Feature selection for Protein Fold Recognition using Vortex search algorithm
محل انتشار: سومین کنفرانس سیستم های تصمیم گیری هوشمند
سال انتشار: 1397
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 385
فایل این مقاله در 11 صفحه با فرمت PDF قابل دریافت می باشد
- صدور گواهی نمایه سازی
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
IDS03_041
تاریخ نمایه سازی: 31 اردیبهشت 1398
چکیده مقاله:
Feature selection is one of the most important steps of pre-processing data, which aims to select a subset of relevant features. On the other hand, extracting effective features is one of the challenges in protein fold recognition. In this paper, we propose a feature selection method based on Vortex Search Algorithm (VSA). In addition, Map/Reduce framework has been implemented as a speedup technique to feature selection. In the proposed method, in each step of map function, VSA is employed to find an optimization subset of features, and map and reduce functions are executed in parallel mode. Finally, we evaluated the proposed method in classification of a benchmark dataset for protein fold recognition. The experimental results indicate that the proposal method improves prediction accuracy by ~10%.
کلیدواژه ها:
نویسندگان
Elham Hekmatnia
Department of Computer Engineering, School of Engineering, Azad University, Science and Research Branch.
Hedieh Sajedi
Department of Computer Science, School of Mathematics, Statistics and Computer Science, College of Science, University of Tehran
Ali Habib Agahi
Department of Computer Engineering, School of Engineering, Azad University, South Tehran Branch