Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Jurnal Inkofar Jurnal Komtekinfo
Puspabhuana, Adam
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Engineering Industrial & Manufacturing Engineering Medicine & Pharmacology Public Health Transportation

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
The Role of Artificial Intelligence in Enhancing Cloud-Based Disaster Management Systems Puspabhuana, Adam; Andhika; Triyana, Yudi; Rifky Adhani, Muhamad
Jurnal KomtekInfo Vol. 12 No. 2 (2025): Komtekinfo
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/komtekinfo.v12i2.645

Abstract

Disaster management systems are vital in mitigating the impacts of natural and human-induced disasters. However, traditional methods often struggle with limitations in responsiveness and efficiency, particularly as disaster events become more frequent and severe. This study investigates the role of Artificial Intelligence (AI) in enhancing cloud-based disaster management systems, focusing on improving predictive, analytical, and operational capabilities. The research examines key AI technologies that can be integrated into cloud platforms, including machine learning, natural language processing, and computer vision. AI substantially improves disaster response and recovery by enhancing real-time data processing, decision-making, and resource allocation. The study also highlights AI's potential in early warning and risk assessment, providing decision-makers with more accurate and timely information. Empirical analysis suggests that AI-enhanced cloud systems significantly reduce response times and improve resource distribution during disaster events, reducing loss of life and property. The research concludes with practical recommendations for implementing AI in cloud-based disaster management and identifying areas for future exploration. The findings underscore the transformative potential of AI in creating more resilient disaster management infrastructures.
INTEGRASI CHATGPT, N8N, DAN SUPABASE UNTUK OTOMATISASI ANALISIS CV DAN PENCOCOKAN LOWONGAN KERJA BERBASIS VEKTOR Puspabhuana, Adam; Arliyanto, P Yudi Dwi; Abdurrahman, Mus’ab; Puspita, Ferdilla Ayu; Neta, Fandy
Jurnal Inkofar Vol 9, No 2 (2025)
Publisher : Politeknik META Industri Cikarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46846/jurnalinkofar.v9i2.492

Abstract

The advancement of Artificial Intelligence (AI) has accelerated digital transformation in the recruitment process through automated candidate data analysis. This study aims to develop a prototype of an intelligent recruitment system by integrating ChatGPT (OpenAI LLM), N8N (workflow automation framework), and Supabase (PostgreSQL-based vector database). The proposed system automatically analyzes job seekers’ Curriculum Vitae (CV) stored in Google Drive and transforms them into vector representations using AI embedding models. These vectors are then utilized to match candidate profiles with corresponding job requirements. N8N functions as a workflow orchestrator that connects data sources, AI models, and the Supabase vector database. ChatGPT serves as an interactive agent that enables recruiters to perform conversational analysis and information retrieval based on vectorized data. This research develops an intelligent recruitment prototype by integrating ChatGPT, N8N, and Supabase to automate CV analysis and job matching through vector embeddings. The system extracts CVs from Google Drive, converts them into high-dimensional embeddings, and stores them in Supabase for semantic similarity search. Quantitative evaluation using ten candidate datasets shows an average processing time of 25.6 seconds per batch and a 0.81 relevance score compared to manual screening. The results indicate that AI-driven automation can enhance recruitment efficiency and accuracy by reducing manual effort and bias.
Co-Authors Abdurrahman, Mus’ab Andhika Arliyanto, P Yudi Dwi Neta, Fandy Puspita, Ferdilla Ayu Rifky Adhani, Muhamad Triyana, Yudi