แจ้งเอกสารไม่ครบถ้วน, ไม่ตรงกับชื่อเรื่อง หรือมีข้อผิดพลาดเกี่ยวกับเอกสาร ติดต่อที่นี่ ==>
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
Siriporn Supratid. Impacts of ResNet skip connection levels on inception convolutional neural network using different resized images in object recognition. (). King Mongkut's University of Technology North Bangkok. Central Library. : , 2023.
Impacts of ResNet skip connection levels on inception convolutional neural network using different resized images in object recognition
Name: Tatpon Kongkertsuk
Organization :
Rangsit University. College of Digital Innovation Technology
Email :
tatpon.k64@rsu.ac.th
Name: Siriporn Supratid
Organization :
Rangsit University. College of Digital Innovation Technology
Email :
siriporn.su@rsu.ac.th
keyword:
ResNet
ThaSH:
Optical pattern recognition
Abstract:
This paper focuses on impacts of using 1 -and 2 -level ResNet skip connection on inception convolutional neural network (ICNN), named here as 1L - and 2L -ICRN in object recognition. The 1L - and 2L -ICRN as well as ICNN are brought into comparison studies using CIFAR-10 image dataset, with 70×70, 90×90 and 110×110 resized images. Recognition performance appraisements count on averages of F1, accuracy scores, recall and precision, relying upon 5-fold cross validation for bias reduction purpose. Confusion matrix is also examined for more detail of results inspection. The results denote that 1L-ICRN yields 83.02 percent, 84.85 percent, 85.06 percent best recognition accuracy based on 70×70, 90×90 and 110×110 images, consecutively. However, using 70×70 images, 1L-ICRN generates 1.05 percent and 1.68 percent more accuracy than 2L-ICRN and ICNN, respectively. As image size increases, 1L - and 2L -ICRN generate better performance but in decreasing rate; whilst, ICNN exhibits decreasing performance when expanding the size from 90×90 to 110×110. Nevertheless, at most, 2-second difference of time consumed by each model is pointed, which is insignificant.
King Mongkut's University of Technology North Bangkok. Central Library
Address:
BANGKOK
Email:
library@kmutnb.ac.th
Created:
2023
Modified:
2024-12-03
Issued:
2024-12-03
บทความ/Article
application/pdf
BibliograpyCitation :
In Electrical Engineering Academic Association (Thailand), Mahasarakham University. Faculty of Engineering and ASEFA. The 2023 International Electrical Engineering Congress (iEECON 2023) (pp.109-112). Mahasarakham : Mahasarakham University
eng
©copyrights King Mongkut's University of Technology North Bangkok
RightsAccess:
ใช้เวลา
0.038409 วินาที
Tatpon Kongkertsuk
| Title | Contributor | Type |
|---|---|---|
| Impacts of ResNet skip connection levels on inception convolutional neural network using different resized images in object recognition
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Tatpon Kongkertsuk;Siriporn Supratid | บทความ/Article |
Siriporn Supratid