A Wearable System for Real-Time Continuous Monitoring of Physical Activity

Over the last decades, wearable systems have gained interest for monitoring of physiological variables, promoting health, and improving exercise adherence in different populations ranging from elite athletes to patients. In this paper, we present a wearable system for the continuous real-time monitoring of respiratory frequency (fR), heart rate (HR), and movement cadence during physical activity. The system has been experimentally tested in the laboratory (by simulating the breathing pattern with a mechanical ventilator) and by collecting data from one healthy volunteer. Results show the feasibility of the proposed device for real-time continuous monitoring of fR, HR, and movement cadence both in resting condition and during activity. Finally, different synchronization techniques have been investigated to enable simultaneous data collection from different wearable modules.

Download Full-text

Optimization of Physical Activity Recognition for Real-Time Wearable Systems: Effect of Window Length, Sampling Frequency and Number of Features

Applied Sciences ◽

10.3390/app9224833 ◽

2019 ◽

Vol 9 (22) ◽

pp. 4833 ◽

Cited By ~ 3

Author(s):

Ardo Allik ◽

Kristjan Pilt ◽

Deniss Karai ◽

Ivo Fridolin ◽

Mairo Leier ◽

...

Keyword(s):

Physical Activity ◽

Feature Selection ◽

Real Time ◽

Sampling Frequency ◽

Classification Performance ◽

Window Length ◽

Decision Tree Classifier ◽

Acceleration Signal ◽

Wearable Systems ◽

Tree Classifier

The aim of this study was to develop an optimized physical activity classifier for real-time wearable systems with the focus on reducing the requirements on device power consumption and memory buffer. Classification parameters evaluated in this study were the sampling frequency of the acceleration signal, window length of the classification fragment, and the number of classification features, found with different feature selection methods. For parameter evaluation, a decision tree classifier was created based on the acceleration signals recorded during tests, where 25 healthy test subjects performed various physical activities. Overall average F1-score achieved in this study was about 0.90. Similar F1-scores were achieved with the evaluated window lengths of 5 s (0.92 ± 0.02) and 3 s (0.91 ± 0.02), while classification performance with 1 s were lower (0.87 ± 0.02). Tested sampling frequencies of 50 Hz, 25 Hz, and 13 Hz had similar results with most classified activity types, with an exception of outdoor cycling, where differences were significant. Using forward sequential feature selection enabled the decreasing of the number of features from initial 110 features to about 12 features without lowering the classification performance. The results of this study have been used for developing more efficient real-time physical activity classifiers.

Download Full-text

Wearable physiological sensors and real-time algorithms for detection of acute mountain sickness

Journal of Applied Physiology ◽

10.1152/japplphysiol.00367.2017 ◽

2018 ◽

Vol 124 (3) ◽

pp. 557-563 ◽

Cited By ~ 4

Author(s):

Stephen R. Muza

Keyword(s):

Real Time ◽

Mixed Models ◽

Acute Mountain Sickness ◽

Detection Algorithms ◽

Physiological Variables ◽

Wearable Systems ◽

Embedded Algorithms ◽

Mountain Sickness ◽

Near Term ◽

Physiological Sensors

This is a minireview of potential wearable physiological sensors and algorithms (process and equations) for detection of acute mountain sickness (AMS). Given the emerging status of this effort, the focus of the review is on the current clinical assessment of AMS, known risk factors (environmental, demographic, and physiological), and current understanding of AMS pathophysiology. Studies that have examined a range of physiological variables to develop AMS prediction and/or detection algorithms are reviewed to provide insight and potential technological roadmaps for future development of real-time physiological sensors and algorithms to detect AMS. Given the lack of signs and nonspecific symptoms associated with AMS, development of wearable physiological sensors and embedded algorithms to predict in the near term or detect established AMS will be challenging. Prior work using [Formula: see text], HR, or HRv has not provided the sensitivity and specificity for useful application to predict or detect AMS. Rather than using spot checks as most prior studies have, wearable systems that continuously measure SpO2 and HR are commercially available. Employing other statistical modeling approaches such as general linear and logistic mixed models or time series analysis to these continuously measured variables is the most promising approach for developing algorithms that are sensitive and specific for physiological prediction or detection of AMS.

Download Full-text

IOT Based Wireless Safety System for Monitoring the Physiological and Environmental Variables of Mine Workers.

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.b3762.078219 ◽

2019 ◽

Vol 8 (2) ◽

pp. 5612-5615

Keyword(s):

Real Time ◽

Data Security ◽

Continuous Monitoring ◽

Respiratory Activity ◽

Fall Detection ◽

Time Data ◽

Physiological Variables ◽

Wireless Communication Network ◽

Link Module ◽

Extreme Environmental Condition

The coal mining is essential as well as a risky venture. The miners working here need to handle the extreme environmental condition and the physiological hazardous without specialized examination. A continuous monitoring of the environmental change and the physiological variables is needed in order to enhance the condition for people and the equipment. A Continuous monitoring of the environmental gases and the physiological variables is the major challenge and need to be followed for safety of workers working in mine. This paper present the design and the implementation of real time monitoring device to measure the physiological variables and the gases present in the mining. The proposed system consists of physiological variables, ECG signal, respiratory activity, body temperature, fall detection and also the environmental gases. The sensors will be embedded throughout the T-shirt to measure the variables. The device will monitor the real time data and wireless communication network will be provided by using Wi-Fi link module. By using IOT it is easy to upload the data on the web server and it also provides data security.

Download Full-text

A Multimodal Wearable System for Continuous and Real-Time Breathing Pattern Monitoring During Daily Activity

IEEE Journal of Biomedical and Health Informatics ◽

10.1109/jbhi.2019.2963048 ◽

2020 ◽

Vol 24 (8) ◽

pp. 2199-2207 ◽

Cited By ~ 3

Author(s):

Wen Qi ◽

Andrea Aliverti

Keyword(s):

Real Time ◽

Daily Activity ◽

Breathing Pattern ◽

Wearable System

Download Full-text

Ambulatory Activity Monitoring

European Psychologist ◽

10.1027/1016-9040.14.2.142 ◽

2009 ◽

Vol 14 (2) ◽

pp. 142-152 ◽

Cited By ~ 54

Author(s):

Johannes B.J. Bussmann ◽

Ulrich W. Ebner-Priemer ◽

Jochen Fahrenberg

Keyword(s):

Physical Activity ◽

Activity Monitoring ◽

Main Stream ◽

Computer Algorithms ◽

Ambulatory Activity ◽

Physiological Variables ◽

Piezoresistive Sensors ◽

Self Reports ◽

Recent Developments ◽

Objectively Measured

Behavior is central to psychology in almost any definition. Although observable activity is a core aspect of behavior, assessment strategies have tended to focus on emotional, cognitive, or physiological responses. When physical activity is assessed, it is done so mostly with questionnaires. Converging evidence of only a moderate association between self-reports of physical activity and objectively measured physical activity does raise questions about the validity of these self-reports. Ambulatory activity monitoring, defined as the measurement strategy to assess physical activity, posture, and movement patterns continuously in everyday life, has made major advances over the last decade and has considerable potential for further application in the assessment of observable activity, a core aspect of behavior. With new piezoresistive sensors and advanced computer algorithms, the objective measurement of physical activity, posture, and movement is much more easily achieved and measurement precision has improved tremendously. With this overview, we introduce to the reader some recent developments in ambulatory activity monitoring. We will elucidate the discrepancies between objective and subjective reports of activity, outline recent methodological developments, and offer the reader a framework for developing insight into the state of the art in ambulatory activity-monitoring technology, discuss methodological aspects of time-based design and psychometric properties, and demonstrate recent applications. Although not yet main stream, ambulatory activity monitoring – especially in combination with the simultaneous assessment of emotions, mood, or physiological variables – provides a comprehensive methodology for psychology because of its suitability for explaining behavior in context.

Download Full-text

Structural Relationship between College Level General Physical Activity Classes Fun Factors, Exercise Flow and Exercise Adherence

Korean Journal of Sports Science ◽

10.35159/kjss.2019.06.28.3.497 ◽

2019 ◽

Vol 28 (3) ◽

pp. 497-509

Author(s):

Tae-Woon Kim

Keyword(s):

Physical Activity ◽

Exercise Adherence ◽

Structural Relationship ◽

College Level ◽

General Physical ◽

Physical Activity Classes

Download Full-text

Real-time Judgment of Workload using Heart Rate and Physical Activity

Proceedings of the 37th International Symposium on Automation and Robotics in Construction (ISARC) ◽

10.22260/isarc2020/0117 ◽

2020 ◽

Author(s):

Nobuki Hashiguchi ◽

Lim Yeongjoo ◽

Cyo Sya ◽

Shinichi Kuroishi ◽

Yasuhiro Miyazaki ◽

...

Keyword(s):

Physical Activity ◽

Heart Rate ◽

Real Time ◽

Time Judgment

Download Full-text

Internet of things-based smart wearable system to monitor sports person health

Technology and Health Care ◽

10.3233/thc-213004 ◽

2021 ◽

pp. 1-14

Author(s):

Fen Li ◽

Oscar Sanjuán Martínez ◽

R.S. Aiswarya

Keyword(s):

Internet Of Things ◽

Experimental Result ◽

Wearable System ◽

Wearable Systems ◽

Trading Decisions ◽

Time Basis ◽

And Performance ◽

Individual Sports ◽

Smart Wearable ◽

The Internet Of Things

BACKGROUND: The modern Internet of Things (IoT) makes small devices that can sense, process, interact, connect devices, and other sensors ready to understand the environment. IoT technologies and intelligent health apps have multiplied. The main challenges in the sports environment are playing without injuries and healthily. OBJECTIVE: In this paper the Internet of Things-based Smart Wearable System (IoT-SWS) is introduced for monitoring sports person activity to improve sports person health and performance in a healthy way. METHOD: Wearable systems are commonly used to capture individual sports details on a real-time basis. Collecting data from wearable devices and IoT technologies can help organizations learn how to optimize in-game strategies, identify opponents’ vulnerabilities, and make smarter draft choices and trading decisions for a sportsperson. RESULTS: The experimental result shows that IoT-SWS achieve the highest accuracy of 98.22% and efficient in predicting the sports person’s health to improve sports person performance reliably.

Download Full-text

A Systematic Review of Sensing Technologies for Wearable Sleep Staging

Sensors ◽

10.3390/s21051562 ◽

2021 ◽

Vol 21 (5) ◽

pp. 1562

Author(s):

Syed Anas Imtiaz

Keyword(s):

Systematic Review ◽

Classification Accuracy ◽

Sleep Stages ◽

Sleep Staging ◽

Regulatory Requirements ◽

Wearable System ◽

Wearable Systems

Designing wearable systems for sleep detection and staging is extremely challenging due to the numerous constraints associated with sensing, usability, accuracy, and regulatory requirements. Several researchers have explored the use of signals from a subset of sensors that are used in polysomnography (PSG), whereas others have demonstrated the feasibility of using alternative sensing modalities. In this paper, a systematic review of the different sensing modalities that have been used for wearable sleep staging is presented. Based on a review of 90 papers, 13 different sensing modalities are identified. Each sensing modality is explored to identify signals that can be obtained from it, the sleep stages that can be reliably identified, the classification accuracy of systems and methods using the sensing modality, as well as the usability constraints of the sensor in a wearable system. It concludes that the two most common sensing modalities in use are those based on electroencephalography (EEG) and photoplethysmography (PPG). EEG-based systems are the most accurate, with EEG being the only sensing modality capable of identifying all the stages of sleep. PPG-based systems are much simpler to use and better suited for wearable monitoring but are unable to identify all the sleep stages.

Download Full-text