Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal International Journal of Quantitative Research and Modeling
Panji Agung
Indonesian Operations Research Association, Bandung, Indonesia
Computer Science & IT Decision Sciences, Operations Research & Management Engineering Environmental Science Physics

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

Found 2 Documents
Search

 1 
Analysis of the Impact of Lean Manufacturing Implementation on Assembly Line Efficiency: A Quantitative Study Audrey Ariij Sya'imaa HS; Panji Agung
International Journal of Quantitative Research and Modeling Vol. 7 No. 3 (2026): International Journal of Quantitative Research and Modeling (IJQRM)
Publisher : Research Collaboration Community (RCC)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijqrm.v7i3.1447

Abstract

Manufacturing organisations increasingly require production systems that can improve operational efficiency while reducing process variation, waiting time, resource losses, and production errors. Lean manufacturing provides an established framework for addressing these challenges, yet empirical evidence remains limited regarding the simultaneous contribution of distinct lean practices to assembly-line efficiency. This study examines the effects of 5S, Kaizen, Just-in-Time, and Standardized Work on assembly-line efficiency using a quantitative explanatory design and a cross-sectional survey. Data were obtained from 262 employees involved in assembly-line operations, of which 260 valid responses were retained after data screening. The constructs were measured using a structured five-point Likert-scale questionnaire and analysed using partial least squares structural equation modelling. The measurement model demonstrated satisfactory reliability, convergent validity, and discriminant validity, while collinearity diagnostics indicated no substantive multicollinearity. The structural results show that all four lean practices positively and significantly contribute to assembly-line efficiency. Standardized Work demonstrates the strongest contribution, followed by 5S, Just-in-Time, and Kaizen. Collectively, the four practices explain 51.6% of the variance in assembly-line efficiency and demonstrate meaningful predictive relevance. The findings indicate that lean manufacturing should be operationalised as a multidimensional system rather than a homogeneous managerial construct. From a managerial perspective, assembly-line improvement should prioritise work standardisation while simultaneously strengthening workplace organisation, material-flow synchronisation, and continuous improvement to achieve more consistent and sustainable operational performance.
A Quantitative Study on the Accuracy of Deep Learning Algorithms in Classifying Machine Component Image Defects Hilda Azkiyah; Panji Agung; Astrid Sulistya
International Journal of Quantitative Research and Modeling Vol. 7 No. 3 (2026): International Journal of Quantitative Research and Modeling (IJQRM)
Publisher : Research Collaboration Community (RCC)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46336/ijqrm.v7i3.1454

Abstract

Automated visual inspection increasingly relies on deep learning to identify machine-component damage with high accuracy and consistent performance. However, direct comparison among architectures remains difficult because differences in data preparation, training procedures, and evaluation protocols can substantially affect reported results. This study quantitatively evaluates four deep learning architectures—conventional convolutional neural network, ResNet50, EfficientNet-B0, and MobileNetV3—for multi-class classification of machine-component images comprising Normal, Crack, Wear, Deformation, and Corrosion categories. A dataset of 1,230 images was processed using standardized preprocessing, stratified 70:15:15 partitioning, training-only augmentation, and a common model-development procedure. Performance was assessed using accuracy, macro-precision, macro-recall, macro-F1-score, confusion matrices, repeated five-fold cross-validation, feature-importance analysis, and computational indicators. On the independent test set, the baseline convolutional neural network, EfficientNet-B0, and MobileNetV3 achieved perfect classification performance, with accuracy and macro-F1-score of 1.000, whereas ResNet50 achieved 0.989 accuracy and 0.988 macro-F1-score. Cross-validation provided a more nuanced result: ResNet50 obtained the highest mean macro-F1-score (0.9934) and the lowest variability (SD = 0.0021), while the difference between the baseline convolutional neural network and EfficientNet-B0 was not statistically significant. No model misclassified a damaged component as Normal. Feature-importance analysis identified a concentrated contribution from selected image-derived descriptors, while MobileNetV3 demonstrated the lowest computational burden. The findings demonstrate that predictive performance, stability, interpretability, and computational efficiency should be jointly considered when evaluating deep learning models for industrial visual inspection.
Co-Authors Astrid Sulistya Audrey Ariij Sya'imaa HS Hilda Azkiyah