웨어러블 기기의 심박수 센서를 통한 LSTM 기반 부정맥 예측
LSTM-based Predicting Arrhythmia through Heart Rate Sensors in Wearable Devices
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
최근 급속한 발전으로 인해 신체에 직접적으로 부정적인 영향을 미칠 수 있는 음식이나 여가 활동이 늘어나면서, 전 세계적으로 젊은 세대에서도 많은 건강 문제가 발생하고 있다. 이에 따라 개인 건강에 대한 관심이 높아지고 스마트 워치 등의 웨어러블 기기를 사용하여 자신의 건강 상태를 확인하고자 하는 양상이 급증하고 있다. 그러나 기기마다 제공되는 서비스가 다르며 직접 정보를 확인하고 비교하기는 어렵다는 문제점이 있다. 이러한 문제점을 해결하기 위해 웨어러블 기기의 심박수 센서를 통한 LSTM 기반 부정맥 예측을 제안한다. 제안하는 방법은 전문 의료 장비가 아닌 일반 웨어러블 기기를 통해 착용자의 심박수를 측정하여 LSTM을 이용해 착용자의 평균 심박수 데이터를 학습하고 부정맥을 예측하는 방법이다. 이를 통해 착용자의 현재 심박수가 평소 심박수와 어떻게 다르고, 변화하는지 확인할 수 있다.
Abstract
With the recent rapid development, there has been an increase in foods and leisure activities that can have a direct negative impact on the body, leading to a rise in health problems among the younger generation worldwide.. As a result, interest in personal health is increasing, and the tendency to check one's health status using wearable devices such as smart watches is increasing rapidly. However, there is a problem that the services provided by each device are different, and it is difficult to directly check and compare information. To solve this problem, we propose LSTM-based arrhythmia prediction through a heart rate sensor on a wearable device. The proposed method is to measure the wearer's heart rate through general wearable devices rather than professional medical equipment, learn the wearer's average heart rate data using LSTM, and predict arrhythmia. Through this, it is possible to check how the wearer's current heart rate is different from and changes from the usual heart rate.
참고문헌 (11)
- "PHARMNEWS"[URL]
- G. Zhang, "A wearable device for health management detection of multiple physiological parameters based on ZigBee wireless networks", Measurement, 165, pp.108168~ (2020)
- N. Isakadze, "How useful is the smartwatch ECG?", Trends in cardiovascular medicine, 30(7), pp.442~448 (2020)
- A. K. Sangaiah, "An intelligent learning approach for improving ECG signal classification and arrhythmia analysis", Artificial intelligence in medicine, 103, pp.101788~ (2020)
- C. Chen, "Automated arrhythmia classification based on a combination network of CNN and LSTM", Biomedical Signal Processing and Control, 57, pp.101819~ (2020)
- H. M. Rai, "Hybrid CNN-LSTM deep learning model and ensemble technique for automatic detection of myocardial infarction using big ECG data", Applied Intelligence, 52(5), pp.5366~5384 (2022)
- A. Narin, "Early prediction of paroxysmal atrial fibrillation based on short-term heart rate variability", Physica A : Statistical Mechanics and its Applications, 509, pp.56~65 (2018)
- J. Wang, "NGCU : A new RNN model for time-series data prediction", Big Data Research, 27, pp.100296~ (2022)
- Y. Yu, "A review of recurrent neural networks : LSTM cells and network architectures", Neural computation, 31(7), pp.1235~1270 (2019)
- H. J. Kwon, "Voice Frequency Synthesis using VAWGAN based Amplitude Scaling for Emotion Transformation", KSII Trans. Internet Inf. Syst, 16(2), pp.713~725 (2022)
- B. U. Jeon, "CutPaste-Based Anomaly Detection Model using Multi Scale Feature Extraction in Time Series Streaming Data", KSII Trans. Internet Inf. Syst, 16(8), pp.2787~2800 (2022)