Claim Missing Document
Check
Articles

Found 2 Documents
Search

Enhancing Hazy Image Quality with a Modular CNN Encoder–Decoder ANDIKA MUHAMMAD NUR KHOLIQ; ARIEF SURYADI SATYAWAN; MOKH MIRZA ETNISA HAQIQI; FAJAR RAHMAT AKBAR; IASYA FAIQOH NURROHMAH; AULIA ADAWIYAH; ESTI FITRIA WULANDARI; RENDI TRI SUGIAN
ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika Vol 14, No 1: Published January 2026
Publisher : Institut Teknologi Nasional, Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/elkomika.v14i1.69

Abstract

This study develops a modular CNN encoder–decoder framework for single-image dehazing by replacing the conventional bottleneck with interchangeable token-mixing modules such as FNet, Spatial-FNet, MLP-Mixer, and gMLP-style designs. The pipeline integrates adaptive preprocessing (CLAHE and histogram matching), photometric augmentations, and training on a controlled subset of the SOTS dataset. Comprehensive quantitative and qualitative evaluations demonstrate substantial improvements over a baseline CNN, with mean PSNR increasing from approximately 18.4 dB to the 23.0–24.0 dB range and SSIM rising from about 0.75 to roughly 0.89–0.91. However, several variants require careful hyperparameter selection and loss-weight tuning to achieve stable performance. The results offer practical guidance for deployment in real-world vision systems.
Rancang Bangun Sistem Irigasi Otomatis Berbasis Jaringan Sensor Nirkabel dan Monitoring Web Laravel Ilham Padia; Risan Fathan; Muhammad Irzi Suryanto Putra; Muhammad Nizar; Ade Rukmana; Sipa Nurpadillah; Andika Muhammad Nur Kholiq
Jurnal JTIK (Jurnal Teknologi Informasi dan Komunikasi) Vol 11 No 1 (2026): JANUARY
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/jtik.v11i1.7838

Abstract

Conventional irrigation often triggers water waste or crop failure due to inaccurate manual scheduling. This study aims to design, implement, and evaluate a web-based smart irrigation system prototype to optimize water management using Wireless Sensor Networks (WSN). The methodology utilizes a star topology with two YL-69 sensor nodes transmitting data via the ESP-NOW communication protocol directly to an ESP32 Gateway integrated with a Laravel website. The calibration procedure was strictly conducted through 30 independent reading repetitions for each soil variant sample. Experimental results show high accuracy with a Mean Absolute Percentage Error (MAPE) of 1.58% and a minimum error of 0.04% in extreme water-saturated conditions. The hardware system successfully controls a 12V solenoid valve based on an inverted active-low threshold control algorithm of < 40%. The Laravel platform achieves real-time telemetry synchronization without data lag, supported by network performance with a Packet Delivery Ratio (PDR) above 99% and stable latency between 242–252 ms. In conclusion, this system provides an efficient, fail-safe, and automated remote monitoring solution to support precision farming.