Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Marrisaeka Mawarni
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Sistem Klasifikasi Langit Cerah dan Berawan menggunakan Gray Level Co-Occurrence Matrix dan K-Nearest Neighbor berbasis Raspberry Pi Marrisaeka Mawarni; Hurriyatul Fitriyah; Rizal Maulana
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 6 (2021): Juni 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Weather is a condition in the atmosphere that occurs in an area in a short time. Weather can be predicted by observing weather elements, such as clouds. This research will perform a weather classification based on sky and clouds conditions in the form of sunny and cloudy weather. Sunny weather occurs when the sun shines brights, and there are no clouds in the sky. Cloudy weather occurs when sunlight is covered by clouds that contain water vapor in the atmosphere. The system used fisheye images so that we have a wider field of view images than panoramic images. The classification process for clear and cloudy skies uses the Gray Level Co-occurrence Matrices (GLCM) method to extract the texture features. The features for the classification of sky conditions in the GLCM method are energy, contrast, correlation, homogeneity, and dissimilarity with four angular variations, namely 0,45,90, and 135. The sky classification process is using the K-Nearest Neighbor method with k = 3,5,7, and 9. The Raspberry Pi 4 is used for the whole data processing, and then the classification results are displayed on the LCD. the Accuracy testing was carried out using k-fold with 5 fold, obtaining an average accuracy result of 100% and an average computation time of 2.3516 seconds.
Co-Authors Fitriyah, Hurriyatul Rizal Maulana