Smartphone thermal imaging for stressed people classification using CNN+MobileNetV2
Fragment książki (Materiały konferencyjne)
MNiSW
70
konferencja
| Status: | |
| Autorzy: | Baran Katarzyna |
| Dyscypliny: | |
| Aby zobaczyć szczegóły należy się zalogować. | |
| Wersja dokumentu: | Drukowana | Elektroniczna |
| Język: | angielski |
| Strony: | 2507 - 2515 |
| Scopus® Cytowania: | 0 |
| Bazy: | Scopus |
| Efekt badań statutowych | NIE |
| Finansowanie: | The research project titled: “Application of thermal imaging for stress detection” was approved by the Commission for Research Ethics, No. 2/2021 dated 6.07.2021. |
| Materiał konferencyjny: | TAK |
| Nazwa konferencji: | 27th International Conference on Knowledge Based and Intelligent Information and Engineering Sytems |
| Skrócona nazwa konferencji: | KES 2023 |
| URL serii konferencji: | LINK |
| Termin konferencji: | 6 września 2023 do 8 września 2023 |
| Miasto konferencji: | Ateny |
| Państwo konferencji: | GRECJA |
| Publikacja OA: | TAK |
| Licencja: | |
| Sposób udostępnienia: | Witryna wydawcy |
| Wersja tekstu: | Ostateczna wersja opublikowana |
| Czas opublikowania: | W momencie opublikowania |
| Data opublikowania w OA: | 8 grudnia 2023 |
| Abstrakty: | angielski |
| Stress as a mental and physical imbalance is the experience of every human being. It can have a positive effect on human motivation and performance, as well as negatively contributing to the formation of chronic diseases. So far, stress is most often detected using EEG, ECG, GSR, BVP. A minority of researchers undertake stress detection from thermal images or video. The author, seeing the great potential in this area and looking for low-budget solutions that are more easily accessible to the average person, conducted a stress study using smartphone thermal imaging. The faces of the study participants were recorded by a low-cost thermographic camera in the smartphone version (external connection) – FLIR ONE Pro. As a stressor, arithmetic tasks with a time limit were used. The subjects additionally supplemented the MiniCOPE test to assess the level of coping with stress. These data were additional parameters that were taken into account during stress classification using CNN+MobileNetV2. The final results indicated high accuracy of stress classification based on thermal image sequences, confirming the thermal potential in stress detection. |
