We are living in an AI and data-driven era. A huge volume of data is generated from all sectors including smart cities, intelligent transportation systems, smart healthcare, education, smart agriculture and smart industrial processes. This information comprises multiple modalities such as textual data, images, sound, gestures and genetic sequences, which are generated through various sources.

The internet of multimedia things (IoMT) is one of the key contributors to the collection, analysis and management of voluminous multimodal data. The dominating features of IoMTs are well-timed delivery of data and dependability, but they require high levels of memory and computational power, which requires higher bandwidth and more power. Therefore, they require rigorous quality of service (QoS) and efficient, reliable and secure network frameworks.

The objective of this book is to explore machine learning (ML) and deep learning (DL) techniques for securing data with multiple modalities in a wide range of data-centric smart applications in the IoMT framework. In all data-centric application domains where on-time availability of data and reliability are the major concerns, IoMT is contributing significantly. The authors present the challenges faced to organize and process multimodal data in data-centric applications, several types of data modalities, and innovative IoMT frameworks. A particular focus is placed on the role of ML and DL techniques in securing multi-modal data for real-time monitoring in smart environment applications.

Machine Learning and Deep Learning Driven Techniques for Multimodal Data Security in the Internet of Multimedia Things caters to the needs of AI, big data and IoT advanced students, academic and industry researchers, engineers, security experts, data analysts, and AI and data-centric application developers.