対数尤度の時間変動を考慮したHMMによるELF帯環境電磁波中の異常信号検出に関する性能評価  [in Japanese] Performance of Anomalous Signal Detection with HMM Approach in Electromagnetic Wave Observation Using Moving Window  [in Japanese]

Search this Article

Author(s)

Abstract

現在,環境電磁波から地震発生に由来する異常な電磁放射信号(以下,異常信号)を検出する研究が行われており,著者等は極超低周波数帯による電磁波観測,解析を行っている.先行研究により様々な異常信号検出手法が提案されているが,学習データ数の制限により,未知の異常信号を検出できない,異常信号と関連のない突発的な非定常信号を誤検出してしまうなどの問題がある.それらの問題を解決する為,異常信号を含まない振幅密度分布のみをHMMに学習させ,異常信号を検出する手法を提案し,誤検出率を用いて検出精度の評価を行った.本稿では,新たに観測信号の時間に対する対数尤度の推移に着目し,異常信号検出精度の評価を行う.

It is known that the detection of an anomalous signal radiated from the earth's crust is useful for predicting the precursor of the earthquakes. We observed the electromagnetic (EM) wave using the Extremely Low Frequency band. Various methods for detection of an anomalous signal have been proposed. Those methods have some problems. We proposed the anomalous signal detection based on HMM using the amplitude density distribution of an EM wave, which does not contain an anomalous signal. The input signals are calculated from the observed EM wave. An amplitude density distribution calculated from the image of an EM wave is employed as the input of HMM. In this paper, we evaluate the accuracy of an anomalous signal detection by using a temporal change of log likelihood calculated from EM wave data.

Journal

  • IEICE technical report

    IEICE technical report 110(445), 77-81, 2011-02-24

    The Institute of Electronics, Information and Communication Engineers

References:  20

Cited by:  1

Codes

  • NII Article ID (NAID)
    110008688609
  • NII NACSIS-CAT ID (NCID)
    AA1196239X
  • Text Lang
    JPN
  • Article Type
    Journal Article
  • ISSN
    09135685
  • NDL Article ID
    11047581
  • NDL Source Classification
    ZN33(科学技術--電気工学・電気機械工業--電子工学・電気通信)
  • NDL Call No.
    Z16-940
  • Data Source
    CJP  CJPref  NDL  NII-ELS 
Page Top