scholarly journals Diagnosis of Breast Cancer using Decision Tree Data Mining Technique

2014 ◽  
Vol 98 (10) ◽  
pp. 16-24 ◽  
Author(s):  
Ronak Sumbaly ◽  
N. Vishnusri ◽  
S. Jeyalatha
Keyword(s):  
Breast Cancer ◽  
Data Mining ◽  
Decision Tree ◽  
Data Mining Technique ◽  
Mining Technique ◽  
Tree Data

Application of Data Mining Technology in Sports Teaching Quality Evaluation

2014 ◽  
Vol 543-547 ◽  
pp. 4694-4697
Author(s):  
Li Min Zhou
Keyword(s):  
Data Mining ◽  
Decision Tree ◽  
Scientific Method ◽  
Quality Evaluation ◽  
Teaching Quality ◽  
Evaluation Index ◽  
Data Mining Technique ◽  
Mining Technology ◽  
Mining Technique ◽  
Sign System

The unreasonable phenomenon caused by the lack of effective scientific method, The essay attempts to carry on related analysis and research of combining the data mining technique with sport teaching quality evaluation by mining valid sport teaching quality evaluation index sign system, making full use of the decision tree technique to solve the unreasonableness of the sports teaching quality evaluation and putting forward technical method for sports teaching quality evaluation based on the decision tree, aimed at making it fair, just, reasonable and efficient.

scholarly journals A Student Performance Prediction Model Using Data Mining Technique

2018 ◽  
Vol 7 (2.15) ◽  
pp. 61
Author(s):  
Rohaila Abdul Razak ◽  
Mazni Omar ◽  
Mazida Ahmad
Keyword(s):  
Data Mining ◽  
Linear Regression ◽  
Decision Tree ◽  
Student Performance ◽  
Prediction Accuracy ◽  
Significant Variable ◽  
Data Mining Technique ◽  
Mining Technique ◽  
Predicting Performance ◽  
Using Data

Predicting performance is very significant in the education world nowadays. This paper will describe the process of doing a prediction of student performance by using data mining technique. 257 data sets were taken from the student of semester 6 KPTM that involved four (4) academic programs which are Diploma in Computer System and Networking, Diploma in Information Technology, Diploma in Business Management and Diploma in Accountancy. Knowledge Discovery in Database (KDD) was used as a guide to the process of finding and extracting a knowledge from the dataset. A decision tree and linear regression were used to analyze the dataset based on variables selected. The variables used are Gender, Financing, SPM, GPASem1, GPASem2, GPASem3, GPASem4, GPASem5 and CGPA as a dependent variable. The result from this indicate the significant variable that contribute most to the students’ performance. Based on the analysis, the decision tree shows that GPASem1 has a strong significant to the CGPA final semester of the student and the prediction accuracy is 82%. The linear regression shows that the GPA for each semester has a highly significant with the dependent variable with 96.2% prediction accuracy. By having this information, the management of KPTM can make a plan to ensure that the student can maintain a good result and at the same time to make a strategic plans for those without a good result.  

scholarly journals MINING SIMILAR PATTERN WITH ATTRIBUTE ORIENTED INDUCTION HIGH LEVEL EMERGING PATTERN (AOI-HEP) DATA MINING TECHNIQUE

2017 ◽  
Vol 79 (7-2) ◽  
Author(s):  
Harco Leslie Hendric Spits Warnars ◽  
Nizirwan Anwar ◽  
Richard Randriatoamanana ◽  
Horacio Emilio Perez Sanchez
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Data Mining ◽  
Similar Pattern ◽  
Frequent Pattern ◽  
Data Mining Technique ◽  
Mining Technique ◽  
High Level ◽  
Concept Attribute ◽  
Emerging Pattern

AOI-HEP (Attribute Oriented Induction High Emerging Pattern) as new data mining technique has been success to mine frequent pattern and is extended to mine similar patterns. AOI-HEP is success to mine 3 and 1 similar patterns from IPUMS and breast cancer UCI machine learning datasets respectively. Meanwhile, the experiments showed that there was no finding similar patterns on adult and census UCI machine learning datasets. The experiments showed that finding AOI-HEP similar pattern in dataset is influenced by learning on chosen high level concept attribute in concept hierarchy and it is applied to AOI-HEP frequent pattern in previous research as well. The experiments chosed high level concept attributes such as workclass, clump thickness, means and marts for adult, breast cancer, census and IPUMS datasets respectively. In order to proof that the chosen high level concept attribute will influences the AOI-HEP similar pattern in dataset, then extended experiments were carried on and the finding were census dataset which had been none AOI-HEP similar pattern, had AOI-HEP similar pattern when learned on high level concept in marital attribute. Meanwhile, Breast cancer which had been had 1 AOI-HEP similar pattern, had none AOI-HEP similar pattern when learned on high level concept in attributes such as cell size, cell shape and bare nuclei. The 2 of 3 finding Similar patterns in IPUMS dataset have strong discriminant rule since having large growth rates such as 1.53% and 3.47%, and having large supports in target dataset such as 4.54% and 5.45 respectively. Moreover, there have small supports in contrasting dataset such as 2.96% and 1.57% respectively.         

scholarly journals Utilization of Machine Learning in Brain Tumor Classification

2019 ◽  
pp. 325-330
Author(s):  
Sanjeet Pandey ◽  
Brijesh Bharadwaj ◽  
Himanshu Pandey ◽  
Vineet Kr. Singh
Keyword(s):  
Data Mining ◽  
Decision Tree ◽  
Early Stage ◽  
Data Mining Technique ◽  
Data Mining Techniques ◽  
Mining Technique ◽  
Diabetes Prediction ◽  
System Data ◽  
Health System Data ◽  
Prediction Of Diabetes

Since past few years data mining lot of attention related to knowledge like extracting methods in health care system like diabetes, cancer, CVS etc. There are lot of technique of data mining like decision tree, Naive base, KNN; J48 etc. are being used for prediction of diabetes. Diabetes is metabolic disorder related to poor absorption of insulin into body mussels or poor lowered secretion of insulin from pancreases. As this disease, this is main death causes disease in the world. So, prediction of these diseases with the help of data mining technique may help to protect many lives. In this study, we have to discuss various data mining technique, types of diabetes, application of these data mining technique. Prediction of diabetes or any other disease could play a significant role in health system. Data mining are very useful in the scenario. These techniques help in selection, understanding and designing of large size data to analysis the chances of diseases occurrence. Recently who has announced diseases a major cause of death worldwide. The prediction and identification early stage of diabetes can play major role to treat this disease significantly. Various data mining techniques like KNN, Decision tree, Naïve Bays etc. would be a significant asset for the researcher for gaining various data about diabetes, its causes, symptoms and possible treatment that have been using in the past and currently used by various physician. In this study we have briefly discussed various data mining techniques/models. Which have been currently used for diabetes prediction? Along with this discussion, we have also focused on performance and short coming of existing models/techniques time to time evaluated by researchers.

Islamists vs. Far Right Extremists

2021 ◽  
Vol 11 (4) ◽  
pp. 74-92
Author(s):  
Yeslam Al-Saggaf ◽  
Patrick F. Walsh
Keyword(s):  
United States ◽  
Data Mining ◽  
Decision Tree ◽  
The United States ◽  
Far Right ◽  
Data Mining Technique ◽  
Mining Technique ◽  
Violent Extremism ◽  
Similarities And Differences

In this study, a data mining technique, specifically a decision tree, was applied to look at the similarities and differences between Islamists and Far Right extremists in the Profiles of Individual Radicalisation in the United States (PIRUS) dataset. The aim was to identify differences and similarities across various groups that may highlight overlaps and variations across both Islamists and Far Right extremists. The data mining technique analysed data in the PIRUS dataset according to the PIRUS codebook's grouping of variables. The decision tree technique generated a number of rules that provided insights about previously unknown similarities and differences between Islamists and Far Right extremists. This study demonstrates that data mining is a valuable approach for shedding light on factors and patterns related to different forms of violent extremism.

Sign in / Sign up

Export Citation Format

Share Document