Article Per Year (5 Year)
p-Index From 2020 - 2025
7.592
P-Index
This Author published in this journals
All Journal Media Ilmu Keolahragaan Indonesia Journal of Physical Education Health and Sport Sistemasi: Jurnal Sistem Informasi Scholaria: Jurnal Pendidikan dan Kebudayaan JOURNAL OF APPLIED INFORMATICS AND COMPUTING Triadik Gelanggang Olahraga: Jurnal Pendidikan Jasmani dan Olahraga (JPJO) JURNAL PENDIDIKAN TAMBUSAI JUARA : Jurnal Olahraga JURIKOM (Jurnal Riset Komputer) Jurnal Bidan Komunitas ACTIVE: Journal of Physical Education, Sport, Health and Recreation Journal of Physical Education and Sports Mobile and Forensics Respati Madani : Indonesian Journal of Civil Society Journal of Research and Educational Research Evaluation Community Empowerment Indonesian Journal of Sport Management Indonesian Journal for Physical Education and Sport Prosiding Seminar Nasional Pascasarjana Proceeding of International Conference on Science, Education, and Technology Journal Of Artificial Intelligence And Software Engineering
Rumini -
Unknown Affiliation
Arts Humanities Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering Health Professions Library & Information Science Mathematics Neuroscience Physics Public Health Social Sciences Other

Published : 88 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 88 Documents
Search

 5   6   7   8   9 
Pap Smear Image Classification for Cervical Cancer Prediction with Transfer Learning on ResNet101 Architecture Dewi, Sila Cahya; Rumini, Rumini
Journal of Applied Informatics and Computing Vol. 9 No. 5 (2025): October 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i5.10343

Abstract

Early detection of cervical cancer remains a pivotal strategy to improve clinical outcomes and mitigate mortality associated with this disease. This study introduces a robust deep learning framework employing the ResNet101 architecture to facilitate the automated classification of cervical cell images derived from Pap smear examinations. By leveraging transfer learning, the pre-trained ResNet101 model was fine-tuned to extract salient morphological features critical for distinguishing among diverse cervical cell categories. A comprehensive dataset of labeled Pap smear images, systematically expanded through augmentation techniques, was utilized to enhance model generalizability. The proposed approach achieved a remarkable classification accuracy of 99.6%, highlighting its effectiveness in reliably differentiating between normal and abnormal cellular structures. These findings substantiate the promise of deep residual networks coupled with transfer learning as a powerful tool in advancing computer-aided diagnostic systems, thereby reinforcing early screening initiatives for cervical cancer.
Comparative Study of Logistic Regression, Random Forest, and XGBoost for Bank Loan Approval Classification Putra, Hamdika; Rumini, Rumini
Journal of Applied Informatics and Computing Vol. 9 No. 5 (2025): October 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i5.10862

Abstract

Bank loan approval plays a vital role in ensuring financial institutions can minimize credit risk while supporting economic growth. Default prediction is a crucial aspect of banking credit risk management. This study compares three machine learning algorithms Logistic Regression, Random Forest, and Extreme Gradient Boosting (XGBoost) to classify bank loan approvals using a combination of application, previous application, and bureau datasets. The workflow includes data merging, cleaning, missing value imputation, handling unknown values, feature engineering (such as converting day-based variables into years, calculating total submitted documents, income-to-annuity ratio, and employment-to-income ratio), encoding (label and one-hot), scaling (min-max normalization), feature selection based on correlation analysis, handling class imbalance with SMOTE, as well as modeling and evaluation using Accuracy, Precision, Recall, F1-score, and AUC. The results show that Logistic Regression yields the highest AUC of 0.741498, outperforming Random Forest (0.713758) and XGBoost (0.715944). From a business perspective, implementing the best model reduced the Loss Given Default (LGD) by 39.77 %, from $1,705,098,055.50 to $1,026,944,185.50. This finding confirms that simpler models remain competitive on imbalanced datasets when supported by appropriate preprocessing and balancing strategies.
Meningkatkan Kemampuan Mengenal Bilangan Asli Menggunakan Medi ”Wordwall” pada Siswa Disabilitas Fisik Kategori Poliomylities PTK di SLBN Sungai Bahar Jambi Rumini, Rumini; bubunrum@gmail.com, Irda
Jurnal Pendidikan Tambusai Vol. 8 No. 2 (2024)
Publisher : LPPM Universitas Pahlawan Tuanku Tambusai, Riau, Indonesia

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

Abstract

Penelitian ini dilatarbelakangi oleh rendahnya kemampuan siswa Disabilitas Fisik fase A dalam mengenal bilangan asli.Tujuan dari penelitian ini yaitu meningkatkan kemampuan mengenal bilangan asli pada siswa disabilitas fisik kategori Poliomylities fase A di SLBN Sungai Bahar dengan menggunakan media “ wordwall”. Penelitian ini merupakan Penelitian Tindakan kelas dengan subjek sebanyak 3 orang siswa. Instrument yang digunakan yaitu dalam bentuk tes. Adapun hasil dari penelitian ini adalah pada siklus I siswa Disabilitas fisik fase A dapat menyebut angka sampai dengan angka 6 dan menunjuk angka sampai dengan angka 5, sedangkan pada siklus II siswa Disabilitas fisik mampu menyebut angka sampai dengan angka 9.Maka dapat disimpulkan bahwa penggunaan media Wordwall dapat meningkatkan kemampuan mengenal bilangan asli pada siswa Disabilitas fisik fase A.
Comparison of Phishing Detection Tests using the SVM Method with RBF and Linear Kernels Rumini, Rumini; Norhikmah, Norhikmah; Mustofa, Ali; Pradana, Sulistyo
Sistemasi: Jurnal Sistem Informasi Vol 12, No 3 (2023): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v12i3.2882

Abstract

Phising adalah sebuah tindakan kriminal untuk mencuri informasi pribadi orang lain menggunakan entitas electronic, salah satunya adalah website. Informasi ini dicuri dari website yang telah diakses yang mengandung phising atau dengan kata lain masuk ke dalam kategori website phising. Tujuan dari web phising adalah membuat pengguna percaya bahwa mereka berinteraksi dengan situs resmi. Umumnya informasi yang dicari phisher (pelaku phising) adalah berupa username, password, baik itu akun media sosial atau akun nomor kartu kredit dengan cara diarahkan ke sebuah situs website palsu. Maka dari itu perlu adanya deteksi web phising yang berguna untuk melindungi user dari tindak pencurian informasi pengguna. Penelitian ini membahas dua kernel dalam metode SVM (Support Vector Machine) untuk deteksi web phising yaitu kernel RBF (Radial Basis Function) dan kernel linear. Akurasi yang didapatkan dengan ketiga kernel menghasilkan nilai akurasi yang berbeda-beda. Hasil akurasi pengujian sistem deketksi web phising dengan Kernel Linear sebesar 92.582 % dan Kernel Radial Basis Function sebesar 96.426 %. Akurasi paling tinggi dengan metode SVM untuk deteksi web phising yaitu menggunakan kernel RBF (Radial Basis Function).
Breast Cancer Classification based on Ultrasound Images using the Support Vector Machine (SVM) Algorithm Aprilia, Nurazmi; Rumini, Rumini
Sistemasi: Jurnal Sistem Informasi Vol 13, No 4 (2024): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v13i4.4113

Abstract

According to statistics from the Global Burden of Cancer Study (Globocon) of the World Health Organization (WHO), cancer, particularly breast cancer, is a severe health issue in Indonesia with 68,858 new cases and 22,000 deaths recorded in 2020. Ultrasonography (USG) technology is acknowledged as one of the potentials to support early detection, which is vital in reducing mortality from breast cancer. This study focuses on classifying ultrasound images using the Support Vector Machine (SVM) algorithm, GLCM feature extraction, Min-Max normalization, and Mutual Information with SelectKBest Feature Selection. From several experiments using the SVM algorithm with various combinations of parameter values that have been set and different Tests, namely using a Train/Test Split with a proportion of 80/20 and K-Fold Cross Validation, it shows that the SVM algorithm is capable of classifying ultrasound images of breast cancer. into two categories (Benign Tumor and Malignant Tumor) with the same maximum accuracy of 79% after applying the SMOTE Balancing Data technique or without using the Balancing Data technique. As a result, the Support Vector Machine (SVM) algorithm has the potential to be an effective model for identifying breast cancer ultrasound images, both on data from the original set that has not been balanced and data from the set that has been balanced.
Implementation of the Support Vector Machine (SVM) Algorithm on Sentiment Analysis of Public Opinion on The Prohibition of the use of Syrupy Drugs for Kidney Health Purnomo, Galih; Rumini, Rumini; Susanto, Tri
Sistemasi: Jurnal Sistem Informasi Vol 13, No 6 (2024): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v13i6.4444

Abstract

In 2022, the Indonesian Ministry of Health reported several cases of pediatric acute renal failure (GGAPA), which resulted in a mortality rate of 59%, mainly among children aged between 1-5 years. The main causes were identified by Health Minister Budi Gunadi Sadikin as the three solvents ethylene glycol (EG), diethylene glycol (DEG), and ethylene glycol butyl ether (EGBE). In response, the government implemented restrictions on the consumption of these condensed substances, which led to mixed public reactions observed in the YouTube comments section. The purpose of this study is to evaluate public opinions on the syrup ban for kidney health. The comments will be classified using the Support Vector Machine (SVM) method, and the most effective kernel among linear, sigmoid, polynomial, and RBF will be identified. Data was collected through web scraping with 5000 initial data, and after preprocessing, 4794 data were processed. The analysis results show that the linear kernel has the highest accuracy of 75.63%, followed by the sigmoid kernel 75.29%, RBF 74.79%, and polynomial 71.09%. While the K-Fold Cross Validation test with a value of k = 10, produced a value of 74.64% for the linear kernel. This research concludes that the Support Vector Machine (SVM) algorithm with a linear kernel achieves the highest accuracy in sentiment analysis.
MRI Classification of Brain Tumors Using EfficientNetB0 Feature Extraction and Machine Learning Methods Jiven, Firza Findia; Rumini, Rumini
Journal of Applied Informatics and Computing Vol. 9 No. 6 (2025): December 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i6.10363

Abstract

Brain tumor classification using MRI images plays a crucial role in modern medical diagnostics, offering fast and accurate support for disease detection. This study proposes a classification approach that combines feature extraction using EfficientNet B0 with conventional machine learning algorithms. MRI brain images are preprocessed and resized to match EfficientNet B0 input dimensions. Feature vectors are extracted and subsequently processed using PCA for dimensionality reduction and SMOTE for class balancing. The resulting data are classified using various machine learning algorithms including Support Vector Machine, XGBoost, LightGBM, and others. Experimental results show that Support Vector Machine achieved the highest accuracy of 96%, followed by XGBoost and LightGBM at 94%. The combination of EfficientNet B0 feature extraction and lightweight classifiers proved to be effective, matching the performance of more complex deep learning models. This study does not focus on measuring computational cost directly, but rather demonstrates that combining EfficientNetB0 feature extraction with machine learning algorithms can achieve performance comparable to deep learning approaches. This highlights that lightweight models remain competitive in terms of accuracy without requiring highly complex architectures. Future work can explore this method on other medical imaging datasets and enhance model interpretability for clinical adoption.
Hypertension Risk Prediction Using Stacking Ensemble of CatBoost, XGBoost, and LightGBM: A Machine Learning Approach Alfath, Abisakha Saif; Wardhana, Ajie Kusuma; Rumini, Rumini
Journal of Applied Informatics and Computing Vol. 9 No. 6 (2025): December 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i6.10370

Abstract

Hypertension is a leading cause of cardiovascular diseases, chronic kidney failure, and strokes, affecting millions worldwide. Early detection and accurate risk prediction are crucial for effective management and prevention. This study aims to evaluate and compare the performance of different algorithms for predicting hypertension risk using a stacking ensemble approach. The model combines three gradient boosting algorithms XGBoost, LightGBM, and CatBoost as base learners, with Logistic Regression as the meta learner. The dataset, sourced from Kaggle, contains 4,240 instances with demographic and clinical attributes relevant to hypertension. The preprocessing steps included imputing missing values using the median, removing residual null entries, and addressing class imbalance through the SMOTE algorithm. Data were divided into 80% for training and 20% for testing. The evaluation showed that the stacking ensemble model achieved an overall accuracy of 92,65%, with precision, recall, and F1-scores consistently reaching 0.92 for both classes. The confusion matrix revealed minimal misclassification, indicating the model’s strong ability to differentiate between low and high risk individuals. These results emphasize that the primary goal of this research is to identify which algorithm provides the best performance for hypertension risk prediction. By evaluating and comparing different models, this study offers insights into choosing the most effective algorithm for clinical decision-making and early detection strategies.
Co-Authors A.A. Ketut Agung Cahyawan W Abdillah, Rusli Abidarin Rosidi Adzalika, Ayu Reza Agung Wahyudi Ahmad Alwi Nurudin Ahmad Alwi Nurudin Aisyah, Hanif Akhirmaini, Zelda Alam, Bima Tangguh Alfath, Abisakha Saif Ali Mustofa Alirman Sarpan Amalia, Ikhlasul Ansori, Ikhsan Anwar Anwar Aprilandri, Gusti Aprilia, Nurazmi Aribowo, Dhany Suhartantyo Ariyadi, Jamal Imam Asmoro, Jimy Purbo Bambang Priyono Billy Castyana, Billy bubunrum@gmail.com, Irda Dewi, Sila Cahya Dina Maulina Donny Firmansyah Dwinanda Saputra, Ahmad Faris Eunike Raffy Rustiana Fakhruddin Fakhruddin Farah Nur Oktavia Febriyanto, Dimas Bayu Gema, Abdul Rachim Gilang, Meillenio Agung Gumono Gumono, Gumono Handoko, Lovi Harry Pramono, Harry Harsono, Tri Nur Heny Setyawati Hermahayu Hidayah, Ayu Nur Ilman Zuda Septiawan Imawati, Veni Indriyanti Indriyanti, Indriyanti Irawan, Fredi Januarto, Khoerul Rohman Jiven, Firza Findia Kasmudi, Udin Khotibul Umam Kusuma, Donny Wira Yudha Kusuma, Prita Widia Lesmana, Dian Lukmanul Hakim Luthfi, Auliya Ma'muroh, Ma'muroh Mardanto, Langgeng Asmoro Budi Mugi Hartono Nasuka Nasuka, Nasuka Norhikmah Norhikmah Oktia Woro Kasmini Handayani Pambudi, Satrio Rilo Parista, Vivi Septiana Patria, Lalu Demung Pradana, Sulistyo Pradana, Toufan Wahyu Pramandhika, Reddy Prasepty, Winda Pratama, Rifqy Rayhan Andi Riga Pratiwi, Adinda Resta Putri pratiwi, Debby Purnomo, Galih Puspita Sari, Ika Endah Putra, Hamdika Rachman, Imaniar Ranu Baskora Aji Putra Ria Lumintuarso Rizki SP, Tri Agustin Wulandari Roas Irsyada, Roas roni, Ahmad Sya'roni S.Pd. M Kes I Ketut Sudiana . Said Junaidi Saputra, Irawan Hadi Saputro, Irfan Toni Satria Armanjaya Seran, Yohanes Arka Maria Setya Rahayu Shodikin, Shodikin Siti Baitul Mukarromah Siti Hajar SOEGIYANTO Soegiyanto Soegiyanto, Soegiyanto Sudarmawan, Sudarmawan Sugiharto - Sugiharto Sugiharto Sugiharto Sugiharto Sukestiyarno, Y.L Sulaiman Sulaiman Suratman Suratman Tandiyo Rahayu Taufiq Hidayah Taufiq Hidayah Tommy Soenyoto Tri Rustiadi, Tri Tri Susanto Ucu Muhammad Afif Wahyuli, Wahyuli Wardhana, Ajie Kusuma Wibowo, Ristianto Adi Wicaksono, Restu Aji Wicaksono, Wisnu Widy Astuti, Widy Winara Winara Winasis, Probo Wiwit Kurniawan, Wiwit Wiyono, Indra Zahirma, Mutia Zola, Nicko