22 September 2023 in Biomedical Signal Processing and Control
19 July 2023 in International Journal of Medical Informatics
12 May 2025 in Research Square
Mental fatigue impairs cognitive performance and productivity, posing risks in domains such as healthcare, education, and workplace safety. There is a growing need for objective, accessible tools to detect fatigue in real time. Leveraging the widespread availability and sensing capabilities of smartphones, this study presents a cross-platform system (iOS and Android) that detects mental fatigue using fine motor skill tests and a self-report questionnaire. Data were collected from 347 sessions across 166 smartphones, where participants completed tasks before and after cognitively demanding activities. From the raw motion and touch data, 60 features were engineered. Feature selection was performed using a wrapper-based method, and six machine learning algorithms were evaluated: Logistic Regression, Support Vector Machine, K-Nearest Neighbors, Decision Tree, Random Forest, and AdaBoost. Models were validated using a nested k-fold cross-validation strategy. The best-performing model achieved a sensitivity of 0.86 by combining self-reported fatigue indicators (e.g., anxiety and effort levels) with microkinematic features related to handwriting and hand tremor. This multi-dimensional approach demonstrates the feasibility of using smartphone-based motion analysis for fatigue classification. The system offers potential applications in remote health monitoring, educational assessment, and occupational safety. Additionally, the publicly available dataset provides a valuable resource for further research on cognitive and motor function assessment using mobile devices.
27 October 2025 in Cognition, Technology & Work
25 September 2023 in arXiv
Subject: In this article, convolutional networks of one, two, and three dimensions are compared with respect to their ability to distinguish between the drawing tests produced by Parkinson's disease patients and healthy control subjects. Motivation: The application of deep learning techniques for the analysis of drawing tests to support the diagnosis of Parkinson's disease has become a growing trend in the area of Artificial Intelligence. Method: The dynamic features of the handwriting signal are embedded in the static test data to generate one-dimensional time series, two-dimensional RGB images and three-dimensional voxelized point clouds, and then one-, two-, and three-dimensional CNN can be used to automatically extract features for effective diagnosis. Novelty: While there are many results that describe the application of two-dimensional convolutional models to the problem, to the best knowledge of the authors, there are no results based on the application of three-dimensional models and very few using one-dimensional models. Main result: The accuracy of the one-, two- and three-dimensional CNN models was 62.50%, 77.78% and 83.34% in the DraWritePD dataset (acquired by the authors) and 73.33%, 80.00% and 86.67% in the PaHaW dataset (well known from the literature), respectively. For these two data sets, the proposed three-dimensional convolutional classification method exhibits the best diagnostic performance.