Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Bulletin of Information Technology (BIT)

Rancang Bangun Sistem Top-Up Meteran PDAM Berbasis Mikrokontroller Indar Kusmanto; Yuyun; Andani Achmad
Bulletin of Information Technology (BIT) Vol 3 No 3: September 2022
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bit.v3i3.314

Abstract

This research aims to build a top-up based PDAM meter tools, which allows users to control water use in their daily needs. This type of research is experimental research where the scope of the problem can be carried out using the literature study method, field data collection methods. The system is made in the form of a prototype. This research produces a product in the form of a tool with a top-up as a payment system. This study uses an RFID sensor as a tool to enter voucher balances into the system. Then arduino uno as a controller of water use through a waterflow sensor and a solenoid valve instead of a faucet to close the water flow. The result of this research is that the device can display information in the form of remaining voucher balances and the amount of water consumption. In this study, water measurement trials have been carried out with an error value of 2.53 percent, and trial charging vouchers worth 20,000 to 100,000, as well as trial use and remaining balance with appropriate results
Klasifikasi Pembibitan Udang Vanamey Yang Ideal Menggunakan Algoritma Naive Bayes Hidayat Hidayat; Wardi; Andani Achmad; Yuyun
Bulletin of Information Technology (BIT) Vol 3 No 3: September 2022
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bit.v3i3.316

Abstract

Data mining is the process of finding information by looking for certain patterns or rules from large amounts of data. This study applies the Naïve Bayes algorithm to classify the yield of Vanamey shrimp into three classes, namely successful, less successful and failed from the harvest sample data owned. To facilitate the analysis, the data is divided into 2 categories, namely 90 training data and 10 for testing data. Nine parameters were used, namely the number of distributions, land area, type of disease, water color, soil conditions, season, feed, capital and yields. To validate the classification, we used a confusion matrix to test the accuracy of the algorithm. The test results show an accuracy of 54.4%, 100% precision, and 77.7% recall