Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Emotion-aware systems enable Personalized User Interaction (PUI) by dynamically adapting responses based on users’ emotional states. However, existing systems failed to capture latent emotional states between features, which affected emotion detection accuracy. Hence, this paper proposes an IoT-based emotion-aware PUI framework with Latent Emotional State Identification (LESI) using Weibull Ramp-Fuzzy (WR-Fuzzy) and Tied Covariance Gaussian Hidden Markov Emission Probability Model (TCGHMEPM). Initially, the DREAMER dataset is pre-processed, followed by data augmentation using Generative Adversarial Network (GAN), clustering using Forgy Soergel K-Means (FSK-Means), and feature extraction. Next, from the extracted features, LESI is performed using TCGHMEPM, and feature fusion is done using Multimodal Autoencoder (MA). Based on LESI and the fused features, emotion classification is conducted using Manifold Gated Swim Recurrent Unit (MGSRU), followed by deep explanation using Rényi Sphere SHapley Additive exPlanations (RSSHAP). Finally, PUI is provided using WR-Fuzzy. Therefore, the proposed MGSRU classified emotions with a higher accuracy (98.8745%) than existing techniques.
Keywords:
Personalized User Interaction, Emotions, Internet of Things (IoT), Artificial Intelligence (AI), Latent Emotional State Identification, Human Automated AI System, and Valence-Arousal-Dominance (VAD).
Cite Article:
"An enhanced iot-based emotion-aware personalized user interaction framework with lesi using wr-fuzzy and TCGHMEPM", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2455-2631, Vol.11, Issue 1, page no.a94-a111, January-2026, Available :http://www.ijrti.org/papers/IJRTI2601016.pdf
Downloads:
000144
ISSN:
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator