Leveraging Deep Neural Networks and Surface Electromyography for Real-Time Airwriting Gesture Recognition / (Record no. 612425)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 02470nam a22001577a 4500 |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 610 |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Saeed, Atiqa |
| 245 ## - TITLE STATEMENT | |
| Title | Leveraging Deep Neural Networks and Surface Electromyography for Real-Time Airwriting Gesture Recognition / |
| Statement of responsibility, etc. | Atiqa Saeed |
| 264 ## - PRODUCTION, PUBLICATION, DISTRIBUTION, MANUFACTURE, AND COPYRIGHT NOTICE | |
| Place of production, publication, distribution, manufacture | Islamabad : |
| Name of producer, publisher, distributor, manufacturer | SMME- NUST; |
| Date of production, publication, distribution, manufacture, or copyright notice | 2024. |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | 70p. |
| Other physical details | Soft Copy |
| Dimensions | 30p. |
| 500 ## - GENERAL NOTE | |
| General note | Airwriting enables users to write letters or characters in free space using hand or finger<br/>movements, with potential applications in human-computer interaction, virtual reality,<br/>augmented reality and development of assistive technologies. Despite advancements in<br/>gesture recognition technology, dynamic airwriting faces challenges with accuracy and<br/>often lacks real-time capabilities, limiting its application in non-verbal communication<br/>and rehabilitation devices. The primary objective of this research is to develop a novel<br/>real-time deep learning-based framework for airwriting recognition using surface<br/>electromyography (sEMG). This study presents a technique for real-time identification of<br/>uppercase English language alphabets written in free space by analyzing the electrical<br/>activity of forearm muscles involved in writing letters. The proposed framework involves<br/>sEMG data collection from 16 right handed healthy subjects with no neuromuscular or<br/>motor impairments, signal preprocessing, feature extraction, classification using<br/>Convolution neural network (CNN), Deep neural network (DNN) and Recurrent Neural<br/>Network (RNN).The best performing model was implemented in real-time and it was<br/>evaluated using performance metrics such as accuracy, precision, recall, F1 score,<br/>Confusion metrics and latency. Results show that 1 Dimensional (1D) CNN outperforms<br/>other models (p<0.05) and achieved an offline test accuracy of 89.81 ±0.87% and an<br/>average real-time test accuracy of 73.71 ±8.46% across subjects. The individual model of<br/>each subject performed even better, with an accuracy of 90.01 ±2.85% on offline testing<br/>of data and 75.45 ±1.53 % in real-time alphabet prediction. Thus, this work highlights the<br/>potential of deep learning models for real-time airwriting detection and provides<br/>foundations for sEMG-based airwriting applications in healthcare and telemedicine. |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | MS Biomedical Engineering |
| 700 ## - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Supervisor : Dr. Muhammad Asim Waris |
| 856 ## - ELECTRONIC LOCATION AND ACCESS | |
| Uniform Resource Identifier | <a href="http://10.250.8.41:8080/xmlui/handle/123456789/48529">http://10.250.8.41:8080/xmlui/handle/123456789/48529</a> |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Source of classification or shelving scheme | |
| Koha item type | Thesis |
| Withdrawn status | Permanent Location | Current Location | Shelving location | Date acquired | Full call number | Barcode | Koha item type |
|---|---|---|---|---|---|---|---|
| School of Mechanical & Manufacturing Engineering (SMME) | School of Mechanical & Manufacturing Engineering (SMME) | E-Books | 12/24/2024 | 610 | SMME-TH-1103 | Thesis |