Learning Embeddings For Wearable Based Human Activity Analysis

The embedded sensors in widely used smartphones, wearable devices and smart environments make the sensor data stream of human activity more accessible. With the development of deep neural networks, extensive studies have been conducted using deep learning methods to extract useful information from the sensor data to recognize the human activity, identify the person, or monitor the health condition of the person. However, applying deep neural networks to the sensor based human activity analysis task remains a challenging research problem in ubiquitous computing. Some of the reasons are: (i) The majority of the acquired data has no labels; (ii) Most of the previous works in activity and sensor stream analysis have been focusing on one aspect of the data, e.g. only recognizing the type of the activity or only identifying the person who performed the activity; (iii) Segmenting a continuous sensor stream and preserving the completeness of each human activity is difficult. In this dissertation, various deep learning techniques have been studied to address these problems in a weakly supervised, unsupervised, or semi-supervised manner. All the developed techniques use deep learning networks to learn embedding spaces in which activities group and thus classifiers can be trained efficiently. For this, both siamese network architectures for weakly supervised data and autoencoder-type networks for unsupervised techniques are learned and combined.

Learn How to Design and Implement HAR Systems The pervasiveness and range of capabilities of today’s mobile devices have enabled a wide spectrum of mobile applications that are transforming our daily lives, from smartphones equipped with GPS to integrated mobile sensors that acquire physiological data. Human Activity Recognition: Using Wearable Sensors and Smartphones focuses on the automatic identification of human activities from pervasive wearable sensors—a crucial component for health monitoring and also applicable to other areas, such as entertainment and tactical operations. Developed from the authors’ nearly four years of rigorous research in the field, the book covers the theory, fundamentals, and applications of human activity recognition (HAR). The authors examine how machine learning and pattern recognition tools help determine a user’s activity during a certain period of time. They propose two systems for performing HAR: Centinela, an offline server-oriented HAR system, and Vigilante, a completely mobile real-time activity recognition system. The book also provides a practical guide to the development of activity recognition applications in the Android framework.

The book reports on the author’s original work to address the use of today’s state-of-the-art smartphones for human physical activity recognition. By exploiting the sensing, computing and communication capabilities currently available in these devices, the author developed a novel smartphone-based activity-recognition system, which takes into consideration all aspects of online human activity recognition, from experimental data collection, to machine learning algorithms and hardware implementation. The book also discusses and describes solutions to some of the challenges that arose during the development of this approach, such as real-time operation, high accuracy, low battery consumption and unobtrusiveness. It clearly shows that it is possible to perform real-time recognition of activities with high accuracy using current smartphone technologies. As well as a detailed description of the methods, this book also provides readers with a comprehensive review of the fundamental concepts in human activity recognition. It also gives an accurate analysis of the most influential works in the field and discusses them in detail. This thesis was supervised by both the Universitat Politècnica de Catalunya (primary institution) and University of Genoa (secondary institution) as part of the Erasmus Mundus Joint Doctorate in Interactive and Cognitive Environments.

The average age of people has increased due to advances in health sciences, which has led to an increase in the elderly population. This is positive news, but it also raises questions about the quality of independent living for older people. Clinicians use Activities of Daily Living (ADLs) to assess older people's ability to live independently. In recent years, portable computing devices have become more present in our daily lives. Therefore, a software system that can detect ADLs based on sensor data collected from wearable devices is beneficial for detecting health problems and supporting health care. In this context, this book presents several machine learning-based approaches for human activity recognition (HAR) using time-series data collected by wearable sensors in the home environment. In the first part of the book, machine learning-based approaches for atomic activity recognition are presented, which are relatively simple and short-term activities. In the second part, the algorithms for detecting long-term and complex ADLs are presented. In this part, a two-stage recognition framework is also presented, as well as an online recognition system for continuous monitoring of HAR. In the third and final part, a novel approach is proposed that not only solves the problem of data scarcity but also improves the performance of HAR by implementing multitask learning-based methods. The proposed approach simultaneously trains the models of short- and long-term activities, regardless of their temporal scale. The results show that the proposed approach improves classification performance compared to single-task learning.

This book constitutes refereed proceedings of the Second International Workshop on Deep Learning for Human Activity Recognition, DL-HAR 2020, held in conjunction with IJCAI-PRICAI 2020, in Kyoto, Japan, in January 2021. Due to the COVID-19 pandemic the workshop was postponed to the year 2021 and held in a virtual format. The 10 presented papers were thorougly reviewed and included in the volume. They present recent research on applications of human activity recognition for various areas such as healthcare services, smart home applications, and more.

Human Activity and Behavior Analysis relates to the field of vision and sensor-based human action or activity and behavior analysis and recognition. The book includes a series of methodologies, surveys, relevant datasets, challenging applications, ideas, and future prospects. The book discusses topics such as action recognition, action understanding, gait analysis, gesture recognition, behavior analysis, emotion and affective computing, and related areas. This volume focuses on two main subject areas: Movement and Sensors, and Sports Activity Analysis. The editors are experts in these arenas, and the contributing authors are drawn from high-impact research groups around the world. This book will be of great interest to academics, students, and professionals working and researching in the field of human activity and behavior analysis.

This book provides a unique view of human activity recognition, especially fine-grained human activity structure learning, human-interaction recognition, RGB-D data based action recognition, temporal decomposition, and causality learning in unconstrained human activity videos. The techniques discussed give readers tools that provide a significant improvement over existing methodologies of video content understanding by taking advantage of activity recognition. It links multiple popular research fields in computer vision, machine learning, human-centered computing, human-computer interaction, image classification, and pattern recognition. In addition, the book includes several key chapters covering multiple emerging topics in the field. Contributed by top experts and practitioners, the chapters present key topics from different angles and blend both methodology and application, composing a solid overview of the human activity recognition techniques.

The book introduces some challenging methods and solutions to solve the human activity recognition challenge. This book highlights the challenge that will lead the researchers in academia and industry to move further related to human activity recognition and behavior analysis, concentrating on cooking challenge. Current activity recognition systems focus on recognizing either the complex label (macro-activity) or the small steps (micro-activities) but their combined recognition is critical for analysis like the challenge proposed in this book. It has 10 chapters from 13 institutes and 8 countries (Japan, USA, Switzerland, France, Slovenia, China, Bangladesh, and Columbia).

Technological advancements in healthcare can contribute unquestionably in reducing healthcare strains by ensuring clinicians, doctors and other medical staff operate and conduct their daily activities more efficiently in the hospital vicinity. Since the turn of the 21st century, Human Activity Recognition (HAR) has undergone significant research in the healthcare domain. HAR utilised with powerful technologies can benefit remote patient monitoring, the elderly, patients suffering from chronic illness and ambient assisted living. Human activity recognition has shown to be effective in benefiting clinicians in the treatment and remote monitoring of patients. This field is not only vital for diagnosis and treatment, but also an assessment of how likely a medical patient will fall ill or die from certain diseases or health problems. To show the great importance of activity recognition in the health sector, analytically driving an improvement in accuracy in classifying patients' activities improves the relationship of patients and clinicians as well as reducing the possibility of a fatality. With Artificial Intelligence at the forefront of its revolutionary capabilities, a bright future is in store if we can implement it beneficially into our healthcare service. This book reveals how.

Wearable sensors are becoming increasingly common and they permit the capture of physiological data during exercise, recuperation and everyday activities. This work investigated and advanced the current state-of-the-art in machine learning technology for the automatic classification of captured physiological data from wearable sensors. The overall goal of the work presented here is to research and investigate every aspect of the technology and methods involved in this field and to create a framework of technology that can be utilised on low-cost platforms across a wide range of activities. Both rudimentary and advanced techniques were compared, including those that allowed for both real-time processing on an android platform and highly accurate postprocessing on a desktop computer. State-of-the-art feature extraction methods such as Fourier and Wavelet analysis were also researched to ascertain how well they could extract discriminative physiological information. Various classifiers were investigated in terms of their ability to work with different feature extraction methods. Consequently, complex classification fusion models were created to increase the overall accuracy of the activity recognition process. Genetic algorithms were also employed to optimise classifier parameter selection in the multidimensional search space. Large annotated sporting activity datasets were created for a range of sports that allowed different classification models to be compared. This allowed for a machine learning framework to be constructed that could potentially create accurate models when applied to any unknown dataset. This framework was also successfully applied to medical and everyday-activity datasets confirming that the approach could be deployed in different application settings.