This article describes an investigation to determine the optimal placement of accelerometers for the purpose of detecting a range of everyday activities. The paper investigates the effect of combining data from accelerometers placed at various bodily locations on the accuracy of activity detection. Eight healthy males participated within the study. Data were collected from six wireless tri-axial accelerometers placed at the chest, wrist, lower back, hip, thigh and foot. Activities included walking, running on a motorized treadmill, sitting, lying, standing and walking up and down stairs. The Support Vector Machine provided the most accurate detection of activities of all the machine learning algorithms investigated. Although data from all locations provided similar levels of accuracy, the hip was the best single location to record data for activity detection using a Support Vector Machine, providing small but significantly better accuracy than the other investigated locations. Increasing the number of sensing locations from one to two or more statistically increased the accuracy of classification. There was no significant difference in accuracy when using two or more sensors. It was noted, however, that the difference in activity detection using single or multiple accelerometers may be more pronounced when OPEN ACCESSSensors 2013, 13 9184 trying to detect finer grain activities. Future work shall therefore investigate the effects of accelerometer placement on a larger range of these activities.
BackgroundPhysical activity has multiple health benefits; however, the majority of children around the world do not attain the recommended levels of daily physical activity. Research has shown that the game Poké mon GO has increased the amount of physical activity of players and that the game has the potential to reach populations that traditionally have low levels of physical activity. Therefore, there is a need to understand which game components can promote initial and sustained physical activity. By using a qualitative research approach, it is possible to achieve rich descriptions and enhance a deep understanding of the components promoting physical activity among children in a game such as Poké mon GO.ObjectiveThe objective of this study was to explore children’s and parents’ experiences playing Poké mon GO.MethodsEight families comprising 13 children (aged 7-12 years) and 9 parents were selected using purposeful sampling. Data collected using focus groups were analyzed using qualitative latent content analysis.ResultsThe following three themes were revealed: (1) exciting and enjoyable exploration; (2) dangers and disadvantages; and (3) cooperation conquers competition. The first centers around the present and possible future aspects of Poké mon GO that promote physical activity. The second focuses on unwanted aspects and specific threats to safety when playing the game. The third shows that cooperation and togetherness are highly valued by the participants and that competition is fun but less important.ConclusionsComponents from Poké mon GO could enhance the efficacy of physical activity interventions. Cooperation and exploration are aspects of the game that preferably could be transferred into interventions aimed at promoting children’s physical activity.
This article brings a comprehensive tutorial on radio-frequency (RF) positioning in Bluetooth and Ultra-Wideband (UWB) Wireless Personal Area Networks (WPANs), carrying out an extensive literature review, providing the reader an overview of Bluetooth and UWB RF positioning state-of-the-art. It also delves into some key issues, such as multilateration (MLAT) based solutions using received signal strength and time-of-arrival, multi-slope linear regression, RF fingerprinting and the use of clustering techniques to improve its localization accuracy, the interrelation between Bluetooth versions improvements and new positioning capabilities, as well as localization prospects in future UWB networks.
Data annotation is a time-consuming process posing major limitations to the development of Human Activity Recognition (HAR) systems. The availability of a large amount of labeled data is required for supervised Machine Learning (ML) approaches, especially in the case of online and personalized approaches requiring user specific datasets to be labeled. The availability of such datasets has the potential to help address common problems of smartphone-based HAR, such as inter-person variability. In this work, we present (i) an automatic labeling method facilitating the collection of labeled datasets in free-living conditions using the smartphone, and (ii) we investigate the robustness of common supervised classification approaches under instances of noisy data. We evaluated the results with a dataset consisting of 38 days of manually labeled data collected in free living. The comparison between the manually and the automatically labeled ground truth demonstrated that it was possible to obtain labels automatically with an 80–85% average precision rate. Results obtained also show how a supervised approach trained using automatically generated labels achieved an 84% f-score (using Neural Networks and Random Forests); however, results also demonstrated how the presence of label noise could lower the f-score up to 64–74% depending on the classification approach (Nearest Centroid and Multi-Class Support Vector Machine).
Usually, approaches driven by data proposed in literature for sensor-based activity recognition use the begin label and the end label of each activity in the dataset, fixing a temporal window with sensor data events to identify the activity carried out in this window. This type of approach cannot be carried out in real time because it is not possible to predict the start time of an activity, i.e., the class of the future activity that an inhabitant will perform, neither when he/she will begin to carry out this activity. However, an activity can be marked as finished in real time only with the previous observations. Therefore, there is a need of online activity recognition approaches that classify activities using only the end label of the activity. In this paper, we propose and evaluate a new approach for online activity recognition with three temporal sub-windows that uses only the end label of the activity. The advantage of our approach is that the temporal sub-windows keep a partial order in the sensor data stream from the end time of the activity in a short-term, medium-term, long-term. The experiments conducted to evaluate our approach suggest the importance of the use of temporal sub-windows versus a single temporal window in terms of accuracy, using only the end time of the activity. The use of temporal sub-windows has improved the accuracy in the 98.95% of experiments carried out.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.