Claim Missing Document
Check
Articles

Found 3 Documents
Search

Explainable Machine Learning for Network Intrusion Detection Using SHAP-Based Feature Interpretation Eka Wahyu Sholeha; Dery Yuswanto Jaya; Qorry Aina Fitroh
CHAIN: Journal of Computer Technology, Computer Engineering, and Informatics Vol. 4 No. 3 (2026): Volume 4 Number 3 July 2026
Publisher : PT. Tech Cart Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58602/chain.v4i3.283

Abstract

Network Intrusion Detection Systems (NIDS) play a crucial role in protecting computer networks from increasingly sophisticated cyberattacks. Although machine learning techniques have demonstrated high detection performance, many models operate as black-box systems, making it difficult for security analysts to understand the reasoning behind prediction outcomes. This study proposes an explainable machine learning framework for network intrusion detection using the Random Forest algorithm and SHAP (SHapley Additive exPlanations)-based feature interpretation. The CICIDS2017 Friday-WorkingHours-Afternoon-DDos dataset was utilized to evaluate the effectiveness of the proposed approach. Data preprocessing included data cleaning, handling missing values, label encoding, and dataset partitioning. The Random Forest classifier was trained and evaluated using Accuracy, Precision, Recall, and F1-Score metrics. Experimental results demonstrated excellent classification performance, achieving an accuracy of 99.9889%, precision of 99.9922%, recall of 99.9883%, and F1-score of 99.9902%. Furthermore, SHAP analysis was employed to improve model interpretability by identifying the contribution of individual features to intrusion detection decisions. The results revealed that Fwd Packet Length Max, Destination Port, Avg Fwd Segment Size, and Fwd Packet Length Mean were among the most influential features affecting classification outcomes. The integration of Random Forest and SHAP not only achieved highly accurate intrusion detection but also enhanced transparency and trustworthiness by providing meaningful explanations for model predictions. Therefore, the proposed framework offers an effective and interpretable solution for network intrusion detection in modern cybersecurity environments.
Analisis Statistik Pengaruh Mata Kuliah Ekonometrika Terhadap Minat Mahasiswa Jurusan Ekonomi dalam Penelitian Kuantitatif Arwin Wahyu Saputra; Liny Mardhiyatirrahmah; Dewi Indra Anggraeni; Dery Yuswanto Jaya; I Made Candra Girinata; Budi Styawan
Griya Journal of Mathematics Education and Application Vol. 6 No. 2 (2026): Juni 2026
Publisher : Pendidikan Matematika FKIP Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/griya.v6i2.1089

Abstract

Penelitian ini bertujuan untuk menganalisis pengaruh penguasaan mata kuliah Ekonometrika terhadap minat mahasiswa dalam melakukan penelitian kuantitatif. Penguasaan metode kuantitatif merupakan kompetensi penting bagi mahasiswa ekonomi dalam menghadapi tantangan penelitian berbasis data. Penelitian ini menggunakan pendekatan kuantitatif dengan desain survei. Data dikumpulkan melalui kuesioner skala Likert dan dokumentasi nilai akhir mata kuliah Ekonometrika. Sampel penelitian terdiri atas mahasiswa Program Studi Ekonomi Syariah STAI Al-Gazali Soppeng yang telah menempuh mata kuliah Ekonometrika. Analisis data dilakukan menggunakan korelasi Pearson dan regresi linear sederhana setelah terlebih dahulu memenuhi uji asumsi klasik. Hasil penelitian menunjukkan bahwa penguasaan mata kuliah Ekonometrika berpengaruh positif dan signifikan terhadap minat mahasiswa dalam penelitian kuantitatif dengan koefisien regresi sebesar 0,654 dan nilai signifikansi . Koefisien determinasi menunjukkan bahwa penguasaan Ekonometrika menjelaskan 39,9% variasi minat penelitian kuantitatif mahasiswa. Temuan ini menegaskan pentingnya pembelajaran Ekonometrika yang aplikatif dan berpusat pada mahasiswa untuk meningkatkan minat dan keterlibatan mahasiswa dalam penelitian kuantitatif.
Optimizing The Use Of Wi-Fi Bandwidth In The Bumi Jaya Village Office Environment Eka Wahyu Sholeha; Herpendi; Dery Yuswanto Jaya; Dewi Indra Anggraeni
Jurnal Abdimas Cendekiawan Indonesia Vol. 2 No. 2 (2025): May
Publisher : Yayasan Cendekiawan Digital Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56134/jaci.v2i2.120

Abstract

The efficient management of internet networks in public service environments is critical to supporting productivity and ensuring uninterrupted administrative operations. In Bumi Jaya Village, Pelaihari, Tanah Laut Regency, South Kalimantan, unrestricted use of Wi-Fi particularly for online gaming by local youth had disrupted office activities and compromised service quality. To address this issue, this study implemented the Queue Tree bandwidth management feature on Mikrotik devices, aimed at optimizing network performance and prioritizing essential services. The research was conducted through initial surveys and observations to assess usage patterns and existing infrastructure. A customized Queue Tree configuration was then applied to limit bandwidth for non-essential activities while preserving access. The results demonstrated a substantial improvement in bandwidth efficiency, with administrative and public service tasks receiving consistent and prioritized connectivity. Moreover, the initiative contributed to a more professional work atmosphere, reducing distractions, noise, and improper use of public facilities. Importantly, the program also involved capacity building for village office staff, equipping them with practical knowledge to monitor and manage the network sustainably. This approach not only resolved technical issues but also supported the development of digital governance competencies at the local level. The implementation of Queue Tree proved to be a strategic solution that enhances digital infrastructure, promotes responsible internet use, and fosters a more effective public service environment.