แจ้งเอกสารไม่ครบถ้วน, ไม่ตรงกับชื่อเรื่อง หรือมีข้อผิดพลาดเกี่ยวกับเอกสาร ติดต่อที่นี่ ==>
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
Prapaporn Rattanatamrong. Prototyping a low-cost pest detection system for CNT0718-26-1-1-1 rice farming. (). King Mongkut's University of Technology North Bangkok. Central Library. : , 2023.
Prototyping a low-cost pest detection system for CNT0718-26-1-1-1 rice farming
Name: Ratthapoom Rangubtook
Organization :
Thammasat University. Faculty of Science and Technology
Name: Thapanan Plubplai
Organization :
Thammasat University. Faculty of Science and Technology
Name: Supet Jirakajohnkool
Organization :
Thammasat University. Faculty of Science and Technology
Name: Prapaporn Rattanatamrong
Organization :
Thammasat University. Faculty of Science and Technology
LCSH:
Image processing
Abstract:
Pests are significant and challenging issues to handle
for rice farming and have negative influence on rice quality
and production. Various fields of applications are now using
real-time object detection technology, which transforms visual
data into quantitative data that may be later examined in more
detail. This technology has also been applied in pest detection
systems along with real-time notification. This paper presents
the design and implementation of a digital technology tools for
rice farmers to handle pest issues by using an ESP32 with an
OV2640 camera in order to take pictures of pests and transfer
the captured pictures to Google Drive for further processing. We
developed a pest detection model using the Googles TensorFlow
framework. The model was trained using 50 images for each of
four pest types, namely rice roller, rice gall midge, rice earhead
and rice stem borer. The trained model is then used for detecting
pests in the captured images stored in Google Drive. Realtime
notification is sent when the insect pests of interest are
detected to users via the LINE application. Since the amount
of image data available to train the model is rather small, our
initial pest detection model can achieve only 65 percent accuracy.
We explored possibility in improving accuracy of the model by
conducting a comparison study between using an ensemble of
multiple binary-class pest classifiers versus the original single
multiple-class pest classifier. From our evaluation results, the
use of multiple binary-class classification method can improve
the accuracy/precision by up to 80 percent without the need to
increase training images.
King Mongkut's University of Technology North Bangkok. Central Library
Address:
BANGKOK
Email:
library@kmutnb.ac.th
Created:
2023
Modified:
2024-04-17
Issued:
2024-04-17
บทความ/Article
application/pdf
BibliograpyCitation :
In Institute of Electrical and Electronics Engineers. The 27th International Computer Science and Engineering Conference 2023 (ICSEC 2023) (pp.94-97). Bangkok : Institute of Electrical and Electronics Engineers
eng
©copyrights King Mongkut's University of Technology North Bangkok
RightsAccess:
ใช้เวลา
-0.964946 วินาที
Ratthapoom Rangubtook
| Title | Contributor | Type |
|---|---|---|
| Prototyping a low-cost pest detection system for CNT0718-26-1-1-1 rice farming
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Ratthapoom Rangubtook;Thapanan Plubplai;Supet Jirakajohnkool;Prapaporn Rattanatamrong | บทความ/Article |
Thapanan Plubplai
| Title | Contributor | Type |
|---|---|---|
| Prototyping a low-cost pest detection system for CNT0718-26-1-1-1 rice farming
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Ratthapoom Rangubtook;Thapanan Plubplai;Supet Jirakajohnkool;Prapaporn Rattanatamrong | บทความ/Article |
Supet Jirakajohnkool
| Title | Contributor | Type |
|---|---|---|
| Prototyping a low-cost pest detection system for CNT0718-26-1-1-1 rice farming
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Ratthapoom Rangubtook;Thapanan Plubplai;Supet Jirakajohnkool;Prapaporn Rattanatamrong | บทความ/Article | |
| Identification of risk areas for road traffic accidents using K-means clustering: a case study of Northern Thailand
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Kanwara Suwanthip;Supitchanut Chotpichet;Sangdao Wongsai;Noppachai Wongsai;Supet Jirakajohnkool | บทความ/Article |
Prapaporn Rattanatamrong
| Title | Contributor | Type |
|---|---|---|
| Overhead study of Telegraf as a real-time monitoring agent
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Prapaporn Rattanatamrong;Yoottana Boonpalit;Siwakorn Suwanjinda;Ayuth Mangmeesap;Subraties, Ken;Daneshmand, Vahid;Smallen, Shava ;Haga, Jason | บทความ/Article | |
| From bim to digital twin: a case study experience
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Prapaporn Rattanatamrong;Jarunchai Srisawat;Peemapat Podsoonthorn;Thapana Boonchoo;Wanida Putthividhya;Veerasak Likhitruangsilp | บทความ/Article | |
| Prototyping a low-cost pest detection system for CNT0718-26-1-1-1 rice farming
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Ratthapoom Rangubtook;Thapanan Plubplai;Supet Jirakajohnkool;Prapaporn Rattanatamrong | บทความ/Article | |
| Human-computer interaction for decision making in digital twins with various display environments
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Jarunchai Srisawat;Sutthida Patimakornpong;Prerapong Ramunudom;Wanida Putthividhya;Nuttanont Hongwarittorrn;Prapaporn Rattanatamrong | บทความ/Article |