Ranking forest model performance in ROC space for all balance features.

<p>By applying the Ranking Forest machine learning algorithm to the dataset under all conditions (eyes-open firm surface, eyes-closed firm surface, eyes-open foam surface, and eyes-closed foam surface), we evaluated the ROC space of the models for all balance features (both original parameters...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Yuqi Cheng (428511) (author)
مؤلفون آخرون: Dawei Wu (519682) (author), Ying Wu (19057) (author), Youcai Guo (20642726) (author), Xinze Cui (20642729) (author), Pengquan Zhang (20642732) (author), Jie Gao (10266) (author), Yanming Fu (1844281) (author), Xin Wang (91924) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
الوصف
الملخص:<p>By applying the Ranking Forest machine learning algorithm to the dataset under all conditions (eyes-open firm surface, eyes-closed firm surface, eyes-open foam surface, and eyes-closed foam surface), we evaluated the ROC space of the models for all balance features (both original parameters and those processed using the CMCI method). The models developed using the datasets processed with the CMCI technique exhibited superior performance. Each model’s name follows the naming convention described below: The first uppercase letters indicate the set of variables used, with OR = original features, CMCI = variables processed with the CMCI method, and (a, b, c, d) representing different balance tasks(T1-T4).</p>