Automatic detection of volcano-seismic events by modeling state and event duration in hidden Markov models
详细信息 查看全文
- 作者：Sohail Masood Bhattia ; 1 ; sohail.masood@cs.uol.edu.pk" class="auth_mail" title="E-mail the corresponding author ; Muhammad Salman Khana ; 2 ; salmankhan@uetpeshawar.edu.pk" class="auth_mail" title="E-mail the corresponding author ; Jorge Wutha ; jwuths@gmail.com" class="auth_mail" title="E-mail the corresponding author ; Fernando Huenupanb ; fernando.huenupan@ufrontera.cl" class="auth_mail" title="E-mail the corresponding author ; Millaray Curilemb ; millaray.curilem@ufrontera.cl" class="auth_mail" title="E-mail the corresponding author ; Luis Francoc ; luis.franco@sernageomin.cl" class="auth_mail" title="E-mail the corresponding author ; Nestor Becerra Yomaa ; nbecerra@ing.uchile.cl" class="auth_mail" title="E-mail the corresponding author
- 关键词：Volcano monitoring ; Duration model ; Hidden Markov models ; Signal processing ; Pattern recognition
- 刊名：Journal of Volcanology and Geothermal Research
- 出版年：2016
- 出版时间：15 September 2016
- 年：2016
- 卷：324
- 期：Complete
- 页码：134-143
- 全文大小：1345 K
文摘
- •
Volcano event durations are modeled in the HMM framework.
- •
State duration are modeling with max and min bounds.
- •
Event duration are modeled with max and min bounds and with a gamma distribution.
- •
New event penalization is incorporated to reduce false positives.