Machine Learning and IoT

A Biological Perspective

Shampa Sen, Leonid Datta, Sayak Mitra, Shampa Sen, Leonid Datta, Sayak Mitra

• Publisher: CRC Press
• Year: 2018
• Print ISBN: 9781138492691
• eBook ISBN: 9781351029926
• Topic: Computer Science
• Subtopic: Computer Science General
• Index: Computer Science

This book discusses some of the innumerable ways in which computational methods can be used to facilitate research in biology and medicine - from storing enormous amounts of biological data to solving complex biological problems and enhancing treatment of various grave diseases.

1

Machine Learning

A Powerful Tool for Biologists

Mohd Zafar, Ramkumar Lakshmi Narayanan, Saroj K. Meher, and Shishir K. Behera

Contents

1.1Machine Learning (ML): An Overview

1.1.1What is ML?

1.1.2ML versus Other Computing Environments

1.1.2.1ML versus Deep Learning

1.1.2.2ML versus Statistics

1.2Various Approaches to ML

1.2.1Decision Tree (DT)

1.2.2Artificial Neural Networks

1.2.3Deep Learning

1.2.3.1Deep Learning Algorithm

1.2.4Support Vector Machines

1.2.5Clustering

1.2.6Bayesian Networks

1.2.7Mining Methods

1.3Data Mining

1.3.1Knowledge Discovery Process

1.3.2Classification

1.3.3Clustering

1.3.4Regression

1.3.5Outlier Analysis

1.4Big Data

1.4.1Why Big Data?

1.4.2Big Data Implementation Framework

1.4.3MapReduce

1.4.4Big Data and Biology

1.4.4.1Cluster Computing in System Biology

1.4.4.2Grid Computing in System Biology

1.4.4.3General Purpose Graphic Processing Units (GPGPUs) Computing in System Biology

1.4.4.4Cloud Computing in System Biology

References

1.1Machine Learning (ML): An Overview

1.1.1What is ML?

ML is a method of data analysis dealing with the construction and evaluation of algorithms. It is the science that gives computers and computing machines the ability to act without being explicitly being programmed. It is defined by the ability to choose effective features for pattern recognition, classification, and prediction based on the models derived from existing data (Tarca et al. 2007). A suitably programmed computing machine is required to perform the aforementioned tasks with the help of an efficient data analysis algorithm in such a way that the classifier itself is highly mechanized without the involvement of human input.

1.1.2ML versus Other Computing Environments

Data mining is an advanced technique used for data exploration in these domains and is broadly categorized into descriptive and predictive approaches. Under the descriptive approaches, the interesting patterns (i.e., relations) in the dataset can be identified and clustered into meaningful groups. The predictive approaches refer to supervised learning which establishes the relationship between input (independent) variables and target (dependent) variables through a structural presentation, that is, a model. Among different ML algorithms, a supervised learning algorithm includes a set of mathematical instructions which can derive a typical, high-dimensional model in the form of input-output relationships. The developed supervised learning model help in identification of mapping of input variables to output variables based on a given example of joint observations of the values of these variables (Geurts et al. 2009).

Data science compares and overlaps with many related fields such as ML, deep learning, artificial intelligence, statistics, operations research, and applied mathematics. ML is largely a hybrid field, taking its motivation and practices from both computational science and mathematics. It is the core part of both data mining and predictive analytics.

1.1.2.1ML versus Deep Learning

The two main supervised models of ML are classification and regression. The regression model is used to predict the demand of a given product in relation to its characteristics. However, the classification model maps the input variables into predefined classes. The widely used classifiers under ML approaches are support vector machine (SVM), artificial neural network (ANN), and decision trees (DT). Deep learning is referred to as the intersection between ML and artificial intelligence. It is a subfield of ML focusing narrowly on a subset of ML tools and techniques supported by neural network inspired algorithms.

1.1.2.2ML versus Statistics

The main focus of ML is the study and design of systems which can learn from data. On the other hand, stati...

Table of contents

• Cover
• Half Title
• Title Page
• Copyright Page
• Dedication
• Contents
• Foreword
• Preface
• About the Editors
• Contributors
• Chapter 1: Machine Learning: A Powerful Tool for Biologists
• Chapter 2: Mining and Analysis of Bioprocess Data
• Chapter 3: Data Mining in Nutrigenomics
• Chapter 4: Machine Learning in Metabolic Engineering
• Chapter 5: Big Data and Transcriptomics
• Chapter 6: Comparative Study of Predictive Models in Microbial-Induced Corrosion
• Chapter 7: Application of Data Mining Techniques in Autoimmune Diseases Research and Treatment
• Chapter 8: Data Mining Techniques in Imaging of Embryogenesis
• Chapter 9: Machine Learning Approach to Overcome the Challenges in Theranostics: A Review
• Chapter 10: Emotion Detection System
• Chapter 11: Segmentation and Clinical Outcome Prediction in Brain Lesions
• Chapter 12: Machine Learning Based Hospital-Acquired Infection Control System
• Chapter 13: No Human Doctor: Learning of the Machine
• Chapter 14: The IoT Revolution
• Chapter 15: Healthcare IoT (H-IoT): Applications and Ethical Concerns
• Chapter 16: Brain–Computer Interface
• Chapter 17: IoT-Based Wearable Medical Devices
• Chapter 18: People with Disabilities: The Helping Hand of IoT
• Chapter 19: Smart Analytical Lab
• Chapter 20: Crop and Animal Farming IoT (CAF-IoT)
• Index