ARTÍCULO
TITULO

Kernel Comparison on Support Vector Machine for Detecting Stairs Descent DOI : 10.24114/cess.v7i2.33477 | Abstract views : 99 times

Ahmad Wali Satria Bahari Johan    
Ardian Yusuf Wicaksono    
Muhammad Dzulfikar Fauzi    
Rizky Fenaldo Maulana    
Kharisma Monika Dian Pertiwi    

Resumen

Terdapat 4 kernel yang dapat digunakan dalam klasifikasi Support Vector Machine dalam membuat hyperplane. Keempat kernel tersebut adalah linear, polynomial, gaussian dan sigmoid. Setiap kernel dapat menghasilkan akurasi yang berbeda-beda. Hal ini dikarenakan pengaruh sebaran data yang diklasifikasikan. Terdapat 2 kelas yang diklasifikasikan, yaitu lantai dan tangga turun. Dilakukan proses ekstraksi fitur tekstur terhadap citra lantai dan tangga turun menggunakan metode Gray Level Co-occurence Matrix. Terdapat 7 fitur dari GLCM yang dihasilkan pada proses ekstraksi fitur. Selanjutnya dilakukan klasifikasi menggunakan Support Vector Machine dengan mencoba setiap kernelnya. Dari hasil pengujian didapatkan kernel linear menghasilkan akurasi yang paling tinggi, yaitu 89%. Kernel sigmoid mendapatkan akurasi 84%. Kernel Gaussian mendapatkan akurasi sebesar 85%. Sedangkan kernel polynomial mendapatkan akurasi yang paling rendah yaitu 78%.

Palabras claves

 Artículos similares

       
 
Liang Han, Feng Liu and Kaifeng Chen    
Analog circuits play an important role in modern electronic systems. Aiming to accurately diagnose the faults of analog circuits, this paper proposes a novel variant of a convolutional neural network, namely, a multi-scale convolutional neural network wi... ver más
Revista: Algorithms

 
Pengfei Xu, Qingbo Cao, Yalin Shen, Meiya Chen, Yanxu Ding and Hongxia Cheng    
Predicting the maneuvering motion of an unmanned surface vehicle (USV) plays an important role in intelligent applications. To more precisely predict this empirically, this study proposes a method based on the support vector regression with a mixed kerne... ver más

 
Kai Zhao, Jia Song, Shaojie Ai, Xiaowei Xu and Yang Liu    
Due to the harsh working environment, Near-Space Hypersonic Vehicles (NSHVs) have the characteristics of frequent faults, which seriously affect flight safety. However, most researches focus on active fault-tolerant control for actuator faults. In order ... ver más
Revista: Aerospace

 
Kaidong Tao, Xueqian Zhou and Huilong Ren    
Due to the convenience and flexibility in modeling complex geometries and deformable objects, local ghost particles methods are becoming more and more popular. In the present study, a novel local semi-fixed ghost particles method is proposed for weakly c... ver más

 
Jinsong Zhang, Yongtao Peng, Bo Ren and Taoying Li    
The concentration of PM2.5 is an important index to measure the degree of air pollution. When it exceeds the standard value, it is considered to cause pollution and lower the air quality, which is harmful to human health and can cause a variety of diseas... ver más
Revista: Algorithms