This book explains the complete loop to effectively use self-tracking data for machine learning. While it focuses on self-tracking data, the techniques explained are also applicable to sensory data in general, making it useful for a wider audience. Discussing concepts drawn from from state-of-the-art scientific literature, it illustrates the approaches using a case study of a rich self-tracking data set. Self-tracking has become part of the modern lifestyle, and the amount of data generated by these devices is so overwhelming that it is difficult to obtain useful insights from it. Luckily, in the domain of artificial intelligence there are techniques that can help out: machine-learning approaches allow this type of data to be analyzed. While there are ample books that explain machine-learning techniques, self-tracking data comes with its own difficulties that require dedicated techniques such as learning over time and across users.

What happens when people turn their everyday experience into data: an introduction to the essential ideas and key challenges of self-tracking. People keep track. In the eighteenth century, Benjamin Franklin kept charts of time spent and virtues lived up to. Today, people use technology to self-track: hours slept, steps taken, calories consumed, medications administered. Ninety million wearable sensors were shipped in 2014 to help us gather data about our lives. This book examines how people record, analyze, and reflect on this data, looking at the tools they use and the communities they become part of. Gina Neff and Dawn Nafus describe what happens when people turn their everyday experience—in particular, health and wellness-related experience—into data, and offer an introduction to the essential ideas and key challenges of using these technologies. They consider self-tracking as a social and cultural phenomenon, describing not only the use of data as a kind of mirror of the self but also how this enables people to connect to, and learn from, others. Neff and Nafus consider what's at stake: who wants our data and why; the practices of serious self-tracking enthusiasts; the design of commercial self-tracking technology; and how self-tracking can fill gaps in the healthcare system. Today, no one can lead an entirely untracked life. Neff and Nafus show us how to use data in a way that empowers and educates.

With the advent of digital devices and software, self-tracking practices have gained new adherents and have spread into a wide array of social domains. The Quantified Self movement has emerged to promote 'self-knowledge through numbers'. In this groundbreaking book Deborah Lupton critically analyses the social, cultural and political dimensions of contemporary self-tracking and identifies the concepts of selfhood and human embodiment and the value of the data that underpin them. The book incorporates discussion of the consolations and frustrations of self-tracking, as well as about the proliferating ways in which people's personal data are now used beyond their private rationales. Lupton outlines how the information that is generated through self-tracking is taken up and repurposed for commercial, governmental, managerial and research purposes. In the relationship between personal data practices and big data politics, the implications of self-tracking are becoming ever more crucial.

Humans are accustomed to being tool bearers, but what happens when machines become tool bearers, calculating human labour via the use of big data and people analytics by metrics? The Quantified Self in Precarity highlights how, whether it be in insecure ‘gig’ work or office work, such digitalisation is not an inevitable process – nor is it one that necessarily improves working conditions. Indeed, through unique research and empirical data, Moore demonstrates how workplace quantification leads to high turnover rates, workplace rationalisation and worker stress and anxiety, with these issues linked to increased rates of subjective and objective precarity. Scientific management asked us to be efficient. Now, we are asked to be agile. But what does this mean for the everyday lives we lead? With a fresh perspective on how technology and the use of technology for management and self-management changes the ‘quantified’, precarious workplace today, The Quantified Self in Precarity will appeal to undergraduate and postgraduate students interested in fields such as Science and Technology, Organisation Management, Sociology and Politics.

An inquiry into what we can know in an age of surveillance and algorithms Knitting together contemporary technologies of datafication to reveal a broader, underlying shift in what counts as knowledge, Technologies of Speculation reframes today’s major moral and political controversies around algorithms and artificial intelligence. How many times we toss and turn in our sleep, our voluminous social media activity and location data, our average resting heart rate and body temperature: new technologies of state and self-surveillance promise to re-enlighten the black boxes of our bodies and minds. But Sun-ha Hong suggests that the burden to know and to digest this information at alarming rates is stripping away the liberal subject that ‘knows for themselves’, and risks undermining the pursuit of a rational public. What we choose to track, and what kind of data is extracted from us, shapes a society in which my own experience and sensation is increasingly overruled by data-driven systems. From the rapidly growing Quantified Self community to large-scale dragnet data collection in the name of counter-terrorism and drone warfare, Hong argues that data’s promise of objective truth results in new cultures of speculation. In his analysis of the Snowden affair, Hong demonstrates an entirely new way of thinking through what we could know, and the political and philosophical stakes of the belief that data equates to knowledge. When we simply cannot process all the data at our fingertips, he argues, we look past the inconvenient and the complicated to favor the comprehensible. In the process, racial stereotypes and other longstanding prejudices re-enter our newest technologies by the back door. Hong reveals the moral and philosophical equations embedded into the algorithmic eye that now follows us all.

Focuses on mathematical understanding Presentation is self-contained, accessible, and comprehensive Full color throughout Extensive list of exercises and worked-out examples Many concrete algorithms with actual code

Machine Learning for Subsurface Characterization develops and applies neural networks, random forests, deep learning, unsupervised learning, Bayesian frameworks, and clustering methods for subsurface characterization. Machine learning (ML) focusses on developing computational methods/algorithms that learn to recognize patterns and quantify functional relationships by processing large data sets, also referred to as the "big data." Deep learning (DL) is a subset of machine learning that processes "big data" to construct numerous layers of abstraction to accomplish the learning task. DL methods do not require the manual step of extracting/engineering features; however, it requires us to provide large amounts of data along with high-performance computing to obtain reliable results in a timely manner. This reference helps the engineers, geophysicists, and geoscientists get familiar with data science and analytics terminology relevant to subsurface characterization and demonstrates the use of data-driven methods for outlier detection, geomechanical/electromagnetic characterization, image analysis, fluid saturation estimation, and pore-scale characterization in the subsurface. - Learn from 13 practical case studies using field, laboratory, and simulation data - Become knowledgeable with data science and analytics terminology relevant to subsurface characterization - Learn frameworks, concepts, and methods important for the engineer's and geoscientist's toolbox needed to support

Introduction to Data Science: Data Analysis and Prediction Algorithms with R introduces concepts and skills that can help you tackle real-world data analysis challenges. It covers concepts from probability, statistical inference, linear regression, and machine learning. It also helps you develop skills such as R programming, data wrangling, data visualization, predictive algorithm building, file organization with UNIX/Linux shell, version control with Git and GitHub, and reproducible document preparation. This book is a textbook for a first course in data science. No previous knowledge of R is necessary, although some experience with programming may be helpful. The book is divided into six parts: R, data visualization, statistics with R, data wrangling, machine learning, and productivity tools. Each part has several chapters meant to be presented as one lecture. The author uses motivating case studies that realistically mimic a data scientist’s experience. He starts by asking specific questions and answers these through data analysis so concepts are learned as a means to answering the questions. Examples of the case studies included are: US murder rates by state, self-reported student heights, trends in world health and economics, the impact of vaccines on infectious disease rates, the financial crisis of 2007-2008, election forecasting, building a baseball team, image processing of hand-written digits, and movie recommendation systems. The statistical concepts used to answer the case study questions are only briefly introduced, so complementing with a probability and statistics textbook is highly recommended for in-depth understanding of these concepts. If you read and understand the chapters and complete the exercises, you will be prepared to learn the more advanced concepts and skills needed to become an expert.

The following anthology delivers sound analysis to the theoretical classification of the current societal phenomenon - between innovative, world changing and yet disruptive technology, as well as societal and cultural transformation. Lifelogging, digital self-tracking and the real-time chronicling of man’s lifetime, is not only a relevant societal topic in the world of research and academic science these days, but can also be found in literature, cultural pages of the written press and the theatre. The spectrum of Lifelogging ranges from sleep, mood, sex and work logging to Thing and Deathlogging. This leads to several questions: How does one live in a data society? Is “measured” man automatically also “better” man? And if so, what is the cost? Do new categories of reality or principles of social classification develop as a result of Lifelogging? How does the “social view” on things change? The authors in this anthology provide insightful answers to these pressing questions.

This open access book presents the first comprehensive overview of general methods in Automated Machine Learning (AutoML), collects descriptions of existing systems based on these methods, and discusses the first series of international challenges of AutoML systems. The recent success of commercial ML applications and the rapid growth of the field has created a high demand for off-the-shelf ML methods that can be used easily and without expert knowledge. However, many of the recent machine learning successes crucially rely on human experts, who manually select appropriate ML architectures (deep learning architectures or more traditional ML workflows) and their hyperparameters. To overcome this problem, the field of AutoML targets a progressive automation of machine learning, based on principles from optimization and machine learning itself. This book serves as a point of entry into this quickly-developing field for researchers and advanced students alike, as well as providing a reference for practitioners aiming to use AutoML in their work.