| 000 -LEADER |
|---|
| fixed length control field |
02847nam a22001577a 4500 |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER |
|---|
| Classification number |
610 |
| 100 ## - MAIN ENTRY--PERSONAL NAME |
|---|
| Personal name |
Nayab, Maham |
| 245 ## - TITLE STATEMENT |
|---|
| Title |
Emg-Based Force Estimation Using Deep Learning Models / |
| Statement of responsibility, etc. |
Maham Nayab |
| 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 |
94p. |
| Other physical details |
Soft Copy |
| Dimensions |
30cm |
| 500 ## - GENERAL NOTE |
|---|
| General note |
The estimation of force through electromyography (EMG) assumes paramount importance in<br/>diverse domains, including neurorehabilitation, myoelectric control, and neurofeedback systems.<br/>The intricate relationship between muscle contraction and force, characterized by linear<br/>associations in small muscles with narrow motor units and nonlinear relationships in larger<br/>muscles with wider motor units, underscores the complexity of this physiological interplay.<br/>Against the backdrop of a global demand for advanced technologies to address limb loss<br/>limitations, with an estimated 100 million individuals worldwide in need of prosthetics, there arises<br/>an urgent need for sophisticated solutions. Meeting the diverse needs of prosthetic users<br/>emphasizes the crucial role of EMG-based force prediction, striving to provide adaptive and<br/>personalized solutions for an inclusive and effective approach to limb rehabilitation. This<br/>comprehensive study explores the dynamic interplay between surface electromyography (sEMG)<br/>and intramuscular electromyography (iEMG) signals and force estimation. Leveraging a diverse<br/>set of machine learning and deep learning models, the research aims to predict forces in both<br/>healthy individuals and those with trans-radial amputations. Across sEMG and iEMG modalities,<br/>deep learning models, including Long Short-Term Memory (LSTM), Temporal Convolutional<br/>Network (TCN), and the hybrid LSTM-TCN, consistently exhibit remarkable efficacy. These<br/>models, boasting R² values surpassing 0.90 in force prediction, offer promising advancements in<br/>refining force estimation through electromyography. Notably, the TCN emerges as an exemplary<br/>performer, yielding R² values of 0.98 for able-bodied individuals and 0.87 for amputees in sEMG.<br/>Simultaneously, the hybrid TCN-LSTM model maintains strong performance with R² values of<br/>0.98 for able-bodied individuals and 0.85 for amputees in sEMG. The LSTM model also upholds<br/>notable performance, showcasing R² values of 0.99 for able-bodied individuals and 0.80 for<br/>amputees in sEMG. Beyond unraveling the intricacies of EMG-based force estimation, this study<br/>sheds light on the unique challenges posed by amputations, contributing substantively to the<br/>ongoing quest for enhanced precision and effectiveness in rehabilitation interventions. |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM |
|---|
| Topical term or geographic name entry element |
MS Biomedical Engineering (BME) |
| 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/123456789/42213">http://10.250.8.41:8080/xmlui/handle/123456789/42213</a> |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) |
|---|
| Source of classification or shelving scheme |
|
| Koha item type |
Thesis |
