Название: Intelligent Decision Support System for IoT-Enabling Technologies: Opportunities, Challenges and Applications
Автор: Subrata Sahana, Anil Kumar Sagar, Sanjoy Das
Издательство: Nova Science Publishers
Серия: Internet of Things and Machine Learning
Год: 2024
Страниц: 346
Язык: английский
Формат: pdf (true)
Размер: 28.8 MB

This book focuses on the Internet of Things (IoT) and Decision Support Systems to proffer preventive and intelligent systems. The major areas covered in this book are IoT challenges and opportunities, IoT-enabling technologies, decision support systems, smart applications, and intelligent systems to satisfy the goals of societal and economic issues. This book includes various problems in healthcare, insurance, and agricultural sectors. Intelligent and IoT-based applications like healthcare systems, intelligent transportation systems, business intelligence, and Artificial Intelligence (AI) in sustainable agriculture are extensively discussed in various chapters. IoT and Machine Learning Applications for the industrial sector are also highlighted. This book is most suitable for data scientists, doctors, engineers, economists, and specialists in the agricultural sector. This book will benefit the UG/PG and research scholars to understand various domains like agriculture, insurance, enviroment and healthcare sectors with applications of IoT, Machine Learning, Artificial Intelligence etc.

Algorithms that can learn on their own from data are the subject of Artificial Intelligence (AI) and Machine Learning (ML) research. Deep Learning (DL) principles utilized in video games and self-driving cars are evidence that machine learning techniques have evolved greatly over the past ten years. As a result, researchers have started to look at machine learning’s potential for use in the industry. According to various studies, Machine Learning is one of the key enabling technologies that will enable the transition from an old-school production system to Industry 4.0. Contrarily, industrial applications remain uncommon and exclusive to a select few global businesses. To clarify both the genuine potential of Machine Learning algorithms in operation management and their potential drawbacks, this chapter tackles these problems. Production organizations must constantly advance, which calls for flat, adaptable organizations as well as versatile data and material management frameworks. The study looks at ML approaches that seem to be used to build intelligent behavior-producing systems. It is contingent on two workshops on learning the intelligent manufacturing system, a comprehensive literature review, and several obligations. In addition, symbolic, hybrids, and sub-symbolic approaches, together with their uses in manufacturing, are examined. Hybrid solutions aim to combine the benefits of numerous methodologies. The best can be chosen by course of action for a particular set of circumstances; several methods of production are compared and contrasted.