Название: Foundations of Data Science for Engineering Problem Solving
Автор: Parikshit Narendra Mahalle, Gitanjali Rahul Shinde
Издательство: Springer
Год: 2022
Страниц: 125
Язык: английский
Формат: pdf (true), epub
Размер: 22.7 MB

The book Foundations of Data Science for Engineering Problem Solving is envisioned to present the detailed and comprehensive overview of Data Science foundations including Data Science evolution, data collection, preparation, analysis of data using Machine Learning (ML) algorithm, data visualization and how Data Science can make better insights into various use cases in science and engineering. Since the last decade, there is much advancement in very large scale integration technology and the semiconductor industry making electronic wearable devices, and all Wi-Fi-enabled devices cheaper and tiny having functionalities of sensing, computing and communication. In addition to this, the Internet is also available at a more faster and affordable cost as compared to the past. Due to these reasons, the data generated by these devices and its posting on the cloud is increasing at a very faster rate. The data has become big in terms of volume, variety, velocity and complexity, and all information technology leaders are facing the problem of how to deal with this Big Data.

The book focuses on how Data Science can enrich the applications of the science and engineering domain for making it smarter. The main objective of this book is to help readers to understand how this evolving field of Data Science is going to be useful in forecasting, prediction, estimation and recommendation. The entire notion of the book is exploring foundations of data science from the basics to applications followed by case studies in science and engineering. The entire book is mainly divided into three parts. The first part of the book deals with Big data and its emergence in today’s context, data science basics, its evolution and need for today, and various applications. Data collection and preparation is the main part of any data science application which includes data exploration, various types of datasets, their classification based on the sources and types, data preprocessing phases and different tasks involved; web scrapping tools like Beautiful Soap, Scrapy and URLLIB are presented and discussed in this part of the book.

The next part of the book covers the important topic of data visualization, its need, challenges, respective tools and modelling of data. Visualization tools like Tableau, Matplotlib, Looker, Seaborn, PowerBI, IBM Cognos Analytics and their functioning are also discussed in detail in this part of the book. The process of data modelling, impact of modelling on the outcomes, decision making process as well as the role of data science in engineering problem solving are also elucidated in this part of the book. The main objective of this part of the book is to focus on various emerging tools and techniques adapted in industry for data science applications to enhance business intelligence.

The last part of the book discusses case studies of data science in the field of information, communication, technology, civil engineering, mechanical engineering and health care. This part covers important use cases like structural engineering, geotechnical engineering, construction management, recommendation system, clinical decision support system, preventive health care, control engineering, solid mechanics, predicting mechanical failure, etc. The detailed use of data science in these areas, open research issues and future outlook of data science are also presented and discussed.

The main characteristics of this book are:

• In-depth and detailed description of all the topics;
• Use case and scenario-based descriptions for easier understanding;
• Individual chapters covering case studies in prominent branches of engineering;
• Research and application development perspective with implementation details;
• Hands-on results and discussion;
• Numerous examples, technical descriptions and real-world scenarios;
• Simple and easy language so that it can be useful to a wide range of stakeholders like laymen to educate users, from villages to metros and national to global levels.

Data science and its applications to various branches of science, technology and engineering are now fundamental courses to all undergraduate courses in Computer Science, Computer Engineering, Information Technology as well as Electronics and Telecommunication engineering. Many universities and autonomous institutes across the globe have started an undergraduate programme titled “Artificial Intelligence and Data Science” as well as honours programmes in the same subject which is open for all branches of engineering. Because of this, this book is useful to all undergraduate students of these courses for project development and product design in data science, machine learning and artificial intelligence. This book is also useful to a wider range of researchers and design engineers who are concerned with exploring data science for engineering use cases. Essentially, this book is most useful to all entrepreneurs who are interested to start their start-ups in the field of application of data science to civil, mechanical, chemical engineering and healthcare domains as well as related product development. The book is useful for Undergraduates, Postgraduates, Industry, Researchers and Research Scholars in ICT, and we are sure that this book will be well-received by all stakeholders.

Contents:
1. Introduction to Data Science
2. Data Collection and Preparation
3. Data Analytics and Learning Techniques
4. Data Visualization Tools and Data Modelling
5. Data Science in Information, Communication and Technology
6. Data Science in Civil Engineering and Mechanical Engineering
7. Data Science in Clinical Decision System
8. Conclusions