Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{208599,
        author = {Tanishka Pansare and Vivek Bokefode},
        title = {A Neuro-Inspired Computational Framework for Modeling Human Emotional States Using Multimodal Physiological and Thermal Signals},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {no},
        pages = {582-588},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=208599},
        abstract = {Human emotion recognition remains a complex challenge due to the subjective, dynamic, and multi-layered nature of affective states. Existing systems that primarily rely on Facial Expression Recognition (FER), facial landmark detection, and iris tracking can be affected by environmental conditions and may not fully capture the involuntary physiological changes associated with emotional responses. 
To address these limitations, this paper presents a neuro-inspired multimodal framework that integrates facial analysis with infrared thermal imaging for human emotional-state monitoring. Thermal imaging provides non-contact information related to facial temperature distribution and physiological changes associated with autonomic nervous system activity. A Convolutional Neural Network (CNN) is proposed for extracting spatial characteristics from thermal patterns, while a Long Short-Term Memory (LSTM) network is employed to model temporal variations in emotional responses. 
The framework further proposes a neural transmission pathway model that conceptually connects detected emotional states with underlying neurobiological processes as a computational abstraction. By integrating affective computing with concepts from neuroscience, the framework establishes a foundation for biologically inspired emotional-state modeling, with potential applications in human-computer interaction, adaptive systems, emotional well-being monitoring, and future neuro-rehabilitative technologies.},
        keywords = {.},
        month = {September},
        }