A Feature Weighting Based Artificial Bee Colony Algorithm for Data Clustering

سال انتشار: 1395
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 717

فایل این مقاله در 5 صفحه با فرمت PDF قابل دریافت می باشد

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

ICIKT08_022

تاریخ نمایه سازی: 5 بهمن 1395

چکیده مقاله:

Data clustering is a powerful technique for data analysis that used in many applications. The goal of clustering is to detect groups that objects of each group have the most similarity together. Artificial bee colony (ABC) is a simple algorithm with few control parameters to solve clustering problem. However, traditional ABC algorithm is considered the equal importance for all features, while real world applications carry different importance on features. To overcome this issue, we proposed a feature weighting based artificial bee colony (FWABC) algorithm for data clustering. The proposed algorithm considers a specific importance to each feature. The performance of the proposed method has been tested on various datasets and compared to well-known and state-of-the-art methods, the reported results show that the proposed method outperforms other methods.

کلیدواژه ها:

Data clustering ، Artifitial bee colony algorithm ، feature weigthing

نویسندگان

Manijeh Reisi

Department of Computer Engineering University of Kurdistan Sanandaj, Iran

Parham Moradi

Department of Computer Engineering University of Kurdistan Sanandaj, Iran

Alireza Abdollahpouri

Department of Computer Engineering University of Kurdistan Sanandaj, Iran