Deployable Multimodal Machine Intelligence

This book highlights the principles, design and characterization of mechanically compliant soft and foldable robots. Traditional rigid robots with bulky footprints and complicated components prolong the design iteration and optimization for keyhole and minimally invasive transluminal applications. Therefore, there is an interest in developing soft and foldable robots with remote actuation, multimodal sensing and machine intelligence. This book discusses the use of foldable and cuttable structures to design biomimetic deployable soft robots, that can exhibit a fair number of motions with consistency and repeatability. It presents the overall design principles, methodology, instrumentation, metamorphic sensing, multi-modal perception, and machine intelligence for creating untethered foldable active structures. These robotic structures can generate a variety of motions such as wave induction, compression, inchworm, peristalsis, flipping, tumbling, walking, swimming, flexion/extension etc. Remote actuation can control motions along regular and irregular surfaces from proximal sides. For self-deployable medical robots, motion diversity and shape reconfiguration are crucial factors. Deployable robots, with the use of malleable and resilient smart actuators, hold this crucial advantage over their conventional rigid robot counterparts. Such flexible structures capable of being compressed and expanded with intelligence perceptions hold enormous potential in biomedical applications.

Multimodal Machine Learning: Techniques and Applications explains recent advances in multimodal machine learning, providing a coherent set of fundamentals for designing efficient multimodal learning algorithms for different applications. The book addresses the main challenges in multimodal machine learning based computing paradigms, including multimodal representation learning, translation and mapping, modality alignment, multimodal fusion and co-learning. The book also explores the important texture feature descriptors based on recognition and transform techniques. It is ideal for senior undergraduates, graduate students, and researchers in data science, engineering, computer science and statistics. Presents new representation, classification and identification algorithms for data prediction and analysis on feature characteristics Discusses recent and future advancements in diversified fields of computer vision , pattern recognition, generative adversarial network-based learning, video analytics and data science Provides an overview of future research challenges and directions

This book constitutes the refereed proceedings of the Third Southern African Conference on Artificial Intelligence Research, SACAIR 2022, held in Stellenbosch, South Africa, in December 2022. The 26 papers presented were thoroughly reviewed and selected from the 73 submissions. They are organized on the topical sections on​ algorithmic, data driven and symbolic AI; socio-technical and human-centered AI; responsible and ethical AI.

This edited book will serve as a source of reference for technologies and applications for multimodality data analytics in big data environments. After an introduction, the editors organize the book into four main parts on sentiment, affect and emotion analytics for big multimodal data; unsupervised learning strategies for big multimodal data; supervised learning strategies for big multimodal data; and multimodal big data processing and applications. The book will be of value to researchers, professionals and students in engineering and computer science, particularly those engaged with image and speech processing, multimodal information processing, data science, and artificial intelligence.

Intelligent systems are technologically advanced machines that perceive and respond to the world around them. Artificial Intelligence and Machine Learning for Smart Community: Concepts and Applications presents the evolution, challenges, and limitations of the application of machine learning and artificial intelligence to intelligent systems and smart communities. Covers the core and fundamental aspects of artificial intelligence, machine learning, and computational algorithms in smart intelligent systems Discusses the integration of artificial intelligence with machine learning using mathematical modeling Elaborates concepts like supervised and unsupervised learning, and machine learning algorithms, such as linear regression, logistic regression, random forest, and performance evaluation matrices Introduces modern algorithms such as convolutional neural networks and support vector machines Presents case studies on smart healthcare, smart traffic management, smart buildings, autonomous vehicles, smart education, modern community, and smart machines Artificial Intelligence and Machine Learning for Smart Community: Concepts and Applications is primarily written for graduate students and academic researchers working in the fields of computer science and engineering, electrical engineering, and information technology. Seasonal Blurb: This reference text presents the most recent and advanced research on the application of artificial intelligence and machine learning on intelligent systems. It will discuss important topics such as business intelligence, reinforcement learning, supervised learning, and unsupervised learning in a comprehensive manner.

With the increasing amount of various data types, machine learning methods capable of leveraging diverse sources of information have become highly relevant. Deep learning-based approaches have made significant progress in learning from texts and images in recent years. These methods enable simultaneous learning from different types of representations (embeddings). Substantial advancements have also been made in joint learning from different types of spaces. Additionally, other modalities such as sound, physical signals from the environment, and time series-based data have been recently explored. Multimodal machine learning, which involves processing and learning from data across multiple modalities, has opened up new possibilities in a wide range of applications, including speech recognition, natural language processing, and image recognition. From Unimodal to Multimodal Machine Learning: An Overview gradually introduces the concept of multimodal machine learning, providing readers with the necessary background to understand this type of learning and its implications. Key methods representative of different modalities are described in more detail, aiming to offer an understanding of the peculiarities of various types of data and how multimodal approaches tend to address them (although not yet in some cases). The book examines the implications of multimodal learning in other domains and presents alternative approaches that offer computationally simpler yet still applicable solutions. The final part of the book focuses on intriguing open research problems, making it useful for practitioners who wish to better understand the limitations of existing methods and explore potential research avenues to overcome them