A novel Complemented input matching model for accurate and Timely emotion recognition

Emotion identification is a fundamental requirement for patient-centered healthcare, as it enables prompt understanding of patients’ emotional states during clinical care. Patient suffering and rehabilitation stress are increased by the current methods’ incapacity to swiftly and accurately identify emotions based on hand and facial movement analysis. To address this problem, this study proposes the Complemented Input Matching Model (CIMM), which aims to achieve accurate emotion recognition with low processing delay. The proposed model employs a multi-data fusion strategy that integrates temporal emotion data with expected isolation inputs to reduce combinatorial errors and improve decision-making efficacy. Trials are conducted to define emotions using EEG and ECG signals from an updated publicly available dataset collected from 50 individuals at 20-second intervals and sorted into 180–200 labels. A variety of fusion events, including error-free and time-efficient examples, are identified using both existing and prior isolation techniques. The performance of the proposed model is evaluated using metrics such as fusion ratio, accessibility, accuracy, mistake rate, and time required. Experimental results demonstrate the effectiveness of the CIMM for accurate and efficient emotion recognition in healthcare settings, with a 10.65% improvement in fusion ratio, an 8.72% increase in accessibility, a 9.34% increase in precision, a 9.35% decrease in error, and an 8.87% reduction in time requirement across various data instances.