A Framework for Categorize Feature Selection Algorithms for Classification and Clustering

  • سال انتشار: 1395
  • محل انتشار: کنفرانس بین المللی مهندسی کامپیوتر و فناوری اطلاعات
  • کد COI اختصاصی: CITCOMP01_031
  • زبان مقاله: انگلیسی
  • تعداد مشاهده: 812
دانلود فایل این مقاله

نویسندگان

Ali Asghar Nadri

Department of Computer Engineering, College of Engineering, Yasooj Branch, Islamic Azad University, Yasooj, Iran

Farhad Rad

Department of Computer Engineering, College of Engineering, Yasooj Branch, Islamic Azad University, Yasooj, Iran

Hamid Parvin

Department of Computer Engineering, College of Engineering, Yasooj Branch, Islamic Azad University, Yasooj, Iran

چکیده

At first the dimension reduction techniques such as feature extraction and feature selection are explained. The Concepts, principles and existing feature selection methods for classification and clustering are also described. Then, a categorizing framework consisting of the procedures of finding selected subsets, including Search-based procedures and non-search based, evaluation criteria and data mining tasks will be completed and developed. During the grouping of Feature selection algorithms, categorizing framework represent guidelines to choose appropriate algorithm(s) for each application. In the above-mentioned categorizing, similar algorithms which follow the same process of selected subset finding and have the same evaluation criteria, are placed in the one block. Empty blocks indicates that no algorithm has been designed for them and this is a motive to start a new investigation in this regard. The design principles of an intelligent system for intelligent feature selection are established according to the above ordination.

کلیدواژه ها

Feature selection, generator function, evaluation criteria, classification, clustering, categorizing framework

مقالات مرتبط جدید

اطلاعات بیشتر در مورد COI

COI مخفف عبارت CIVILICA Object Identifier به معنی شناسه سیویلیکا برای اسناد است. COI کدی است که مطابق محل انتشار، به مقالات کنفرانسها و ژورنالهای داخل کشور به هنگام نمایه سازی بر روی پایگاه استنادی سیویلیکا اختصاص می یابد.

کد COI به مفهوم کد ملی اسناد نمایه شده در سیویلیکا است و کدی یکتا و ثابت است و به همین دلیل همواره قابلیت استناد و پیگیری دارد.