion References 5 COVID-19 Curve Exploration Using Time Series Data for India 5.1 Introduction 5.2 Materials Methods 5.2.1 Data Acquisition 5.2.2 Exploratory Data Analysis (EDA) 5.3 Concl usion and Future Work References 6 A Case Study on Cluster Based Application Mapping Method for Power Optimization in 2D NoC 6.1 Introduction 6.2 Concept Graph Theory and NOC Definition 1.1 Definition 1.2 Definition 1.3 Definition 1.4 6.3 Related Work 6.3.1 Cluster-Based Mapping with KL Algorithm 6.3.2 Cluster-Based Mapping with Tailor Made Algorithm 6.3.3 Cluster-Based Mapping with Depth First Search (DFS) Algorithm 6.4 Proposed Methodology 6.4.1 Cluster-Based Mapping with FM Algorithm 6.4.2 Calculation of Total Power Consumption 6.4.3 Total Power Calculation by Using Tabu Search 6.5 Experimental Results and Discussion 6.5.1 Total Power Consumption in 2D NoC 6.5.2 Performance of Tabu Search for Power Optimization with Mesh Topology 6.5.3 Performance of Tabu Search for Power Optimization with Ring Topology 6.5.4 Average Hop Counts for 2D NoC 6.6 Conclusion References 7 Healthcare Case Study: COVID19 Detection, Prevention Measures, and Prediction Using Machine Learning & Deep Learning Algorithms 7.1 Introduction 7.2 Literature Review 7.3 Coronavirus (Covid19) 7.3.1 History of Coronavirus 7.3.2 Transmission Stages of COVID19 7.3.3 Restrictions of COVID19 7.3.4 Symptoms of COVID19 7.3.5 Prevention of COVID19 7.3.6 COVID19 Diagnosis and Awareness 7.3.7 Measures to Perform by COVID19 Patients 7.3.8 High-Risk People 7.3.9 Problem Formulation 7.4 Proposed Working Model 7.4.1 Data Selection 7.4.2 Important Symptoms for Prediction 7.4.3 Data Classification 7.5 Experimental Evaluation 7.5.1 Experiment Results 7.5.2 Experiment Analysis 7.6 Conclusion and Future Work References 8 Analysis and Impact of Climatic Conditions on COVID-19 Using Machine Learning 8.1 Introduction 8.1.1 Types of Coronavirus 8.1.2 Transmission of Virus 8.2 COVID-19 8.3 Experimental Setup 8.4 Proposed Methodology 8.5 Results Discussion 8.6 Conclusion and Future Work References 9 Application of Hadoop in Data Science 9.1 Introduction 9.1.1 Data Science 9.1.2 Big Data 9.2 Hadoop Distributed Processing 9.2.1 Anatomy of the Hadoop Ecosystem 9.2.2 Other Important Components of Hadoop Ecosystem 9.2.3 MapReduce 9.2.4 Need for Hadoop 9.2.5 Applications of Hadoop 9.2.6 Use of Hadoop with Data Science 9.3 Using Hadoop with Data Science 9.3.1 Reasons for Hadoop Being a Preferred Choice for Data Science 9.3.2 Studies Using Data Science with Hadoop 9.4 Conclusion References 10 Networking Technologies and Challenges for Green IOT Applications in Urban Climate 10.1 Introduction 10.2 Background 10.2.1 Internet of Things 10.3 Green Internet of Things 10.3.1 Green IOT Networking Technologies 10.3.2 Green IOT Applications in Urban Climate 10.3.3 Intelligent Housing 10.3.4 Intelligent Industrial Technology 10.3.5 Intelligent Healthcare 10.3.6 Intelligent Grid 10.3.7 Intelligent Harvesting 10.4 Different Energy-Efficient Implementation of Green IOT 10.5 Recycling Principal for Green IOT 10.6 Green IOT Architecture of Urban Climate 10.7 Challenges of Green IOT in Urban Climate 10.8 Discussion & Future Research Directions 10.9 Conclusion References 11 Analysis of Human Activity Recognition Algorithms Using Trimmed Video Datasets 11.1 Introduction 11.2 Contributions in the Field of Activity Recognition from Video Sequences 11.2.1 Activity Recognition from Trimmed Video Sequences Using Convolutional Neural Networks 11.3 Conclusion References 12 Solving Direction Sense Based Reasoning Problems Using Natural Language Processing 12.1 Introduction 12.2 Methodology 12.2.1 Phases of NLP d. Semantic Analysis e. Pragmatic Analysis 12.3 Description of Position 12.3.1 Distance Relation 12.3.2 Direction Relation 12.3.3 Description of Combined Distance and Direction Relation 12.4 Results and Discussion 12.5 Graphical User Interface Conclusion References 13 Drowsiness Detection Using Digital Image Processing 13.1 Introduction 13.2 Literature Review 13.3 Proposed System 13.4 The Dataset 13.5 Working Principle 13.5.1 Face Detection 13.5.2 Drowsiness Detection Approach 13.6 Convolutional Neural Networks 13.6.1 CNN Design for Decisive State of the Eye 13.7 Performance Evaluation 13.7.1 Observations 13.8 Conclusion References Index Also of Interest Check out these other related titles from Scrivener Publishing EULA