ECG Derived Respiratory With AM Modulation
2026 International Conference on Cybersecurity, Digital Forensics, and AI Applications, ICCSDFAI 2026, İstanbul, Türkiye, 25 - 27 Haziran 2026, ss.555-559, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Doi Numarası: 10.1109/iccsdfai70505.2026.11648065
- Basıldığı Şehir: İstanbul
- Basıldığı Ülke: Türkiye
- Sayfa Sayıları: ss.555-559
- Anahtar Kelimeler: AM Envelope, ECG, EDR, Respiratory
- Gazi Üniversitesi Adresli: Evet
Özet
Accurate estimation of an individual's respiratory status plays a crucial role in treatments and wearable technologies. In many situations respiratory sensors are used to estimate people's respiratory status, but this method can be complex and expensive. This study focuses on estimating respiration signals based on ECG (Electrocardiogram) signals without the need for any other sensors other than ECG sensor. The suggested method involves a modulation-demodulation approach using a carrier signal derived from original ECG signals' R-peaks. The original ECG signal is modulated by a carrier signal and subsequently passed through low-pass filter to extract respiration-related components. In addition, an AM (Amplitude Modulation) envelope extraction method is additionally employed to improve estimation accuracy. To increase stability and adaptability, the obtained signals are normalized using adaptive estimation and smoothing techniques. An inclusive feature representation is obtained through window-based analysis that includes both time-domain and statistical properties of derived signals. Experimental results show that the proposed EDR (ECG- Derived Respiration) method is capable of identifying respiratory patterns and offers a simpler and more inexpensive method. The suggested method can be used in wearable technologies and monitoring physical status with one sensor.