|
E3Graphy: A Novel Integrated Model for Bio-signals Acquisition & Disease Detection |
|---|---|
| รหัสดีโอไอ | |
| Creator | Muhammad Amjid, Hammad Hussain, Mumtaz Ali, Bilal Khan, Shahab Haider |
| Title | E3Graphy: A Novel Integrated Model for Bio-signals Acquisition & Disease Detection |
| Contributor | - |
| Publisher | TuEngr Group |
| Publication Year | 2566 |
| Journal Title | International Transaction Journal of Engineering, Management, & Applied Sciences & Technologies |
| Journal Vol. | 14 |
| Journal No. | 1 |
| Page no. | 14A1U: 1-14 |
| Keyword | Bio-Signals Acquisition, Disease Detection, ECG, EEG, EMG, SVM, Health Monitoring Model, Machine learning, E3Graphy, Deep Neural Network, XG Boost, Gradient Boosting, Ada Boost, Na?ve Bayes, Decision Tree, BioSPPy. |
| URL Website | http://TuEngr.com/Vol14-1.html |
| Website title | ITJEMAST V14(1) 2023 @ TuEngr.com |
| ISSN | 2228-9860 |
| Abstract | Recent technological advancements and the escalating number of Internet of Things-enabled systems have improved health monitoring to a significant level. The human body emits various bio-signals that include Electrocardiograph (ECG), Electromyography (EMG), and Electroencephalogram (EEG). These bio-signals are observed to monitor health status and disease diagnosis. However, noise and power line interference adversely affect the accuracy. To that end, this paper proposes a novel portable health monitoring model, namely, E3Graphy that aims to bridge the communication gap between doctors and patients, thereby, enhancing diagnostics. E3Grpahy integrates the features of ECG, EMG, and EEG in a less power-consuming smaller-sized monitoring model, which comprises sensors, a microcontroller, a Bluetooth module, and a mobile application. Moreover, E3Graphy employs machine learning techniques, such as Support Vector Machine, Na?ve Bayes, Neural Network, and Extreme Gradient Boosting to enable early disease detection. Results demonstrate that E3Graphy achieves an accuracy of 90.58% in ECG and 98.28% in EEG, and classifies diseases for ECG with a confidence score of 70.47%. |
