Article Per Year (5 Year)
p-Index From 2021 - 2026
1.116
P-Index
This Author published in this journals
All Journal METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Jurnal Riset Informatika Journal of Intelligent Computing and Health Informatics (JICHI) Journal of Novel Engineering Science and Technology Jurnal Pengabdian Masyarakat
Irwansyah Saputra
Universitas Nusa Mandiri
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Dentistry Economics, Econometrics & Finance Electrical & Electronics Engineering Environmental Science Mechanical Engineering Medicine & Pharmacology Public Health

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

 1 
COMPARATIVE ANALYSIS OF THE K-NEAREST NEIGHBOR ALGORITHM ON VARIOUS INTRUSION DETECTION DATASETS Andri Agung Riyadi; Fachri Amsury; Irwansyah Saputra; Tiska Pattiasina; Jupriyanto Jupriyanto
Jurnal Riset Informatika Vol 4 No 1 (2021): Period of December 2021
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (945.029 KB) | DOI: 10.34288/jri.v4i1.341

Abstract

Security in computer networks can be vulnerable, this is because we have weaknesses in making security policies, weak computer system configurations, or software bugs. Intrusion detection is a mechanism for securing computer networks by detecting, preventing, and blocking illegal attempts to access confidential information. The IDS mechanism is designed to protect the system and reduce the impact of damage from any attack on a computer network for violating computer security policies including availability, confidentiality, and integrity. Data mining techniques have been used to obtain useful knowledge from the use of IDS datasets. Some IDS datasets that are commonly used are Full KDD, Corrected KDD99, NSL-KDD, 10% KDD, UNSW-NB15, Caida, ADFA Windows, and UNM have been used to get the accuracy rate using the k-Nearest Neighbors algorithm (k-NN). The latest IDS dataset provided by the Canadian Institute of Cybersecurity contains most of the latest attack scenarios named the CICIDS2017 dataset. A preliminary experiment shows that the approach using the k-NN method on the CICIDS2017 dataset successfully produces the highest average value of intrusion detection accuracy than other IDS datasets.
Resource Efficient Semantic Retrieval Pipeline via Generative Captioning and Text-to-Text Transformers for Bridging the Modality Gap Muhammad Firmansyah; Dhendra Marutho; Irwansyah Saputra; Eleni Vogiatzi
Journal of Intelligent Computing & Health Informatics Vol 6, No 2 (2025): September
Publisher : Universitas Muhammadiyah Semarang Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jichi.v6i2.19240

Abstract

The rapid expansion of multimodal digital content necessitates the development of robust information retrieval systems capable of bridging the semantic gap between visual and textual data. However, contemporary cross- modal models, such as CLIP, impose significant computational demands, rendering them impractical for real-time deployment in resource-limited environments. To address this efficiency challenge, this study introduces a novel lightweight retrieval pipeline that reconceptualizes cross-modal retrieval as a text-to-text task through generative transformation. The proposed methodology employs the Bootstrapped Language-Image Pretraining (BLIP) model to distill visual features into rich textual descriptions, which are subsequently encoded into dense semantic vectors using the T5 transformer architecture. Extensive experiments conducted on the MSCOCO and Flickr30K datasets demonstrate that the proposed pipeline achieves a Semantic Average Recall (SAR@5) of 0.561, significantly surpassing traditional lexical (BM25) and dense (SBERT) baselines. Notably, while the computationally intensive CLIP model retains a slight advantage in absolute accuracy, our approach delivers approximately 90% of CLIP’s semantic performance while enhancing inference throughput by 2.1× and reducing GPU memory consumption by 62%. These findings confirm that generative semantic distillation offers a scalable, cost-effective alternative to end-to-end multimodal systems, particularly for latency-sensitive applications requiring high semantic fidelity.
A Multimodal Graph-Based Recommendation Architecture for Vendor Discovery in Context-Aware Event Planning Nuryani Mawar Putri; Irwansyah Saputra
Journal of Novel Engineering Science and Technology Vol. 5 No. 01 (2026): Journal of Novel Engineering Science and Technology
Publisher : The Indonesian Institute of Science and Technology Research

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56741/jnest.v5i01.1050

Abstract

Context-aware vendor recommendation remains a critical challenge in dynamic event planning systems, particularly in multilingual and temporally sensitive markets such as Indonesia. This paper presents MAMRS (Multi-Agent Multimodal Recommendation System), a novel graph-based architecture that integrates semantic similarity, temporal availability, and user interaction history within a heterogeneous knowledge graph processed using Graph Attention Networks (GAT). The system uniquely combines CSR-aware attention mechanisms with a local LLM (Mistral-7B) to deliver explainable, sustainability-focused recommendations while preserving data privacy. MAMRS introduces three key innovations: (1) A GAT-based reasoning layer that dynamically weights vendor relevance using both structural relationships and corporate social responsibility (CSR) scores. (2) A fusion scoring engine that optimizes for semantic, temporal, behavioral, and sustainability constraints (achieving 93.4% CSR compliance in output, validated through grid search and rule-based scoring), (3) A locally deployed LLM that generates natural-language justifications with 18.7% higher BLEU scores, complemented by ROUGE-L (0.44) and METEOR (0.39), and validated through a small-scale Likert-scale user study (n=5). Evaluation on 250+ real user queries and 1,200+ vendor profiles from BuatEvent.id demonstrates that MAMRS achieves: (1) 21.3% improvement in top-3 accuracy over dense retrieval baselines (with p < 0.05, two-tailed t-test). (2) 1.6s average latency (1.9s p95) on local infrastructure. (3) 88.7% recall@5 in cold-start vendor scenarios, including new vendors with sparse metadata. This paragraph of the first footnote will contain the date on which you submitted your paper for review, which is populated by IEEE. It is IEEE style to display support information, including sponsor and financial support acknowledgments, here rather than in an acknowledgment section at the end of the article. The current implementation supports Indonesian and English queries, with future work planned for additional ASEAN languages and domains such as education and healthcare. These results position MAMRS as an effective solution for regulation-sensitive, multilingual event-planning platforms that require auditable, trustworthy, and scalable recommendation rationales.
Interplanetary File System for Custom Logging System Integrated with Smart Contract Onesinus Saut Parulian; Irwansyah Saputra
METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Vol. 9 No. 1 (2025): METHOMIKA: Jurnal Manajemen Informatika & Komputersisasi Akuntansi
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/jmika.Vol9No1.pp121-126

Abstract

The agricultural sector faces challenges in managing dynamic data during transactions, particularly price quotations between farmers and buyers. Traditional smart contract systems often lack the flexibility to handle real-time data changes. This research proposes a customized logging system that integrates smart contracts with the InterPlanetary File System (IPFS) within a web application. By storing data references (hashes) on the blockchain and actual logs on IPFS, the system ensures reliable data recording, flexibility in updating transaction logs, and improved storage efficiency. This integration enhances the system's ability to manage fluctuating agricultural transactions. The proposed method aims to create a robust framework for managing price quotations, which can be extended to other industries with similar requirements.
Multi-Stage Hybrid Retrieval with Neural Re-Ranking and Rule-Based Context Validation for Domain-Specific Retrieval-Augmented Generation Suharyadi; Irwansyah Saputra
Journal of Novel Engineering Science and Technology Vol. 5 No. 03 (2026): In Press - Journal of Novel Engineering Science and Technology
Publisher : The Indonesian Institute of Science and Technology Research

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56741/jnest.v5i03.2329

Abstract

Retrieval-Augmented Generation (RAG) has emerged as a widely adopted approach for grounding responses generated by large language models (LLMs) in external document corpora. However, conventional single-stage retrieval pipelines frequently fail to surface the most relevant context at top-ranked positions and lack explicit mechanisms to verify evidence adequacy prior to generation. This paper proposes a multi-stage RAG pipeline integrating three sequential components: hybrid retrieval combining BM25 and dense vector search via Reciprocal Rank Fusion (RRF), neural re-ranking using a cross-encoder transformer model, and a rule-based context validation gate that classifies retrieved context into three categories OK, WEAK, or ABSTAIN before answer generation. The system is evaluated on a domain-specific administrative corpus from the Indonesian AID Scholarship (TIAS) program using 50 annotated queries across four question types. Results demonstrate that hybrid retrieval improves recall at rank 10 (Recall@10) from 0.6391 to 0.8097 compared with BM25 alone, while neural re-ranking further increases mean reciprocal rank at rank 10 (MRR@10) from 0.6702 to 0.8040 (p = 0.0043, Wilcoxon signed-rank test). The complete pipeline achieves token-level F1 scores of 0.4429 and 0.4999 for the 4-billion-parameter (4B) and 12-billion-parameter (12B) model configurations, respectively, with a faithfulness score of 1.00. In comparison, the LLM-only baselines obtain token-level F1 scores below 0.09. The context validation mechanism correctly triggers ABSTAIN on 90% of out-of-domain queries, confirming its utility as a reliability control layer. These findings demonstrate that multi-stage retrieval with explicit context validation substantially improves both ranking quality and answer reliability in domain-specific RAG deployments.
Implementasi Artificial Intelligence untuk Meningkatkan Administrasi Dakwah Digital pada Jaringan Pemuda Remaja Masjid Indonesia Laela Kurniawati; Lindung Parningotan Manik; Irwansyah Saputra; Zico Pratama Putra
Jurnal Pengabdian Masyarakat Vol 2 No 1 (2026): Jurnal Pengabdian Masyarakat Universitas Islam Cordoba Banyuwangi
Publisher : LPPM Universitas Islam Cordoba Banyuwangi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.67008/1kzhnc25

Abstract

Perkembangan Artificial Intelligence (AI) memberikan peluang besar dalam meningkatkan efektivitas pengelolaan organisasi, termasuk organisasi dakwah. Namun, pemanfaatan teknologi digital pada organisasi pemuda dan remaja masjid masih menghadapi berbagai kendala, seperti pengelolaan data yang belum terpusat, dokumen administrasi yang belum terstandarisasi, serta proses penyusunan laporan dan publikasi yang masih dilakukan secara manual. Kegiatan pengabdian kepada masyarakat ini bertujuan meningkatkan kemampuan pengurus dan anggota Jaringan Pemuda Remaja Masjid Indonesia (JPRMI) dalam memanfaatkan AI untuk mendukung administrasi dakwah digital. Metode yang digunakan meliputi tahap persiapan, pelatihan, pendampingan, dan evaluasi. Kegiatan dilaksanakan secara luring dengan melibatkan 10 peserta. Hasil kegiatan menunjukkan bahwa peserta mampu memanfaatkan AI untuk penyusunan surat, notulen, laporan kegiatan, pengelolaan data, dan pembuatan konten publikasi dakwah. Hasil evaluasi menunjukkan 80% peserta sangat setuju bahwa kegiatan memberikan manfaat, 70% peserta sangat berminat mengikuti kegiatan serupa, dan 60% peserta menyatakan sangat puas terhadap pelaksanaan kegiatan secara keseluruhan. Kegiatan ini berhasil meningkatkan literasi digital, keterampilan administrasi, serta efisiensi pengelolaan organisasi dakwah berbasis teknologi.
Co-Authors Andri Agung Riyadi Dhendra Marutho Eleni Vogiatzi Fachri Amsury Jupriyanto . Laela Kurniawati Lindung Parningotan Manik Muhammad Firmansyah Nuryani Mawar Putri Onesinus Saut Parulian Suharyadi Zico Pratama Putra