Bagula, AKyamakya, KAl-Machot, F2021-04-152021-04-152021Bagula, A. et al. (2021). Emotion and stress recognition related sensors and machine learning technologies. Sensors ,21(7),22731424-822010.3390/s21072273http://hdl.handle.net/10566/6055Intelligent sociotechnical systems are gaining momentum in today’s informationrich society, where different technologies are used to collect data from such systems and mine this data to make useful insights about our daily activities. These systems range from driver-assistance systems, to medical-patient monitoring systems, to emotion-aware intelligent systems, to complex collaborative robotics systems. They are built around (i) intrusive technologies such as physiological sensors, used for example in EEG, ECG, electrodermal activity and skin conductance and (ii) nonintrusive technologies that use piezo-vibration sensors, facial images, chairborne differential vibration sensors and bedborne differential vibration sensors. However, despite their undisputable advantages in our daily lives, there are a number of issues relating to the design and development of such systems, as they rely on emotion and stress classification from physiological signals. These issues can be viewed from various perspectives including: (a) quality and reliability of sensor data; (b) classification performance in terms of accuracy, precision, specificity, recall and F1-measure; (c) robustness of subject-independent recognition; (d) portability of the classification systems to different environments and (e) the estimation of the emotional state for dynamic systems.enMachine learning technologiesSensorsStress recognitionDriver-assistance systemsMedical-patient monitoring systemsArticle