Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Knowledge Engineering and Data Science ILKOM Jurnal Ilmiah
Pradnyana, I Putu Bagus Arya
Unknown Affiliation
Computer Science & IT Engineering

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

Found 2 Documents
Search

 1 
Comparative Performance Analysis of Modified VGG16 and Slim-CNN for Arabica Coffee Bean Defect Classification Ardian, Yusriel; Astawa, I Nyoman gede Arya; Irawan, Novta Danyel; Pradnyana, I Putu Bagus Arya; Sulistyo, Agung
ILKOM Jurnal Ilmiah Vol 18, No 1 (2026)
Publisher : Prodi Teknik Informatika FIK Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v18i1.3244.85-96

Abstract

Defect detection in Arabica coffee beans is a critical aspect of quality control, particularly for export-oriented commodities that require consistent visual standards and uniform quality across production batches. Black and partial-black defects are known to significantly affect market value, quality perception, and sensory characteristics. Meanwhile, manual inspection processes remain vulnerable to evaluator subjectivity and inter-operator inconsistency.This study aims to conduct a comparative analysis between a Modified VGG16 architecture and Slim-CNN for detecting these two defect categories using a deep learning-based Convolutional Neural Network (CNN) approach. The dataset consists of 4,080 high-resolution images of Arabica green coffee beans captured using a 24.2 MP macro camera under controlled lighting conditions to minimize shadows and visual distortion. To preserve the natural characteristics of the defects, minimal data augmentation was applied using cropping and 15-degree rotation techniques. The Modified VGG16 architecture was simplified by reducing the complexity of the fully connected layers, integrating batch normalization, and applying dropout to enhance training stability and computational efficiency. Slim-CNN was employed as a lightweight comparative model with fewer parameters and lower memory requirements, making it suitable for resource-constrained deployment scenarios. Four training schemes were evaluated using variations in learning rate and epoch number to assess configuration impacts on performance. Experimental results show that Modified VGG16 achieved the highest test accuracy of 86.7% at a learning rate of 0.001 with 3 epochs, demonstrating a strong balance between training and validation accuracy. Slim-CNN exhibited shorter training time and lower computational complexity, although with slightly lower classification accuracy compared to Modified VGG16. These findings highlight a trade-off between classification performance and computational efficiency in selecting CNN architectures for coffee bean defect detection. Although the results demonstrate potential for industrial automatic classification systems, further validation using larger datasets and more comprehensive evaluation schemes is required to improve model generalization. This study contributes to the development of a more measurable, adaptive, and efficient deep learning-based coffee quality inspection system to support agro-export industry requirements.
Social Media Mining with Fuzzy Text Matching: A Knowledge Extraction on Tourism After COVID-19 Pandemic Manuaba, Ida Bagus Putra; Sentana, I Wayan Budi; Astawa, I Nyoman Gede Arya; Suasnawa, I Wayan; Pradnyana, I Putu Bagus Arya
Knowledge Engineering and Data Science
Publisher : citeus

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Social media mining is an emerging technique for analyzing data to extract valuable knowledge related to various domains. However, traditional text matching techniques, such as exact matching, are not always suitable for social media data, which can contain spelling mistakes, abbreviations, and variations in the use of words. Fuzzy matching is a text matching technique that can handle such variations and identify similarities between two texts, even if there are differences in spelling or phrasing. The gap in existing research is the limited use of fuzzy matching in social media mining for tourism recovery analysis. By applying fuzzy matching to social media data related to COVID-19 and tourism recovery, this research seeks to bridge this gap and extract valuable insights related to the impact of the pandemic on tourism recovery. We manually retrieved 19,462 Twitter records and differentiated the data sources using four diver parameters to indicate data related to the impact of COVID-19 on the tourism industry, such as the economy, restrictions, government policies, and vaccination. We conducted text mining analysis on the collected 7,352 words and identified 25 highly recommended words that indicated COVID-19 recovery from a tourism perspective. We separated the four words representing the tourism perspective to perform fuzzy matching as a dataset. We then used the inbound dataset on the fuzzy matching process, with the 7,352-word data collected from the text mining process. The matching process resulted in 18 words representing COVID-19 recovery from a tourism perspective.
Co-Authors Agung Sulistyo I Nyoman Gede Arya Astawa I Wayan Budi Sentana, I Wayan Budi Ida Bagus Putra Manuaba Irawan, Novta Danyel Suasnawa, I Wayan Yusriel Ardian