Authors | U. Rawat, P. Singh , V. Tripathi |
Affiliations |
Department of Computer Science and Engineering, Graphic Era (Deemed to be University), Dehradun, Uttarakhand 248001, India |
Е-mail | |
Issue | Volume 16, Year 2024, Number 5 |
Dates | Received 09 June 2024; revised manuscript received 14 October 2024; published online 30 October 2024 |
Citation | U. Rawat, P. Singh, V. Tripathi, J. Nano- Electron. Phys. 16 No 5, 05018 (2024) |
DOI | https://doi.org/10.21272/jnep.16(5).05018 |
PACS Number(s) | 07.05.Tp |
Keywords | ML (2) , Healthcare, IoT (4) , Cloud computing. |
Annotation |
Recognizing emotion expression has become more difficult in recent years due to significant variation. Pain intensity detection using ML involves leveraging algorithms to analyze various indicators, viz. facial expressions, physiological signals, or behavioral patterns, to objectively assess and categorize the severity of pain. ML models, trained on diverse datasets, enable accurate predictions and contribute to advancing non-invasive and automated approaches for evaluating pain intensity in clinical settings. This paper survey the different models that have been used by researchers in last few years and the accuracy achieved by them in various pain datasets used in their existing literature. It also suggests a general framework idea for a system that opens the door for individualized, data-driven treatment plans in addition to providing healthcare professionals with fast and accurate diagnostic information. The limitations of traditional methods, which often rely on subjective self-reporting, especially when dealing with patients who are unconscious or partially abled and unable to communicate verbally, are recognized in our research. Such type of designed system can excel in detecting pain sentiments by closely examining facial expressions, providing a valuable non-verbal avenue of communication for individuals who face challenges in articulating their pain verbally. The opportunity for IoT and cloud computing to transform healthcare by offering a real-time, non-invasive way to measure pain intensity have been suggested in this paper. |
List of References |