Claim Missing Document
Check
Articles

Found 18 Documents
Search

Multi-Class Brain Tumor Segmentation and Classification in MRI Using a U-Net and Machine Learning Model Hendrik, Jackri; Pribadi, Octara; Hendri, Hendri; Hoki, Leony; Tarigan, Feriani Astuti; Wijaya, Edi; Ali, Rabei Raad
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 5 (2025): JUTIF Volume 6, Number 5, Oktober 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.5.5369

Abstract

Brain tumor diagnosis remains a critical challenge in medical imaging, as accurate classification and precise localization are essential for effective treatment planning. Traditional diagnostic approaches often rely on manual interpretation of MRI scans, which can be time-consuming, subjective, and prone to variability across radiologists. To address this limitation, this study proposes a two-stage framework that integrates machine learning (ML) based classifiers for tumor type recognition and a U-Net architecture for tumor segmentation. The classifier was trained to distinguish four tumor categories: glioma, meningioma, pituitary, and no tumor, while the U-Net model was employed to delineate tumor regions at the pixel level, enabling volumetric assessment. The novelty of this research lies in its dual focus that combines classification and segmentation within a single framework, which enhances clinical applicability by offering both diagnostic and spatial insights. Experimental results demonstrated that among the evaluated classifiers, XGBoost achieved the highest accuracy of 86 percent, surpassing other models such as Random Forest, SVC, and Logistic Regression, while the U-Net model delivered consistent segmentation performance across tumor types. These findings highlight the potential of hybrid ML and deep learning solutions to improve reliability, efficiency, and objectivity in brain tumor analysis. In real-world practice, the proposed framework can serve as a valuable decision-support tool, assisting radiologists in early detection, reducing diagnostic workload, and supporting personalized treatment strategies.
Comparative Analysis of Four Machine Learning Algorithms for Smoke Detection Using SMOTE-Rebalanced Sensor Data Liecero, Marcus; Robet, Robet; Hendrik, Jackri
Sinkron : jurnal dan penelitian teknik informatika Vol. 10 No. 1 (2026): Article Research January 2026
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v10i1.15546

Abstract

Smoke detection plays a critical role in preventing fire-related hazards, particularly in intelligent monitoring and early warning systems. Conventional smoke sensors often exhibit limited responsiveness in dynamic environmental conditions, prompting the adoption of IoT-based sensor data combined with machine learning techniques. This study presents a comparative evaluation of four supervised classification algorithms, K-Nearest Neighbors (KNN), Decision Tree, Random Forest, and Gradient Boosting, using the Smoke Detection Dataset from Kaggle. The methodology integrates SMOTE to address class imbalance and Z-score normalization for feature standardization. Hyperparameter tuning was performed using GridSearchCV with 5-fold cross-validation, and model performance was assessed based on accuracy and execution time. Experimental results show that KNN achieved the highest accuracy (98.33%) with the lowest execution time (0.0327 s), whereas Decision Tree recorded the lowest accuracy (84.17%) but remained computationally fast (0.0406 s). Random Forest and Gradient Boosting demonstrated strong predictive capability (97.22% and 96.94%, respectively), but at higher computational costs (1.4338 s and 8.3819 s, respectively). Almost all models achieved perfect scores (1.00) for precision, recall, and F1-score following SMOTE-based balancing, except KNN which obtained slightly lower values (0.99). The findings indicate a trade-off between predictive performance and computational efficiency, suggesting that lightweight models such as KNN are better suited for real-time IoT-based smoke detection. In contrast, ensemble models may be more appropriate for backend analysis. This research contributes an integrated evaluation framework that combines data rebalancing, multi-model benchmarking, and time-based performance analysis, providing practical insights for the development of responsive and scalable early smoke detection systems.
Comparative Performance of Machine Learning Algorithms for Detecting Online Gambling Promotional Comments on Youtube Michael Angelo; Robet; Hendrik, Jackri
Jurnal Teknologi dan Manajemen Informatika Vol. 11 No. 2 (2025): Desember 2025
Publisher : Universitas Merdeka Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26905/jtmi.v11i2.16286

Abstract

Online-gambling promoters increasingly exploit YouTube comment sections, using text obfuscation, Unicode characters, emojis, irregular spacing, and symbols to evade automated moderation. This study aims to identify the most effective machine-learning algorithm for detecting such promotional comments by comparing models on standard metrics (precision, recall, F1-score, accuracy). We employ semi-supervised pseudo-labelling to expand the labelled set from 1,648 to 9,111 comments without additional manual annotation, admitting only high-confidence predictions. The pipeline includes customised character normalization, selective cleaning, tokenization, stopword removal, and Nazief–Adriani stemming, followed by TF–IDF feature extraction. Four algorithms are evaluated: Multinomial Naive Bayes, Logistic Regression, Random Forest, and Support Vector Machine, with hyperparameter optimization and class balancing via SMOTE. On a 1,823-sample test set, all models achieve over 98% accuracy; SVM yields the most balanced performance, resulting in the highest F1-score for the promotion class (0.9908). Confusion matrices and learning curves indicate stable behavior without overfitting or underfitting. We therefore recommend SVM for operational deployment in automated moderation of gambling-promotion comments on YouTube. These findings provide practical guidance for platform safety teams and suggest methodological baselines for similar NLP moderation tasks. Future work should explore ensemble and deep learning approaches, incorporate character and subword-level features, and further evaluate robustness under adversarial obfuscation and domain shift.
Application of Bagging and Boosting Methods for Heart Disease Classification Parapak, Yehezkiel E.A; Robet, Robet; Hendrik, Jackri
Journal of Applied Computer Science and Technology Vol. 6 No. 2 (2025): Desember 2025
Publisher : Indonesian Society of Applied Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52158/we9asn06

Abstract

Cardiovascular disease remains a primary contributor to global mortality, underscoring the urgent need for accurate and early diagnostic tools. This study aims to develop a robust classification model for heart disease by conducting a comparative analysis of six ensemble machine learning algorithms, comprising three from the Bagging family (Random Forest, Bagged Decision Tree, Extra Trees) and three from the Boosting family (AdaBoost, Gradient Boosting, XGBoost). The research utilizes the publicly available UCI Cleveland Heart Disease dataset, which exhibits a mild class imbalance. To address this, the Synthetic Minority Over-sampling Technique (SMOTE) was strategically applied to the training data. The performance of each model was rigorously evaluated using accuracy, precision, recall, and F1-score. Experimental results revealed that the Extra Trees algorithm, when combined with SMOTE, achieved the highest overall performance with 90% accuracy, 96% precision, 82% recall, and an 88% F1-score. The primary contribution of this work lies in its comprehensive analysis demonstrating that the randomization strategy of Extra Trees provides a superior and more reliable framework for this classification task compared to other common ensemble techniques, particularly after data balancing. These findings confirm that an integrated approach of ensemble learning and proper data balancing can significantly enhance the development of fair and effective diagnostic tools to support medical professionals.
Rancang Bangun Sistem Informasi Rekomendasi Berita dan Pembelajaran Budaya di Indonesia Menggunakan Metode Simple Weighted Average (SWA) Jackri Hendrik; Leony Hoki
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 3 No. 3 (2022): Maret 2022
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v3i3.3723

Abstract

Culture is a pattern or way of life that continues to develop by a group of people and is passed down to the next generation. A culture is usually passed down from generation to generation to their children and grandchildren with the aim that the culture will still exist and be known by the heirs. In practice, introducing the culture/customs of an area is usually done manually, that is, where the advice will convey cultural information to their children and grandchildren. This manual process is certainly not very effective and efficient because it has a very small range of information so it is difficult to introduce cultural information to all regions in Indonesia. In addition to manually, to obtain cultural information in Indonesia can also be done via the internet such as through the Google website or other applications. However, the drawbacks of existing websites and applications are that they only provide news and cultural information in Indonesia at this time and there is no use of intelligent systems in them such as recommendation systems. Therefore, a research will be conducted to design a website information system for news recommendations and cultural learning by applying the Simple Weighted Average method. The results showed that the application of the Simple Weighted Average method proved to be quite accurate in providing recommendations for news and cultural learning in Indonesia because it was based on rating patterns from other users.
Performance Analysis of Machine Learning Model Combination for Spaceship Titanic Classification using Voting Classifier Haria Wirawan; Robet Robet; Jackri Hendrik
JIKO (Jurnal Informatika dan Komputer) Vol 8 No 3 (2025)
Publisher : Program Studi Teknik Informatika Universitas Khairun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33387/jiko.v8i3.10866

Abstract

The Spaceship Titanic dataset is fictional yet complex and challenging, featuring a mix of numerical and categorical features and missing values. This study aims to evaluate the performance of three machine learning model scenarios for classifying passenger status as “Transported” or “not”. The three scenarios implemented include linear-like models, a combination of the Top 5 Diverse models, and tree-based/ensemble models, each using a voting classifier approach. The voting model is employed because it can combine the strengths of multiple algorithms to reduce bias and variance, thus improving overall prediction accuracy and stability. The voting mechanism aggregates predictions from several base classifiers using two strategies: hard voting, which selects the majority class, and soft voting, which averages the predicted probabilities across models. The dataset was obtained from Kaggle and processed through several stages: data preprocessing, data splitting, model training, and evaluation. The evaluation results show that the tree-based/ensemble scenario achieved the highest accuracy of 90.38%, followed by the Top 5 Diverse model combination at 87.31% and the Linear-like model at 76.51%. Visualization using the confusion matrix, ROC Curve, and Feature importance analysis further supports the claim that ensemble models are superior at detecting complex classification patterns. These findings suggest that tree-based ensemble models provide the most optimal approach for classification tasks on a dataset like Spaceship Titanic.
Implementation of the Heuristic Evaluation Method in the Design of the School Academic Information System Website Michelle Francisca; Jackri Hendrik; Hendri
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 5 No. 3 (2026): June 2026
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v5i3.2236

Abstract

In the world of education, the role of teachers and parents is very influential in the process of improving student learning achievement. However, in reality, most parents only give responsibility to teachers at school to improve student learning achievement. Parents of students rarely monitor the development of their children's learning abilities due to the lack of information about it. Global Prima National Plus School is one of the leading private schools in Medan, located on Jalan Brigjend Katamso. Currently, Global Prima National Plus School uses Microsoft Excel to manage student data and student test scores. However, the implementation of this system still has several weaknesses, namely parents cannot monitor attendance and directly know the development of student scores and behavior. This will reduce parental participation in their children's educational development. To solve the problems faced by Global Prima National Plus School, an application can be created to monitor student learning development. By using this application, parents of students can obtain information about student attendance data, attitude and behavior scores, assignment scores, and test scores directly, without having to wait for report cards to be distributed. With this web-based student learning progress monitoring application, parents can find out information about student attendance, attitude scores, behavior, exam scores and assignment scores which can be accessed directly through the school website.
Development of a Web-Based System for Recording and Reporting Palm Weights Using Laravel at PT. Graha Prima Lestari Fredynand Marcos; Wilson; Jackri Hendrik
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 5 No. 3 (2026): June 2026
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v5i3.2241

Abstract

This research was initiated by operational problems in the palm oil weighing process, which was conducted manually. The manual method often caused calculation errors, delays in making report , and risk of data loss. To address these issues, a web-based palm oil weighing application was developed using the Laravel framework and the Waterfall development method, supported by a relational database to manage data in an integrated manner. The application implements a role-based access system to manage permissions for administrators, weighing operators, and management. The system records gross weight, tare weight, and automatically calculates net weight while generating accurate reports efficiently. With this system, the weighing process is expected to become more efficient , precise and structured.