Pemanfaatan Convolutional Neural Network untuk Klasifikasi Citra Awan Menggunakan Raspberry Pi

Prismana, Rahdriawan and , Endang Wahyu Pamungkas, S.Kom., M.Kom, Ph.D (2024) Pemanfaatan Convolutional Neural Network untuk Klasifikasi Citra Awan Menggunakan Raspberry Pi. Skripsi thesis, Universitas Muhammadiyah Surakarta.

	PDF (Naskah Publikasi) Naskah.pdf Download (1MB)
	PDF (Surat Pernyataan Publikasi) Pernyataan-Publikasi_L200200031.pdf Restricted to Repository staff only Download (405kB) | Request a copy

Abstract

The rainy season can cause problems such as forgetfulness of items that are dried in the sun. This research aims to build a rain cloud image recognition model by utilizing computer vision and applying CNN technology and the Raspbery Pi embedded system. An important aspect in this research is cloud classification, by applying CNN the feature selection process will be done by computer and does not require human intervention. The cloud image Dataset uses the Multi-Class Weather Dataset taken from the Kaggle platform. In building the architecture, we will use the EfficientNet B3 architecture to extract and generate features from images, and use a Fully Connected Layer that is made separately following the specifications of the Dataset used in this study. The CNN model that has been trained is applied to Raspberry Pi for testing with images in the field. The evaluation results show that the accuracy of the model reaches 96% on the validation data and the loss is 0.557 on the same data. Confusion Matrix metric calculation, This after showing good evaluation results and performance, the next process is to install and run the model on the Raspberry Pi planting device. The Raspberry Pi device is able to run Deep Learning inference properly and issue output in the form of LED lights to find out the prediction results are rain or not, if it is detected as rain then the green LED light will be on and vice versa if it is not raining the red LED is on.

Item Type:	Thesis (Skripsi)
Uncontrolled Keywords:	CNN, EfficientNet B3, Klasifikasi awan, Raspberry Pi
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA75 Electronic computers. Computer science > QA751 Artificial Intelligence Q Science > QA Mathematics > QA75 Electronic computers. Computer science > QA753 Computer Systems and Networks T Technology > TZ Technical Information T Technology > TZ Technical Information > TA02 Software. Aplication > Pemograman
Divisions:	Fakultas Ilmu Komunikasi dan Informatika > Teknik Informatika
Depositing User:	RAHDRIAWAN PRISMANA
Date Deposited:	01 Aug 2024 07:23
Last Modified:	01 Aug 2024 07:23
URI:	http://eprints.ums.ac.id/id/eprint/125781

Actions (login required)

View Item