Article Per Year (5 Year)
p-Index From 2021 - 2026
5.362
P-Index
This Author published in this journals
All Journal Bulletin of Electrical Engineering and Informatics Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI) International Journal of Advances in Intelligent Informatics Scientific Journal of Informatics JAIS (Journal of Applied Intelligent System) JOIN (Jurnal Online Informatika) Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Indonesian Journal of Artificial Intelligence and Data Mining JMM (Jurnal Masyarakat Mandiri) MATRIK : Jurnal Manajemen, Teknik Informatika, dan Rekayasa Komputer JISKa (Jurnal Informatika Sunan Kalijaga) Abdimasku : Jurnal Pengabdian Masyarakat Dinamika Informatika: Jurnal Ilmiah Teknologi Informasi Innovation in Research of Informatics (INNOVATICS) Journal of Soft Computing Exploration Prosiding Seminar Nasional Sisfotek (Sistem Informasi dan Teknologi Informasi) Journal of Information System Exploration and Research Journal of Electronics Technology Exploration (JOeTEx) Scientific Journal of Informatics Jurnal Panjar : Pengabdian Bidang Pembelajaran Journal of Vocational, Informatics and Computer Education Journal of Soft Computing Exploration Journal of Information System Exploration and Research
Jumanto Unjung
Department Of Computer Science, Universitas Negeri Semarang, Indonesia
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Health Professions Industrial & Manufacturing Engineering Library & Information Science Social Sciences Other

Published : 36 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 36 Documents
Search

 1   2   3   4 
Malaria Disease Detection System in Humans Using Convolutional Neural Network (CNN) Yana, Natasya Siska Fitri; Shabaha, Achmad Rozin; Unjung, Jumanto
Journal of Electronics Technology Exploration Vol. 3 No. 2 (2025): December 2025
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joetex.v3i2.646

Abstract

Malaria is a deadly disease transmitted by the Plasmodium parasite. Detection is performed by trained microscopists who analyze microscopic images of blood smears. This analysis can be done automatically using modern deep learning techniques. The need for skilled labor can be significantly reduced by developing accurate and efficient automated models. In this article, we propose a fully automated convolutional neural network (CNN)-based model for diagnosing malaria from microscopic images of blood smears. Various techniques including knowledge distillation, data augmentation, autoencoder, feature extraction with CNN model to optimize and improve model accuracy and reasoning performance. Our deep learning model can detect malaria parasites from microscopic images with 95% accuracy requiring more than 27,600 images. This shows that the mode is able to provide more accurate predictions compared to malaria disease detection models using other algorithms such as in previous studies with an accuracy of 90%. By using CNN algorithm, this article can contribute novelty in the development of effective malaria detection methods for malaria disease.
Optimization of SVM and Gradient Boosting Models Using GridSearchCV in Detecting Fake Job Postings Rofik Rofik; Roshan Aland Hakim; Jumanto Unjung; Budi Prasetiyo; Much Aziz Muslim
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 23 No. 2 (2024)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v23i2.3566

Abstract

Online job searching is one of the most efficient ways to do this, and it is widely used by people worldwide because of the automated process of transferring job recruitment information. The easy and fast process of transferring information in job recruitment has led to the rise of fake job vacancy fraud. Several studies have been conducted to predict fake job vacancies, focusing on improving accuracy. However, the main problem in prediction is choosing the wrong parameters so that the classification algorithm does not work optimally. This research aimed to increase the accuracy of fake job vacancy predictions by tuning parameters using GridSearchCV. The research method used was SVM and Gradient Boosting with parameter adjustments to improve the parameter combination and align it with the predicted model characteristics. The research process was divided into preprocessing, feature extraction, data separation, and modeling stages. The model was tested using the EMSCAD dataset. This research showed that the SVM algorithm can achieve the highest accuracy of 98.88%, while gradient enhancement produces an accuracy of 98.08%. This research showed that optimizing the SVM model with GridSearchCV can increase accuracy in predicting fake job recruitment.
Classification of Pancreatic Cancer Diagnosis with CatBoost Using Urine Biomarker Combination Tanga, Yulizchia Malica Pinkan; Utami, Putri; Darmawan, Aditya Yoga; Unjung, Jumanto
Journal of Electronics Technology Exploration Vol. 4 No. 1 (2026): June 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joetex.v4i1.651

Abstract

Uncontrolled cell growth in the pancreatic gland, is one of the most aggressive types of cancer with a high mortality rate, called pancreatic cancer. This research focuses on improving early diagnosis methods for pancreatic cancer by using CatBoost. Urine biomarker datasets were collected and subjected to pre-processing, including label coding, standardized scaling, and balancing via the Synthetic Minority Oversampling Technique (SMOTE). The CatBoost model achieved an accuracy of 98.89%, specificity of 99.35%, sensitivity of 98.71%, and Area Under the Curve (AUC) of 0.9951. These results show that the CatBoost model significantly outperforms the diagnosis models in previous studies, overcoming the challenges of early detection and classification of pancreatic cancer. This study shows that CatBoost is effective for diagnosing pancreatic cancer and suggests that future research explore other models on larger and more diverse datasets.
Hybrid Chi-Square and Binary Particle Swarm Optimization Feature Selection with Prior-Corrected Multinomial Naive Bayes for SMS Spam Detection Chrisandito Sebastian Erlangga Bia; Jumanto Unjung
Journal of Vocational, Informatics and Computer Education Vol 4, No 2 (2026): June 2026
Publisher : Academic Bright Collaboration

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66053/voice.v4i2.730

Abstract

Purpose – SMS spam remains a persistent cybersecurity threat, with 68% of mobile users exposed to unsolicited messages. Existing lightweight classifiers suffer from two compounding problems: feature representations that fail to capture semantic spam patterns, and class imbalance that biases probabilistic classifiers toward the majority class. This study proposes a unified pipeline that resolves both problems simultaneously. Methods – A dual feature extraction scheme combining TF-IDF with 12 empirically validated semantic features feeds a two-stage Chi-Square and Binary Particle Swarm Optimization (BPSO) feature selection pipeline. A Prior-Corrected Multinomial Naive Bayes (PC-MNB) recalibrates class priors at inference time to counteract Random Oversampling bias. Experiments were conducted on the UCI SMS Spam Collection. Findings – The proposed model achieved 98.07% accuracy, 95.45% macro F1, and 96.64% spam precision with only 4 false positives across 903 legitimate messages reducing false alarms by 89.5% over the strongest baseline. Research implications – Evaluation is limited to English-language SMS; generalization to multilingual corpora remains unvalidated. The rule-based semantic features are brittle against adversarial obfuscation, and BPSO incurs a one-time offline training cost of 10–25 minutes. Originality – This study is the first to integrate dual semantic-statistical feature extraction, filter-wrapper hybrid selection, and inference-time prior correction into a single CPU-deployable pipeline for SMS spam detection, distinguished from prior CS-BPSO work by domain, feature architecture, and probabilistic calibration mechanism. Future work will explore multilingual validation and SHAP-based explainability.
Deep Learning Model Implementation Using Convolutional Neural Network Algorithm for Default P2P Lending Prediction Tiara Lailatul Nikmah; Jumanto Jumanto; Budi Prasetiyo; Nina Fitriani; Much Aziz Muslim
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 9 No. 3 (2023): September
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v9i3.26366

Abstract

Peer-to-peer (P2P) lending is one of the innovations in the field of fintech that offers microloan services through online channels without intermediaries. P2P  lending facilitates the lending and borrowing process between borrowers and lenders, but on the other hand, there is a threat that can harm lenders, namely default.  Defaults on  P2P  lending platforms result in significant losses for lenders and pose a threat to the overall efficiency of the peer-to-peer lending system. So it is essential to have an understanding of such risk management methods. However, designing feature extractors with very complicated information about borrowers and loan products takes a lot of work. In this study, we present a deep convolutional neural network (CNN) architecture for predicting default in P2P lending, with the goal of extracting features automatically and improving performance. CNN is a deep learning technique for classifying complex information that automatically extracts discriminative features from input data using convolutional operations. The dataset used is the Lending Club dataset from P2P lending platforms in America containing 9,578 data. The results of the model performance evaluation got an accuracy of 85.43%. This study shows reasonably decent results in predicting p2p lending based on CNN. This research is expected to contribute to the development of new methods of deep learning that are more complex and effective in predicting risks on P2P lending platforms.
Enhancing diabetes classification performance using XGBoost integrated with SMOTE and bayesian hyperparameter optimization Muhammad Nurul Ihyaul Ulum; Jumanto Unjung
Journal of Soft Computing Exploration Vol. 7 No. 1 (2026): March 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i1.3

Abstract

Diabetes mellitus is a long-term metabolic disorder that is becoming more common around the world. Finding people at risk early can help prevent serious health problems and improve patient outcomes. Machine learning is often used to predict diabetes, but imbalanced medical data can make it harder for models to spot positive cases. In this study, we created a diabetes classification model by combining the Extreme Gradient Boosting (XGBoost) algorithm with the Synthetic Minority Over-sampling Technique (SMOTE), and we used Bayesian Optimization to fine-tune the model’s settings. We worked with the Pima Indians Diabetes Dataset, which has 768 patient records and eight clinical features. Our steps included preprocessing the data, splitting it into training and testing sets, using SMOTE to balance the training data classes, training the XGBoost model, and performing hyperparameter tuning using Bayesian Optimization with Stratified 5-Fold Cross-Validation to determine the optimal parameter configuration. The final model reached an accuracy of 0.88, a precision of 0.79, a recall of 0.91, an F1-score of 0.84, and a ROC-AUC of 0.955. These results show that our approach can identify diabetes cases more effectively while keeping strong overall performance.
Optimizing Stacking Ensemble Models for Customer Churn Prediction in the Telecommunications Industry Rofik Rofik; Jumanto Unjung; Dwika Ananda Agustina Pertiwi; Much Aziz Muslim
JOIN (Jurnal Online Informatika) Vol 11 No 1 (2026)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v11i1.1783

Abstract

One of the biggest challenges in the telecommunications industry is predicting churn, which is the condition when a customer unsubscribes and switches to another service provider. In an era of competitive market conditions, retaining customers is much more efficient than acquiring new customers. Conventional prediction models are often unable to capture the complexity of customer behavior patterns, resulting in a lower accuracy than optimal. This study aims to optimize customer churn prediction performance by developing a stacking ensemble model that combines several classification algorithms to improve model performance. Fourteen algorithms were tested, and the six algorithms with the best accuracy were selected as base learners, while Logistic Regression was selected as the meta-learner. The stacking model testing was carried out sequentially through a combination of 6 algorithms with the same meta-learner algorithm. Testing was also carried out with and without using the SMOTE data balancing method to evaluate the effect of data balancing on the prediction results. The results of this study show that the combination of the Adaboost, Ridge Classifier, and Logistic Regression algorithms can produce the highest accuracy of 82.97%, which exceeds the prediction performance of a single algorithm. This research contributes to demonstrating an effective stacking ensemble configuration for predicting customer churn in the telecommunications industry and emphasizes that the selection of the right algorithm combination has a greater impact on model performance than the number of algorithms used.
Strengthening the Preparedness of Elementary School Physical Education Teachers in Injury Prevention and Initial Emergency Response Adi S; Cahyo Yuwono; Sugianto Parulian Simanjuntak; Dicky Budhi Setyawan; Jumanto; Ummi Nur Laila Sulistyani; Erika Afriana; Karina Permata Andhini
Jurnal Panjar: Pengabdian Bidang Pembelajaran Vol. 6 No. 1 (2026)
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/panjar.v6i1.52281

Abstract

The limited preparedness of elementary school Physical Education (PE) teachers in managing injuries and emergency situations remains a significant challenge for ensuring student safety. This community service programme aimed to strengthen teachers’ competencies in injury prevention, emergency response, and school safety management through an integrated training and mentoring approach. The programme involved 33 PE teachers from the Physical Education Teachers’ Working Group (KKG PJOK) in Gunungpati Sub-district, Semarang, Indonesia. Activities included needs assessment, training on school safety management, injury prevention, first aid, Emergency Cardiac Care (ECC), cardiopulmonary resuscitation (CPR), simulation-based practice, the development of school safety Standard Operating Procedures (SOPs), and the implementation of SIGAPEdu as a digital injury reporting system. Programme effectiveness was evaluated using pre-test and post-test assessments, practical performance observations, and monitoring of programme outputs. The results demonstrated substantial improvements in teachers’ knowledge and practical competencies. The mean knowledge score increased from 58.24 ± 9.17 in the pre-test to 86.73 ± 6.84 in the post-test, representing an overall improvement of 48.9%. The proportion of teachers capable of performing basic CPR increased from 12.1% to 84.8%, exceeding the programme target of 80%. Furthermore, school-based safety SOPs were developed and implemented, three safety-oriented PE teaching materials were produced, and SIGAPEdu was adopted by 72.7% of participants, surpassing the predetermined target. These outcomes indicate that the programme successfully strengthened teachers’ emergency preparedness, promoted the integration of safety principles into PE learning, and supported the development of data-driven school safety practices. Continuous implementation of similar programmes is recommended to foster safer and higher-quality learning environments in schools. 
A comparative benchmark of vision transformer architectures for chili leaf disease classification Acihmah Sidauruk; Danang Wijayanto; I Made Artha Agastya; Jumanto Unjung; Mulia Sulistiyono
Journal of Soft Computing Exploration Vol. 7 No. 3 (2026): September 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joscex.v7i3.62

Abstract

Chili plant disease detection represents a critical component for enhancing agricultural productivity. Although Convolutional Neural Networks (CNN) have demonstrated promising results, they encounter limitations in capturing global contextual relationships within images. However, existing Vision Transformer studies on plant disease commonly assess only a single architecture, leaving the relative performance of different Vision Transformer families on chili disease data largely unexamined. This research aims to conduct a comparative benchmark analysis of five Vision Transformer-based architectures ViT, Swin Transformer, MaxViT, DINOv2, and EVA-02 to identify the most optimal model for chili plant disease classification. The methodology begins with data preprocessing and augmentation on a chili leaf dataset comprising five classes: healthy, leaf curl, leaf spot, whitefly, and yellowish. Each model is then fine-tuned under consistent training configurations with early stopping to prevent overfitting, and evaluated using accuracy, precision, recall, F1-score, and AUC. The results indicate that DINOv2 achieves superior performance with 96% accuracy, 96% precision, 96% recall, 96% F1-score, and 99% AUC, along with the highest training efficiency through convergence at epoch 12, outperforming ViT (92%), Swin (88%), MaxViT (88%), EVA-02 (86%), and previous CNN-based approaches. These findings confirm the superior potential of Vision Transformers, particularly self-supervised models, as a promising alternative for agricultural disease detection applications. The main contribution of this study is the first unified, head-to-head benchmark of five distinct Vision Transformer families for chili leaf disease classification, providing practical guidance on model selection in terms of both accuracy and training efficiency.
Performance Comparison of Naive Bayes and Support Vector Machine Algorithms in Sentiment Analysis of TIX ID Application Reviews Using VADER Automatic Labeling Zenia Kumala Rizka; Jumanto Unjung; Zaki Zaini
Journal of Information System Exploration and Research Vol. 4 No. 2: April 2026
Publisher : SHM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52465/joiser.v4i2.3

Abstract

This study compares the sentiment classification performance of Naive Bayes and Support Vector Machine (SVM). It uses 28247 user reviews for the Google Play Store app TIX ID collected from Kaggle. The reviews were first translated into English, then their sentiment was labeled using VADER. After completing text preprocessing, feature extraction via TF-IDF combined with 1-gram and 2-gram features, and class balancing through random oversampling, test results show that SVM achieved an accuracy of 93.45% and an F1-score of 93.78%, which outperforms Naive Bayes’ respective scores of 90.90% accuracy and 91.72% F1-score. Experiments in this study found that the Support Vector Machine (SVM) outperformed Naive Bayes across all three evaluation metrics: precision, recall, and F1-score. This verifies that the approach consisting of VADER annotation, TF-IDF feature extraction, and SVM can effectively conduct sentiment analysis on mobile application reviews, and meets the needs of the industry.
Co-Authors Abas Setiawan Acihmah Sidauruk Adi S Al Qohar, Bagus Alamsyah - Anisa, Devi Nurul Annisaa Utami Budi Prasetiyo Budi Prasetiyo Budi Prasetiyo, Budi Cahyo Yuwono Ceorido Ghalib Wibowo Chrisandito Sebastian Erlangga Bia DAA Pertiwi Danang Wijayanto Darmawan, Aditya Yoga Devi Ajeng Efrilianda Dicky Budhi Setyawan Dimas Fanny Hebrasianto Permadi Dullah, Ahmad Ubai Dwika Ananda Agustina Pertiwi Dwika Ananda Agustina Pertiwi Dwika Ananda Agustina Pertiwi Dwika Ananda Agustina Pertiwi Endang Sugiharti, Endang Erika Afriana Farih, Habib al Fathimah Az Zahra Sanjani Franki SW Gea Destadia Al-Zahra Heri Ardiyanto I Made Artha Agastya Kamilah Ahmad Karina Permata Andhini Khalidah, Saidatul M. Faris Al Hakim M. Faris Al Hakim Maylinna Rahayu Ningsih Maylinna Rahayu Ningsih Maylinna Rahayu Ningsih Much Aziz Muslim Much Aziz Muslim Much Aziz Muslim Much Aziz Muslim Much Aziz Muslim Much. Aziz Muslim Muhammad Nurul Ihyaul Ulum Mulia Sulistiyono Nina Fitriani Ningsih, Maylinna Rahayu Nurul Hidayat Pertiwi, Dwika Ananda Agustina Prabowo Yudho Jayanto Purwoko, Agus Putri Utami, Putri Qohar, Bagus Al Rianto, Nur Azis Kurnia Riza Arifudin Riza Arifudin Rofik Rofik Rofik Rofik Rofik Rofik Rofik Rofik, Rofik Roshan Aland Hakim Shabaha, Achmad Rozin Shahrul Nizam Bin Salahudin Sidiq Noor Kharisma Sugianto Parulian Simanjuntak Syamsudin, Hilmi Tanga, Yulizchia Malica Pinkan Tiara Lailatul Nikmah Ummi Nur Laila Sulistyani Wibowo, Kevyn Alifian Hernanda Yana, Natasya Siska Fitri Yesy Diah Rosita Yopi Julia Nurriski Zaenal Abidin Zaki Zaini Zenia Kumala Rizka