A Python-based Data mining to Address Class Imbalance Problem

Publish Year: 1395
نوع سند: مقاله کنفرانسی
زبان: English
View: 503

This Paper With 7 Page And PDF and WORD Format Ready To Download

  • Certificate
  • من نویسنده این مقاله هستم

این Paper در بخشهای موضوعی زیر دسته بندی شده است:

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این Paper:

شناسه ملی سند علمی:

COMCONF03_093

تاریخ نمایه سازی: 6 اردیبهشت 1396

Abstract:

Orange canvas is an open source data mining tool that is based on Python scripting, visual programming and scientific computing. We developed analytical frameworks, which have advanced theoretical studies of practical learning methods, to address the class imbalance problem. In a two-class classification task, when the number of one class (majority) is greater than another (minority), this class is called imbalanced. The classification of this imbalanced class causes imbalanced distribution, poor predictive classification accuracy and a Class Imbalance Problem (CIP). We will focus on clarifying and writing a simple or clear Python script and visualize the frameworks of existing learning methods that address the CIP with well-known Synthetic over-sampling technique (SMOTE) based ensemble methods. The introduced orange workflows, Python scripting, and experimental results, will assist researchers and students to address the CIP simply. This study’s aim is to design innovative methods to address CIP.

Authors

Seyyedali Fattahi

Data Mining and Optimization Research Group, Centre for Artificial Intelligence, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, UKM Bangi, 43600, Selangor, Malaysia

Zalinda Othman

Data Mining and Optimization Research Group, Centre for Artificial Intelligence, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, UKM Bangi, 43600, Selangor, Malaysia

مراجع و منابع این Paper:

لیست زیر مراجع و منابع استفاده شده در این Paper را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود Paper لینک شده اند :