Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Anugrah Zeputra
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 
Perbandingan Akurasi untuk Deteksi Pintu berbasis HOG dengan Klasifikasi SVM menggunakan Kernel Linear, Radial Basis Function dan Polinomial pada Raspberry Pi Anugrah Zeputra; Fitri Utaminingrum
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 11 (2021): November 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

The Covid-19 virus pandemic causes new problems in people's lives in Indonesia. The pandemic requires the implementation of all activities to run with a distance limitation or is called social distancing, as a result of which many of the activities that take place are hampered and inefficient. Therefore, developing a system that can work autonomously is an idea that can provide solutions to these problems. an autonomous system that can be used in this problem is a detection system using a Machine Learning algorithm. The detection system uses Computer Vision to get input to detect objects such as open doors, closed doors and walls. this system works autonomously in real time. Computer Vision uses image data as input. Therefore the image data extraction feature using the Histogram of Oriented Gradient (HOG) is a suitable basis for processing image data when juxtaposed with a Support Vector Machine (SVM). SVM has several types of kernels that can be used to classify image data, some of which are Linear, Polynomial and Radial Basis Function (RBF) kernels. the way each kernel works is different from one another to classify image data. Therefore, research to examine the comparison of the SVM kernel to the classification of image data was investigated in order to obtain a more optimal system performance.
Co-Authors Utaminingrum, Fitri