Search

Stress has become a major health concern and there is a need to study and develop new digital means for real-time stress detection. Currently, the majority of stress detection research is using population based approaches that lack the capability to adapt to individual differences. They also use supervised learning methods, requiring extensive labeling of training data, and they are typically tested on data collected in a laboratory and thus do not generalize to field conditions. To address these issues, we present multiple personalized models based on an unsupervised algorithm, the Self-Organizing Map (SOM), and we propose an algorithmic pipeline to apply the method for both laboratory and field data. The performance is evaluated on a dataset of physiological measurements from a laboratory test and on a field dataset consisting of four weeks of physiological and smartphone usage data. In these tests, the performance on the field data was steady across the different personalization levels (accuracy around 60%) and a fully personalized model performed the best on the laboratory data, achieving accuracy of 92% which is comparable to state-of-the-art supervised classifiers. These results demonstrate the feasibility of SOM in personalized mental stress detection both in constrained and free-living environment.

The work described in this paper deals with the subjective assessment of the visual design of packages. The difference of subjectively assessing visual package designs using either the real physical packages or their pictures on a computer screen was studied in experiments using an eye tracking device. Analysis of the gaze path during the viewing of the packages or pictures of the packages showed similar patterns between the two cases. The variation between the observers appeared larger than the variation between the two cases. Due to the limited scale of the experiments, the results cannot be taken as conclusive evidence that there are no significant differences in the gaze patterns between viewing real packages and their images on computer screens. On the other hand, neither did the data point to any obvious differences, suggesting that simulating package designs on computer screens could be a feasible option to producing actual packages or physical mock-ups to test the consumer response to visual package design, at least in some instances in which the 3-dimensional form and the touch and feel attributes of the packages are of lesser interest.