| 000 -LEADER |
|---|
| fixed length control field |
02557nam a22001577a 4500 |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER |
|---|
| Classification number |
610 |
| 100 ## - MAIN ENTRY--PERSONAL NAME |
|---|
| Personal name |
Mansoor, Mariam |
| 245 ## - TITLE STATEMENT |
|---|
| Title |
An Intelligent Framework for Real-Time PCG Classification and Cardiac Monitoring Using Machine Learning / |
| Statement of responsibility, etc. |
Mariam Mansoor |
| 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 |
2026. |
| 300 ## - PHYSICAL DESCRIPTION |
|---|
| Extent |
103p. |
| Other physical details |
Soft Copy |
| Dimensions |
30cm |
| 500 ## - GENERAL NOTE |
|---|
| General note |
The accurate and timely diagnosis of cardiovascular diseases, particularly valvular heart<br/>disorders, is essential for reducing morbidity and mortality. However, conventional<br/>auscultation remains limited by subjectivity, ambient noise, and an inability to record or<br/>analyse sounds. This thesis addresses these limitations through a two-fold contribution: the<br/>development of a wearable, high-fidelity digital auscultation system and the integration of<br/>a real-time, AI-assisted classification framework for automated diagnosis. The first part of<br/>the research presents a custom-designed wearable digital stethoscope using a piezoelectric<br/>contact sensor embedded in an aluminium chestpiece. This configuration offers superior<br/>acoustic coupling and environmental noise rejection. A multi-stage low-noise analog signal<br/>chain was designed, incorporating band-specific filtering to isolate heart and lung signals.<br/>A miniaturized PCB was fabricated to house the circuit, and a Python-based GUI was<br/>developed to visualize, record, and archive phonocardiogram (PCG) signals while<br/>generating patient-linked reports. In the second phase, a lightweight 1D convolutional<br/>neural network (CardioSynx) was introduced for real-time classification of five PCG<br/>classes, including normal and pathological valve conditions. The model trained offline<br/>using Butterworth filtering, Hilbert envelope segmentation, and wavelet denoising,<br/>achieved 97.5% ± 0.22 accuracy on validation data. For deployment, the system employed<br/>a parallel processing architecture to enable simultaneous audio acquisition, denoising,<br/>feature extraction, and inference, achieving a frame-level latency of 58 ms, well below<br/>clinical standards and an SNR of 16.8 dB. Real-time evaluation on patients yielded over<br/>90% accuracy across key pathologies. Together, the proposed system delivers a scalable,<br/>real-time, and clinically robust platform for digital auscultation and decision support in<br/>modern healthcare. |
| 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/123456789/57337">http://10.250.8.41:8080/xmlui/handle/123456789/57337</a> |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) |
|---|
| Source of classification or shelving scheme |
|
| Koha item type |
Thesis |
