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.

Brain-machine interfacing or brain-computer interfacing (BMI/BCI) is an emerging and challenging technology used in engineering and neuroscience. The ultimate goal is to provide a pathway from the brain to the external world via mapping, assisting, augmenting or repairing human cognitive or sensory-motor functions. In this book an international panel of experts introduce signal processing and machine learning techniques for BMI/BCI and outline their practical and future applications in neuroscience, medicine, and rehabilitation, with a focus on EEG-based BMI/BCI methods and technologies. Topics covered include discriminative learning of connectivity pattern of EEG; feature extraction from EEG recordings; EEG signal processing; transfer learning algorithms in BCI; convolutional neural networks for event-related potential detection; spatial filtering techniques for improving individual template-based SSVEP detection; feature extraction and classification algorithms for image RSVP based BCI; decoding music perception and imagination using deep learning techniques; neurofeedback games using EEG-based Brain-Computer Interface Technology; affective computing system and more.

Securing Delay-Tolerant Networks with BPSec One-stop reference on how to secure a Delay-Tolerant Network (DTN), written by experienced industry insiders Securing Delay-Tolerant Networks with BPSec answers the question, "How can delay-tolerant networks be secured when operating in environments that would otherwise break many of the common security approaches used on the terrestrial Internet today?" The text is composed of three sections: (1) security considerations for delay-tolerant networks, (2) the design, implementation, and customization of the BPSec protocol, and (3) how this protocol can be applied, combined with other security protocols, and deployed in emerging network environments. The text includes pragmatic considerations for deploying BPSec in both regular and delay-tolerant networks. It also features a tutorial on how to achieve several important security outcomes with a combination of security protocols, BPSec included. Overall, it covers best practices for common security functions, clearly showing designers how to prevent network architecture from being over-constrained by traditional security approaches. Written by the lead author and originator of the BPSec protocol specification, Securing Delay-Tolerant Networks (DTNs) with BPSec includes information on: The gap between cryptography and network security, how security requirements constrain network architectures, and why we need something different DTN stressing conditions, covering intermittent connectivity, congested paths, partitioned topologies, limited link state, and multiple administrative controls Securing the terrestrial internet, involving a layered approach to security, the impact of protocol design on security services, and securing the internetworking and transport layers A delay-tolerant security architecture, including desirable properties of a DTN secure protocol, fine-grained security services, and protocol augmentation Securing Delay-Tolerant Networks (DTNs) with BPSec is a one-stop reference on the subject for any professional operationally deploying BP who must use BPSec for its security, including software technical leads, software developers, space flight mission leaders, network operators, and technology and product development leaders in general.

More individuals than ever are utilizing internet technologies to work from home, teach and learn, shop, interact with peers, review medical records, and more. While it is certainly convenient to conduct such tasks via the internet, this increased internet presence has also led to a rise in the search and availability of personal information, which in turn is resulting in more cyber-attacks, privacy breaches, and information leaks. Cyber criminals are using such opportunities to attack governments, organizations, and individuals, making it necessary to anticipate, assess, and mitigate privacy and security threats during this infodemic. The Handbook of Research on Technical, Privacy, and Security Challenges in a Modern World discusses the design and development of different machine learning systems, including next generation applications, in order to mitigate cyber-attacks and address security challenges in everyday technologies. It further explores select methods and algorithms of learning for implementing better security methods in fields such as business and healthcare. It recognizes the future of privacy and the importance of preserving data through recommended practice, feedback loops, and smart agents. Covering topics such as face mask detection, gesture recognition, and botnet attacks and detection, this major reference work is a dynamic resource for medical professionals, healthcare administrators, government officials, business executives and managers, IT managers, students and faculty of higher education, librarians, researchers, and academicians.

With new technologies, such as computer vision, internet of things, mobile computing, e-governance and e-commerce, and wide applications of social media, organizations generate a huge volume of data and at a much faster rate than several years ago. Big data in large-/small-scale systems, characterized by high volume, diversity, and velocity, increasingly drives decision making and is changing the landscape of business intelligence. From governments to private organizations, from communities to individuals, all areas are being affected by this shift. There is a high demand for big data analytics that offer insights for computing efficiency, knowledge discovery, problem solving, and event prediction. To handle this demand and this increase in big data, there needs to be research on innovative and optimized machine learning algorithms in both large- and small-scale systems. Applications of Big Data in Large- and Small-Scale Systems includes state-of-the-art research findings on the latest development, up-to-date issues, and challenges in the field of big data and presents the latest innovative and intelligent applications related to big data. This book encompasses big data in various multidisciplinary fields from the medical field to agriculture, business research, and smart cities. While highlighting topics including machine learning, cloud computing, data visualization, and more, this book is a valuable reference tool for computer scientists, data scientists and analysts, engineers, practitioners, stakeholders, researchers, academicians, and students interested in the versatile and innovative use of big data in both large-scale and small-scale systems.

This open access book provides a comprehensive overview of the state of the art in research and applications of Foundation Models and is intended for readers familiar with basic Natural Language Processing (NLP) concepts.  Over the recent years, a revolutionary new paradigm has been developed for training models for NLP. These models are first pre-trained on large collections of text documents to acquire general syntactic knowledge and semantic information. Then, they are fine-tuned for specific tasks, which they can often solve with superhuman accuracy. When the models are large enough, they can be instructed by prompts to solve new tasks without any fine-tuning. Moreover, they can be applied to a wide range of different media and problem domains, ranging from image and video processing to robot control learning. Because they provide a blueprint for solving many tasks in artificial intelligence, they have been called Foundation Models.  After a brief introduction to basic NLP models the main pre-trained language models BERT, GPT and sequence-to-sequence transformer are described, as well as the concepts of self-attention and context-sensitive embedding. Then, different approaches to improving these models are discussed, such as expanding the pre-training criteria, increasing the length of input texts, or including extra knowledge. An overview of the best-performing models for about twenty application areas is then presented, e.g., question answering, translation, story generation, dialog systems, generating images from text, etc. For each application area, the strengths and weaknesses of current models are discussed, and an outlook on further developments is given. In addition, links are provided to freely available program code. A concluding chapter summarizes the economic opportunities, mitigation of risks, and potential developments of AI.

The emergent phenomena of virtual reality, augmented reality, and mixed reality is having an impact on ways people communicate with technology and with each other. Schools and higher education institutions are embracing these emerging technologies and implementing them at a rapid pace. The challenge, however, is to identify well-defined problems where these innovative technologies can support successful solutions and subsequently determine the efficacy of effective virtual learning environments. Emerging Technologies in Virtual Learning Environments is an essential scholarly research publication that provides a deeper look into 3D virtual environments and how they can be developed and applied for the benefit of student learning and teacher training. This book features a wide range of topics in the areas of science, technology, engineering, arts, and math to ensure a blend of both science and humanities research. Therefore, it is ideal for curriculum developers, instructional designers, teachers, school administrators, higher education faculty, professionals, researchers, and students studying across all academic disciplines.

Practical Guide for Biomedical Signals Analysis Using Machine Learning Techniques: A MATLAB Based Approach presents how machine learning and biomedical signal processing methods can be used in biomedical signal analysis. Different machine learning applications in biomedical signal analysis, including those for electrocardiogram, electroencephalogram and electromyogram are described in a practical and comprehensive way, helping readers with limited knowledge. Sections cover biomedical signals and machine learning techniques, biomedical signals, such as electroencephalogram (EEG), electromyogram (EMG) and electrocardiogram (ECG), different signal-processing techniques, signal de-noising, feature extraction and dimension reduction techniques, such as PCA, ICA, KPCA, MSPCA, entropy measures, and other statistical measures, and more. This book is a valuable source for bioinformaticians, medical doctors and other members of the biomedical field who need a cogent resource on the most recent and promising machine learning techniques for biomedical signals analysis.

Safety and security are crucial to the operations of nuclear power plants, but cyber threats to these facilities are increasing significantly. Instrumentation and control systems, which play a vital role in the prevention of these incidents, have seen major design modifications with the implementation of digital technologies. Advanced computing systems are assisting in the protection and safety of nuclear power plants; however, significant research on these computational methods is deficient. Cyber Security and Safety of Nuclear Power Plant Instrumentation and Control Systems is a pivotal reference source that provides vital research on the digital developments of instrumentation and control systems for assuring the safety and security of nuclear power plants. While highlighting topics such as accident monitoring systems, classification measures, and UAV fleets, this publication explores individual cases of security breaches as well as future methods of practice. This book is ideally designed for engineers, industry specialists, researchers, policymakers, scientists, academicians, practitioners, and students involved in the development and operation of instrumentation and control systems for nuclear power plants, chemical and petrochemical industries, transport, and medical equipment.

Recent advances in information and communication technologies have enhanced the standards of metropolitan planning and development. With the increase in mobile communication, this will help to deliver innovative new services and apps in the field of urban e-planning. New Approaches, Methods, and Tools in Urban E-Planning is a key resource for the latest academic research on recent innovations in urban e-planning, citizen e-participation, the use of social media, and new forms of data collection and idea generation for urban planning. Presenting broad coverage among a variety of pertinent views and themes such as ethnography, e-consultation, and civic engagement, this book is ideally designed for planners, policymakers, researchers, and graduate students interested in how recent technological advancements are enhancing the traditional practices in e-planning.