scholarly journals Estimating Daily Reference Evapotranspiration using Data Mining Methods of Support Vector Regression and M5 Model Tree

2019 ◽  
Vol 9 (18) ◽  
pp. 157-167
Author(s):  
Saeed Samadianfard ◽  
Solmaz Panahi ◽  
◽  
Keyword(s):  
Data Mining ◽  
Support Vector Regression ◽  
Reference Evapotranspiration ◽  
Support Vector ◽  
M5 Model Tree ◽  
Model Tree ◽  
Mining Methods ◽  
Using Data ◽  
M5 Model

Early Breast Cancer Prediction Using Dermatoglyphics: Data Mining Pilot Study in a General Hospital in Iran (Preprint)

2020 ◽  
Author(s):  
Seyed Mohammad Ayyoubzadeh ◽  
Aysan Almasizand ◽  
Sharareh R. Niakan Kalhori ◽  
Sakineh Abbasi
Keyword(s):  
Breast Cancer ◽  
Data Mining ◽  
Random Forest ◽  
Early Breast Cancer ◽  
Information Gain ◽  
Support Vector ◽  
Mining Methods ◽  
Using Data ◽  
Birth Family ◽  
Hands And Feet

BACKGROUND Dermatoglyphics is the study of skin patterns on hands and feet. It has been shown in some studies that specific finger patterns could be a risk factor of breast cancer. There are several studies using data mining methods to evaluate the risk of breast cancer; while there is no or little study that evaluates finger patterns with data mining for breast cancer risk prediction. OBJECTIVE This study aims to evaluate fingerprint patterns along with other easy-to-obtain features in the risk of breast cancer. METHODS A dataset containing 462 records includes female patients in Imam Khomeini Hospital Complex, Tehran, Iran was obtained. The dataset has comprised of age, menstruation age, menopause age, and situation, has a child, age at first live birth, family history of breast cancer, and figure print patterns features of hands. The factors weight was determined by the Information Gain index. Predictive models were built once without fingerprint features and once with fingerprint features using Naïve Bayes, Decision Tree, Random Forest (RF), Support Vector Machine (SVM), and Deep Learning classifiers. RESULTS The most important factor determining breast cancer were age, having a child, menopause situation, and menopause age. The best performance belongs to the RF model with accuracy and AUC of 84.43% and 0.923 respectively. The fingerprint patterns feature increased the RF accuracy from 79.44% to 84.43%. CONCLUSIONS An early breast cancer screening model could be built with the use of data mining methods. The fingerprint patterns could increase the performance of these models. The Random Forest model could be used. The results of such models could be used in designing apps for self-screening breast cancer.

Modeling reference evapotranspiration using a novel regression-based method: radial basis M5 model tree

2021 ◽  
Author(s):  
Ozgur Kisi ◽  
Behrooz Keshtegar ◽  
Mohammad Zounemat-Kermani ◽  
Salim Heddam ◽  
Nguyen-Thoi Trung
Keyword(s):  
Reference Evapotranspiration ◽  
M5 Model Tree ◽  
Model Tree ◽  
Radial Basis ◽  
M5 Model

Estimation of Scour Downstream of a Ski-Jump Bucket Using Support Vector and M5 Model Tree

2011 ◽  
Vol 25 (9) ◽  
pp. 2177-2195 ◽  
Author(s):  
Manish Kumar Goyal ◽  
C. S. P. Ojha
Keyword(s):  
Support Vector ◽  
M5 Model Tree ◽  
Model Tree ◽  
M5 Model
Sign in / Sign up

Export Citation Format

Share Document