Monitoring dan Klasifikasi Kualitas Air Kolam Ikan Gurami Berbasis Internet of Things Menggunakan Metode Naive Bayes

Jurnal Komtika (Komputasi dan Informatika) Pub Date : 2023-11-30 DOI:10.31603/komtika.v7i2.10200

Arip Kristiyanto, Fari Katul Fikriah, Rully Inkiriwang, Zulfi Andriansah

{"title":"Monitoring dan Klasifikasi Kualitas Air Kolam Ikan Gurami Berbasis Internet of Things Menggunakan Metode Naive Bayes","authors":"Arip Kristiyanto, Fari Katul Fikriah, Rully Inkiriwang, Zulfi Andriansah","doi":"10.31603/komtika.v7i2.10200","DOIUrl":null,"url":null,"abstract":"Ministry of Marine Affairs and Fisheries (KKP) noted that Indonesia produced 56,539 tons of gourami fish in the second quarter of 2022 High market demand and economical selling prices encourage farmers to cultivate gourami fish. In cultivating gourami fish there are several obstacles, for example, disease caused by poor water quality. Water quality is the main parameter in the success of gourami fish farming. This research aims to develop a water quality monitoring system based on the Internet of Things. The system prototype uses a temperature sensor (DS18B20), Ph sensor (dfrobot SEN0161), turbidity sensor (dfrobot SEN0189), flowmeter, and ultrasonic sensor (JSN-SR04) as input. The Arduino Mega R3 microcontroller is the processor and the Oled module (SSD1306) is the output. Thingboard is a cloud server that functions as sensor data monitoring. Temperature sensor testing results (DS18B20) average error 0.48%, Ph(dfrobot SEN0161) sensor testing average error 0.64%, ultrasonic sensor testing (JSN-SR04) average error 7.83%, testing Turbidity sensors can measure the level of water turbidity. Next, the water quality parameter data is processed using the Naïve Bayes algorithm method for classifying the water quality of gourami ponds. The results of this classification obtained an accuracy of 99.94% a Kappa Statistics value of 0.9989 and a Mean Absolute Error of 0.0003","PeriodicalId":292404,"journal":{"name":"Jurnal Komtika (Komputasi dan Informatika)","volume":"38 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Jurnal Komtika (Komputasi dan Informatika)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.31603/komtika.v7i2.10200","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

Ministry of Marine Affairs and Fisheries (KKP) noted that Indonesia produced 56,539 tons of gourami fish in the second quarter of 2022 High market demand and economical selling prices encourage farmers to cultivate gourami fish. In cultivating gourami fish there are several obstacles, for example, disease caused by poor water quality. Water quality is the main parameter in the success of gourami fish farming. This research aims to develop a water quality monitoring system based on the Internet of Things. The system prototype uses a temperature sensor (DS18B20), Ph sensor (dfrobot SEN0161), turbidity sensor (dfrobot SEN0189), flowmeter, and ultrasonic sensor (JSN-SR04) as input. The Arduino Mega R3 microcontroller is the processor and the Oled module (SSD1306) is the output. Thingboard is a cloud server that functions as sensor data monitoring. Temperature sensor testing results (DS18B20) average error 0.48%, Ph(dfrobot SEN0161) sensor testing average error 0.64%, ultrasonic sensor testing (JSN-SR04) average error 7.83%, testing Turbidity sensors can measure the level of water turbidity. Next, the water quality parameter data is processed using the Naïve Bayes algorithm method for classifying the water quality of gourami ponds. The results of this classification obtained an accuracy of 99.94% a Kappa Statistics value of 0.9989 and a Mean Absolute Error of 0.0003

查看原文本刊更多论文

使用 Naive Bayes 方法监测和分类基于物联网的斑鲤鱼池塘水质

海洋事务和渔业部（KKP）指出，2022 年第二季度印尼生产了 56539 吨胭脂鱼。高市场需求和经济实惠的销售价格鼓励农民养殖胭脂鱼。在养殖胭脂鱼的过程中会遇到一些障碍，例如水质差导致的疾病。水质是胭脂鱼养殖成功与否的主要参数。本研究旨在开发一个基于物联网的水质监测系统。系统原型使用温度传感器（DS18B20）、Ph 传感器（dfrobot SEN0161）、浊度传感器（dfrobot SEN0189）、流量计和超声波传感器（JSN-SR04）作为输入。Arduino Mega R3 微控制器是处理器，Oled 模块（SSD1306）是输出。Thingboard 是一个云服务器，具有传感器数据监控功能。温度传感器测试结果（DS18B20）平均误差为 0.48%，Ph（dfrobot SEN0161）传感器测试平均误差为 0.64%，超声波传感器测试（JSN-SR04）平均误差为 7.83%，测试浊度传感器可以测量水的浊度水平。接下来，使用奈伊夫贝叶斯算法对水质参数数据进行处理，以对库页岛池塘的水质进行分类。分类结果的准确率为 99.94%，Kappa 统计值为 0.9989，平均绝对误差为 0.0003。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Jurnal Komtika (Komputasi dan Informatika)

自引率

0.00%

发文量