ISBN 978-1-119-79179-9
Cover image: Pixabay.Com
Cover design by Russell Richardson
Set in size of 11pt and Minion Pro by Manila Typesetting Company, Makati, Philippines
Printed in the USA
10 9 8 7 6 5 4 3 2 1
Preface
The power of healthcare data analytics is being increasingly used in the industry. With this in mind, we wanted to write a book geared towards those who want to learn more about the techniques used in healthcare analytics for efficient analysis of data. Since data is generally generated in enormous amounts and pumped into data pools, analyzing data patterns can help to ensure a better quality of life for patients. As a result of small amounts of health data from patients suffering from various health issues being collectively pooled, researchers and doctors can find patterns in the statistics, helping them develop new ways of forecasting or diagnosing health issues, and identifying possible ways to improve quality clinical care. Big data analytics supports this research by applying various processes to examine large and varied healthcare data sets. Advanced analytics techniques are used against large data sets to uncover hidden patterns, unknown correlations, market trends, customer preferences, and other useful information. This book covers both the theory and application of the tools, techniques and algorithms for use in big data in healthcare and clinical research. It provides the most recent research findings to derive knowledge using big data analytics, which helps to analyze huge amounts of real-time healthcare data, the analysis of which can provide further insights in terms of procedural, technical, medical, and other types of improvements in healthcare. In addition, this book also explores various sources of personalized healthcare data.
For those who are healthcare researchers, this book reveals the innovative hybrid machine learning and deep learning techniques applied in various healthcare data sets. Since machine learning algorithms play a major role in analyzing the volume, veracity and velocity of big data, the scope of this book focuses on various kinds of machine learning algorithms existing in the areas such as supervised, unsupervised, semi-supervised, and reinforcement learning. It guides readers in implementing the Python environment for machine learning in various application domains. Furthermore, predictive analytics in healthcare is explored, which can help to detect early signs of patient deterioration from the ICU to a general ward, identify at-risk patients in their homes to prevent hospital readmissions, and prevent avoidable downtime of medical equipment.
Also explored in the book are a wide variety of machine learning techniques that can be applied to infer intelligence from the data set and the capabilities of an application. The significance of data sets for various applications is also discussed along with sample case studies. Moreover, the challenges presented by the techniques and budding research avenues necessary to see their further advancement are highlighted.
Patient’s healthcare data needs to be protected by organizations in order to prevent data loss through unauthorized access. This data needs to be protected from attacks that can encrypt or destroy data, such as ransomware, as well as those attacks that can modify or corrupt a patient’s data. Security is paramount since a lot of devices are connected through the internet of things and serve many healthcare applications, including supporting smart healthcare systems in the management of various diseases such as diabetes, monitoring heart functions, predicting heart failure, etc. Therefore, this book explores the various challenges for smart healthcare, including privacy, confidentiality, authenticity, loss of information, attacks, etc., which create a new burden for providers to maintain compliance with healthcare data security.
In addition to inferring knowledge fusion patterns in healthcare, the book also explores the commercial platforms for healthcare data analytics. The new benefits that healthcare data analytics brings to the table, run analytics and unearth information that could be used in the decision-making of practitioners by providing insights that can be used to make immediate decisions. Also investigated are the new trends and applications of big data analytics for medical science and healthcare. Healthcare professionals, researchers, and practitioners who wish to figure out the core concepts of smart healthcare applications and the innovative methods and technologies used in healthcare will all benefit from this book.
Editors
Dr. A. Jaya
Dr. K. Kalaiselvi*
Dr. Dinesh Goyal
Prof. Dhiya AL-Jumeily
*Corresponding Editor
1
An Introduction to Knowledge Engineering and Data Analytics
D. Karthika* and K. Kalaiselvi†
Department of Computer Applications, Vels Institute of Science, Technology & Advanced Studies (Formerly Vels University), Chennai, Tamil Nadu, India
Abstract
In recent years, the philosophy of Knowledge Engineering has become important. Information engineering is an area of system engineering which meets unclear process demands by emphasizing the development of knowledge in a knowledge-based system and its representation. A broad architecture for knowledge engineering that manages the fragmented modeling and online learning of knowledge from numerous sources of information, non-linear incorporation of fragmented knowledge, and automatic demand-based knowledge navigation. The project aims to provide petabytes in the defined application domains with data and information tools. Knowledge-based engineering (KBE) frameworks are based on the working standards and core features with a special focus on their built-in programming language. This language is the key element of a KBE framework and promotes the development and re-use of the design skills necessary to model complex engineering goods. This facility allows for the automation of the process preparation step of multidisciplinary research (MDA), which is particularly important for this novel. The key types of design rules to be implemented in the implementation of the KBE are listed, and several examples illustrating the significant differences between the KBE and the traditional CAD approaches are presented. This chapter discusses KBE principles and how this technology will facilitate and enable the multidisciplinary optimization (MDO) of the design of complex products. This chapter discusses their reach goes beyond existing CAD structure constraints and other practical parametric and space exploration approaches. There is a discussion of the concept of KBE and its usage in architecture that supports the use of MDO. Finally, this chapter discusses on the key measures and latest trends in the development of KBE.
Keywords: Data analytics, knowledge, knowledge engineering, principles, knowledge acquisition
1.1 Introduction
1.1.1 Online Learning and Fragmented Learning Modeling
Applied artificial intelligence (AI) was defined as knowledge engineering [1], with three major scientific questions: knowledge representation, the use of information, and the acquisition of knowledge. In the big data age, the three fundamental problems must evolve with the basic characteristics of the complex and evolving connections between data objects, which are autonomous sources of information. Big data not only rely on domain awareness but also distribute knowledge from numerous information sources. To have knowledge of engineering tools for big data, we need tons of experience. Three primary research issues need to be addressed for the 54-month, RMB 45-million, 15-year Big Data Knowledge Engineering (BigKE) project sponsored by China’s Ministry of Science and Technology and several other domestic agencies: 1) online