Farrahi, V., Muhammad, U., Rostami, M., & Oussalah, M. (2023). AccNet24: A deep learning framework for classifying 24-hour activity behaviours from wrist-worn accelerometer data under free-living environments. In International Journal of Medical Informatics (Vol. 172, p. 105004). Elsevier BV. https://doi.org/10.1016/j.ijmedinf.2023.105004
AccNet24 : a deep learning framework for classifying 24-hour activity behaviours from wrist-worn accelerometer data under free-living environments
|Author:||Farrahi, Vahid1,2; Muhammad, Usman2; Rostami, Mehrdad2;|
1Research Unit of Health Sciences and Technology, Faculty of Medicine, University of Oulu, Oulu, Finland
2Center of Machine Vision and Signal Analysis, Faculty of Information Technology and Electrical Engineering, University of Oulu, Oulu, Finland
|Online Access:||PDF Full Text (PDF, 3.7 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe20230915127390
|Publish Date:|| 2023-09-15
Objective: Although machine learning techniques have been repeatedly used for activity prediction from wearable devices, accurate classification of 24-hour activity behaviour categories from accelerometry data remains a challenge. We developed and validated a deep learning-based framework for classifying 24-hour activity behaviours from wrist-worn accelerometers.
Methods: Using an openly available dataset with free-living wrist-based raw accelerometry data from 151 participants (aged 18–91 years), we developed a deep learning framework named AccNet24 to classify 24-hour activity behaviours. First, the acceleration signal (x, y, and z-axes) was segmented into 30-second nonoverlapping windows, and signal-to-image conversion was performed for each segment. Deep features were automatically extracted from the signal images using transfer learning and transformed into a lower-dimensional feature space. These transformed features were then employed to classify the activity behaviours as sleep, sedentary behaviour, and light-intensity (LPA) and moderate-to-vigorous physical activity (MVPA) using a bidirectional long short-term memory (BiLSTM) recurrent neural network. AccNet24 was trained and validated with data from 101 and 25 randomly selected participants and tested with the remaining unseen 25 participants. We also extracted 112 hand-crafted time and frequency domain features from 30-second windows and used them as inputs to five commonly used machine learning classifiers, including random forest, support vector machines, artificial neural networks, decision tree, and naïve Bayes to classify the 24-hour activity behaviour categories.
Results: Using the same training, validation, and test data and window size, the classification accuracy of AccNet24 outperformed the accuracy of the other five machine learning classification algorithms by 16%–30% on unseen data.
Conclusion: AccNet24, relying on signal-to-image conversion, deep feature extraction, and BiLSTM achieved consistently high accuracy (>95 %) in classifying the 24-hour activity behaviour categories as sleep, sedentary, LPA, and MVPA. The next generation accelerometry analytics may rely on deep learning techniques for activity prediction.
International journal of medical informatics
|Type of Publication:||
A1 Journal article – refereed
|Field of Science:||
217 Medical engineering
113 Computer and information sciences
The present study is connected to the DigiHealth-project, a strategic profiling project at the University of Oulu. The project is supported by the Academy of Finland (project number 326291) and the University of Oulu. This study has also received funding from the Ministry of Education and Culture in Finland [grant number OKM/20/626/2022]. The funders played no role in designing the study, or collecting, analyzing, and interpreting the data, or writing the manuscript.
© 2023 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).