Article Per Year (5 Year)
p-Index From 2020 - 2025
0.444
P-Index
This Author published in this journals
All Journal Indonesian Journal of Electrical Engineering and Computer Science JURNAL POLI-TEKNOLOGI
Wiwi Prastiwinarti
Politeknik Negeri Jakarta
Aerospace Engineering Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Materials Science & Nanotechnology Mechanical Engineering Transportation

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Efficient packaging defect detection: leveraging pre-trained vision models through transfer learning Wiwi Prastiwinarti; Mera Kartika Delimayanti; Hendra Kurniawan; Yoga Putra Pratama; Hanin Wendho; Rizky Adi
Indonesian Journal of Electrical Engineering and Computer Science Vol 34, No 3: June 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v34.i3.pp2096-2106

Abstract

The inspection of packaging defects is a crucial aspect of maintaining the quality of industrial production, especially in the case of boxed products. This study introduces a novel approach for detecting physical defects in product packaging boxes by integrating image processing with deep learning, specifically transfer learning with two images as an input. The proposed method utilizes both top view and side view images of the packaging to determine its condition, a significant departure from the conventional single image input. Our approach incorporates 16 pre-trained model variants from EfficientNetV2, MobileNetV3, and ResNetV2 for transfer learning as feature extractors. The experimental findings demonstrate that the best model that leverages EfficientNetV2 variant achieves 100% accuracy and F1 score in terms of classification performance. However, the most optimal model in terms of classification performance and inference speed was the one that leveraged ResNetV2 variant. This model scored 95% accuracy and 95.24% F1 score, with an inference speed of 91 ms per prediction.
Analisis Tingkat Kecacatan Produk Cetak Kemasan Karton Lipat Dengan Pendekatan DMAIC Six Sigma Saeful Imam; Wiwi Prastiwinarti
Jurnal Poli-Teknologi Vol. 19 No. 2 (2020)
Publisher : Politeknik Negeri Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32722/pt.v19i2.2951

Abstract

The map of competition in the business world in the industrial sector makes consumers' demands on the quality of products produced even higher so that the industry has an obligation to provide the best service to consumers in order to maintain the sustainability of its business. This is evenly distributed in all industrial sectors including the printing industry. Based on preliminary observations at one of the large printing presses in Jabodetabek the failure rate of printed folding carton packaging products produced is still quite large. The integrated production process makes the process results affect each other the number of defects in the next process. The results of observations show that of the 3 main processes of folding cardboard packaging production at PT.X, the aim of printing and ponding has the highest defect percentage of 47% and 44% of the total defect, while the glueing  process has the lowest percentage of 7% with a total total defect of 827,347 packages of a total production of 4,735,350. From the results of data recapitulation and calculation of the number of defects, it can be seen that the sigma value of the company with the sample production data taken has an average sigma of 3.6. Through the application of the Six Sigma DMAIC method this research seeks to provide solutions in overcoming the problems of defective products that occur during the production process so that the main purpose of the printing industri in increasing productivity can be achieved.
Co-Authors Hanin Wendho Hendra Kurniawan Mera Kartika Delimayanti Rizky Adi Saeful Imam, Saeful Yoga Putra Pratama