Classification Algorithms Comparison: Case Study: Cancer Patients SEER Data Set
مقارنه خوارزميات التصنيف: دراسة حالة مرضى السرطان
Musab Abdalgader Abdalkreem, Mohamed Elhafiz Mustafa Musa
كلية الدراسات العليا-جامعة السودان للعلوم والتكنولوجيا · السودان
الموضوعات
إحصاء
الملخص
Data mining is the automatic search of huge data to discover patterns and trends that gobeyond simple analysis. Data mining is also known as Knowledge Discovery in Data(KDD). This study investigates the discovery of the survival rate or survivability of acertain disease is possible by extracting the knowledge from the data related to thatdisease. To do such investigate a large data set needed one of these data sources isSEER[1] (Surveillance Epidemiology and End Results), which is a unique, reliable andessential resource for investigating the different aspects of cancer. In this study we haveinvestigated three data mining techniques Multilayer Perceptron (MLP), K-nearestneighbor and the C4.5 decision trees the goal is to find the best accuracy to predict 5years survivability of breast cancer.SEER database (period of 1973-2009 with 657,712 records) were used, starting fromprevious study we determined common variables use, after preprocessed there are 18variables and 180,302 records.Weka was used to train and test the three techniques. The result show that the besttechnique is C4.5 accuracy is %95.6 and the second technique is K-nearest neighborwith accuracy %95.4 and the worst is MLP with accuracy %95.3.
روابط وملفات
التعريف والنوع
- رقم الوثيقة
- edfbe7de-a01c-4621-b717-e56c1deb0a47
- رقم العقد
- 0
- نوع الوسائط
- Crawler
- نوع المحتوى
- الرسائل العلمية
- صيغة المصدر
- رسائل ماجيستير
- نوع الملف
- pdf text
- أسماء الملفات
- 25456_1.pdf, 25456_2.pdf
بيانات النشر
- ترجمة العنوان
- مقارنه خوارزميات التصنيف: دراسة حالة مرضى السرطان
- ألقاب المؤلفين
- [{"name_ar":" Musab Abdalgader Abdalkreem","title_ar":"اعداد","title_en":"Preparation"},{"name_ar":"Mohamed Elhafiz Mustafa Musa","title_ar":"اشراف","title_en":"Supervision"}]
- اللغة
- English
المصدر والدورية
- اسم المصدر
- Classification Algorithms Comparison: Case Study: Cancer Patients SEER Data Set
المحتوى والصفحات
- عدد الصفحات
- 0
إشراف وإعداد
- الإشراف
- Mohamed Elhafiz Mustafa Musa
- الإعداد
- Musab Abdalgader Abdalkreem
الاقتباسات الببليوغرافية
APA
MLA