Claim Missing Document
Check
Articles

Found 2 Documents
Search

Implementation of IoT in Water Quality Monitoring and Management System for Koi Fish Ponds Based on Web with RESTful API Ida Bagus Gede Baskara; Made Adi Paramartha Putra; Putu Trisna Hady Permana S; I Nyoman Yudi Anggara Wijaya; I Gede Juliana Eka Putra
JURAL RISET RUMPUN ILMU TEKNIK Vol. 4 No. 3 (2025): Desember : Jurnal Riset Rumpun Ilmu Teknik
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jurritek.v4i3.6828

Abstract

Technological advancements, particularly in microcontrollers and the Internet of Things (IoT), have brought significant changes to various aspects of life. Microcontrollers such as the ESP32, DS18B20 sensor, water pH sensor, and other supporting sensors enable the development of efficient automation systems. This research addresses issues related to the design and development of IoT devices for water quality monitoring, as well as the integration of these devices with web-based systems. The objective is to develop a device capable of monitoring water quality parameters such as pH, temperature, turbidity, dissolved materials, salinity projection, and dissolved oxygen projection, while providing automatic notifications under certain conditions. The development process applies the Agile methodology, which allows for rapid and adaptive iterations. Theoretically, this study contributes to improving understanding of IoT implementation and information systems, while practically, it provides a technological solution to support Koi fish farmers in monitoring and managing pond water quality. The expected outcome is a web-based water quality monitoring and management device for Koi ponds that can deliver real-time information and condition notifications, thereby reducing aquaculture risks and improving productivity.
Enhancing Federated Learning Performance through Adaptive Client Optimization with Hyperparameter Tuning Made Adi Paramartha Putra; I Komang Ram Pramartha Utama; Nengah Widya Utami; I Gede Juliana Eka Putra
Journal of Applied Data Sciences Vol 5, No 2: MAY 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i2.251

Abstract

The effectiveness of Industrial Internet of Things (IIoT) systems requires a robust fault detection mechanism, a task effectively accomplished by leveraging Artificial Intelligence (AI). However, the current centralized learning approach proves inadequate. In response to this limitation, Federated Learning (FL) enables decentralized training, ensuring the protection of individual data. The traditional FL settings are not sufficient to provide an effective learning process, which needs to be refined. This paper introduces an Adaptive Distributed Client Training (ADCT) mechanism designed to optimize performance for each FL participant, thereby establishing an efficient and resilient system. The proposed ADCT utilizes two parameters, namely the accuracy threshold and grid search step, to find the optimal hyperparameter for each client in a specific number of federation rounds. The evaluation results, conducted using the MNIST and FMNIST datasets in non-IID settings, indicate that the proposed ADCT enhances the F1-score by up to 37.13% compared to state-of-the-art methods.