Search for collections on Pradita Repository

Supervised learning from data mining on process data loggers on micro-controllers

Saputra, Adi Dwifana and Hindarto, Djarot and Haryono, Haryono (2023) Supervised learning from data mining on process data loggers on micro-controllers. Sinkron : Jurnal dan Penelitian Teknik Informatika, 7 (1). ISSN 2541-2019

[thumbnail of 11942-Article Text-9487-1-10-20230101.pdf] Text
11942-Article Text-9487-1-10-20230101.pdf - Published Version

Download (730kB)

Abstract

In processing data science, data is needed as input. Sometimes the data needed is not available in public data, this is where the purpose of this research was made. The acquisition process is very important to process information into data. After that, the data is processed to make a decision. Microcontrollers in controlling conditions, such as temperature, and humidity are very common devices, and many studies have been carried out. Sometimes discussing it just shows how to serialize and save it on online platforms, like firebase, tinger.io and many other online platforms. So that the process of storing data on external or online platforms is an advantage for platform providers, where platform providers don't need to do business and get data for free. This is unnoticed by researchers who have produced microcontroller devices. The many platforms for storing data range from hardware and software. Some tools are paid or open source. This research uses software that is open source. Because using open source-based tools will be easy to develop and for further research purposes. The development of further research by entering the code into the microcontroller system or what is called an embedded system. Data is a very valuable asset. Because data is one of the most important components in processing data science. And better take care of the data logger. This study uses a microcontroller and ultrasonic distance sensor and potentiometer. The method from the results of the logger (dataset) is used for classification using the support vector machine and decision tree algorithms. Accuracy with the support vector machine reaches 97% and the decision tree reaches 100% accuracy

Item Type: Article
Subjects: T Technology > T Technology (General)
Depositing User: Pradita Librarian
Date Deposited: 03 May 2024 08:47
Last Modified: 03 May 2024 08:47
URI: https://repository.pradita.ac.id/id/eprint/272

Actions (login required)

View Item
View Item