Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Indonesian Journal of Artificial Intelligence and Data Mining INTI Nusa Mandiri
Riadi Marta Dinata
Institut Sains dan Teknologi Nasional
Computer Science & IT

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Personalized Behavioral Analytics for GPS-Validated Attendance Systems Using K-Means Clustering and Individual-Baseline Anomaly Detection Ashari Abidin; Riadi Marta Dinata; Bambang Satrio; Risma Petrus; Seno Lamsir
Indonesian Journal of Artificial Intelligence and Data Mining Vol. 9 No. 1 (2026): March 2026
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study develops and evaluates a GPS-based attendance analytics framework integrating three complementary analytical layers for higher education environments. The proposed system combines spatial validation using Haversine-based geofencing, behavioral segmentation through K-Means clustering with multi-metric validation, and personalized anomaly detection employing individual-baseline Z-Score computation. Empirical evaluation utilized 4,300 attendance records from 13 lecturers at FSTT ISTN Jakarta over a 16-month period. K-Means clustering with K=3 achieved a Silhouette Score of 0.634 and a Davies-Bouldin Index of 0.621, identifying three behavioral segments: High Performers (30.8%), Moderate (38.5%), and Improvement Needed (30.8%). The personalized Z-Score method detected 19.9% more anomalies compared to population-based thresholds and reduced detection inequity across lecturer groups. Practically, the framework transforms passive attendance logging into a decision-support tool that enables differentiated monitoring, early behavioral change detection, and fairer evaluation policies. However, the study is limited by a relatively small sample size (13 lecturers) within a single institutional context, which may affect model generalizability. Broader validation across larger and multi-institutional datasets is recommended for future work.
SISTEM DETEKSI GEMPA BERBASIS IOT DENGAN VISUALISASI REAL-TIME DAN NOTIFIKASI CERDAS Riadi Marta Dinata; Ariman Ariman; Muhammad Ikrar Yamin
INTI Nusa Mandiri Vol. 19 No. 2 (2025): INTI Periode Februari 2025
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/inti.v19i2.6394

Abstract

Indonesia, as a region with high seismic activity, requires a fast, accurate, and reliable disaster mitigation system. However, most existing earthquake detection systems still focus primarily on data collection without automatic notifications, which delays response times in emergency situations. This study develops an Internet of Things (IoT)-based early earthquake detection system that integrates a gyroscope sensor, the ThingSpeak cloud platform, and an Android application to provide real-time information to users. The system detects orientation changes along the X, Y, and Z axes, calculates vibration magnitude through a calibrated algorithm, and sends automatic notifications via WhatsApp to mitigation officers. Testing was conducted through simulations using Wokwi to validate the algorithm and physical implementation in real-world conditions, demonstrating that the system achieves high accuracy in detecting seismic activity, with an average accelerometer magnitude of 3.35 and a gyroscope magnitude of 4.19. Data visualization on ThingSpeak, along with graphical displays in the Android application, enables intuitive and real-time earthquake monitoring. The integration of smart notifications via WhatsApp ensures a fast response from mitigation officers, making it an effective and applicable solution for earthquake risk mitigation.
PENGEMBANGAN SISTEM ROBOT PENJELAJAH BERBASIS MQTT MITIGASI BENCANA DENGAN DUKUNGAN IMAGE PROCESSING Riadi Marta Dinata; Muhammad Ikrar Yamin; Agus Sofwan; Ariman Ariman; Niko Purnomo Niko
INTI Nusa Mandiri Vol. 20 No. 1 (2025): INTI Periode Agustus 2025
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/inti.v20i1.7047

Abstract

Disaster mitigation is a global challenge that requires innovation to enhance the effectiveness of emergency response, particularly in the rapid and safe detection of victims. Although much research focuses on optimizing individual components such as sensors or algorithms, a gap remains in the development of holistically integrated frameworks. This study develops and evaluates an integrated explorer robot system based on Message Queuing Telemetry Transport (MQTT) and artificial intelligence for real-time disaster victim detection. Using a Design Science Research approach, the system architecture integrates an explorer robot based on ESP32-CAM and GPS for data acquisition, a central server running the You Only Look Once (YOLO) algorithm for image analysis, and involves a human operator for critical decision validation. Experimental results show that the system can detect victims with an average accuracy of 87.3% across various simulated scenarios. Communication via the MQTT protocol proved to be highly reliable and efficient, with an average latency of 127 ms and a packet loss rate of only 2.3%, enabling swift coordination between components. This research successfully validates an effective and replicable end-to-end architectural model, thereby presenting a practical blueprint for the development of low-cost Search and Rescue (SAR) robotic systems
Co-Authors Agus Sofwan Ariman Ariman Ashari Abidin Bambang Satrio Muhammad Ikrar Yamin Niko Purnomo Niko Risma Petrus Seno Lamsir