Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Journal of Artificial Intelligence and Technology Information Riau Jurnal Teknik Informatika
Dita Novita Sari
Institut Bakti Nusantara
Computer Science & IT Engineering

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

Found 2 Documents
Search

 1 
Smart Farming: Optimalisasi Produksi Telur Ayam Petelur menggunakan Sistem Cerdas Monitoring Suhu dan Kelembaban Kandang Berbasis IoT Panji Pratomo; Kurniawan Saputra; Dita Novita Sari; Yoeyong Rahsel; Ricco Herdiyan Saputra; Bambang Suprapto; Henry Simanjuntak
Riau Jurnal Teknik Informatika Vol. 4 No. 1 (2025): Maret 2025
Publisher : Prodi Teknik Informatika Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjti.v4i1.3264

Abstract

Egg production of laying hens is influenced by various factors, including temperature, humidity, and the quality of the cage environment. The main problem in this study is the fluctuation of production due to changes in environmental conditions that are not optimal. This study aims to develop and implement a smart farming system based on the internet of things (IoT) that is able to optimize egg production of laying hens through automatic monitoring of cage temperature and humidity. The methods used include needs analysis, design, implementation and testing. The results showed that the accuracy of the system reached 80% which could maintain the cage environmental conditions within the optimal range, so that egg production increased from an average of 383.67 eggs per month to 390.33 eggs per month.
Application of AI Agentic Workflow Algorithms in Contemporary Business Process Automation Dita Novita Sari; Ricco Herdiyan Saputra
Journal of Artificial Intelligence and Technology Information (JAITI) Vol. 4 No. 3 (2026): Volume 4 Number 3 September 2026 (Issue in Progress)
Publisher : PT. Tech Cart Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58602/jaiti.v4i3.307

Abstract

Contemporary business process automation faces a critical anomaly: conventional Robotic Process Automation (RPA) frameworks often experience fatal runtime crashes when encountering minor structural variations in enterprise documents. This instability triggers severe operational bottlenecks and exponentially increases manual intervention costs. To resolve this fragility, this study proposes and evaluates a novel AI Agentic Workflow architecture based on Multi-Agent Reinforcement Learning. The dynamic system orchestrates specialized sub-agents, specifically Planning, Tool-Execution, and Self-Reflection agents, to enable autonomous fault tolerance and contextual reasoning without relying on rigid scripts. Experimental testing was conducted across standard, structural drift, and ambiguous input scenarios using 5,000 synthetic and real-world supply chain documents. The empirical results demonstrate that the multi-agent architecture drastically outperforms legacy RPA and single-prompt Large Language Models, achieving a 98.9% Task Success Rate under severe structural drift. Furthermore, the system recorded a 99.2% Error Self-Correction Efficiency, successfully resolving runtime faults autonomously without human triage. Although the cognitive reasoning loops introduced an increased mean latency of 19.8 seconds, the computational trade-off is justified by the elimination of technical debt. Ultimately, this framework ensures highly adaptive enterprise resource planning ecosystems, safeguarding business continuity against unpredictable data fluctuations and volatile external integrations.
Co-Authors Bambang Suprapto Henry Simanjuntak Kurniawan Saputra Panji Pratomo Ricco Herdiyan Saputra Yoeyong Rahsel