Contact with Mental Health Consumers in an Educational Setting: Sustainability and the Medium of Contact

O’Reilly, Claire F.; Bell, Janet; Nguyen, Elizabeth; Chen, Timothy

doi:10.1037/e506852013-112

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, we found that most data sets in the field of mobile HAR, such as the one provided by Anguita et al [13] only cover activities of daily living and not fitness activities. Other data sets such as the BasicMotions data set [14] and the CounterMovementJump data set [15] feature relatively few activities and only a single body-worn sensor. Furthermore, many public HAR data sets already consist of statistical features such as mean, minimum, and maximum values across a recording and, therefore, are not suitable for the CNN approaches evaluated in this study.…”

Section: Data Acquisitionmentioning

confidence: 99%

IMU-Based Fitness Activity Recognition Using CNNs for Time Series Classification

Müller,

Achenbach

et al. 2023

Preprint

View full text Add to dashboard Cite

Augmented reality (AR) provides an opportunity for mobile fitness applications to show users real-time feedback on their current fitness activity. For such applications, it is essential to accurately track the user’s current fitness activity using available mobile sensors, such as inertial measurement units (IMUs). Convolutional neural networks (CNNs) have been shown to produce strong results in different time series classification tasks, including the recognition of activities of daily living. However, fitness activities can present unique challenges to the human activity recognition task (HAR), including greater similarity between individual activities and fewer available data for model training. In this paper, we evaluate the applicability of CNNs to the fitness activity recognition task (FAR) using IMU data and determine the impact of input data size and sensor count on performance. For this purpose, we adapted three existing CNN architectures to the FAR task and designed a fourth CNN variant, which we call the scaling fully convolutional network (Scaling-FCN). We designed a preprocessing pipeline and recorded a running exercise data set with 20 participants, in which we evaluated the respective recognition performances of the four networks, comparing them with three traditional machine learning methods commonly used in HAR. On our data set, all CNN architectures significantly outperformed traditional machine learning methods, reaching up to 97.14±1.36% classification accuracy on the test set for ResNet. Whereas a reduced input data size invariably led to a performance loss, removing specific sensors improved the performance of all CNN architectures, with our Scaling-FCN reaching the highest accuracy of 99.86±0.11%. Our results suggest that CNNs are generally well suited for fitness activity recognition, and noticeable performance improvements can be achieved if sensors are dropped selectively.

show abstract

Section: Data Acquisitionmentioning

confidence: 99%