Predicting Momentary Mood in Daily Life from Accelerometer Data: Evaluating Single vs. Multiple Sensor Locations Using Machine Learning

Physical activity is a key lifestyle factor for mental health prevention, yet the influence of accelerometer placement on mood prediction remains unclear. We merged high-resolution acceleration data and Ecological Momentary Assessment (EMA) mood reports from 259 healthy participants across three ambulatory studies (SedMood, 24 hrCog, HO). Additionally, 15 min pre-assessment movement windows consisting of raw triaxial acceleration (64 Hz) from hip, thigh, chest, and wrist sensors were paired with six-item mood EMA queries. Features (e.g., mean, entropy, spectral power) were extracted and fed into gradient-boosted decision tree models (XGBoost), trained separately for energetic arousal, valence, and calmness. Performance was measured using the metrics MAE, RMSE and R2. Within individual studies, chest and hip sensors achieved the highest performance, followed by wrist and thigh. In the combined dataset, hip sensors again outperformed thigh (R2 0.38 vs. 0.20). Multi-sensor models rarely surpassed the best single-sensor configuration and sometimes reduced accuracy. These results suggest that sensor location modestly impacts mood-prediction performance, with hip and chest offering the most reliable signals, while adding sensors does not reliably enhance predictive power. Future work should explore larger, homogenous datasets and location-specific feature engineering to refine wearable-based mental health monitoring.