فا   |   En
Login
مشاهده‌ مشخصات مقاله

Threshold-Based Hidden Markov Model for Anomaly Detection in SAX-Represented ECG Signals

Authors
  • Milad Zandi-Goharrizy
  • Mohammad-Reza Zare-Mirakabad
  • Fatemeh Kaveh-Yazdy
Conference سمپوزیوم هوش مصنوعی و پردازش سیگنال 2013
Abstract Electrocardiogram (ECG) signals are widely used in healthcare systems for monitoring vital status of patients. Anomalous patterns in ECG of a patient might trigger an alarm for an emergency case; therefore anomaly detec-tion is a basic problem in health monitoring systems. In this paper, we propose a hidden Markov model (HMM) based novel anomaly detection framework, which uses SAX1-represented ECGs. According to basic investigations, typical HMM and SAX are not good candidates for anomaly detection, because of low resolu-tion of SAX. However, we contribute a threshold-based hidden Markov model which compensates for the SAX low-resolution problem. Furthermore, our pro-posed threshold reduces the dependency of the model to the distribution of hidden state by taking into account the likelihood probability of anomalous patterns. Re-sults of experiments demonstrate that the threshold based HMM labels samples with the accuracy of 96% and 99% in two datasets
قیمت
  • برای اعضای سایت : 100,000 Rial
  • برای دانشجویان عضو انجمن : 20,000 Rial
  • برای اعضای عادی انجمن : 40,000 Rial

خرید مقاله