p-Index From 2021 - 2026
10.913
P-Index
This Author published in this journals
All Journal Jurnal Sarjana Teknik Informatika EKONOMIA Jurnal Informatika dan Teknik Elektro Terapan Informatika Mulawarman: Jurnal Ilmiah Ilmu Komputer JIKO (Jurnal Informatika dan Komputer) JURNAL MEDIA INFORMATIKA BUDIDARMA Indonesian Journal of Artificial Intelligence and Data Mining Jurnal Ilmiah Matrik JURNAL INSTEK (Informatika Sains dan Teknologi) Jurnal Teknologi Sistem Informasi dan Aplikasi JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Psychology, Evaluation, and Technology in Educational Research INFOMATEK: Jurnal Informatika, Manajemen dan Teknologi METIK JURNAL Building of Informatics, Technology and Science Progresif: Jurnal Ilmiah Komputer JISKa (Jurnal Informatika Sunan Kalijaga) Jurnal Ilmiah Betrik : Besemah Teknologi Informasi dan Komputer Jurnal Mnemonic JATI (Jurnal Mahasiswa Teknik Informatika) Scientific Journal of Informatics JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) Didaktik : Jurnal Ilmiah PGSD STKIP Subang Reswara: Jurnal Pengabdian Kepada Masyarakat TIN: TERAPAN INFORMATIKA NUSANTARA Journal of Computer Networks, Architecture and High Performance Computing BAKTI BANUA : JURNAL PENGABDIAN KEPADA MASYARAKAT Teknika Jurnal Informatika Teknologi dan Sains (Jinteks) Prisma Sains: Jurnal Pengkajian Ilmu dan Pembelajaran Matematika dan IPA IKIP Mataram Jurnal Bangkit Indonesia CONSEN: Indonesian Journal of Community Services and Engagement Jurtik STMIK Bandung Bulletin of Network Engineer and Informatics (BUFNETS) Jurnal Abdimas Lamin Jurnal Informatika: Jurnal Pengembangan IT Journal of Innovative and Creativity Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Buffer Informatika Computer Journal INOVTEK Polbeng - Seri Informatika JSE Journal of Science and Engineering Journal of Information Technology KREATIF: Jurnal Pengabdian Masyarakat Nusantara Jurnal Abdimas Mahakam
Claim Missing Document
Check
Articles

Implementation of the PSO-SMOTE Method on the Naive Bayes Algorithm to Address Class Imbalance in Landslide Disaster Data Azwar Damari; Taghfirul Azhima Yoga Siswa; Wawan Joko Pranoto
Journal of Innovation and Technology Polbeng Series on Informatics (INOVTEK Polbeng - Seri Informatika) Vol. 10 No. 1 (2025): March
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/7wcvrb72

Abstract

Landslides in Samarinda, which often occur after floods, pose a threat to settlements, infrastructure, and the agricultural sector. This study proposes a combination of Naïve Bayes, SMOTE (Synthetic Minority Oversampling Technique), and PSO (Particle Swarm Optimization) to address class imbalance in landslide prediction. The results show that while PSO successfully improves the accuracy of the Naïve Bayes model, the application of SMOTE led to a decrease in accuracy for some method combinations. This decrease is due to changes in data distribution caused by synthetic data, which can introduce noise and affect feature selection and model optimisation. However, the combination of Naïve Bayes with PSO optimisation resulted in a modest accuracy improvement (+0.48%). These findings suggest that SMOTE should be used cautiously, while PSO is more effective in enhancing the accuracy of the landslide prediction model. The implications for practical application are that although SMOTE and PSO can improve accuracy, the impact of synthetic data on data distribution must be considered, and further testing is needed to ensure its effectiveness in real-world conditions.
Revitalisasi Infrastruktur dan Digitalisasi UMKM Kerajinan Dayak di Desa Budaya Pampang Samarinda Catur Kumala Dewi; Faizal Bahrudin; Rina Masithoh Haryadi; Taghfirul Azima Yoga Siswa; Ekawati Ekawati
Jurnal Pengabdian Masyarakat Lamin Vol 5, No 1 (2026)
Publisher : Fakultas Ekonomi dan Bisnis Universitas 17 Agustus 1945 Samarinda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31293/jpml.v5i1.9299

Abstract

Program pengabdian masyarakat ini bertujuan untuk mentransformasi kapasitas operasional dan jangkauan pasar pelaku Usaha Mikro, Kecil, dan Menengah (UMKM) Lamin Pamung Tawai di Desa Budaya Pampang, Samarinda. Permasalahan utama yang diidentifikasi meliputi keterbatasan infrastruktur fisik tempat berjualan yang rentan terhadap faktor cuaca dan risiko keamanan, serta stagnasi strategi pemasaran yang masih bersifat konvensional. Melalui pendekatan Participatory Action Research (PAR), intervensi dilakukan dalam dua dimensi utama: revitalisasi fasilitas fisik melalui pemasangan folding gate dan partisi modular, serta akselerasi digital melalui pengembangan portal e-commerce pada domain budayapampang.web.id. Hasil implementasi menunjukkan peningkatan signifikan dalam kenyamanan kerja dan efisiensi manajemen inventaris. Selain itu, integrasi teknologi digital telah memperluas visibilitas produk kerajinan Dayak ke pasar nasional dan internasional. Keberlanjutan program dijamin melalui pembentukan tim pengelola fasilitas dan peningkatan literasi digital pemuda desa sebagai admin pemasaran. Sinergi antara penguatan fisik dan digital ini tidak hanya meningkatkan kesejahteraan ekonomi lokal, tetapi juga berfungsi sebagai mekanisme pelestarian warisan budaya Dayak Kenyah di era industri 4.0.
Optimization of the SVM Algorithm with Chi-Square and SMOTE for High-Dimensional Stunting Data in Samarinda Taghfirul Azhima Yoga Siswa; Naufal Azmi Verdikha
Prisma Sains : Jurnal Pengkajian Ilmu dan Pembelajaran Matematika dan IPA IKIP Mataram Vol. 14 No. 3: July 2026
Publisher : Universitas Pendidikan Mandalika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33394/j-ps.v14i3.21848

Abstract

Stunting is still considered a serious problem and has become a focus of government attention in the national research priorities for 2020-2024, with a stunting prevalence of 21.6% in 2022. The city of Samarinda ranked second highest after the Kutai Kartanegara district in East Kalimantan Province in 2022, with a percentage of 25.3%. Based on previous data mining research trends, the use of classification methods such as KNN, Naïve Bayes, Random Forest, Neural Network, CART, and SVM has generally produced quite high accuracy but still focuses on low-dimensional data, which can lead to significant information loss, potential overfitting, and difficulty in interpretation. Whereas in research topics related to high-dimensional stunting data, the majority still yield low accuracy. This is further supported by the still prevalent class imbalance found in other studies, which can affect the accuracy and recall values of the built model's performance. The objective of this research is to apply the Support Vector Machine (SVM) algorithm with Chi-Square feature selection and the Synthetic Minority Over-sampling Technique (SMOTE) to address high-dimensional stunting data and handle class imbalance. The dataset for this research is sourced from the Samarinda City Health Office, consisting of 26 community health centers with 20 attributes and 102,534 records. The division of training and testing data uses the k-fold cross-validation technique with k=10. The research results show the model's performance is very good, with an accuracy of 96.6%, supported by precision, recall, and f1-score values of 97% each.
MODEL HYBRID PSO, CORELATION FEATURE SELECTION DAN KNN UNTUK DETEKSI PENYAKIT JANTUNG Dion Ikhzanza Rabbil; Taghfirul Azhima Yoga Siswa; Wawan Joko Pranoto
JURNAL INFORMATIKA DAN KOMPUTER Vol 10, No 2 (2026): Juni 2026
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat - Universitas Teknologi Digital Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26798/jiko.v10i2.2662

Abstract

The high mortality rate caused by disorders of the cardiovascular system highlights the need for accurate early detection methods to support medical decision-making. This study aims to develop and evaluate a heart disease classification model using the K-Nearest Neighbor (KNN) algorithm optimized with Particle Swarm Optimization (PSO). In its implementation, the KNN algorithm employs the Manhattan distance parameter to measure the similarity between data instances. The dataset used in this study is a secondary heart disease dataset consisting of 302 records after preprocessing. The preprocessing stage includes data cleaning, numerical feature standardization using StandardScaler, and correlation-based feature selection to identify attributes that have significant relationships with the target variable. Model evaluation is conducted using a 10-fold cross-validation scheme and assessed using accuracy, precision, recall, and F1-score. The experimental results show that the baseline KNN model achieves an accuracy of 81.16%, while the PSO-optimized KNN model demonstrates improved performance with an accuracy of 82.81%, precision of 79.02%, recall of 92.13%, and an F1-score of 84.84%. These findings indicate that the application of PSO effectively enhances the performance and stability of the KNN algorithm in heart disease classification.
Model Hybrid Particle Swarm Optimization, Correlation Feature Selection dan Naive Bayes untuk Deteksi Penyakit Jantung Renaldi Yoga Rendy Menono; Taghfirul Azhima Yoga Siswa; Wawan Joko Pranoto
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 2 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i2.10240

Abstract

Heart disease is a leading cause of mortality in Indonesia, with the number of cases reaching 15.5 million in 2022. This study aims to classify heart disease using the Naïve Bayes algorithm optimized with Particle Swarm Optimization (PSO) to improve classification performance. The dataset used in this study was obtained from the Zenodo repository, consisting of 1,025 heart disease records with 14 features. The data were processed through preprocessing stages and divided into training and testing sets using the 10-Fold Cross Validation method. PSO optimization was applied to the var_smoothing parameter of the Naïve Bayes algorithm. Model performance was evaluated using a confusion matrix to obtain accuracy, precision, recall, and F1-score values. The results indicate that Particle Swarm Optimization (PSO) improves the performance of the Naïve Bayes algorithm. On the correlation-based feature selection dataset, accuracy increased from 81.49% to 84.48%, precision slightly decreased from 82.57% to 82.37%, recall increased from 84.38% to 91.62%, and F1-score increased from 83.00% to 86.33%. These findings demonstrate that the combination of Naïve Bayes and Particle Swarm Optimization (PSO) is effective in enhancing heart disease classification performance.
Model Hybrid PSO-SMOTE, Correlation Feature Selection dan Random Forest untuk Deteksi Penyakit Jantung Nur Dila Yuanti; Taghfirul Azhima Yoga Siswa; Wawan Joko Pranoto
Jurnal Informatika: Jurnal Pengembangan IT Vol 11, No 2 (2026)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v11i2.10241

Abstract

Heart disease is one of the leading causes of death worldwide, with approximately 17.8 million deaths reported in 2021. In Indonesia, the number of cases reached an estimated 15.5 million in 2022, highlighting the need for accurate early detection. This study aims to improve heart disease classification by integrating Correlation Feature Selection (CFS), Synthetic Minority Oversampling Technique (SMOTE), Particle Swarm Optimization (PSO), and Random Forest. CFS was applied to remove less relevant features before classification, SMOTE addressed class imbalance, and PSO optimized the Random Forest hyperparameters. The dataset consisted of 1,025 records from four heart disease datasets, which were cleaned into 302 unique instances. CFS eliminated the fasting blood sugar (fbs) attribute due to its very weak correlation with the target variable. Evaluation using 10-fold cross-validation showed that the baseline Random Forest achieved an accuracy of 82.80%, precision of 83.62%, recall of 86.07%, and f1-score of 84.46%, while Random Forest–PSO with SMOTE produced the best performance, achieving 85.11% accuracy, 84.62% precision, 89.74% recall, and 86.77% f1-score. These findings indicate that PSO provides the greatest performance improvement, while CFS simplifies the feature set before classification. The proposed hybrid model contributes by integrating feature selection, data balancing, and hyperparameter optimization into a single classification framework for more effective heart disease prediction.
Analisis Sentimen Ulasan Pengguna inDrive Menggunakan IndoBERT dan Algoritma Genetika pada Klasifikasi K-Nearest Neighbor Muhammad Sigit Nurhafid; Rudiman Rudiman; Taghfirul Azhima Yoga
Computer Journal Vol. 4 No. 2 (2026): August
Publisher : Yayasan Pendidikan Mitra Mandiri Aceh (YPMMA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58477/cj.v4i2.497

Abstract

This study analyzes sentiment in InDrive user reviews from the Google Play Store using IndoBERT, Genetic Algorithm (GA), and K-Nearest Neighbor (KNN). A total of 2,000 reviews were assigned to three sentiment classes: 1,695 negative, 235 positive, and 70 neutral reviews. The pretrained indobenchmark/indobert-base-p1 model was used as a feature extractor by taking the [CLS] representation to produce 768-dimensional embeddings. The dataset was divided using a stratified 80:20 split into 1,600 training and 400 testing samples. The optimal K value was determined through stratified five-fold cross-validation on the training data. GA was applied only to the training set using a population of 30 individuals, 25 generations, a crossover rate of 0.8, a mutation rate of 0.005, and a feature penalty of 0.002. GA selected 250 features, reducing the dimensionality by 67.45%. IndoBERT + KNN correctly classified 365 of 400 test samples, achieving 91.25% accuracy (95% CI: 88.07–93.64%) and a macro F1-score of 66.88%. IndoBERT + GA + KNN correctly classified 362 samples, achieving 90.50% accuracy (95% CI: 87.23–93.00%) and a macro F1-score of 62.71%. Both models exceeded the 84.75% majority-class baseline. However, only three and two of the 14 neutral samples were correctly classified, respectively. GA substantially reduced feature dimensionality but did not improve predictive performance, indicating a trade-off between representation compactness and minority-class classification performance.
Optimasi Hyperparameter K-Nearest Neighbor Menggunakan Genetic Algorithm untuk Klasifikasi Penyakit Liver Muhammad Nur Ramadhani; Taghfirul Azhima Yoga Siswa; Muhammad Ridwan
Jurnal Sarjana Teknik Informatika Vol. 14 No. 3 (2026): Oktober
Publisher : Program Studi Informatika, Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/jstie.v14i3.32755

Abstract

Penyakit liver merupakan salah satu gangguan kesehatan yang memerlukan deteksi secara tepat karena gejalanya sering kali tidak spesifik. Klasifikasi berbasis data dapat digunakan untuk membantu mengidentifikasi pasien yang berpotensi mengalami penyakit liver. Penelitian ini bertujuan menerapkan metode K-Nearest Neighbor (KNN) untuk klasifikasi penyakit liver serta mengoptimasi hyperparameter KNN menggunakan Genetic Algorithm (GA). Dataset yang digunakan adalah Indian Liver Patient Dataset (ILPD) yang terdiri dari 583 data. Tahapan penelitian meliputi preprocessing berupa penanganan missing value, penghapusan data duplikat, transformasi variabel kategorikal, dan standardisasi data. Proses klasifikasi dievaluasi menggunakan 10-Fold Cross Validation. Dataset memiliki distribusi kelas yang tidak seimbang, sehingga evaluasi menggunakan beberapa metrik diperlukan untuk melihat kemampuan model secara lebih menyeluruh dan menghindari penilaian yang hanya berfokus pada accuracy. Pada model KNN dengan optimasi Genetic Algorithm, ruang pencarian hyperparameter meliputi jumlah tetangga (n_neighbors), metode pembobotan (weights), dan metrik jarak (metric). Hasil optimasi menghasilkan kombinasi hyperparameter terbaik berupa n_neighbors=2, weights=distance, dan metric=euclidean. Hasil evaluasi menunjukkan bahwa model KNN menghasilkan Accuracy sebesar 68,94%, Precision sebesar 67,76%, Recall sebesar 68,94%, dan F1-Score sebesar 68,01%. Sementara itu, model KNN yang dioptimasi menggunakan Genetic Algorithm menghasilkan Accuracy sebesar 69,12%, Precision sebesar 62,57%, Recall sebesar 69,12%, dan F1-Score sebesar 63,94%. Dengan demikian, optimasi Genetic Algorithm meningkatkan Accuracy dan Recall sebesar 0,18%, tetapi menurunkan Precision sebesar 5,19% dan F1-Score sebesar 4,07%. Hasil tersebut menunjukkan bahwa optimasi hyperparameter menggunakan Genetic Algorithm memberikan perubahan terhadap karakteristik kinerja KNN, tetapi belum meningkatkan seluruh metrik evaluasi secara bersamaan.
Application of the Forward Selection and ADASYN Methods in the K-Nearest Neighbor (KNN) Algorithm for Traffic Accident Data Classification Agus Tri Waluyo; Taghfirul Azhima Yoga Siswa; Wawan Joko Pranoto
Bulletin of Network Engineer and Informatics Vol. 4 No. 2 (2026): BUFNETS (Bulletin of Network Engineer and Informatics) October 2026
Publisher : PT. GWEX NET PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59688/px197639

Abstract

Traffic accidents are a serious problem that threaten public safety and cause material losses, particularly in Samarinda City, where the number of cases rose by 69.61% between 2021 and 2023. This study aims to improve the performance of a traffic-accident-severity classification model by optimizing the K-Nearest Neighbor (KNN) algorithm through a combination of Adaptive Synthetic Sampling (ADASYN) and Forward Selection. The dataset, obtained from accident reports of the Samarinda City Police for 2020–2024, consists of 2,385 records and 35 attributes, split using 10-fold cross-validation and evaluated with a confusion matrix. The standard KNN model achieved an accuracy of 79.61%, precision of 25.06%, recall of 23.81%, and an f1-score of 24.29%. After applying ADASYN, performance improved to an accuracy of 92.54%, precision of 93.08%, recall of 92.01%, and an f1-score of 92.50%. The largest gain occurred after Forward Selection narrowed the feature set to four attributes, yielding an accuracy of 99.62%, precision of 99.89%, recall of 99.34%, and an f1-score of 99.62%. These results demonstrate that combining ADASYN with Forward Selection significantly improves the classification performance of the KNN model in predicting traffic-accident severity, and offers an effective approach for future accident-severity prediction systems.
Co-Authors Abdul Rahim Abdul Rahim Abror, Irfan Fiqry Agus Tri Waluyo Agustya Nanda Pratiwi Akbar, Zakaria Ihza Alfi Arif Anis Siti Nurrohkayati Anitasari, Dini Anton Prafanto Anton Saputra Arbansyah Arbansyah Ari Ahmad Dhani Ariyadi, Dedy Asnur Karima Aspianur Azwar Damari Bahrudin, Faizal Bayu Wijayantini, Bayu Betris Dea Maretta, Nanda Catur Kumala Dewi Damari, Azwar Darmawan Setiya Budi Daryanto Dion Ikhzanza Rabbil Dzul Rachman, Dzul Ekawati Ekawati Enriko Chiesa Sipahutar Fadhil Irsyad Ramadhani Faizal Bahrudin FAUZI Fendy Yulianto Fendy Yulianto Gubtha Mahendra Putra Haryadi, Rina Mashitoh Hasudungan, Rofilde Heri Abijono Hery Kurniawan Hidayati Ramadhani, Novia Hidayatullah, Muhammad Wahyu Istimaroh Istimaroh Jubaidi Khanisa Octavia Khatimah, Khusnul lia, Alvina Lidya Sari Mardiana Mardiana Mi'raj Fattah Mu. Aldi Rahmad Fahrozi Muhamad Ridwan Muhammad Aditya Rahman Muhammad Afif Aunur Rohman Muhammad Fadly Ramadhani Muhammad Najeri Al Syahrin Muhammad Norhalimi Muhammad Nur Ramadhani Muhammad Rhosyid Akhmad Muhammad Sigit Nurhafid Muhammad Ulil Albab Muhammad Wildan Hadinata Naufal Azmi Verdhika Naufal Azmi Verdikha Naufal Azmi Verdikha Naufal Azmi Verdikha Nur Dila Yuanti Nursaid Nursaid Pambudi, Faldy Alfareza Paula Mariana Kustiawan Pitoyo Pitoyo Pitoyo, Pitoyo Poernamawan, Ahmad Nugraha Prihandoko . Putri, Azzahra Namira Raenald Syaputra Rahman, Febrian Nor Ramadhani, Daib Jidan Renaldi Panji Wibowo Renaldi Yoga Rendy Menono Restu, Anggiq Karisma Aji Rina Masithoh Haryadi Rivaldo, Vito Junivan Rizky Aspiah Rochman, Bagus Fathur Rofilde Hasudungan Rudiman Rudiman Rudiman, R Rudiman, Rudiman Salsabila, Cindy Azra Santi Yatnikasari Sarina Safitri Satria, Bima Sidiq, Reza June Siti Muawwanah Taufik Sobri Taufiq, Ilham Taufiqurrahman Taufiqurrahman Triawan Adi Cahyanto Wahyu Hidayat Wawan Joko Pranoto Wawan Joko Pranoto Wawan Joko Pranoto Wawan Joko Pranoto Widyastuti, Dessy Yoga Priantama