Prediction of disease-resistant gene in rice based on SVM-RFE

Ren, Yanjiao; Wang, Deping; Wang, Yan; Jinbo, Zhou; Zhang, Hanyuan; Liang, Y. Daniel

doi:10.1109/bmei.2010.5640583

Cited by 4 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Y. Ren et al used SVM-RFE to predict disease-resistant gene in rice and Z. Rustam and N. Maghfirah used the SVM-RFE to classify cancer with a good accuracy rate [2,3]. Not only in the microarray database but has been applied in a wide range of application, the used of SVM and Fuzzy Kernel C-Means as classifiers for intrusion detection systems [4,5].…”

Section: Introductionmentioning

confidence: 99%

Prediction of Disease-Resistant Gene in Rice Based on Support Vector Machine and Fuzzy Kernel C-Means

Saragih¹

2018

Proceedings of the 1st Annual International Conference on Mathematics, Science, and Education (ICoMSE 2017)

View full text Add to dashboard Cite

Rice production in Indonesia is important especially for national economy. Rice is the staple food for Indonesian, so Indonesia is the biggest rice consumers in the world, averaging more than 200 kilograms per head each year. Therefore, Indonesia needs to be aware of rice production systems because there are many diseases that distract from the growth of rice. One of that is Bacterial Leaf Blight (BLB) causes severe damages in many rice cultivation regions of the world. Bacterial Leaf Blight disease control through the development of resistant varieties is one of the effective and easiest ways to apply to farmers. The computational method is a way out to solve this problem with the use of machine learning. However, the two most popular, efficient and high accuracy methods are Support Vector Machine (SVM) and Fuzzy Kernel C-Means. Therefore, we propose to compare these two methods to assess the chance of a protein being disease-resistant. In this research, we found that SVM is better than Fuzzy Kernel C-Means because SVM has represented protein information with 90.91% accuracy and Fuzzy Kernel C-Means with 80.58% accuracy in the model. However, if the researcher is stuck on finding data, based on this research Fuzzy Kernel C-Means gives the highest accuracy in smallest dataset then SVM. Fuzzy Kernel C-Means has represented protein information with 80.58% and SVM just 23.2% accuracy in 10% training data set

show abstract