Search for: All records

Detecting stress from wearable sensor data enables those struggling with unhealthy stress coping mechanisms to better manage their stress. Previous studies have investigated how mechanisms for detecting stress from sensor data can be optimized, comparing alternative algorithms and approaches to find the best possible outcome. One strategy to make these mechanisms more accessible is to reduce the number of sensors that wearable devices must support. Reducing the number of sensors will enable wearable devices to be a smaller size, require less battery, and last longer, making use of these wearable devices more accessible. To progress towards this more convenient stress detection mechanism, we investigate how learning algorithms perform on singular modalities and compare the outcome with results from multiple modalities. We found that singular modalities performed comparably or better than combined modalities on two stress-detection datasets, suggesting that there is promise for detecting stress with fewer sensor requirements. From the four modalities we tested, acceleration, blood volume pulse, and electrodermal activity, we saw acceleration and electrodermal activity to stand out in a few cases, but all modalities showed potential. Our results are acquired from testing with random holdout and leave-one-subject-out validation, using several machine learning techniques. Our results can inspire work on optimizing stress detection with singular modalities to make the benefits of these detection mechanisms more convenient. 

Emotion detection using machine learning and data gathered from an electroencephalogram (EEG) holds the potential for architecture and creating smart adaptive spaces which can respond to the user's current emotional state detected from the Neurophysiological data in real-time. This technology can help people with mental and physical disabilities to have a greater role in shaping their environment and live more independent lives. In this paper, two different machine learning approaches, the Long Short Term memory network, (LSTM) and Convolutional Neural Network (CNN) are compared in order to assess their potential to satisfy this goal of emotion detection. The LSTM network was trained on eight-channel time-series data which had undergone a Fast Fourier Transform, and the CNN was trained on the un-transformed data in the form of a unique plot-image based approach.