Claim Missing Document
Check
Articles

Analisis Sistem Monitoring dan Perancangan Alat Pendeteksi Kemiringan Tiang Listrik Dan Kerusakan Lampu Penerangan Jalan Umum (LPJU) Berbasis Internet of Things (IoT) Andi Muhammad Resky; Wardi Wardi; Abdul Latief Arda
Jurnal Mosfet Vol. 5 No. 2 (2025): 2025
Publisher : Fakultas Teknik Universitas Muhammadiyah Parepare (FT-UMPAR)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31850/jmosfet.v5i2.3971

Abstract

This study aims to design and implement an Internet of Things (IoT)-based monitoring system for detecting electric pole tilt and Public Street Lighting (LPJU) failures. Stable pole structures and optimal street lighting are critical to ensure public safety and comfort, especially at night. However, manual inspections are inefficient and often fail to provide early detection of infrastructure damage. The system was developed using NodeMCU ESP8266 integrated with a potentiometer-based tilt sensor and a voltage sensor. The sensors acquire data on pole tilt and LPJU status, which are transmitted via Wi-Fi to a web-based monitoring application. Experimental procedures were carried out through laboratory testing and limited field simulations to evaluate both hardware and software performance. The test results show that the tilt sensor provides a linear response between the tilt angle and the output voltage, allowing accurate detection of pole inclination. In addition, the system successfully identified LPJU conditions (on/off) and displayed them in real-time on the monitoring dashboard. In conclusion, the proposed IoT-based monitoring system has proven reliable in detecting pole tilt and LPJU failures. This approach not only improves the efficiency of infrastructure maintenance but also contributes to the development of smart city solutions through more advanced and real-time monitoring technologies
Comparative Analysis of CNN, MobileNetV2 and EffecientNetBO in Smart Farming System for Chili Leaf Disease Detection Abdul Latief Arda; Syamsu Alam; Matalangi
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 6 (2025): December 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i6.6709

Abstract

Chili leaf diseases greatly affect agricultural productivity, making early and accurate detection essential to support smart farming systems. This study presents a comparative analysis of three deep learning architectures—Convolutional Neural Network (CNN), MobileNetV2, and EfficientNetB0—for detecting chili leaf diseases using RGB images. The dataset consists of three main disease classes: Bacterial Spot, Curl Virus, and White Spot. Each model was trained and evaluated using accuracy, precision, recall, F1-score, macro AUC, and training time as performance metrics. Experimental results show that MobileNetV2 achieved the highest performance with 99% accuracy, 0.99 F1-score, and 0.99 macro AUC, although it required the longest training time of 115.12 seconds. CNN demonstrated competitive results with 96% accuracy and the shortest training time of 60 seconds, while EfficientNetB0 performed poorly with only 38% accuracy and an F1-score of 0.18. These findings highlight that model architecture, dataset characteristics, and training configuration significantly influence performance outcomes. This study contributes to the development of intelligent agricultural monitoring systems by identifying the most suitable deep learning architecture for real-time chili leaf disease detection in smart farming applications.
Performance Evaluation of IoT-Based AC Control Using Multi-Modal Fuzzy Sensors Amiruddin A; Abdul Latief Arda; Abdul Jalil; Andani Achmad; Supriadi Sahibu; Yuyun Yuyun
Journal of System and Computer Engineering Vol 7 No 2 (2026): JSCE: April 2026
Publisher : Universitas Pancasakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61628/jsce.v7i2.2649

Abstract

his study addresses the challenge of controlling Air Conditioner (AC) temperature in enclosed spaces in tropical climates, where improper operation often leads to thermal discomfort and excessive energy consumption. The research aims to develop and implement an Internet of Things (IoT)-based system for monitoring and controlling AC temperature by integrating multi-modal sensors and applying a fuzzy logic approach. The proposed system employs a DHT22 sensor to measure temperature and humidity, a thermopile sensor to capture human body temperature, and a PIR sensor to detect occupancy and movement within the room. Sensor data are processed using an ESP32 microcontroller with FreeRTOS-based multitasking and transmitted to the Blynk platform for real-time monitoring. Decision-making is carried out using fuzzy logic based on the temperature difference (ΔT) between body temperature and ambient conditions to automatically regulate AC operation. Experimental results indicate that the system performs reliably and provides adaptive control, achieving a fuzzy logic accuracy of 64.34% under real-world conditions. Furthermore, the automated control mechanism reduces energy consumption by 35.7% compared to conventional manual operation. Overall, the findings confirm that the integration of multi-modal sensing, IoT technology, and fuzzy logic can effectively enhance energy efficiency while maintaining thermal comfort in indoor environments.
PERSONAL MOBILITY ASSISTANT UNTUK MENUNJANG MOBILITAS AMAN BAGI ANAK DI KOTA KENDARI MENGGUNAKAN ALGORITMA RANDOM FOREST DAN PENDEKATAN CONTEXT-AWARENESS Etika Purnamasari; Hazriani Hazriani; Abdul Latief Arda
Information System Journal Vol. 8 No. 02 (2025): Information System Journal (INFOS)
Publisher : Universitas Amikom Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24076/infosjournal.2025v8i02.2417

Abstract

Penelitian ini bertujuan mengembangkan aplikasi Personal mobility assistant untuk mendukung mobilitas aman anak di Kota Kendari. Sistem dirancang untuk memprediksi tingkat keamanan lokasi menggunakan algoritma Random Forest berdasarkan lima fitur location context: pertemuan dengan orang asing, kepadatan lalu lintas, pencahayaan, visibilitas, dan pantauan CCTV. Dataset diperoleh dari observasi lapangan pada 96 titik lokasi dengan total 279 variasi data, kemudian diolah menggunakan Python dan diintegrasikan ke aplikasi Flutter melalui API Flask. Hasil pelatihan model menunjukkan akurasi rata-rata 94,64% dengan 5-fold cross-validation, serta akurasi 100% pada 56 data uji. Parameter pengguna dan waktu diterapkan dengan pendekatan rule based untuk memberikan respons sesuai usia dan kondisi. Uji coba aplikasi menunjukkan peringatan dalam 1 detik dan performa yang efisien. Penelitian ini membuktikan bahwa sistem mampu mengklasifikasi keamanan lokasi dan berfungsi efektif untuk meningkatkan keselamatan mobilitas anak.
Co-Authors Abdul Jalil Abdul Jalil Abdul Rahman Agussalim Agussalim Agussalim, Agussalim Akbar Iskandar Akmal Hidayah A Aksa, Andi Nurul Amiruddin A Andani Achmad Andani Achmad Andani Achmad Andani Ahmad Andi Muhammad Resky Andi Taufiqurrahman Akbar Andi Zulkifli Nusri Andryanto A Ansar Ansar Antonius Riman Tampang Arthanugraha, Wahyu As'ad, Miftah Fadhli ASNIMAR ASNIMAR, ASNIMAR Dhimas Tribuana Dra Najira Umar Erwin, Ibnu Taimiyah Etika Purnamasari Eva Yulia Puspaningrum Fajar Husain Asy'ari Fakhirah, Andi Lulu Guntur Guntur Hakis, Andi Wahyunita Hasanuddin, Zulfajri B Hasruddin Hasruddin. B Hazriani Hazriani, Hazriani Hermawati Mappiwali Hilyatul Auliyah Erwin Holyness Nurdin Singadimedja Imam Akbar Imam Akbar, Imam Imran Taufik Imran Taufiq Iskandar Surdin Isman Ita Sarmita Samad Ita Sarmita Samad, Ita Sarmita J Sadly, Adnan Jusman Jusman Kherani, Riska M. Risal Mashur Razak Matalangi Matalangi Matalangi Muh Al Hijr Asqalani Muh. Fauzan Said Muhammad Erwin Rosyadi. S Munawirah, Munawirah Nasrullah Nasrullah Nasrullah Nasrullah Nur Iman Nurahmad Nurul Humaera Baharudin Rabi’a H Maudjik Rahmaniar Rahmaniar, Rahmaniar Rian Sultan Asizan Rijal Rijal Saidi, Muliyana Sarmila, Sarmila Sitti Sahara Syamel Sumarlina Sumarlina Supriadi Sahibu Syafruddin Syarif SYAMSU ALAM Symsu Alam Syuryadi, Syuryadi Taufik, Imran Tengku Riza Zarzani N Umar, Dra Najira Wardhani, Nurilmiyanti Wardi Wardi Wardi Wardi Wardi Wardi Wardi, Wardi Weya, Sermi Yuyun Yuyun Yuyun, Yuyun Zahir Zainuddin Zahir Zainuddin Zahir Zainuddin Zanudin Husain Zuhriyah, Sitti