Presentation 2013-01-24
A Basic Study on Individual Recognition Using Microwave Doppler Sensors
Shunsuke Mashima, Hiroaki Morino,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In household appliances, game machines and so on, the individual recognition by hands-free technology attracts attentions these days. Here, it is an important issue to develop recognition technologies with performance less affected by the user's conditions or the surrounding environments. Conventionally, image recognitions represented by those used in Kinect or speech recognitions have been studied and put to practical use in a wide range of applications, such as user authentication in a PC shared by two or more persons, based on image recognition using a camera. However, image recognition has some drawbacks such as it cannot be used in dark places, or in the circumstances where users are sensitive to infringement of their privacies. Also, speech recognition tends to be affected by the surrounding noise. In this paper, we propose a novel individual recognition technique using microwave Doppler sensors. This technique extracts feature quantity specific to the target individual from the frequency spectrum data of reflected signal received by the Doppler sensors Based on the results of our preliminary experiments, we determine weight values used for feature quantity extraction, in order to efficiently derive the spectrum data specific to each individual, leading to improvement of recognition performance. With the experiment targeted for three participants, it is shown that the proposed scheme improves the success ratio of the recognition by about 8 % on average compared with the existing scheme where weighting to spectrum data is not performed. Moreover, if deployment is taken into consideration, it is also important to stop set the number of tests for obtaining learning data as few as possible. This paper examines the optimal number of tests for learning.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Individual Recognition / Microwave Doppler Sensor / FFT / Feature quantity
Paper # USN2012-60
Date of Issue

Conference Information
Committee USN
Conference Date 2013/1/17(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 Ubiquitous and Sensor Networks(USN)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Basic Study on Individual Recognition Using Microwave Doppler Sensors
Sub Title (in English)
Keyword(1) Individual Recognition
Keyword(2) Microwave Doppler Sensor
Keyword(3) FFT
Keyword(4) Feature quantity
1st Author's Name Shunsuke Mashima
1st Author's Affiliation Graduate School of Engineering and Science, Shibaura Institute of Technology()
2nd Author's Name Hiroaki Morino
2nd Author's Affiliation Graduate School of Engineering and Science, Shibaura Institute of Technology
Date 2013-01-24
Paper # USN2012-60
Volume (vol) vol.112
Number (no) 406
Page pp.pp.-
#Pages 6
Date of Issue