Article Per Year (5 Year)
p-Index From 2021 - 2026
0.817
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah Kursor Tibuana : Journal of Applied Industrial Engineering Information Technology International Journal (ITIJ)
Hadi, Surjo
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management Electrical & Electronics Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Analysis of Factors Affecting Minimum Salary of Workers in Indonesia Using Binary Logistic Regression Hadi, Surjo; Renaldi, Sahat; Trimono, Trimono; Susrama Mas Diyasa , I Gede
Information Technology International Journal Vol. 2 No. 1 (2024): Information Technology International Journal
Publisher : Magister Teknologi Informasi UPN "Veteran" Jawa Timur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33005/itij.v2i1.20

Abstract

Salary is an important indicator used to measure the compensation and recognition individuals receive for their contributions to the workforce. Investigating the factors that influence salary levels is an intriguing research area. This study uses a logistic regression approach to analyze the relationship and influence of job field, job level, company location, and tenure on workers' salaries in Indonesia. The research findings reveal that the variables of job level and company location have a significant relationship with the minimum salary level received by workers. Based on the logistic regression modeling results, the variables that influence the minimum salary level are the company location (foreign) and average tenure
Implementation Of Hybrid EfficientNet V2 And Vision Transformer for Apple Leaf Diseases Classification Santoso, Sri Fuji; Hadi, Surjo; Nugroho, Budi; Mas Diyasa, I Gede Susrama
Information Technology International Journal Vol. 3 No. 1 (2025): Information Technology International Journal
Publisher : Magister Teknologi Informasi UPN "Veteran" Jawa Timur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33005/itij.v3i1.42

Abstract

The apple farming industry faces challenges in managing apple leaf diseases. Current manual detection methods have limitations in expertise variability, time required, potential delays in identification leading to disease spread, and difficulty distinguishing diseases with similar visual symptoms. This research aims to develop an accurate, efficient, and automated apple leaf disease classification system using a hybrid approach that combines EfficientNet V2 architecture and Vision Transformer. The main objectives are to improve disease detection accuracy, reduce computational requirements, facilitate more effective plant management, and support modern agricultural practices in the apple industry. This research uses a hybrid deep learning model that integrates EfficientNet V2 and Vision Transformer components. Experiments were conducted on an apple leaf disease dataset to evaluate model performance. Results show the effectiveness of this method in classifying apple leaf diseases, achieving 98.56% accuracy and an F1 score of 0.9856 on test data. The proposed model has 15.6 million parameters, lighter than the original EfficientNetV2S model with 20 million parameters. Training time was reduced to 6 minutes 32 seconds compared to the original EfficientNetV2S model that required 8 minutes 41 seconds for 5 epochs on the same dataset.
Convolutional layer exertion on few-shot learning for brain tumor classification Sunarko, Victor Immanuel; Puspaningrum, Eva Yulia; Widiastuty, Riana Retno; Hadi, Surjo; Awang, Mohd Khalid; Mas Diyasa, I Gede Susrama
Jurnal Ilmiah Kursor Vol. 13 No. 2 (2025)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/kursor.v13i2.430

Abstract

Brain tumors, though relatively rare, pose a significant threat due to their critical location within the brain, impacting essential bodily functions. Accurate and timely diagnosis is vital, but traditional diagnostic methods are time-intensive and rely heavily on large labeled datasets. This study addresses these challenges by proposing a Few-Shot Learning (FSL) framework enhanced with Convolutional Neural Networks (CNNs) to classify brain tumors using MRI images. By employing the Matching Network architecture, the model leverages limited training data through an N-way-K-shot setup. Training results demonstrated accuracy levels of 71.58% (1-shot) and 82.89% (5-shot) for 1-layer CNNs, 66.65% (1-shot) and 84.03% (5-shot) for 3-layer CNNs, and 63.43% (1-shot) and 84.94% (5-shot) for 5-layer CNNs. However, validation accuracy revealed overfitting concerns, with the highest performance at 51.56% (1-layer, 1-shot). These results underscore the potential of FSL in medical imaging while highlighting the need for advanced augmentation and feature representation techniques to improve generalization.
The Usage of Monte Carlo Simulation to Predict The Sales of Sustainable Batik Products in Small Medium Enterprise Ayu, Manik; Hadi, Surjo; Nafiuddin, Muhammad Rizky
Tibuana Vol 6 No 1 (2023): Tibuana
Publisher : UNIPA PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36456/tibuana.6.1.6315.65-70

Abstract

As an intangible cultural heritage, Indonesian Batik continues to develop and is increasingly in demand by domestic and foreign people. In the current era, the concept of making batik that is sustainable or more environmentally friendly has emerged, one of the efforts is in terms of coloring that uses natural dyes. This innovation produces softer batik colors aka soil colors, besides that the manufacturing process is longer than using chemical dyes, so the price is more expensive. With these changes, analyzing the development of sustainable batik sales is important to identify an increase in sales. This study aims to determine the prediction of sustainable batik sales with Monte Carlo simulations precisely and accurately. The data processed is batik production using natural dyes, then converted into probability distributions in the form of compulsive frequencies and then generated random numbers to obtain random numbers. After that, group the interval limit of the random number that has been obtained and continue with the simulation process so that it gets the simulation results and the percentage of accuracy using the Monte Carlo method. The results of the study on data processing from 2020 to 2021 have an accuracy of 90%. So this research is very appropriate for predicting sales for the next year.
Co-Authors Awang, Mohd Khalid Ayu, Manik Budi Nugroho Eva Yulia Puspaningrum I Gede Susrama Mas Diyasa Nafiuddin, Muhammad Rizky Renaldi, Sahat Santoso, Sri Fuji Sunarko, Victor Immanuel Susrama Mas Diyasa , I Gede Trimono, Trimono Widiastuty, Riana Retno