scholarly journals Predict Students' Performance by Using J48 Algorithm

2020 ◽  
pp. 578-582
Author(s):  
Myo Thandar Tun ◽  
Yin Yin Htay
Keyword(s):  
Data Mining ◽  
Classification Accuracy ◽  
Critical Issue ◽  
Academic Community ◽  
Classification Algorithms ◽  
Data Mining Technique ◽  
Data Set ◽  
Mining Technique ◽  
Computer Studies ◽  
Machine Learning Tool

The critical issue to the academic community of higher education is to monitor the progress of students’ academic performance. We can use data mining techniques for this purpose. J48 algorithm is one of the famous classification algorithms present today to generate decision trees in data mining technique. The data set used in this study is taken from University of Computer Studies (Mandalay). Weka machine learning tool is applied to make classification. In this work, we tested result classification accuracy was computed. This J48 classification algorithm give accuracy with 78.2%.

scholarly journals The Observation Report of Red Blood Cell Morphology in Thailand Teenager by Using Data Mining Technique

2014 ◽  
Vol 2014 ◽  
pp. 1-5 ◽  
Author(s):  
Sarawut Saichanma ◽  
Sucha Chulsomlee ◽  
Nonthaya Thangrua ◽  
Pornsuri Pongsuchart ◽  
Duangmanee Sanmun
Keyword(s):  
Data Mining ◽  
Blood Cell ◽  
Hematological Parameters ◽  
Medical Science ◽  
Peripheral Blood Smear ◽  
Medical Laboratory ◽  
Data Mining Technique ◽  
Data Set ◽  
Mining Technique ◽  
Laboratory Results

It is undeniable that laboratory information is important in healthcare in many ways such as management, planning, and quality improvement. Laboratory diagnosis and laboratory results from each patient are organized from every treatment. These data are useful for retrospective study exploring a relationship between laboratory results and diseases. By doing so, it increases efficiency in diagnosis and quality in laboratory report. Our study will utilize J48 algorithm, a data mining technique to predict abnormality in peripheral blood smear from 1,362 students by using 13 data set of hematological parameters gathered from automated blood cell counter. We found that the decision tree which is created from the algorithm can be used as a practical guideline for RBC morphology prediction by using 4 hematological parameters (MCV, MCH, Hct, and RBC). The average prediction of RBC morphology has true positive, false positive, precision, recall, and accuracy of 0.940, 0.050, 0.945, 0.940, and 0.943, respectively. A newly found paradigm in managing medical laboratory information will be helpful in organizing, researching, and assisting correlation in multiple disciplinary other than medical science which will eventually lead to an improvement in quality of test results and more accurate diagnosis.

scholarly journals Provissional Access For Improving Classification Accuracy On Diabetes Dataset

2019 ◽  
Vol 8 (6) ◽  
pp. 5245-5248
Keyword(s):  
Data Mining ◽  
Experimental System ◽  
Classification Algorithms ◽  
Data Mining Technique ◽  
Real World Data ◽  
Mining Technique ◽  
Complete Set ◽  
The Impact ◽  
Speed And Accuracy

Data mining helps to solve many problems in the area of medical diagnosis using real-world data. However, much of the data is unrealizable as it does not have desirable features and contains a lot of gaps and errors. A complete set of data is a prerequisite for precise grouping and classification of a dataset. Preprocessing is a data mining technique that transforms the unrefined dataset into reliable and useful data. It is used for resolving the issues and changes raw data for next level processing. Discretization is a necessary step for data preprocessing task. It reduces the large chunks of numeric values to a group of well-organized values. It offers remarkable improvements in speed and accuracy in classification. This paper investigates the impact of preprocessing on the classification process. This work implements three techniques such as NaiveBayes, Logistic Regression, and SVM to classify Diabetes dataset. The experimental system is validated using discretize techniques and various classification algorithms.

scholarly journals Data Mining Approach for Educational Decision Support

2021 ◽  
Vol 2 (1) ◽  
pp. 33-44
Author(s):  
Sinta Septi Pangastuti ◽  
Kartika Fithriasari ◽  
Nur Iriawan ◽  
Wahyuni Suryaningtyas
Keyword(s):  
Data Mining ◽  
Random Forest ◽  
Classification Accuracy ◽  
Storage System ◽  
Performance Criteria ◽  
Data Mining Technique ◽  
Mining Technique ◽  
Data Mining Approach ◽  
Educational Decision ◽  
Boosting Algorithm

data mining techniques in education sector have begun to evolve, along with the development of technology and the amount of data that can be stored in an education database storage system. One of them is a database of Bidikmisi scholarships in Indonesia. The Bidikmisi data used in this study will be classified using classification data mining technique. The technique that used in this study is random forest in combination with boosting algorithm and bagging algorithms. These algorithms also combine with SMOTE algorithm to handling the imbalance class in dataset. Based on the performance criteria G-mean and AUC, the algorithm combines with SMOTE tended to be better. The classification accuracy of each method being more than 90%

scholarly journals Penerapan Metode Association Rule Untuk Menganalisa Pola Pemakaian Bahan Kimia Di Laboratorium Menggunakan Algoritma FP-Growth (Studi Kasus di Laboratorium Kimia PT. PLN (Persero) Sektor Pembangkitan Belawan Medan)

2019 ◽  
Vol 3 (2) ◽  
pp. 56
Author(s):  
Buyung Solihin Hasugian
Keyword(s):  
Data Mining ◽  
Association Rule ◽  
Frequent Itemset ◽  
Data Mining Technique ◽  
Data Set ◽  
Mining Technique ◽  
Several Variables ◽  
Alternative Algorithm ◽  
Chemical Usage ◽  
Tree Development

<p class="Default"><em>The pattern of using chemicals in the laboratory of PT. PLN (Persero) </em><em>Sektor Pembangkitan </em><em>Belawan Medan is not only to find out what chemicals are used but also to find out the amount of chemicals left so that laboratory officials can properly manage the use of these chemicals. One appropriate way to determine the pattern of use of these chemicals is to use data mining techniques. The Data Mining technique used in this case is the FP-Growth Algorithm. FP-Growth is an alternative algorithm that can be used to determine the most frequent set of data in a data set. The study was conducted using several variables, namely the date and chemicals used. The results of this study are in the form of a chemical usage pattern which is processed using software, namely implementing the FP-Growth algorithm using the concept of FP-Tree development in searching for Frequent Itemset.</em></p><p class="Default"><em> </em></p><pre><em>Keywords: Data Mining, Association Rules, Frequent Itemset, FP-Growth</em></pre>

scholarly journals A Hybrid Clustering Data Mining Technique (HCDMT) for Predicting SLE

2019 ◽  
Vol 8 (12) ◽  
pp. 3927-3930
Keyword(s):  
Data Mining ◽  
Lupus Erythematosus ◽  
Complex Disease ◽  
Data Mining Technique ◽  
Data Set ◽  
Hybrid Clustering ◽  
Mining Technique ◽  
Machine Learning Approach ◽  
Clustering Data ◽  
High Level

SLE is an auto immune and complex disease. Predicting Systemic Lupus Erythematosus (SLE) is significantly challenging due to its high level of heterogeneity in symptoms. There is a limitation on the tools used for predicting SLE accurately. This paper proposes a machine learning approach to predict the disease from SLE data set and classify patients in whom the disease is active. The data purified and selected for classification improves the accuracy of the proposed method called HCDMT (Hybrid Clustering Data Mining Technique), an amalgamation of CART and k-Means, was evaluated on SLE data. It was found to predict above 95% of SLE cases

scholarly journals A Hybrid Clustering Data Mining Technique (HCDMT) for Predicting SLE

2019 ◽  
Vol 8 (11S2) ◽  
pp. 512-515
Keyword(s):  
Data Mining ◽  
Lupus Erythematosus ◽  
Complex Disease ◽  
Data Mining Technique ◽  
Data Set ◽  
Hybrid Clustering ◽  
Mining Technique ◽  
Machine Learning Approach ◽  
Clustering Data ◽  
High Level

SLE is an auto immune and complex disease. Predicting Systemic Lupus Erythematosus (SLE) is significantly challenging due to its high level of heterogeneity in symptoms. There is a limitation on the tools used for predicting SLE accurately. This paper proposes a machine learning approach to predict the disease from SLE data set and classify patients in whom the disease is active. The data purified and selected for classification improves the accuracy of the proposed method called HCDMT (Hybrid Clustering Data Mining Technique), an amalgamation of CART and k-Means, was evaluated on SLE data. It was found to predict above 95% of SLE cases.

Sign in / Sign up

Export Citation Format

Share Document