IoT-driven smart assistive communication system for the hearing impaired with hybrid deep learning models for sign language recognition

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 20, 2025

Deaf and hard-of-hearing people utilize sign language recognition (SLR) to interconnect. Sign (SL) is vital for deaf individuals communicate. SL uses varied hand gestures speak words, sentences, or letters. It aids in linking the gap of communication between with hearing loss other persons. Also, it creates comfortable convey their feelings. The Internet Things (IoTs) can help persons disabilities sustain desire attain a good quality life permit them contribute economic social lives. Modern machine learning (ML) computer vision (CV) developments have allowed gesture detection decipherment. This study presents Smart Assistive Communication System Hearing-Impaired using Language Recognition Hybrid Deep Learning (SACHI-SLRHDL) methodology IoT. SACHI-SLRHDL technique aims assist impairments by creating an intelligent solution. At primary stage, utilizes bilateral filtering (BF) image pre-processing increase excellence captured images reducing noise while preserving edges. Furthermore, improved MobileNetV3 model employed feature extraction process. Moreover, convolutional neural network bidirectional gated recurrent unit attention (CNN-BiGRU-A) classifier implemented SLR Finally, attraction-repulsion optimization algorithm (AROA) adjusts hyperparameter values CNN-BiGRU-A method optimally, resulting more excellent classification performance. To exhibit significant solution method, comprehensive experimental analysis performed under Indian dataset. validation portrayed superior accuracy value 99.19% over existing techniques.

Language: Английский

Text classification of public online messages in civil aviation: A N-BM25 weighted word vectors method

Information Sciences, Journal Year: 2025, Volume and Issue: unknown, P. 121956 - 121956

Published: Feb. 1, 2025

Language: Английский