| Presentation | 2018-07-19 GPR Image Recognition by Transfer Learning with FDTD Simulation on Deep Learning Jun Sonoda, Tomoyuki Kimoto, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this study, to automatically detect underground objects from the ground penetrating radar (GPR) images by the deep neural network (DNN), we have generated GPR images for training the DNN using a fast finite-difference time-domain (FDTD) simulation with graphics processing units (GPUs). Also, we have obtained characteristics of underground objects using the generated GPR images with a convolutional neural network (CNN) and finetuning using a modified VGG16 trained by the ImageNet. It is shown that the CNN and the VGG16 can identify four materials of experimental GPR images roughly 75% and 80% accuracy, respectively. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Deep learning / transfer learning / VGG16 / CNN / ground penetrating radar / FDTD |
| Paper # | EMT2018-17,MW2018-32,OPE2018-20,EST2018-15,MWP2018-16 |
| Date of Issue | 2018-07-12 (EMT, MW, OPE, EST, MWP) |
| Conference Information | |
| Committee | EST / MW / OPE / MWP / EMT / IEE-EMT |
|---|---|
| Conference Date | 2018/7/19(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Akimasa Hirata(Nagoya Inst. of Tech.) / Masahiro Muraguchi(TUS) / Kouki Sato(Furukawa Electric Industries) / Tetsuya Kawanishi(Waseda Univ.) / Akira Hirose(Univ. of Tokyo) / Keiji Goto(National Defense Academy) |
| Vice Chair | Shinichiro Ohnuki(Nihon Univ.) / Masayuki Kimishima(Advantest) / Jun Shibayama(Hosei Univ.) / Yoshinori Kogami(Utsunomiya Univ.) / Hiroshi Okazaki(NTT DOCOMO) / Kenichi Tajima(Mitsubishi Electric) / Hiroshi Takahashi(Sophia Univ.) / Naoto Yoshimoto(Chitose Inst. of Science and Tech.) / Koichi Hirayama(Kitami Inst. of Tech.) |
| Secretary | Shinichiro Ohnuki(CIST) / Masayuki Kimishima(National Inst. of Tech.,Sendai College) / Jun Shibayama(HITACHI) / Yoshinori Kogami(Utsunomiya Univ.) / Hiroshi Okazaki(Univ. of Tokyo) / Kenichi Tajima(NICT) / Hiroshi Takahashi(NICT) / Naoto Yoshimoto(Chiba Inst. of Tech.) / Koichi Hirayama(Tokyo Metro. Coll. of Tech) / (Fukuoka Inst.of Tech.) |
| Assistant | Takahiro Ito(Nagoya Inst. of Tech.) / Kazuhiro Fujita(Fujitsu) / Mizuki Motoyoshi(Tohoku Univ.) / Satoshi Yoshida(Kagoshima Univ.) / Yuya Shoji(Tokyo Inst. of Tech.) / Kazunori Seno(NTT) / Kensuke Ikeda(CRIEPI) / Kosuke Nishimura(KDDI Research) / Junichiro Sugisaka(Kitami Inst. of Tech.) / Yoshihiro Naka(Kyushu Univ. of Health and Welfare) |
| Paper Information | |
| Registration To | Technical Committee on Electronics Simulation Technology / Technical Committee on Microwaves / Technical Committee on OptoElectronics / Technical Committee on Microwave and Millimeter-wave Photonics / Technical Committee on Electromagnetic Theory / Technical Meeting on Electromagnetic Theory |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | GPR Image Recognition by Transfer Learning with FDTD Simulation on Deep Learning |
| Sub Title (in English) | |
| Keyword(1) | Deep learning |
| Keyword(2) | transfer learning |
| Keyword(3) | VGG16 |
| Keyword(4) | CNN |
| Keyword(5) | ground penetrating radar |
| Keyword(6) | FDTD |
| 1st Author's Name | Jun Sonoda |
| 1st Author's Affiliation | National Institute of Technology, Sendai College(NIT, Sendai) |
| 2nd Author's Name | Tomoyuki Kimoto |
| 2nd Author's Affiliation | National Institute of Technology, Oita College(NIT, Oita) |
| Date | 2018-07-19 |
| Paper # | EMT2018-17,MW2018-32,OPE2018-20,EST2018-15,MWP2018-16 |
| Volume (vol) | vol.118 |
| Number (no) | EMT-141,MW-142,OPE-143,EST-144,MWP-145 |
| Page | pp.pp.59-62(EMT), pp.59-62(MW), pp.59-62(OPE), pp.59-62(EST), pp.59-62(MWP), |
| #Pages | 4 |
| Date of Issue | 2018-07-12 (EMT, MW, OPE, EST, MWP) |