• Publications
  • Influence
Continuous stress detection using a wrist device: in laboratory and real life
TLDR
A method for continuous detection of stressful events using data provided from a commercial wrist device that consists of three machine-learning components: a laboratory stress detector that detects short-term stress every 2 minutes; an activity recognizer that continuously recognizes user's activity and thus provides context information; and a context-based stress detectors that exploits the output of the laboratorystress detector and the user's context in order to provide the final decision on 20 minutes interval.
Automatic Detection of Perceived Stress in Campus Students Using Smartphones
TLDR
The findings show that the perceived stress is highly subjective and that only person-specific models are substantially better than the baseline.The goal is to develop a machine-learning model that can unobtrusively detect the stress level in students using data from several smartphone sources.
How Accurately Can Your Wrist Device Recognize Daily Activities and Detect Falls?
TLDR
A thorough, large-scale evaluation of methods for activity recognition and fall detection on four datasets showed that the left wrist performs better compared to the dominant right one, and also better than the elbow and the chest, but worse than the ankle, knee and belt.
Non-Invasive Blood Pressure Estimation from ECG Using Machine Learning Techniques
TLDR
The experimental results indicate that, when a probability distribution-based calibration is used, the proposed method can achieve results close to those of a certified medical device for BP estimation.
An Inter-domain Study for Arousal Recognition from Physiological Signals
TLDR
An inter-domain study for arousal recognition on six different datasets is presented, presenting a comparison between dataset-specific models, “flat” models build on the overall data, and a novel stacking scheme, developed to utilize knowledge from all six datasets.
Applying Multiple Knowledge to Sussex-Huawei Locomotion Challenge
TLDR
The JSI-Deep team utilized an AR approach based on combining multiple machine-learning methods following the principle of multiple knowledge, which achieved 96% accuracy, which is a significant leap over the baseline 60%.
Datasets for Cognitive Load Inference Using Wearable Sensors and Psychological Traits
This study introduces two datasets for multimodal research on cognitive load inference and personality traits. Different to other datasets in Affective Computing, which disregard participants’
...
...