scholarly journals Breast cancer diagnosis using feature extraction and boosted C5.0 decision tree algorithm with penalty factor

2022 ◽  
Vol 19 (3) ◽  
pp. 2193-2205
Author(s):  
Jian-xue Tian ◽  
◽  
Jue Zhang
Keyword(s):  
Breast Cancer ◽  
Feature Extraction ◽  
Decision Tree ◽  
Cancer Diagnosis ◽  
Class Imbalance ◽  
Breast Cancer Diagnosis ◽  
Decision Tree Algorithm ◽  
Tree Algorithm ◽  
Penalty Factor ◽  
C5.0 Decision Tree

<abstract><p>To overcome the two class imbalance problem among breast cancer diagnosis, a hybrid method by combining principal component analysis (PCA) and boosted C5.0 decision tree algorithm with penalty factor is proposed to address this issue. PCA is used to reduce the dimension of feature subset. The boosted C5.0 decision tree algorithm is utilized as an ensemble classifier for classification. Penalty factor is used to optimize the classification result. To demonstrate the efficiency of the proposed method, it is implemented on biased-representative breast cancer datasets from the University of California Irvine(UCI) machine learning repository. Given the experimental results and further analysis, our proposal is a promising method for breast cancer and can be used as an alternative method in class imbalance learning. Indeed, we observe that the feature extraction process has helped us improve diagnostic accuracy. We also demonstrate that the extracted features considering breast cancer issues are essential to high diagnostic accuracy.</p></abstract>

An Analysis of Factors Influencing Foreign Language Self-Efficacy Based on C5.0 Decision Tree Algorithm in Data Mining

2014 ◽  
Vol 538 ◽  
pp. 460-464
Author(s):  
Xue Li
Keyword(s):  
Data Mining ◽  
Decision Tree ◽  
Foreign Language ◽  
Language Learning ◽  
Learning Strategies ◽  
Self Efficacy ◽  
Foreign Language Learning ◽  
Decision Tree Algorithm ◽  
Tree Algorithm ◽  
C5.0 Decision Tree

Based on inter-correlation and permeability among disciplines, the author makes an attempt to apply the information science to cognitive linguistics to provide a new perspective for the study of foreign languages. The correlation between self-efficacy and such four factors as anxiety, learning strategies, motivation and learners’ past achievement is analyzed by means of data mining and the extent to which the above factors affect self-efficacy in language learning is explored in this paper. The paper employs the decision tree algorithm in SPSS Clementine. C5.0 decision tree algorithm is adopted to analyze data in the study. The results are elicited from the researches carried out in this paper. The increased anxiety is bound to weaken learners’ motivation over time. It is obvious that learners have low self-efficacy. It is very important to employ strategies in foreign language learning. Ignorance of using learning strategies may result in unplanned learning with unsatisfactory achievements in spite of more efforts involved. Self-efficacy in foreign language learning may be weakened accordingly. Learners’ past achievement is a reference dimension in measuring self-efficacy with weaker influence.

scholarly journals CLINICAL APPLICATIONS OF MACHINE LEARNING ON COVID-19: THE USE OF A DECISION TREE ALGORITHM FOR THE ASSESSMENT OF PERCEIVED STRESS IN MEXICAN HEALTHCARE PROFESSIONALS

2020 ◽  
Author(s):  
Juan Luis Delgado-Gallegos ◽  
Gener Avilés-Rodriguez ◽  
Gerardo R. Padilla-Rivas ◽  
María De los Ángeles Cosio-León ◽  
Héctor Franco-Villareal ◽  
...  
Keyword(s):  
Machine Learning ◽  
Decision Tree ◽  
Perceived Stress ◽  
Healthcare Professionals ◽  
Statistical Correlation ◽  
Decision Tree Algorithm ◽  
Tree Algorithm ◽  
Managing Stress ◽  
Applications Of Machine Learning ◽  
C5.0 Decision Tree

AbstractStress and anxiety have shown to be indirect effects of the COVID-19 pandemic, therefore managing stress becomes essential. One of the most affected populations by the pandemic are healthcare professionals. Thus, it is paramount to understand and categorize their perceived levels of stress, as it can be a detonating factor leading to mental illness. In our study, we used a machine learning prediction model to help measure perceived stress; a C5.0 decision tree algorithm was used to analyze and classify datasets obtained from healthcare professionals of the northeast region of Mexico. Our analysis showed that 6 out of 102 instances were incorrectly classified. Missing two cases for mild, three for moderate and 1 for severe (accuracy of 94.1%), statistical correlation analysis was performed to ensure integrity of the method, in addition we concluded that severe stress cases can be related mostly to high levels of Xenophobia and Compulsive stress.

Sign in / Sign up

Export Citation Format

Share Document