Introduction: Wearable technologies play an important contemporary role in the measurement of physical activity (PA) and promotion of human health across the lifespan, including for young people (i.e., children, adolescents, and young adults). As new objective wearable technologies continue to develop, standardized approaches to documenting validation parameters (i.e., measures of accuracy, precision, and bias) are needed to ensure confidence and comparability in step-defined PA. Purpose: To produce validity parameters for step counting wearable technologies during treadmill walking in young people 6-20 years of age Methods: 120 participants completed 5-minute treadmill bouts from13.4 to 134.1 m·min-1. Participants wore eight technologies (two at the arm/wrist, four at the waist, one on the thigh, and one on the ankle) while steps were directly observed. Speed, wear location, and age -specific measures of accuracy (mean absolute percent error; MAPE), precision (correlation coefficient, standard deviation; SD, coefficient of variation; CoV), and bias (percent error; PE) were computed and cataloged. Results: Speed and wear location had a significant effect on accuracy and bias measures for wearable technologies (pConclusion: While the analyses indicate the significance of speed and wear location on wearable technology performance, the useful and comprehensive validity reference values cataloged herein will help optimize measurement of PA in youth. Future research should continue to rigorously validate new wearable technologies as they are developed, and also extend these standardized reference values developed in the laboratory to the free-living environment.

I dagens samhälle har aktivitetsmätare blivit allt vanligare för att logga vår fysiska hälsa. Detta är något som även skulle kunna gynna och användas i sjukvårdssammanhang. Problemet är att dagens kommersiella aktivitetsmätare sparar personlig information och privat data på sina egna servar. Syftet med denna avhandling är därför att påbörja ett projekt där all mjukvara är open-source och där tillförlitlighet, noggrannhet och integritet är drivande attribut. En stegräknaralgoritm implementeras för smartklockor som ska kunna användas inom vården. Utvecklingen av algoritmen bygger på en existerande stegräknaralgoritm för smartphones som har skrivits om och optimerats för inbyggda system, så som aktivitetsmätare. Mjukvaran är konstruerad med ett realtidsoperativsystem där algoritmen är integrerad. För att testa algoritmen har 10 deltagare genomfört ett antal tester, både på löpband men också utomhus på varierat underlag. Den slutliga noggrannheten resulterade i en median på 92% och skulle kunna förbättras genom att vidareutveckla optimeringen med hjälp av större datamängder. Källkoden är tillgänglig för allmänheten på GitHub. / In today’s society, it is quite common to track your own health with the use of a wearable device. These devices track physical activity and physiological signals. This is a concept that could be used in healthcare-applications as well. The main issue with this lies in the fact that commercially available devices send personal data to their own servers. The goal of this thesis is therefore to set in motion a project to build an entirely open-source firmware for smart watches for use in healthcare, where reliability, accuracy and privacy are driving quality attributes. This thesis covers a step counting algorithm in addition to the firmware for the watch. To speed up the process of developing the algorithm, an existing algorithm for smartphones is used as a starting point. This algorithm is rewritten, optimized for wearable devices and tested with an existing dataset. The firmware is built with an existing RTOS implementation and the algorithm is integrated into it. To test the firmware, 10 participants conducted several test scenarios, both on a treadmill and on mixed terrain. The results of this were a median accuracy of 92% and could be improved further with more optimizations with a larger dataset. The source code is publicly available on GitHub.

Fitness tracking is a rapidly growing market as more people desire to take better control over their lives. And the growing availability of smartphones with sensitive sensors makes it possible for anyone to take part. This project aims to implement a Step Counter and create a model for Human Activity Recognition (HAR) to classify activities such as walking, running, cycling, ascending and descending stairs, and standing still, using sensor data from handheld devices. The Step Counter is implemented by processing acceleration data and finding and validating steps. HAR is implemented using three machine learning algorithms on processed sensor data: Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN). The step counter achieved 99.48% accuracy. The HAR models achieved 99.7%, 99.6%, and 99.5% accuracy on RF, ANN, and SVM, respectively. / Aktivitetsspårning är en snabbt växande marknad när fler människor önskar att ta bättre kontroll över deras liv. Den växande tillgängligheten på smartphones med känsliga sensorer gör det möjligt för vem som helst att delta. Detta projekt siktar på att implementera en stegräknare samt skapa en modell för mänsklig aktivitetsigenkänning (HAR) för att klassificera aktiviteter såsom att promenera, springa, cykla, gå upp eller ner för trappor och stå stilla, med användning av sensordata från handhållna enheter. Stegräknaren implementeras genom att bearbeta accelerationsdata och hitta samt validera steg. HAR implementeras med hjälp av tre maskininlärningsalgoritmer på bearbetad sensordata: Random Forest (RF), Support Vector Machine (SVM) och Artificial Neural Network (ANN). Stegräknaren uppnådde en noggrannhet på 99.48%. HAR-modellerna uppnådde en noggrannhet på 99.7%, 99.6% samt 99.5% med RF, ANN och SVM. / Kandidatexjobb i elektroteknik 2022, KTH, Stockholm

Physical activity plays a crucial role in maintaining overall health and reducing the risk of various chronic diseases. Step counting has emerged as a popular method for assessing physical activity levels, given its simplicity and ease of use. However, accurately measuring step counts in free-living environments presents significant challenges, with most activity trackers exhibiting a percent error above 20%. This study aims to address these challenges by creating a machine learning algorithm that leverages activity labels to improve step count accuracy in real-world conditions. Two approaches to balancing data were used: one employed a simpler oversampling technique, while the other adopted a more nuanced approach involving the removal of outliers. Models 1 and 2 were trained on each of these uniquely balanced datasets. Model 1 performed much better than Model 2 on testing datasets, but both achieved better than 20% error on new datasets, indicating their potential for more accurate step counting in real-world conditions. Despite challenges such as data imbalance, the study demonstrated the viability of using activity labels to enhance step counting accuracy. Future research should focus on addressing data imbalances and exploring more advanced machine learning techniques for more reliable activity monitoring.