Real time data evaluation with wearable devices: An Impact of Artifact Calibration Method on Emotion Recognition

Abstract

Smartwatch technology is transforming the environment of transmission and monitoring for stakeholders and research participants who want to provide real-time data for evaluation. A range of sensors are available in smartwatches for gathering physical activity and location data. Here, combining all of these elements allows the collected data to be sent to a remote computer, allowing for real-time monitoring of physical and perhaps emotional development. Photoplethysmography is an easy and economical optical sensing technology that is commonly used to assess heartbeats. PPG is a non-invasive device that measures the volumetric fluctuations of blood flow using a light source and a sensor at the top layer of skin. Models concerning HRV (Heart Rate Variability) analysis are being studied in various domains, including human emotion recognition (HER). Smartwatches as sensor-based devices play an essential role as photoplethysmographic (PPG) data are frequently evaluated for this assessment. However, the nature of these waves (in terms of additional interruptions) may not always be flawless, even though they are susceptible to many factors, such as motion artifacts, light sources, stress distribution, ethnic background, or circumstances. Here techniques for antique rectification play a significant role &, as a response, impact the outcome. This research proposes a novel data distortions mitigation strategy for improving emotion detection classification efficiency using photoplethysmography waves throughout auditory invitation & a Support Vector Machine (SVM) model. Compared to previously undertaken data using a conventional toolset, i.e.,48.81, the presented scheme provides an improved categorization in trigger sensing, i.e., 68.75 percent. An alternative indicator, such as electroencephalographic activity, could be used in conjunction with PPG for further improvement.