Handbook Of Research On Automated Feature Engineering And Advanced Applications In Data Science

In today’s digital world, the huge amount of data being generated is unstructured, messy, and chaotic in nature. Dealing with such data, and attempting to unfold the meaningful information, can be a challenging task. Feature engineering is a process to transform such data into a suitable form that better assists with interpretation and visualization. Through this method, the transformed data is more transparent to the machine learning models, which in turn causes better prediction and analysis of results. Data science is crucial for the data scientist to assess the trade-offs of their decisions regarding the effectiveness of the machine learning model implemented. Investigating the demand in this area today and in the future is a necessity. The Handbook of Research on Automated Feature Engineering and Advanced Applications in Data Science provides an in-depth analysis on both the theoretical and the latest empirical research findings on how features can be extracted and transformed from raw data. The chapters will introduce feature engineering and the recent concepts, methods, and applications with the use of various data types, as well as examine the latest machine learning applications on the data. While highlighting topics such as detection, tracking, selection techniques, and prediction models using data science, this book is ideally intended for research scholars, big data scientists, project developers, data analysts, and computer scientists along with practitioners, researchers, academicians, and students interested in feature engineering and its impact on data.

"This edited book will start with an introduction to feature engineering and then move onto recent concepts, methods and applications with the use of various data types that includes : text, image, streaming data, social network data, financial data, biomedical data, bioinformatics etc. to help readers gain insight into how features can be extracted and transformed from raw data"--

Many fundamental technological and managerial issues surrounding the development and implementation of intelligent analytics within multi-industry applications remain unsolved. There are still questions surrounding the foundation of intelligent analytics, the elements, the big characteristics, and the effects on business, management, technology, and society. Research is devoted to answering these questions and understanding how intelligent analytics can improve healthcare, mobile commerce, web services, cloud services, blockchain, 5G development, digital transformation, and more. Intelligent Analytics With Advanced Multi-Industry Applications is a critical reference source that explores cutting-edge theories, technologies, and methodologies of intelligent analytics with multi-industry applications and emphasizes the integration of artificial intelligence, business intelligence, big data, and analytics from a perspective of computing, service, and management. This book also provides real-world applications of the proposed concept of intelligent analytics to e-SMACS (electronic, social, mobile, analytics, cloud, and service) commerce and services, healthcare, the internet of things, the sharing economy, cloud computing, blockchain, and Industry 4.0. This book is ideal for scientists, engineers, educators, university students, service and management professionals, policymakers, decision makers, practitioners, stakeholders, researchers, and others who have an interest in how intelligent analytics are being implemented and utilized in diverse industries.

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.

Pandemics are disruptive. Thus, there is a need to prepare and plan actions in advance for identifying, assessing, and responding to such events to manage uncertainty and support sustainable livelihood and wellbeing. A detailed assessment of a continuously evolving situation needs to take place, and several aspects must be brought together and examined before the declaration of a pandemic even happens. Various health organizations; crisis management bodies; and authorities at local, national, and international levels are involved in the management of pandemics. There is no better time to revisit current approaches to cope with these new and unforeseen threats. As countries must strike a fine balance between protecting health, minimizing economic and social disruption, and respecting human rights, there has been an emerging interest in lessons learned and specifically in revisiting past and current pandemic approaches. Such approaches involve strategies and practices from several disciplines and fields including healthcare, management, IT, mathematical modeling, and data science. Using data science to advance in-situ practices and prompt future directions could help alleviate or even prevent human, financial, and environmental compromise, and loss and social interruption via state-of-the-art technologies and frameworks. Data Science Advancements in Pandemic and Outbreak Management demonstrates how strategies and state-of-the-art IT have and/or could be applied to serve as the vehicle to advance pandemic and outbreak management. The chapters will introduce both technical and non-technical details of management strategies and advanced IT, data science, and mathematical modelling and demonstrate their applications and their potential utilization within the identification and management of pandemics and outbreaks. It also prompts revisiting and critically reviewing past and current approaches, identifying good and bad practices, and further developing the area for future adaptation. This book is ideal for data scientists, data analysts, infectious disease experts, researchers studying pandemics and outbreaks, IT, crisis and disaster management, academics, practitioners, government officials, and students interested in applicable theories and practices in data science to mitigate, prepare for, respond to, and recover from future pandemics and outbreaks.

Blockchain technology presents numerous advantages that include increased transparency, reduced transaction costs, faster transaction settlement, automation of information, increased traceability, improved customer experience, improved digital identity, better cyber security, and user-controlled networks. These potential applications are widespread and diverse including funds transfer, smart contracts, e-voting, efficient supply chain, and more in nearly every sector of society including finance, healthcare, law, trade, real estate, and other important areas. However, there are challenges and limitations that exist such as high energy consumption, limited scalability, complexity, security, network size, lack of regulations, and other critical issues. Nevertheless, blockchain is an attractive technology and has much to offer to the modern-day industry. Industry Use Cases on Blockchain Technology Applications in IoT and the Financial Sector investigates blockchain technology’s adoption and effectiveness in multiple industries and for the internet of things (IoT)-based applications, presents use cases from industrial and financial sectors as well as from other transaction-based services, and fills a gap in this respect by extending the existing body of knowledge in the suggested field. While highlighting topics such as cybersecurity, use cases, and models for blockchain implementation, this book is ideal for business managers, financial accountants, practitioners, researchers, academicians, and students interested in blockchain technology’s role and implementation in IoT and the financial sector.

This book covers the latest advancements in the areas of machine learning, computer vision, pattern recognition, computational learning theory, big data analytics, network intelligence, signal processing, and their applications in real world. The topics covered in machine learning involve feature extraction, variants of support vector machine (SVM), extreme learning machine (ELM), artificial neural network (ANN), and other areas in machine learning. The mathematical analysis of computer vision and pattern recognition involves the use of geometric techniques, scene understanding and modeling from video, 3D object recognition, localization and tracking, medical image analysis, and so on. Computational learning theory involves different kinds of learning like incremental, online, reinforcement, manifold, multitask, semi-supervised, etc. Further, it covers the real-time challenges involved while processing big data analytics and stream processing with the integration of smart data computing services and interconnectivity. Additionally, it covers the recent developments to network intelligence for analyzing the network information and thereby adapting the algorithms dynamically to improve the efficiency. In the last, it includes the progress in signal processing to process the normal and abnormal categories of real-world signals, for instance signals generated from IoT devices, smart systems, speech, videos, etc., and involves biomedical signal processing: electrocardiogram (ECG), electroencephalogram (EEG), magnetoencephalography (MEG), and electromyogram (EMG).

Optimized linear algebra (LA) libraries that are able to exploit the underlying hardware are always of interest in the high-performance computing community. The implementation of LA software has evolved along with computer architecture, while the specification remains unaltered almost from the beginning. It is important to differentiate between the specification of LA libraries and their implementation. Because LA libraries pursue high performance, the implementation for a given architecture needs to be optimized for it specifically. However, the type of operations included in the libraries, the input/output parameters, and the data types to be handled are common to all of them. This is why, while the specification remains constant, the implementation evolves with the creation of new architectures. Developing Linear Algebra Codes on Modern Processors: Emerging Research and Opportunities presents the main characteristics of LA libraries, showing the differences between the standards for sparse and dense versions. It further explores relevant linear algebra problems and shows, in a clear and understandable way, how to solve them using different computer architectures. Covering topics such as programming models, batched computing, and distributed memory platforms, this premier reference source is an excellent resource for programmers, computer scientists, engineers, students and faculty of higher education, librarians, researchers, and academicians.