cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Risa Suryana
Contact Email
rsuryana@uns.ac.id
Phone
-
Journal Mail Official
ijap@uns.ac.id
Editorial Address
-
Location
Kota surakarta,
Jawa tengah
INDONESIA
INDONESIAN JOURNAL OF APPLIED PHYSICS
Published by Universitas Sebelas Maret
ISSN : 20890133     EISSN : 24776416     DOI : -
Core Subject : Science,
Astronomy Energy Materials Science & Nanotechnology Physics
Indonesia Journal of Apllied Physics provides rapid publication of short reports and important research in all fields of physics. Indonesia Journal of Apllied Physics publishes articles that are of significance in their respective fields whilst also contributing to the disclipline of physics as a whole. Articles should be submitted to the Editorial Office of Indonesia Journal of Apllied Physics through this site. Further information on submission is also available at this site
Arjuna Subject : -
Articles 11 Documents
 1   2 
Search results for , issue "Vol 14, No 1 (2024): April" : 11 Documents clear
A Comparison of CNN-based Image Feature Extractors for Weld Defects Classification Tito Wahyu Purnomo; Harun Al Rasyid Ramadhany; Hapsara Hadi Carita Jati; Djati Handoko
INDONESIAN JOURNAL OF APPLIED PHYSICS Vol 14, No 1 (2024): April
Publisher : Department of Physics, Sebelas Maret University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.13057/ijap.v14i1.72509

Abstract

Classification of the types of weld defects is one of the stages of evaluating radiographic images, which is an essential step in controlling the quality of welded joints in materials. By automating the weld defects classification based on deep learning and the CNN architecture, it is possible to overcome the limitations of visually or manually evaluating radiographic images. Good accuracy in classification models for weld defects requires the availability of sufficient datasets. In reality, however, the radiographic image dataset accessible to the public is limited and imbalanced between classes. Consequently, simple image cropping and augmentation techniques are implemented during the data preparation stage. To construct a weld defect classification model, we proposed to utilize the transfer learning method by employing a pre-trained CNN architecture as a feature extractor, including DenseNet201, InceptionV3, MobileNetV2, NASNetMobile, ResNet50V2, VGG16, VGG19, and Xception, which are linked to a simple classification model based on multilayer perceptron. The test results indicate that the three best classification models were obtained by using the DenseNet201 feature extractor with a test accuracy value of 100%, followed by ResNet50V2 and InceptionV3 with an accuracy of 99.17%. These outcomes are better compared to state-of-the-art classification models with a maximum of six classes of defects. The research findings may assist radiography experts in evaluating radiographic images more accurately and efficiently.

Page 2 of 2 | Total Record : 11

 1   2 

Filter by Year

2024 2024


Reset
Filter By Issues
All Issue Vol 14, No 1 (2024): April Vol 13, No 2 (2023): IJAP Volume 13 ISSUE 02 YEAR 2023 Vol 13, No 1 (2023): IJAP Volume 13 ISSUE 01 YEAR 2023 Vol 13, No 2 (2023): October Vol 13, No 1 (2023): April Vol 12, No 2 (2022): IJAP Volume 12 ISSUE 02 YEAR 2022 Vol 12, No 1 (2022): IJAP Volume 12 ISSUE 01 YEAR 2022 Vol 12, No 2 (2022): October Vol 12, No 1 (2022): April Vol 11, No 2 (2021): IJAP Volume 11 ISSUE 02 YEAR 2021 Vol 11, No 1 (2021): IJAP Volume 11 ISSUE 01 YEAR 2021 Vol 11, No 2 (2021): October Vol 11, No 1 (2021): April Vol 10, No 01 (2020): IJAP Volume 10 ISSUE 01 YEAR 2020 Vol 10, No 2 (2020): IJAP Volume 10 ISSUE 02 YEAR 2020 Vol 10, No 01 (2020): April Vol 10, No 2 (2020): October Vol 9, No 02 (2019): IJAP Volume 9 ISSUE 02 YEAR 2019 Vol 9, No 01 (2019) : IJAP Volume 9 ISSUE 01 YEAR 2019 Vol 9, No 02 (2019): October Vol 9, No 01 (2019): April Vol 8, No 02 (2018) : IJAP Volume 8 ISSUE 02 YEAR 2018 Vol 8, No 1 (2018) : IJAP Volume 8 ISSUE 01 YEAR 2018 Vol 8, No 2 (2018): October Vol 8, No 1 (2018): April Vol 7, No 2 (2017): IJAP Volume 07 ISSUE 02 YEAR 2017 Vol 7, No 1 (2017): IJAP Volume 07 ISSUE 01 YEAR 2017 Vol 7, No 2 (2017): October Vol 7, No 1 (2017): April Vol 6, No 02 (2016): IJAP Volume 06 Issue 02 Year 2016 Vol 6, No 01 (2016): IJAP VOLUME 06 ISSUE 01 YEAR 2016 Vol 6, No 02 (2016): October Vol 6, No 01 (2016): April Vol 5, No 02 (2015): IJAP Volume 05 Issue 02 Year 2015 Vol 5, No 01 (2015): IJAP Volume 05 Issue 01 Year 2015 Vol 5, No 02 (2015): October Vol 5, No 01 (2015): April Vol 4, No 02 (2014): IJAP Volume 04 Issue 02 Year 2014 Vol 4, No 01 (2014): IJAP Volume 04 Issue 01 Year 2014 Vol 4, No 02 (2014): October Vol 4, No 01 (2014): April Vol 3, No 02 (2013): IJAP VOLUME 03 ISSUE 02 YEAR 2013 Vol 3, No 01 (2013): IJAP VOLUME 03 ISSUE 01 YEAR 2013 Vol 3, No 02 (2013): October Vol 3, No 01 (2013): April Vol 2, No 02 (2012): IJAP VOLUME 02 ISSUE 02 YEAR 2012 Vol 2, No 02 (2012): October More Issue