Machine Learning-Driven Color Sensing with SENSIPATCH spectrometer module: A Multi-Wavelength LED Sensor System

ABSTRACT Accurate color classification plays a critical role across diverse fields, from textile man- ufacturing and environmental monitoring to biomedical diagnostics. This study introduces a machine learning-driven approach to spectral color sensing using SENSIPATCH, a compact, wearable sensor system. While SENSIPATCH integrates multiple sensing modalities, including bioimpedance, electrochemical, thermal, humidity, and vibrational sensors, this work specifically utilizes its spectrometer module, which comprises multi-wavelength LEDs and photodiodes. Targeting the classification of 100 standardized PANTONE colors, the proposed framework includes an experimental design simulating real-world wearable usage through both firm and loose contact scenarios. A structured data preprocessing pipeline involving baseline correction, bootstrapping, and Z-score normalization was employed to enhance signal quality and model generalization. Five machine learning models were evaluated: Random Forest, SVM, MLP, CNN, and LSTM, with the MLP demonstrating the strongest classification performance. Notably, the MLP achieved consistent accuracy across both contact conditions, indicating robust generalization under variable sensor placement. These results suggest that compact LED-based wearable spectroscopy, combined with appropriate machine learning techniques, offers a scalable and practical approach to colorimetric sensing. INDEX TERMS Machine Learning, Spectroscopy, Sensors, LED, Wearable, Colors, PANTONE, Color Sensing, Classification