Applying High-level Agreement Ensemble Classification Voting Techniques to Distinguish Inflammatory Bowel Disease
سال انتشار: 1397
نوع سند: مقاله ژورنالی
زبان: انگلیسی
مشاهده: 175
فایل این مقاله در 49 صفحه با فرمت PDF قابل دریافت می باشد
- صدور گواهی نمایه سازی
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
JR_JITM-10-1_004
تاریخ نمایه سازی: 26 بهمن 1400
چکیده مقاله:
Due to the complexity of medical decisions, there is a growing interest in the application of intelligence systems to support these decisions. In this paper, accordingly, the potential of several algorithms such as K Nearest Neighbor, Support Vector Machine, Random Forest, Naive Bayes, and Decision Tree was used to create an ensemble classification. Then, to obtain the voting result, high level agreement voting was used to evaluate the performance and make prediction. According to the involvement of body organs with this disease, the problem of diagnosing and differentiating various types of bowl inflammation was investigated. We should mention that higher prediction accuracy was obtained using the proposed model. The results and the comparisons of these methods showed that the proposed model indicates the highest prediction accuracy which is ۹۸%. In the final step, the proposed model was evaluated applying the receiver operating characteristic curve model (ROC), and the area under the curve (AUC) was calculated.
کلیدواژه ها:
Ensemble classification algorithms ، High-level agreement voting algorithm ، Inflammatory bowel disease ، Noise detection ، ROC Curve
نویسندگان
نیره زاغری
Ph.D. Candidate, Department of Computer Engineering, Shahr-e-Qods Branch, Islamic Azad University, Tehran, Iran
راحیل حسینی
Assistant Prof, Department of Computer engineering, Shahr-e-Qods Branch, Islamic Azad University, Tehran, Iran
مراجع و منابع این مقاله:
لیست زیر مراجع و منابع استفاده شده در این مقاله 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 مقاله لینک شده اند :