A Novel Cost Sensitive Imbalanced Classification Method based on New Hybrid Fuzzy Cost Assigning Approaches, Fuzzy Clustering and Evolutionary Algorithms

سال انتشار: 1394
نوع سند: مقاله ژورنالی
زبان: انگلیسی
مشاهده: 590

فایل این مقاله در 9 صفحه با فرمت PDF قابل دریافت می باشد

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

JR_IJE-28-8_008

تاریخ نمایه سازی: 15 آذر 1394

چکیده مقاله:

In this paper, a new hybrid methodology is introduced to design a cost-sensitive fuzzy rule-based classification system. A novel cost metric is proposed based on the combination of three different concepts: Entropy, Gini index and DKM criterion. In order to calculate the effective cost of patterns, ahybrid of fuzzy c-means clustering and particle swarm optimization algorithm is utilized. This hybrid algorithm finds difficult minority instances; then, their misclassification cost will be calculated usingthe proposed cost measure. Also, to improve classification performance, the lateral tuning ofmembership functions (in data base) is employed by means of a genetic algorithm. The performance of the proposed method is compared with some cost-sensitive classification approaches taken from theliterature. Experiments are performed over 37 imbalanced datasets from KEEL dataset repository; theclassification results are evaluated using the area under the curve (AUC) as a performance measure. Results reveal that our hybrid cost-sensitive fuzzy rule-based classifier outperforms other methods in terms of classification accuracy

کلیدواژه ها:

نویسندگان

m Mahdizadeh

Department of Computer Engineering, Shahid Bahonar University of Kerman, Kerman, Iran

m Eftekhari

Department of Computer Engineering, Shahid Bahonar University of Kerman, Kerman, Iran