- Table View
- List View
Data-driven Analytics for Sustainable Buildings and Cities: From Theory to Application (Sustainable Development Goals Series)
by Xingxing ZhangThis book explores the interdisciplinary and transdisciplinary fields of energy systems, occupant behavior, thermal comfort, air quality and economic modelling across levels of building, communities and cities, through various data analytical approaches. It highlights the complex interplay of heating/cooling, ventilation and power systems in different processes, such as design, renovation and operation, for buildings, communities and cities. Methods from classical statistics, machine learning and artificial intelligence are applied into analyses for different building/urban components and systems. Knowledge from this book assists to accelerate sustainability of the society, which would contribute to a prospective improvement through data analysis in the liveability of both built and urban environment. This book targets a broad readership with specific experience and knowledge in data analysis, energy system, built environment and urban planning. As such, it appeals to researchers, graduate students, data scientists, engineers, consultants, urban scientists, investors and policymakers, with interests in energy flexibility, building/city resilience and climate neutrality.
Data-Driven Analytics for the Geological Storage of CO2
by Shahab MohagheghData-driven analytics is enjoying unprecedented popularity among oil and gas professionals. Many reservoir engineering problems associated with geological storage of CO2 require the development of numerical reservoir simulation models. This book is the first to examine the contribution of artificial intelligence and machine learning in data-driven analytics of fluid flow in porous environments, including saline aquifers and depleted gas and oil reservoirs. Drawing from actual case studies, this book demonstrates how smart proxy models can be developed for complex numerical reservoir simulation models. Smart proxy incorporates pattern recognition capabilities of artificial intelligence and machine learning to build smart models that learn the intricacies of physical, mechanical and chemical interactions using precise numerical simulations. This ground breaking technology makes it possible and practical to use high fidelity, complex numerical reservoir simulation models in the design, analysis and optimization of carbon storage in geological formations projects.
Data Driven Approaches on Medical Imaging
by Bin Zheng Stefan Andrei Md Kamruzzaman Sarker Kishor Datta GuptaThis book deals with the recent advancements in computer vision techniques such as active learning, few-shot learning, zero shot learning, explainable and interpretable ML, online learning, AutoML etc. and their applications in medical domain. Moreover, the key challenges which affect the design, development, and performance of medical imaging systems are addressed. In addition, the state-of-the-art medical imaging methodologies for efficient, interpretable, explainable, and practical implementation of computer imaging techniques are discussed. At present, there are no textbook resources that address the medical imaging technologies. There are ongoing and novel research outcomes which would be useful for the development of novel medical imaging technologies/processes/equipment which can improve the current state of the art.The book particularly focuses on the use of data driven new technologies on medical imaging vision such as Active learning, Online learning, few shot learning, AutoML, segmentation etc.
Data-Driven Decision Making in Entrepreneurship: Tools for Maximizing Human Capital
by Nikki Blacksmith Maureen E. McCuskerSince the beginning of the 21st century, there has been an explosion in startup organizations. Together, these organizations have been valued at over $3 trillion. In 2019, alone, nearly $300 billion of venture capital was invested globally (Global Startup Ecosystem Report 2020). Simultaneously, an explosion in high volume and high velocity of big data is rapidly changing how organizations function. Gone are the days where organizations can make decisions solely on intuition, logic, or experience. Some have gone as far as to say that data is the most valuable currency and resource available to businesses, and startups are no exception. However, startups and small businesses do differ from their larger counterparts and corporations in three distinct ways: 1) they tend to have fewer resources, time, and specialized training to devote to data analytics; 2) they are part of a unique entrepreneurial ecosystem with unique needs; 3) scholarship and academic research on human capital data analytics in startups is lacking. Existing entrepreneurship research focuses almost exclusively on macro-level aspects. There has been little to no integration of micro- and meso-level research (i.e., individual and team sciences), which is unfortunate given how organizational scientists have significantly advanced human capital data analytics. Unlike other books focused on data analytics and decision for organizations, this proposed book is purposefully designed to be more specifically aimed at addressing the unique idiosyncrasies of the science, research, and practice of startups. Each chapter highlights a specific organizational domain and discuss how a novel data analytic technique can help enhance decision-making, provides a tutorial of said regarding the data analytic technique, and lists references and resources for the respective data analytic technique. The volume will be grounded in sound theory and practice of organizational psychology, entrepreneurship and management and is divided into two parts: assessing and evaluating human capital performance and the use of data analytics to manage human capital.
Data Driven Energy Centered Maintenance (Energy Management)
by Marvin T. Howell Fadi AlshakhshirOver recent years, many new technologies have been introduced to drive the digital transformation in the building maintenance industry. The current trend in digital evolution involves data-driven decision making which opens new opportunities for an energy centered maintenance model. Artificial Intelligence and Machine Learning are helping the maintenance team to get to the next level of maintenance intelligence to provide real-time early warning of abnormal equipment performance. This edition follows the same methodology as the First. It provides detailed descriptions of the latest technologies associated with Artificial Intelligence and Machine Learning which enable data-driven decision-making processes about the equipment’s operation and maintenance. Technical topics discussed in the book include: Different Maintenance Types and The Need for Energy Centered Maintenance The Centered Maintenance Model Energy Centered Maintenance Process Measures of Equipment and Maintenance Efficiency and Effectiveness Data-Driven Energy Centered Maintenance Model: Digitally Enabled Energy Centered Maintenance Tasks Artificial Intelligence and Machine Learning in Energy Centered Maintenance Model Capabilities and Analytics Rules Building Management System Schematics The book contains a detailed description of the digital transformation process of most of the maintenance inspection tasks as they move away from being manually triggered. The book is aimed at building operators as well as those building automation companies who are working continuously to digitalize building operation and maintenance procedures. The benefits are reductions in the equipment failure rate, improvements in equipment reliability, increases in equipment efficiency and extended equipment lifespan.
Data Driven Guide to the Analysis of X-ray Photoelectron Spectra using RxpsG
by Giorgio SperanzaThis book provides a theoretical background to X-ray photoelectron spectroscopy (XPS) and a practical guide to the analysis of the XPS spectra using the RxpsG software, a powerful tool for XPS analysis. Although there are several publications and books illustrating the theory behind XPS and the origin of the spectral feature, this book provides an additional practical introduction to the use of RxpsG. It illustrates how to use the RxpsG software to perform specific key operations, with figures and examples which readers can reproduce themselves. The book contains a list of theoretical sections explaining the appearance of the various spectral features (core‑lines, Auger components, valence bands, loss features, etc.). They are accompanied by practical steps, so readers can learn how to analyze specific spectral features using the various functions of the RxpsG software. This book is a useful guide for researchers in physics, chemistry, and material science who are looking to begin using XPS, in addition to experienced researchers who want to learn how to use RxpsG. In the digital format, the spectral data and step-by-step indications are provided to reproduce the examples given in the textbook. RxpsG is a free software for the spectral analysis. Readers can find the installation information and download the package from https://github.com/GSperanza/ website. RxpsG was developed mainly by Giorgio Speranza with the help of his colleague dr. Roberto Canteri working at Fondazione Bruno Kessler. Key Features: Simplifies the use of RxpsG, how it works, and its applications. Demonstrates RxpsG using a reproduction of the graphical interface of RxpsG, showing the steps needed to perform a specific task and the effect on the XPS spectra. Accessible to readers without any prior experience using the RxpsG software. Giorgio Speranza is Senior Researcher at Fondazione Bruno Kessler – Trento Italy, Associate Member of the Italian National Council of Research, and Associate Member of the Department of Industrial Engineering at the University of Trento, Italy.
Data-driven Modeling for Diabetes: Diagnosis and Treatment (Lecture Notes in Bioengineering)
by Vasilis Marmarelis Georgios MitsisThis contributed volume presents computational models of diabetes that quantify the dynamic interrelationships among key physiological variables implicated in the underlying physiology under a variety of metabolic and behavioral conditions. These variables comprise for example blood glucose concentration and various hormones such as insulin, glucagon, epinephrine, norepinephrine as well as cortisol. The presented models provide a powerful diagnostic tool but may also enable treatment via long-term glucose regulation in diabetics through closed-look model-reference control using frequent insulin infusions, which are administered by implanted programmable micro-pumps. This research volume aims at presenting state-of-the-art research on this subject and demonstrating the potential applications of modeling to the diagnosis and treatment of diabetes. The target audience primarily comprises research and experts in the field but the book may also be beneficial for graduate students.
Data-Driven Modeling for Sustainable Engineering: Proceedings of the First International Conference on Engineering, Applied Sciences and System Modeling (ICEASSM), Accra, 2017 (Lecture Notes in Networks and Systems #72)
by Kondo H. Adjallah Babiga Birregah Henry Fonbeyin AbandaThis book gathers the proceedings of the 1st International Conference on Engineering, Applied Sciences and System Modeling (ICEASSM), a four-day event (18th–21st April 2017) held in Accra, Ghana. It focuses on research work promoting a better understanding of engineering problems through applied sciences and modeling, and on solutions generated in an African setting but with relevance to the world as a whole. The book provides a holistic overview of challenges facing Africa, and addresses various areas from research and development perspectives. Presenting contributions by scientists, engineers and experts hailing from a host of international institutions, the book offers original approaches and technological solutions to help solve real-world problems through research and knowledge sharing. Further, it explores promising opportunities for collaborative research on issues of scientific, economic and social development, making it of interest to researchers, scientists and practitioners looking to conduct research in disciplines such as water supply, control, civil engineering, statistical modeling, renewable energy and sustainable urban development.
Data-Driven Modelling of Non-Domestic Buildings Energy Performance: Supporting Building Retrofit Planning (Green Energy and Technology)
by Saleh Seyedzadeh Farzad Pour RahimianThis book outlines the data-driven modelling of building energy performance to support retrofit decision-making. It explains how to determine the appropriate machine learning (ML) model, explores the selection and expansion of a reasonable dataset and discusses the extraction of relevant features and maximisation of model accuracy. This book develops a framework for the quick selection of a ML model based on the data and application. It also proposes a method for optimising ML models for forecasting buildings energy loads by employing multi-objective optimisation with evolutionary algorithms. The book then develops an energy performance prediction model for non-domestic buildings using ML techniques, as well as utilising a case study to lay out the process of model development. Finally, the book outlines a framework to choose suitable artificial intelligence methods for modelling building energy performances. This book is of use to both academics and practising energy engineers, as it provides theoretical and practical advice relating to data-driven modelling for energy retrofitting of non-domestic buildings.
Data Driven Strategies: Theory and Applications
by Wang Jianhong Ricardo A. Ramirez-Mendoza Ruben Morales-MenendezA key challenge in science and engineering is to provide a quantitative description of the systems under investigation, leveraging the noisy data collected. Such a description may be a complete mathematical model or a mechanism to return controllers corresponding to new, unseen inputs. Recent advances in the theories are described in detail, along with their applications in engineering. The book aims to develop model-free system analysis and control strategies, i.e., data-driven control from theoretical analysis and engineering applications based only on measured data. The study aims to develop system identification, and combination in advanced control theory, i.e., data-driven control strategy as system and controller are generated from measured data directly. The book reviews the development of system identification and its combination in advanced control theory, i.e., data-driven control strategy, as they all depend on measured data. Firstly, data-driven identification is developed for the closed-loop, nonlinear system and model validation, i.e., obtaining model descriptions from measured data. Secondly, the data-driven idea is combined with some control strategies to be considered data-driven control strategies, such as data-driven model predictive control, data-driven iterative tuning control, and data-driven subspace predictive control. Thirdly data-driven identification and data-driven control strategies are applied to interested engineering. In this context, the book provides algorithms to perform state estimation of dynamical systems from noisy data and some convex optimization algorithms through identification and control problems.
Data for the People: How to Make Our Post-Privacy Economy Work for You
by Andreas WeigendA long-time chief data scientist at Amazon shows how open data can make everyone, not just corporations, richerEvery time we Google something, Facebook someone, Uber somewhere, or even just turn on a light, we create data that businesses collect and use to make decisions about us. In many ways this has improved our lives, yet, we as individuals do not benefit from this wealth of data as much as we could. Moreover, whether it is a bank evaluating our credit worthiness, an insurance company determining our risk level, or a potential employer deciding whether we get a job, it is likely that this data will be used against us rather than for us.In Data for the People, Andreas Weigend draws on his years as a consultant for commerce, education, healthcare, travel and finance companies to outline how Big Data can work better for all of us. As of today, how much we benefit from Big Data depends on how closely the interests of big companies align with our own. Too often, outdated standards of control and privacy force us into unfair contracts with data companies, but it doesn't have to be this way. Weigend makes a powerful argument that we need to take control of how our data is used to actually make it work for us. Only then can we the people get back more from Big Data than we give it.Big Data is here to stay. Now is the time to find out how we can be empowered by it.
Data-Handling in Biomedical Science
by Peter WhitePacked with worked examples and problems, this book will help the reader improve their confidence and skill in data-handling. The mathematical methods needed for problem-solving are described in the first part of the book, with chapters covering topics such as indices, graphs and logarithms. The following eight chapters explore data-handling in different areas of microbiology and biochemistry including microbial growth, enzymes and radioactivity. Each chapter is fully illustrated with worked examples that provide a step-by-step guide to the solution of the most common problems. Over 30 exercises, ranging in difficulty and length, allow you to practise your skills and are accompanied by a full set of hints and solutions.
Data Journeys in the Sciences
by Sabina Leonelli Niccolò TempiniThis groundbreaking, open access volume analyses and compares data practices across several fields through the analysis of specific cases of data journeys. It brings together leading scholars in the philosophy, history and social studies of science to achieve two goals: tracking the travel of data across different spaces, times and domains of research practice; and documenting how such journeys affect the use of data as evidence and the knowledge being produced. The volume captures the opportunities, challenges and concerns involved in making data move from the sites in which they are originally produced to sites where they can be integrated with other data, analysed and re-used for a variety of purposes. The in-depth study of data journeys provides the necessary ground to examine disciplinary, geographical and historical differences and similarities in data management, processing and interpretation, thus identifying the key conditions of possibility for the widespread data sharing associated with Big and Open Data. The chapters are ordered in sections that broadly correspond to different stages of the journeys of data, from their generation to the legitimisation of their use for specific purposes. Additionally, the preface to the volume provides a variety of alternative “roadmaps” aimed to serve the different interests and entry points of readers; and the introduction provides a substantive overview of what data journeys can teach about the methods and epistemology of research.
Data Mining and Exploration: From Traditional Statistics to Modern Data Science
by Chong Ho Alex YuThis book introduces both conceptual and procedural aspects of cutting-edge data science methods, such as dynamic data visualization, artificial neural networks, ensemble methods, and text mining. There are at least two unique elements that can set the book apart from its rivals. First, most students in social sciences, engineering, and business took at least one class in introductory statistics before learning data science. However, usually these courses do not discuss the similarities and differences between traditional statistics and modern data science; as a result learners are disoriented by this seemingly drastic paradigm shift. In reaction, some traditionalists reject data science altogether while some beginning data analysts employ data mining tools as a “black box”, without a comprehensive view of the foundational differences between traditional and modern methods (e.g., dichotomous thinking vs. pattern recognition, confirmation vs. exploration, single method vs. triangulation, single sample vs. cross-validation etc.). This book delineates the transition between classical methods and data science (e.g. from p value to Log Worth, from resampling to ensemble methods, from content analysis to text mining etc.). Second, this book aims to widen the learner's horizon by covering a plethora of software tools. When a technician has a hammer, every problem seems to be a nail. By the same token, many textbooks focus on a single software package only, and consequently the learner tends to fit the problem with the tool, but not the other way around. To rectify the situation, a competent analyst should be equipped with a tool set, rather than a single tool. For example, when the analyst works with crucial data in a highly regulated industry, such as pharmaceutical and banking, commercial software modules (e.g., SAS) are indispensable. For a mid-size and small company, open-source packages such as Python would come in handy. If the research goal is to create an executive summary quickly, the logical choice is rapid model comparison. If the analyst would like to explore the data by asking what-if questions, then dynamic graphing in JMP Pro is a better option. This book uses concrete examples to explain the pros and cons of various software applications.
Data Mining for Bioinformatics
by Sumeet Dua Pradeep ChowriappaCovering theory, algorithms, and methodologies, as well as data mining technologies, Data Mining for Bioinformatics provides a comprehensive discussion of data-intensive computations used in data mining with applications in bioinformatics. It supplies a broad, yet in-depth, overview of the application domains of data mining for bioinformatics to he
Data Mining for Systems Biology: Methods and Protocols (Methods in Molecular Biology #939)
by Charles Delisi Minoru Kanehisa Hiroshi MamitsukaThe post-genomic revolution is witnessing the generation of petabytes of data annually, with deep implications ranging across evolutionary theory, developmental biology, agriculture, and disease processes. Data Mining for Systems Biology: Methods and Protocols, surveys and demonstrates the science and technology of converting an unprecedented data deluge to new knowledge and biological insight. The volume is organized around two overlapping themes, network inference and functional inference. Written in the highly successful Methods in Molecular BiologyTM series format, chapters include introductions to their respective topics, lists of the necessary materials and reagents, step-by-step, readily reproducible protocols, and key tips on troubleshooting and avoiding known pitfalls. Authoritative and practical, Data Mining for Systems Biology: Methods and Protocols also seeks to aid researchers in the further development of databases, mining and visualization systems that are central to the paradigm altering discoveries being made with increasing frequency.
Data Mining for Systems Biology: Methods and Protocols (Methods in Molecular Biology #1807)
by Hiroshi MamitsukaThis fully updated book collects numerous data mining techniques, reflecting the acceleration and diversity of the development of data-driven approaches to the life sciences. The first half of the volume examines genomics, particularly metagenomics and epigenomics, which promise to deepen our knowledge of genes and genomes, while the second half of the book emphasizes metabolism and the metabolome as well as relevant medicine-oriented subjects. Written for the highly successful Methods in Molecular Biology series, chapters include the kind of detail and expert implementation advice that is useful for getting optimal results. Authoritative and practical, Data Mining for Systems Biology: Methods and Protocols, Second Edition serves as an ideal resource for researchers of biology and relevant fields, such as medical, pharmaceutical, and agricultural sciences, as well as for the scientists and engineers who are working on developing data-driven techniques, such as databases, data sciences, data mining, visualization systems, and machine learning or artificial intelligence that now are central to the paradigm-altering discoveries being made with a higher frequency.
Data Mining in Biomedical Imaging, Signaling, and Systems
by Rajendra Acharya U Sumeet DuaData mining can help pinpoint hidden information in medical data and accurately differentiate pathological from normal data. It can help to extract hidden features from patient groups and disease states and can aid in automated decision making. Data Mining in Biomedical Imaging, Signaling, and Systems provides an in-depth examination of the biomedi
Data Mining in Clinical Medicine (Methods in Molecular Biology #1246)
by Carlos Fernández-Llatas Juan Miguel García-GómezThis volume complies a set of Data Mining techniques and new applications in real biomedical scenarios. Chapters focus on innovative data mining techniques, biomedical datasets and streams analysis, and real applications. Written in the highly successful Methods in Molecular Biology series format, chapters are thought to show to Medical Doctors and Engineers the new trends and techniques that are being applied to Clinical Medicine with the arrival of new Information and Communication technologiesAuthoritative and practical, Data Mining in Clinical Medicine seeks to aid scientists with new approaches and trends in the field.
Data Mining in Crystallography (Structure and Bonding #134)
by D. W. Hofmann Liudmila N. KuleshovaAn Introduction to Data Mining. - Data Bases, the Basis for Data Mining. - Data Mining and Inorganic Crystallography. - Data Mining in Organic Crystallography. - Data Mining for Protein Secondary Structure Prediction.
Data Mining in Proteomics: From Standards to Applications (Methods in Molecular Biology #696)
by Christian Stephan Martin Eisenacher Michael HamacherThrough the rapid development of proteomics methods and technologies, an enormous amount of data was created, leading to a wide-spread rethinking of strategy design and data interpretation. In Data Mining in Proteomics: From Standards to Applications, experts in the field present these new insights within the proteomics community, taking the historical evolution as well as the most important international standardization projects into account. Along with basic and sophisticated overviews of proteomics technologies, standard data formats, and databases, the volume features chapters on data interpretation strategies including statistics, spectra interpretation, and analysis environments as well as specialized tasks such as data annotation, peak picking, phosphoproteomics, spectrum libraries, LC/MS imaging, and splice isoforms. As a part of the highly successful Methods in Molecular BiologyTM series, this work provides the kind of detailed description and implementation advice that is crucial for getting optimal results. Authoritative and cutting-edge, Data Mining in Proteomics: From Standards to Applications is a well-balanced compendium for beginners and experts, offering a broad scope of data mining topics but always focusing on the current state-of-the-art and beyond.
Data Mining in Structural Dynamic Analysis: A Signal Processing Perspective
by Magd Abdel Wahab Yun Lai Zhou Nuno M. M. Maia Linya Liu Elói FigueiredoThis book highlights the applications of data mining technologies in structural dynamic analysis, including structural design, optimization, parameter identification, model updating, damage identification, in civil, mechanical, and aerospace engineering. These engineering applications require precise structural design, fabrication, inspection, and further monitoring to obtain a full life-cycle analysis, and by focusing on data processing, data mining technologies offer another aspect in structural dynamic analysis. Discussing techniques in time/frequency domain, such as Hilbert transforms, wavelet theory, and machine learning for structural dynamic analysis to help in structural monitoring and diagnosis, the book is an essential reference resource for beginners, graduates and industrial professionals in various fields.
Data Mining Techniques for the Life Sciences (Methods in Molecular Biology #1415)
by Oliviero Carugo Frank EisenhaberWhereas getting exact data about living systems and sophisticated experimental procedures have primarily absorbed the minds of researchers previously, the development of high-throughput technologies has caused the weight to increasingly shift to the problem of interpreting accumulated data in terms of biological function and biomolecular mechanisms. In "Data Mining Techniques for the Life Sciences", experts in the field contribute valuable information about the sources of information and the techniques used for "mining" new insights out of databases. Beginning with a section covering the concepts and structures of important groups of databases for biomolecular mechanism research, the book then continues with sections on formal methods for analyzing biomolecular data and reviews of concepts for analyzing biomolecular sequence data in context with other experimental results that can be mapped onto genomes. As a volume of the highly successful Methods in Molecular BiologyTM series, this work provides the kind of detailed description and implementation advice that is crucial for getting optimal results. Authoritative and easy to reference, "Data Mining Techniques for the Life Sciences" seeks to aid students and researchers in the life sciences who wish to get a condensed introduction into the vital world of biological databases and their many applications.
Data Mining Techniques for the Life Sciences (Methods in Molecular Biology #2449)
by Oliviero Carugo Frank EisenhaberThis third edition details new and updated methods and protocols on important databases and data mining tools. Chapters guides readers through archives of macromolecular sequences and three-dimensional structures, databases of protein-protein interactions, methods for prediction conformational disorder, mutant thermodynamic stability, aggregation, and drug response. Quality of structural data and their release, soft mechanics applications in biology, and protein flexibility are considered, too, together with pan-genome analyses, rational drug combination screening and Omics Deep Mining. Written in the format of the highly successful Methods in Molecular Biology series, each chapter includes an introduction to the topic, lists necessary materials, includes step-by-step, readily reproducible protocols. Authoritative and cutting-edge, Data Mining Techniques for the Life Sciences, Third Edition aims to be a practical guide to researches to help further their study in this field.
Data, Models and Analysis: The Highest Impact Articles in 'Atmosphere-Ocean'
by Guoqi Han, Hai Lin and Douw SteynThis volume contains the ten most cited articles that have appeared in the journal Atmosphere-Ocean since 1995. These articles cover a wide range of topics in meteorology, climatology and oceanography. Modelling work is represented in five papers, covering global climate model development; a cumulus parameterization scheme for global climate models; development of a regional forecast modelling system and parameterization of peatland hydraulic processes for climate models. Data rehabilitation and compilation in order to support trend analysis work on comprehensive precipitation and temperature data sets is presented in four papers. Field studies are represented by a paper on the circumpolar lead system. While the modelling studies are global in their application and applicability, the data analysis and field study papers cover environments that are specifically, but not uniquely, Canadian. This book will be of interest to researchers, students and professionals in the various sub-fields of meteorology, oceanography and climate science.