Communication based on the internet of things (IoT) generates huge amounts of data from sensors over time, which opens a wide range of applications and areas for researchers. The application of analytics, machine learning, and deep learning techniques over such a large volume of data is a very challenging task. Therefore, it is essential to find patterns, retrieve novel insights, and predict future behavior using this large amount of sensory data. Artificial intelligence (AI) has an important role in facilitating analytics and learning in the IoT devices. Applying AI-Based IoT Systems to Simulation-Based Information Retrieval provides relevant frameworks and the latest empirical research findings in the area. It is ideal for professionals who wish to improve their understanding of the strategic role of trust at different levels of the information and knowledge society and trust at the levels of the global economy, networks and organizations, teams and work groups, information systems, and individuals as actors in the networked environments. Covering topics such as blockchain visualization, computer-aided drug discovery, and health monitoring, this premier reference source is an excellent resource for business leaders and executives, IT managers, security professionals, data scientists, students and faculty of higher education, librarians, hospital administrators, researchers, and academicians.

It is crucial that forensic science meets challenges such as identifying hidden patterns in data, validating results for accuracy, and understanding varying criminal activities in order to be authoritative so as to hold up justice and public safety. Artificial intelligence, with its potential subsets of machine learning and deep learning, has the potential to transform the domain of forensic science by handling diverse data, recognizing patterns, and analyzing, interpreting, and presenting results. Machine Learning and deep learning frameworks, with developed mathematical and computational tools, facilitate the investigators to provide reliable results. Further study on the potential uses of these technologies is required to better understand their benefits. Aiding Forensic Investigation Through Deep Learning and Machine Learning Frameworks provides an outline of deep learning and machine learning frameworks and methods for use in forensic science to produce accurate and reliable results to aid investigation processes. The book also considers the challenges, developments, advancements, and emerging approaches of deep learning and machine learning. Covering key topics such as biometrics, augmented reality, and fraud investigation, this reference work is crucial for forensic scientists, law enforcement, computer scientists, researchers, scholars, academicians, practitioners, instructors, and students.

DHM and Posturography explores the body of knowledge and state-of-the-art in digital human modeling, along with its application in ergonomics and posturography. The book provides an industry first introductory and practitioner focused overview of human simulation tools, with detailed chapters describing elements of posture, postural interactions, and fields of application. Thus, DHM tools and a specific scientific/practical problem - the study of posture - are linked in a coherent framework. In addition, sections show how DHM interfaces with the most common physical devices for posture analysis. Case studies provide the applied knowledge necessary for practitioners to make informed decisions. Digital Human Modelling is the science of representing humans with their physical properties, characteristics and behaviors in computerized, virtual models. These models can be used standalone, or integrated with other computerized object design systems, to design or study designs, workplaces or products in their relationship with humans.

Uncertainty in Data Envelopment Analysis: Fuzzy and Belief Degree-Based Uncertainties introduces methods to investigate uncertain data in DEA models, providing a deeper look into two types of uncertain DEA methods: Fuzzy DEA and Belief Degree Based Uncertainty DEA, which are based on uncertain measures. These models aim to solve problems encountered by classical data analysis in cases where inputs and outputs of systems and processes are volatile and complex, making measurement difficult. Classical data envelopment analysis (DEA) models use crisp data in order to measure inputs and outputs of a given system. Crisp input and output data are fundamentally indispensable in the conventional DEA models. If these models contain complex-uncertain data, then they will become more important and practical for decision-makers.

Developments and Applications for ECG Signal Processing: Modeling, Segmentation, and Pattern Recognition covers reliable techniques for ECG signal processing and their potential to significantly increase the applicability of ECG use in diagnosis. This book details a wide range of challenges in the processes of acquisition, preprocessing, segmentation, mathematical modelling and pattern recognition in ECG signals, presenting practical and robust solutions based on digital signal processing techniques. Users will find this to be a comprehensive resource that contributes to research on the automatic analysis of ECG signals and extends resources relating to rapid and accurate diagnoses, particularly for long-term signals. Chapters cover classical and modern features surrounding f ECG signals, ECG signal acquisition systems, techniques for noise suppression for ECG signal processing, a delineation of the QRS complex, mathematical modelling of T- and P-waves, and the automatic classification of heartbeats.

This book provides a snapshot of the state of current research at the interface between machine learning and healthcare with special emphasis on machine learning projects that are (or are close to) achieving improvement in patient outcomes. The book provides overviews on a range of technologies including detecting artefactual events in vital signs monitoring data; patient physiological monitoring; tracking infectious disease; predicting antibiotic resistance from genomic data; and managing chronic disease. With contributions from an international panel of leading researchers, this book will find a place on the bookshelves of academic and industrial researchers and advanced students working in healthcare technologies, biomedical engineering, and machine learning.

There is a significant deficiency among contemporary medicine practices reflected by experts making medical decisions for a large proportion of the population for which no or minimal data exists. Fortunately, our capacity to procure and apply such information is rapidly rising. As medicine becomes more individualized, the implementation of health IT and data interoperability become essential components to delivering quality healthcare. Quality Assurance in the Era of Individualized Medicine is a collection of innovative research on the methods and utilization of digital readouts to fashion an individualized therapy instead of a mass-population-directed strategy. While highlighting topics including assistive technologies, patient management, and clinical practices, this book is ideally designed for health professionals, doctors, nurses, hospital management, medical administrators, IT specialists, data scientists, researchers, academicians, and students.

Deep Learning through Sparse Representation and Low-Rank Modeling bridges classical sparse and low rank models-those that emphasize problem-specific Interpretability-with recent deep network models that have enabled a larger learning capacity and better utilization of Big Data. It shows how the toolkit of deep learning is closely tied with the sparse/low rank methods and algorithms, providing a rich variety of theoretical and analytic tools to guide the design and interpretation of deep learning models. The development of the theory and models is supported by a wide variety of applications in computer vision, machine learning, signal processing, and data mining. This book will be highly useful for researchers, graduate students and practitioners working in the fields of computer vision, machine learning, signal processing, optimization and statistics.

Artificial Intelligence in the Age of Neural Networks and Brain Computing demonstrates that existing disruptive implications and applications of AI is a development of the unique attributes of neural networks, mainly machine learning, distributed architectures, massive parallel processing, black-box inference, intrinsic nonlinearity and smart autonomous search engines. The book covers the major basic ideas of brain-like computing behind AI, provides a framework to deep learning, and launches novel and intriguing paradigms as future alternatives. The success of AI-based commercial products proposed by top industry leaders, such as Google, IBM, Microsoft, Intel and Amazon can be interpreted using this book.

Blockchain technology allows value exchange without the need for a central authority and ensures trust powered by its decentralized architecture. As such, the growing use of the internet of things (IoT) and the rise of artificial intelligence (AI) are to be benefited immensely by this technology that can offer devices and applications data security, decentralization, accountability, and reliable authentication. Bringing together blockchain technology, AI, and IoT can allow these tools to complement the strengths and weaknesses of the others and make systems more efficient. Multidisciplinary Functions of Blockchain Technology in AI and IoT Applications deliberates upon prospects of blockchain technology using AI and IoT devices in various application domains. This book contains a comprehensive collection of chapters on machine learning, IoT, and AI in areas that include security issues of IoT, farming, supply chain management, predictive analytics, and natural languages processing. While highlighting these areas, the book is ideally intended for IT industry professionals, students of computer science and software engineering, computer scientists, practitioners, stakeholders, researchers, and academicians interested in updated and advanced research surrounding the functions of blockchain technology in AI and IoT applications across diverse fields of research.

During these uncertain and turbulent times, intelligent technologies including artificial neural networks (ANN) and machine learning (ML) have played an incredible role in being able to predict, analyze, and navigate unprecedented circumstances across a number of industries, ranging from healthcare to hospitality. Multi-factor prediction in particular has been especially helpful in dealing with the most current pressing issues such as COVID-19 prediction, pneumonia detection, cardiovascular diagnosis and disease management, automobile accident prediction, and vacation rental listing analysis. To date, there has not been much research content readily available in these areas, especially content written extensively from a user perspective. Biomedical and Business Applications Using Artificial Neural Networks and Machine Learning is designed to cover a brief and focused range of essential topics in the field with perspectives, models, and first-hand experiences shared by prominent researchers, discussing applications of artificial neural networks (ANN) and machine learning (ML) for biomedical and business applications and a listing of current open-source software for neural networks, machine learning, and artificial intelligence. It also presents summaries of currently available open source software that utilize neural networks and machine learning. The book is ideal for professionals, researchers, students, and practitioners who want to more fully understand in a brief and concise format the realm and technologies of artificial neural networks (ANN) and machine learning (ML) and how they have been used for prediction of multi-disciplinary research problems in a multitude of disciplines.

Source Separation and Machine Learning presents the fundamentals in adaptive learning algorithms for Blind Source Separation (BSS) and emphasizes the importance of machine learning perspectives. It illustrates how BSS problems are tackled through adaptive learning algorithms and model-based approaches using the latest information on mixture signals to build a BSS model that is seen as a statistical model for a whole system. Looking at different models, including independent component analysis (ICA), nonnegative matrix factorization (NMF), nonnegative tensor factorization (NTF), and deep neural network (DNN), the book addresses how they have evolved to deal with multichannel and single-channel source separation.

Due to the increasing availability of affordable internet services, the number of users, and the need for a wider range of multimedia-based applications, internet usage is on the rise. With so many users and such a large amount of data, the requirements of analyzing large data sets leads to the need for further advancements to information processing. Big Data Processing with Hadoop is an essential reference source that discusses possible solutions for millions of users working with a variety of data applications, who expect fast turnaround responses, but encounter issues with processing data at the rate it comes in. Featuring research on topics such as market basket analytics, scheduler load simulator, and writing YARN applications, this book is ideally designed for IoT professionals, students, and engineers seeking coverage on many of the real-world challenges regarding big data.