Claim Missing Document
Check
Articles

Improving Intrusion Detection under Extreme Class Imbalance through Class Representation Restructuring and SMOTE Ghozi, Wildanil; Mohamed Yassin, Warusia; Rakhmat Sani, Ramadhan; Rafrastara, Fauzi Adi
ELKHA Vol. 18 No.2 October 2026
Publisher : Faculty of Engineering, Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/elkha.v18i2.107677

Abstract

Class imbalance is a major challenge in multi-class network intrusion detection, particularly when extremely underrepresented attack categories provide insufficient samples for effective model learning. Such imbalance can cause machine learning models to favor majority classes, resulting in high overall accuracy but poor detection of minority attacks. This study proposes a data-level imbalance handling strategy that restructures the representation of extremely sparse attack classes before applying the Synthetic Minority Over-sampling Technique (SMOTE). Four experimental conditions were evaluated on the UNSW-NB15 dataset using Decision Tree, Random Forest, and XGBoost classifiers to examine the effects of class representation restructuring and SMOTE separately. The evaluation employed accuracy, macro-precision, macro-recall, and macro-F1-score, complemented by class-wise analysis. The results show that, for XGBoost, class representation restructuring without SMOTE increases macro-recall from 54.44% to 68.56% and macro-F1-score from 57.44% to 68.24%, while accuracy remains nearly unchanged. When SMOTE is subsequently applied to the restructured representation, macro-recall further increases to 78.60% and macro-F1-score to 69.05%. Compared with the original non-SMOTE condition, the combined strategy improves macro-recall by 24.16% and macro-F1-score by 11.61%, while accuracy decreases by only 0.73 %, from 98.30% to 97.57%. Class-wise analysis further indicates substantial recall improvements for several underrepresented attack categories, although precision trade-offs remain for some classes. These findings show that restructuring extreme minority-class representations before oversampling can improve minority-oriented detection performance under severe class imbalance.
Spatiotemporal Analysis of Peatland Fire Hotspots and Fire Intensity in Riau Province Using MODIS–VIIRS Multisensor Satellite Data Ratu Afi, Najwa; Sani, Ramadhan Rakhmat; Pramunendar, Ricardus Anggi; Winarsih, Nurul Anisa Sri; Dewi, Ika Novita
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12686

Abstract

Peatland fires in Riau Province frequently occur during the dry season and contribute significantly to regional haze, environmental degradation and carbon emissions. Effective monitoring of these fires remains challenging due to their widespread distribution and varying intensity across peatland areas. This research aims to analyze the spatiotemporal characteristics of peatland fire hotspots in Riau Province using multisensor satellite observations from the NASA Fire Information for Resource Management System (FIRMS). The dataset integrates Moderate Resolution Imaging Spectroradiometer (MODIS) and Visible Infrared Imaging Radiometer Suite (VIIRS) data from the Suomi-NPP, NOAA-20 and NOAA-21 satellites. After applying filtering criteria of confidence ≥70% and Fire Radiative Power (FRP) ≥5 megawatts (MW), a total of 7,297 significant hotspots were identified during the July–October 2025 dry season. The results show that fire activity peaked in July with a maximum daily FRP of 25,611 MW and a monthly total of 65,120 MW, followed by a decline in September and a slight increase in October. The FRP distribution was highly right-skewed, with an average value of13.2 MW, while the most intense hotspots reached 189.4 MW. Estimated carbon dioxide (CO₂) emissions reached approximately 122,472 tons, indicating substantial environmental impacts. Spatial clustering and persistence analysis revealed several high-risk peatland zones with repeated fire occurrences. These findings demonstrate the importance of multisensor satellite monitoring for improving early fire detection, emission assessment and disaster mitigation strategies in peatland regions.
Deteksi URL Phishing yang Tangguh Menggunakan Fitur Leksikal yang Disempurnakan dan Model Pembelajaran Mesin Komparatif Rahmawati, Firnanda; Rafrastara, Fauzi Adi; Ghozi, Wildanil; Rakhmat Sani, Ramadhan; Umam, Chaerul; Alomoush, Ashraf
Journal of Applied Informatics and Computing Vol. 10 No. 5 (2026): October 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i5.14070

Abstract

Phishing URLs continue to evade classical filtering approaches as attackers refine their obfuscation strategies, motivating machine learning-based detection methods that adapt more readily to new patterns. This work compares three classifiers, Random Forest, Extreme Gradient Boosting (XGBoost), and a hybrid CNN-LSTM model, for phishing URL classification using enhanced lexical feature engineering, syntax-aware preprocessing, and systematic component-wise ablation analysis. First, the conventional six-feature lexical representation is extended to fourteen handcrafted features by incorporating cues associated with modern phishing behavior, including suspicious keywords, top-level domain characteristics, hexadecimal encoding, and query-parameter statistics. Second, a syntax-aware preprocessing strategy selectively removes non-structural punctuation while retaining structural URL delimiters. Third, cross-source duplicate URLs are resolved through a two-stage majority-vote deduplication process to reduce redundancy and potential data leakage. Fourth, all classifiers are evaluated under a shared data preparation protocol while retaining model-specific feature representations and configurations. Experiments on the Kaggle Malicious URLs dataset achieved accuracies of 95.47%, 97.86%, and 98.59% for Random Forest, XGBoost, and CNN-LSTM, respectively, with corresponding F1-scores of 92.97%, 96.73%, and 97.89%. CNN-LSTM achieved the highest overall test-set performance with 98.59% accuracy and 99.85% ROC-AUC, while XGBoost provided the strongest performance among the tree-based models. The results indicate that combining syntax-aware preprocessing and expanded lexical features with model-specific representations provides an effective framework for phishing URL classification.
Combining Convolutional Neural Networks and XGBoost for Phishing URL Classification Bagus Nurseto, Muhammad Narendra; Rafrastara, Fauzi Adi; Ghozi, Wildanil; Rakhmat Sani, Ramadhan; Susanto, Ajib; Hamadeh, Emad
Journal of Applied Informatics and Computing Vol. 10 No. 5 (2026): October 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i5.14097

Abstract

Cyber threat detection failures stem from the complexity of psychological exploitation tactics leveraging target anxiety and the limitations of traditional models in analyzing non-linear correlations within the structural features of malicious web URLs. To improve classification performance and computational efficiency in feature engineering, a sequential hybrid framework is developed by combining the spatial feature extraction capabilities of RGB Color Mapping image tensors via a Convolutional Neural Network (CNN) with tree-based boosting classifiers (XGBoost and LightGBM). Experiments are executed using a public dataset containing 11,055 observations, applying an 80:10:10 data splitting schema and isolated MinMaxScaler normalization to eliminate data leakage risks. The evaluation results demonstrate that the hybrid CNN + XGBoost model achieves the highest performance, with a validation accuracy of 97.83% and an F1-score of 98.06%, outperforming the replicated State-of-the-Art Random Forest baseline accuracy (97.38%). The metric stability confirms that the proposed architecture possesses robust generalization capabilities for implementation as a near real-time cyber defense system.
Co-Authors ., Junta Zeniarza ., Junta Zeniarza Abdussalam Abdussalam Abdussalam Abdussalam, Abdussalam Abu Salam Ade Nurul Aisyah Agnes Putri Istiwana Agung Priyo Utomo, Rino Agus Winarno Ahmad Khotibul Umam, Ahmad Khotibul Ajib Susanto Al zami, Farrikh Alomoush, Ashraf Alzami, Farrikh Annisa Ratna Salsabilla Ardytha Luthfiarta ARIYANTO, MUHAMMAD Arta Moro Sundjaja, Arta Moro Arunia, Aurelya Prameswari Asih Rohmani Asih Rohmani Asih Rohmani, Asih Atha Rohmatullah, Fawwaz Bagus Nurseto, Muhammad Narendra Bernadette Chayeenee Norman , Maria Budi Harjo Budi, Setyo Candra Irawan Catur Supriyanto Chaerul Umam Christy Atika Sari Darnell Ignasius Defri Kurniawan Defri Kurniawan Diana Aqmala Doheir, Mohamed Dwi Puji Prabowo, Dwi Puji Eko Hari Rachmawanto Elkaf Rahmawan Pramudya Erika Devi Udayanti Fahmi Amiq Farah Syadza Mufidah Farrikh Al Zami Farrikh Al Zami Fauzi Adi Rafrastara Fauzi Adi Rafrastara Florentina Esti Nilasari Florentina Esti Nilawati Galih Mentari Pangesti Guruh Fajar Shidik Hamadeh, Emad Hanny Haryanto Harun Al Azies Hercio Venceslau Silla Heru Lestiawan Hussein, Jasim Nadheer Hussein, Jassim Nadheer Ifan Rizqa Ignasius, Darnell Ika Novita Dewi Ika Novita Dewi Ikhwansyah Kurniawan Indra Gamayanto Iswahyudi ISWAHYUDI ISWAHYUDI Ivan Bayu Fachreza Junta Zeniarja Karin, Tan Regina Kiki Widia Kurniawan, Defri L. Budi Handoko Lekso Budi Handoko Maszuda, Akbar Alvian Megantara, Rama Aria Melati Anggreni Sitorus Mohamed Yassin, Warusia Muhammad Fais Ramadhani Muhammad Nabhan Rifa’i Muhammad Naufal MY. Teguh Sulistyono Nadya Azizah Nida Aulia Karima Novita Dewi , Ika Nugraha, Purwa Esti Paramita, Cinantya Pergiwati, Dewi Priyo Utomo, Rino Agung Pulung Nurtantio Andono Purwanto Purwanto Rahmawati, Firnanda Ramadhani, Dwi Arya Ratu Afi, Najwa Resha Meiranadi Caturkusuma Rhyan David Levandra Ricardus Anggi Pramunendar Richard Emmerig S. Sukamto, Titien Sarker, Md. Kamruzzaman Sasono Wibowo Sendi Novianto Sendi Novianto Sendi Novianto Setyo Budi Setyo Budi Sirait, Tamsir Hasudungan Soares, Gilardinho Javiere Oscoraldo Pedrosa Solichul Huda Sri Winarno Sri Winarno Suharnawi Suharnawi Suharnawi Suharnawi Suharnawi Sukamto, Titien S. Sukamto, Titien Suhartini Sulistyono, Teguh Syahrizal, Muhammad Iqbal Titien Suhartini Sukamto Titien Suhartini Sukamto Utomo, Danang Wahyu Wibowo, Isro' Rizky Wildanil Ghozi Winarsih, Nurul Anisa Sri Wulan Puspita Loka Yani Parti Astuti Yani Parti Astuti Yanuaresta, Dianna Yunita Ayu Pratiwi Yupie Kusumawati Yuventius Tyas Catur Pramudi Zahro, Azzula Cerliana Zami, Farrikh Al