แจ้งเอกสารไม่ครบถ้วน, ไม่ตรงกับชื่อเรื่อง หรือมีข้อผิดพลาดเกี่ยวกับเอกสาร ติดต่อที่นี่ ==>
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
Pattarapong Phasukkit. Recurrent neural network based underground object detection using A-scan ground penetrating radar. (). King Mongkut's University of Technology North Bangkok. Central Library. : , 2021.
Recurrent neural network based underground object detection using A-scan ground penetrating radar
Name: Poomsak Choochim
Organization :
King Mongkut's Institute of Technology Ladkrabang. School of Engineering
Email :
61010832@kmitl.ac.th
Name: Panut Kasjarun
Organization :
King Mongkut's Institute of Technology Ladkrabang. School of Engineering
Email :
61010686@kmitl.ac.th
Name: Pattarapong Phasukkit
Organization :
King Mongkut's Institute of Technology Ladkrabang. School of Engineering
Email :
pattarapong.ph@kmitl.ac.th
keyword:
Recurrent neural networks
LCSH:
Ground penetrating radar
-- Data processing
LCSH:
Signal processing
-- Digital techniques
LCSH:
Detectors
Abstract:
Ground penetrating radar (GPR) is a highly effective tool for finding objects buried underground. However, there are still some limitations that prevent it from being applied to a wider variety of applications, such as the complexity of processing and the challenges of signal collection. This work applies GPR with AI to reduce processing steps and display object features immediately. The approach is based on a time-series model using a bidirectional recurrent neural network (Bi-RNN), as it is possible to predict the position and shape of the object simultaneously. In this experiment, objects were buried in a sandbox at depths of 1050 centimeters, and two antennas were used to receive and transmit the signal as a GPR system. It was found that the accuracy is 92.8%, which was also measured by F1-score for each target position. By using the results of this work to add features and extend it to multiple functions, it will be possible to use GPR with a neural network model in actual field situations.
King Mongkut's University of Technology North Bangkok. Central Library
Address:
BANGKOK
Email:
library@kmutnb.ac.th
Created:
2021
Modified:
2026-04-28
Issued:
2026-04-28
บทความ/Article
application/pdf
BibliograpyCitation :
In Chiang Mai University. Faculty of Engineering. 2021 18th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON 2021) (pp.1028-1031). Chiang Mai : Chiang Mai University
eng
©copyrights King Mongkut's University of Technology North Bangkok
RightsAccess:
ใช้เวลา
0.039544 วินาที
Poomsak Choochim
| Title | Contributor | Type |
|---|---|---|
| Recurrent neural network based underground object detection using A-scan ground penetrating radar
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Poomsak Choochim;Panut Kasjarun;Pattarapong Phasukkit | บทความ/Article |
Panut Kasjarun
| Title | Contributor | Type |
|---|---|---|
| Recurrent neural network based underground object detection using A-scan ground penetrating radar
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Poomsak Choochim;Panut Kasjarun;Pattarapong Phasukkit | บทความ/Article |
Pattarapong Phasukkit
| Title | Contributor | Type |
|---|---|---|
| Coronavirus infected lung CT scan image segmentation using deep learning
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Kanatat Asipong;Somprasonk Gabbualoy;Pattarapong Phasukkit | บทความ/Article | |
| Recurrent neural network based underground object detection using A-scan ground penetrating radar
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Poomsak Choochim;Panut Kasjarun;Pattarapong Phasukkit | บทความ/Article |