Presentation 2002/1/18
Radar pulse recognition using hidden Markov model
Kaori KAWAKAMI, Hidetoshi TANAKA, Akitoshi MITSUISHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We attempt to clarify the radar source recognition capability through the radar pulse observed by sensor. Pulse data are obtained from two radars of the same type. The recognition has been tried by constructing the model and estimating the fitness. The model based on the hidden Markov model is constructed by : (1) extracting the fragments ; (2) clustering the fragments ; and (3) calculating the state-transition probabilities. Preliminary experiment showed that the recognizability is due to their carrier frequencies. Comparative experiment showed that the potential feature is indicated in the lower frequency of the pulse, since the coefficient of the moving average has some recognition capability.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Sensor / Pulse recognition / Hidden Markov model
Paper #
Date of Issue

Conference Information
Committee SANE
Conference Date 2002/1/18(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Space, Aeronautical and Navigational Electronics (SANE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Radar pulse recognition using hidden Markov model
Sub Title (in English)
Keyword(1) Sensor
Keyword(2) Pulse recognition
Keyword(3) Hidden Markov model
1st Author's Name Kaori KAWAKAMI
1st Author's Affiliation Mitsubishi Electric Corporation Information Technology R&D Center()
2nd Author's Name Hidetoshi TANAKA
2nd Author's Affiliation Mitsubishi Electric Corporation Information Technology R&D Center
3rd Author's Name Akitoshi MITSUISHI
3rd Author's Affiliation Mitsubishi Electric Corporation Information Technology R&D Center
Date 2002/1/18
Paper #
Volume (vol) vol.101
Number (no) 608
Page pp.pp.-
#Pages 6
Date of Issue