Claim Missing Document
Check
Articles

Found 24 Documents
Search

Weighted ANOVA and Mutual Information for Enhanced Intrusion Detection System I Gede Teguh Satya Dharma; I Wayan Rizky Wijaya; I Made Agus Oka Gunawan; Made Pradnyana Ambara
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 11, No. 1, February 2026
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/kinetik.v11i1.2448

Abstract

The rapid escalation in the sophistication of network attacks has exposed the limitations of traditional Intrusion Detection Systems (IDS). While machine learning has shown great promise in enhancing IDS performance, its success often hinges on the effectiveness of feature selection. Standard feature selection techniques, however, struggle in cybersecurity applications due to the highly imbalanced nature of network traffic datasets. In such settings, minority attack classes—though critical—are often overshadowed by majority classes, leading to reduced detection of rare intrusions. To address this challenge, we propose a hybrid feature selection framework that integrates Analysis of Variance (ANOVA) and Mutual Information (MI) with a novel class-frequency weighting mechanism. This weighting scheme adjusts the relevance score of each feature according to the distribution of classes, ensuring that features associated with rare attacks are more strongly emphasized during the selection process. We evaluate our method on the UNSW-NB15 dataset using a Support Vector Machine classifier. The results show that our approach achieves substantial gains in recall for underrepresented classes while simultaneously reducing feature dimensionality and maintaining efficiency. By improving the visibility of features tied to minority attacks, the proposed framework provides a more balanced and reliable solution for modern IDS. This contribution advances the detection of rare but impactful threats and highlights a scalable pathway for building more resilient cybersecurity defenses.
Architecture of the Village Budget Reporting Information System Utilizing the CodeIgniter Framework and a Multi-User Role-Based Access Control Approach I Gusti Agung Oka Sudiadnyani; Made Pradnyana Ambara; I Made Riyan Adi Nugroho; I Made Agus Oka Gunawan
Jurnal Teknologi Informasi dan Pendidikan Vol. 20 No. 1 (2027): Jurnal Teknologi Informasi dan Pendidikan
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/jtip.v20i1.1158

Abstract

Digital transformation in village financial management requires a reporting system with high data integrity to support transparent supervisory functions. In Karangasem Regency, particularly in the pilot locus of Sibetan Village, the management of the Village Revenue and Expenditure Budget (APBDesa) faced challenges with data synchronization, administrative errors, and barriers to conventional audits. This study developed an audit-oriented APBDesa reporting information system architecture that integrates Multi-User Role-Based Access Control (RBAC) and automated logging mechanisms. System requirements were identified and validated through direct observation involving three key stakeholders representing the main reporting roles: the Head of Financial Affairs, the Village Head, and the External Auditor. System development followed four sequential Waterfall phases (requirements, design, implementation, and verification). The system was implemented using the CodeIgniter framework with a Model-View-Controller architecture. Black-box evaluation by five technical testers was organized into seven principal module-level test cases corresponding to authentication, dashboard, revenue management, expenditure management, verification and approval, RBAC, and external-auditor monitoring; all achieved a 100% functional success rate. The system enforced segregation of duties among the Head of Financial Affairs, the Village Head, and the External Auditor while supporting a structured digital audit workflow. These results indicate that embedded role controls and audit stages can strengthen data integrity, traceability, and accountability in APBDesa reporting.
Development of a Smart Repository Based on Rapid Application Development for Automation of Study Program Performance Report Preparation I Made Ari Dwi Suta Atmaja; Putu Wijaya Sunu; Made Pradnyana Ambara; I Made Agus Oka Gunawan
Jurnal Teknologi Informasi dan Pendidikan Vol. 20 No. 1 (2027): Jurnal Teknologi Informasi dan Pendidikan
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/jtip.v20i1.1159

Abstract

The Study Program Performance Report (LKPS) is an important document in the accreditation and quality evaluation process that requires accurate, consistent, and easily traceable data. LKPS management in the D2 Computer Network Administration Study Program at the Bali State Polytechnic is still carried out using separate spreadsheets and cloud-based document storage, which can lead to data duplication, difficulty tracking documents, and low coordination efficiency. This study aims to develop a Smart Repository, an integrated system that automates the management of LKPS data and documents. The system development uses the Rapid Application Development (RAD) method, which includes the stages of Requirements Planning, User Design, Construction, and Cutover. The system is built using the CodeIgniter 4 framework, MySQL database, Model-View-Controller (MVC) architecture, and Role-Based Access Control (RBAC) mechanisms. Black Box Testing results show that all system functions meet user requirements. Smart Repository integrates data and documents into a centralized repository, increasing management efficiency, strengthening data integrity, and supporting the digital transformation of LKPS preparation in higher education
Toward Amodal Instance Segmentation of Overlapping Concrete Aggregates via Occlusion-Conditioned Residual Correction I Gede Teguh Satya Dharma; I Nyoman Gede Arya Astawa; I Nyoman Suardika; Made Pradnyana Ambara
Journal of Applied Data Sciences Vol 7, No 4: December 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i4.1569

Abstract

Concrete aggregate characterization is important for quality control, particularly in estimating particle size and shape distributions. Although computer vision provides a faster alternative to conventional sieve analysis, overlapping particles can hide parts of their boundaries, causing visible-only segmentation to underestimate the complete particle geometry. This study proposes an occlusion-conditioned residual correction mechanism for amodal instance segmentation of overlapping concrete aggregates. Rather than predicting the complete mask from scratch, the method preserves the observed visible region and estimates only the missing geometry along its boundary, using the visible mask as an explicit physical constraint. Local boundary information is incorporated through a ring context to guide residual prediction. The proposed mechanism is implemented within a standard Mask R-CNN framework and evaluated on a synthetic aggregate dataset with controlled occlusion levels. Compared with the corresponding direct amodal baseline, the proposed method improves AP from 48.02% to 52.69%, while ablation results show an additional gain from the ring context. Qualitative results further indicate more faithful reconstruction of irregular contours, narrow gaps, and sharp corners with less excessive mask expansion. These findings support constrained residual reconstruction as an effective mechanism for amodal aggregate segmentation under occlusion.