Motor Activity
Motor activity analysis, using data from wearable sensors, is increasingly employed to objectively assess various health conditions. Current research focuses on extracting meaningful features from these time series data, often using machine learning algorithms like Random Forests, LightGBM, and neural networks, to classify conditions such as food addiction, schizophrenia, and depression. These studies highlight the potential of motor activity data as a non-invasive biomarker for early diagnosis and monitoring of mental and behavioral health issues, offering valuable insights for both clinical practice and personalized healthcare. The effectiveness of these approaches is demonstrated by high classification accuracy in several studies, although further research is needed to validate these findings across diverse populations and settings.