Claim Missing Document
Check
Articles

Found 2 Documents
Search

IMPROVED DESIGN AND ACCURACY OF REAL-TIME WATER QUALITY AND FILTERING SYSTEMS FOR APPLICATION IN IOT-BASED AQUACULTURE Desnanjaya, I Gusti Made Ngurah; Nugraha, I Made Aditya; Ariana, Anak Agung Gde Bagus
Jurnal Riset Akuakultur Vol 20, No 1 (2025): Maret (2025)
Publisher : Politeknik Kelautan dan Perikanan Jembrana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15578/jra.20.1.2025.27-47

Abstract

Maintaining optimal water quality is essential in fish farming, as fluctuations in key parameters, such as pH, turbidity, and dissolved compounds, can lead to stress, disease, and even fish death. This study aimed to design and develop an Internet of Things (IoT)-based water quality monitoring and filtration system that can operate in real-time to support the sustainability of aquaculture. This system integrated pH, turbidity, total dissolved solids (TDS), and ultrasonic sensors with Arduino Uno and ESP32 microcontrollers. Sensor data was transmitted in real-time to an Android application, which displayed it on an LCD, allowing users to monitor water quality and receive alerts when parameters deviated from optimal thresholds. The test results demonstrated a high level of sensor accuracy, specifically 96.51% for pH, 98.19% for TDS, and 97.03% for turbidity, as determined through comparisons with laboratory equipment, commercial devices, and manual measurements. The effectiveness of the filtration system was also proven to be significant: turbidity was reduced by an average of 58.87%, TDS decreased by 26.80%, and pH values became more stable within the optimal range for aquaculture with an improvement of 7.3%. This system was able to maintain the variation of the main water quality parameters within the ranges for raw and drinking water stipulated in Indonesian Government Regulation No. 22 of 2021 and Regulation of the Minister of Health No. 492 of 2010. This improved design is arguably more efficient than conventional methods because it reduces the need for labor and provides early warning of changes in water quality. Menjaga kualitas air yang optimal sangat penting dalam budidaya ikan, karena fluktuasi parameter utama seperti pH, kekeruhan, dan kandungan zat terlarut dapat menyebabkan stres, penyakit, hingga kematian pada ikan. Penelitian ini bertujuan untuk merancang dan mengembangkan sistem pemantauan dan penyaringan kualitas air berbasis internet of things (IoT) yang dapat beroperasi secara real-time untuk mendukung keberlanjutan akuakultur. Sistem ini mengintegrasikan sensor pH, turbiditas, total dissolved solids (TDS), dan sensor ultrasonik dengan mikrokontroler Arduino Uno dan ESP32. Data sensor ditransmisikan secara real-time ke aplikasi Android dan ditampilkan melalui LCD, memungkinkan pengguna memantau kualitas air dan menerima peringatan ketika parameter menyimpang dari ambang batas optimal. Hasil pengujian menunjukkan tingkat akurasi sensor yang tinggi, yaitu 96,51% untuk pH, 98,19% untuk TDS, dan 97,03% untuk kekeruhan, berdasarkan perbandingan dengan alat laboratorium, perangkat komersial, dan pengukuran manual. Efektivitas sistem filtrasi juga terbukti signifikan: kekeruhan berkurang rata-rata 58,87%, TDS menurun sebesar 26,80%, dan nilai pH menjadi lebih stabil dalam kisaran optimal untuk akuakultur dengan perbaikan sebesar 7.3%. Sistem ini telah memenuhi ketentuan Peraturan Pemerintah No. 22 Tahun 2021 dan Peraturan Menteri Kesehatan No. 492 Tahun 2010 untuk kualitas air baku dan minum. Sistem ini terbukti lebih efisien dibanding metode konvensional karena mengurangi kebutuhan tenaga kerja dan memberikan peringatan dini terhadap perubahan kualitas air.
Music-Structure Segmentation in Balinese Gamelan (Tabuh Lelambatan) with SSM, Checkerboard Novelty, and HMM Pertiwi, Ni Nyoman Sucianta; Ariana, Anak Agung Gde Bagus; Meinarni, Ni Putu Suci; Willdahlia, Ayu Gede; Ariantini, Made Suci
Sinkron : jurnal dan penelitian teknik informatika Vol. 10 No. 1 (2026): Article Research January 2026
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v10i1.15494

Abstract

This study aims to automatically segment the musical structure of Balinese gamelan by combining the Self-Similarity Matrix (SSM) method, the Checkerboard Novelty kernel, and Hidden Markov Models (HMM). Balinese gamelan has a complex musical structure that is cyclical and based on a colotomik system, requiring an adaptive analytical approach to repetitive patterns and transitions between musical sections. The research data consists of 30 Tabuh Lelambatan gamelan audio recordings obtained from public digital sources and validated through expert annotation to produce ground truth. The segmentation process was carried out through feature extraction using Constant-Q Transform (CQT), SSM formation to detect acoustic similarity patterns, application of the checkerboard kernel to mark transitions between segments, and temporal sequence modeling using HMM to refine boundary detection. System performance evaluation was carried out by comparing the segmentation results with ground truth using precision, recall, and F1-score metrics. The test results showed an average macro precision value of 0.998, a recall of 0.705, and an F1-score of 0.818, indicating that this method is capable of detecting the main boundaries of musical structures with high accuracy and consistent stability. However, the model still tends to miss gradual micro transitions. This research contributes to the field of Music Information Retrieval (MIR) and supports efforts to preserve traditional Balinese music through data-based analysis and the development of music computing technology.