| Presentation | 2018-10-19 Underground Model Inversion from GPR Images by Deep Learning Using Generative Adversarial Networks Jun Sonoda, Tomoyuki Kimoto, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Recently, deterioration of social infrastructures such as tunnels and bridges become a serious social problem. It is required to rapidly and accurately detect for abnormal parts of the social infrastructures. The ground penetrating radar (GPR) is efficient for the social infrastructure inspection. However, it is difficult to identify the material and size of the underground object from the radar image obtained the GPR. To objectively and quantitatively investigate from the GPR images by the deep learning, we have automatically and massively generated the GPR images by a fast finite-difference time-domain (FDTD) simulation with graphics processing units (GPUs), and it has been learned the underground object using a deep convolutional neural network (CNN), with the generated GPR images. As the results, we have obtained multilayer layers CNN can identify six materials and size with roughly more than 80% accuracy in some inhomogeneous underground. In this study, to estimate the underground objects from the GPR images, we have developed an underground model inversion from the GPR images by the deep learning using the generative adversarial networks (GAN). |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | generative adversarial networks / deep learning / ground penetrating radar / inversion / FDTD method / GPU |
| Paper # | EMCJ2018-53,MW2018-89,EST2018-75 |
| Date of Issue | 2018-10-11 (EMCJ, MW, EST) |
| Conference Information | |
| Committee | EST / MW / EMCJ / IEE-EMC |
|---|---|
| Conference Date | 2018/10/18(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Hachinohe Chamber of Commerce and Industry(Hachinohe city, Aomori) |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Simulation techniques, EMC, Microwave, Electromagnetic field simulation, etc. |
| Chair | Akimasa Hirata(Nagoya Inst. of Tech.) / Masahiro Muraguchi(TUS) / Osami Wada(Kyoto Univ.) / 山崎 健一(電中研) |
| 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) / Kensei Oh(Nagoya Inst. of Tech.) |
| Secretary | Shinichiro Ohnuki(CIST) / Masayuki Kimishima(National Inst. of Tech.,Sendai College) / Jun Shibayama(HITACHI) / Yoshinori Kogami(Utsunomiya Univ.) / Hiroshi Okazaki(Tokyo Inst. of Tech.) / Kenichi Tajima(Mitsubishi Electric) / Kensei Oh(東北学院大) / (鉄道総研) |
| Assistant | Takahiro Ito(Nagoya Inst. of Tech.) / Kazuhiro Fujita(Fujitsu) / Mizuki Motoyoshi(Tohoku Univ.) / Satoshi Yoshida(Kagoshima Univ.) / Shinobu Nagasawa(Mitsubishi Electric) / Shinichiro Yamamoto(Univ. of Hyogo) / Takanori Unou(Denso) / 井渕 貴章(阪大) |
| Paper Information | |
| Registration To | Technical Committee on Electronics Simulation Technology / Technical Committee on Microwaves / Technical Committee on Electromagnetic Compatibility / Technical Meeting on Electromagnetic Compatibility (IEE-EMC) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Underground Model Inversion from GPR Images by Deep Learning Using Generative Adversarial Networks |
| Sub Title (in English) | |
| Keyword(1) | generative adversarial networks |
| Keyword(2) | deep learning |
| Keyword(3) | ground penetrating radar |
| Keyword(4) | inversion |
| Keyword(5) | FDTD method |
| Keyword(6) | GPU |
| 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 | 2018-10-19 |
| Paper # | EMCJ2018-53,MW2018-89,EST2018-75 |
| Volume (vol) | vol.118 |
| Number (no) | EMCJ-247,MW-248,EST-249 |
| Page | pp.pp.115-119(EMCJ), pp.115-119(MW), pp.115-119(EST), |
| #Pages | 5 |
| Date of Issue | 2018-10-11 (EMCJ, MW, EST) |