Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 58754 (05)
- University: Sharif University of Technology
- Department: Electrical Engineering
- Advisor(s): Shamsollahi, Mohammad Bagher; Karimi, Sajjad
- Abstract:
- This study explores hysteresis in cardiac electrical and mechanical responses to heart rate changes. Specifically, the focus is on the RT interval (as a surrogate for QT) and the systolic interval (S1S2), extracted from ECG and PCG signals, respectively. Long Short-Term Memory (LSTM) models were trained to capture the dynamic relationship between RR intervals and each of these modalities. To evaluate temporal memory, synthetic step-like RR inputs were used, and the corresponding delays in model outputs were analyzed. The results showed clear hysteresis in both RT and S1S2 intervals, with delays increasing at higher workloads (i.e., shorter RR), indicating slower cardiovascular adaptation (Approximately 0.6 and 1 second increase in average delay for RT and S1S2 intervals, respectively). In contrast, visual inspection of hysteresis curves revealed that the diastolic interval (S2S1) exhibits negligible delay, suggesting an almost instantaneous response. The low correlation between RT- and S1S2-based delay patterns further implies that electrical and mechanical dynamics reflect complementary aspects of cardiac regulation. These findings highlight the importance of time-aware modeling in characterizing autonomic cardiovascular function
- Keywords:
- Electrocardiogram ; Phonocardiogram ; Dynamic Behavior ; Hysteresis ; Cardiovascular Signals ; Long Short Term Memory (LSTM) ; Electromechanical Intervals
Digital Object List
-
محتواي کتاب
- view
Bookmark