Deteksi Dini Mahasiswa Drop Out Menggunakan C5.0

The decline in the number of active students also occurred at the Faculty of Engineering and Information Technology, Universitas Jenderal Achmad Yani. This greatly affects the profile of study program graduates. So it is necessary to have a system that is able to detect students who are threatened with dropping out early. In this study, the attributes chosen were the student's GPA and the percentage of attendance . This attribute is used to classify students who are predicted to drop out. The research data uses student data from the Faculty of Engineering and Information Technology, Universitas Jenderal Achmad Yani. This study uses the C5.0 algorithm to build a decision tree to assist data classification. The decision tree that was built with 304 data as training data resulted a C5.0 decision tree which had an error rate of 5%. The accuracy results obtained from the 76 test data is 93%.

Download Full-text

Applied-Information Technology with Trojan Horse Detection Method Based on C5.0 Decision Tree

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.540.439 ◽

2014 ◽

Vol 540 ◽

pp. 439-442

Author(s):

Yang Li ◽

Ye Liang ◽

Jing Zhang Liang

Keyword(s):

Information Technology ◽

Decision Tree ◽

Detection Method ◽

Trojan Horse ◽

Detection Methods ◽

File Format ◽

Effective Algorithm ◽

Decision Tree Algorithm ◽

Executable File ◽

C5.0 Decision Tree

This paper discusses the Trojan horse detection methods by analysis on Portable Executable File Format through which we can get much useful information. In order to deal with the information extracted from Portable Executable file, our methods constructed a decision tree based on C5.0 decision tree algorithm. Our approach can be divided into two steps. Firstly, we extracted some features from Portable Executable file by a portable executable attribute filter. Secondly, we handled the features extracted and then construct a classifier to identify the Trojan horse. The original in this paper is the application of a more effective algorithm C5.0 to construct the decision tree.

Download Full-text

ANALISIS REKOMENDASI PEMINATAN MENGGUNAKAN METODE DECISION TREE DENGAN ALGORITMA C4.5

Computatio : Journal of Computer Science and Information Systems ◽

10.24912/computatio.v2i2.2568 ◽

2018 ◽

Vol 2 (2) ◽

pp. 178

Author(s):

Tri Sutrisno ◽

Stefanny Claudia

Keyword(s):

Information Technology ◽

Decision Tree ◽

Training Data ◽

Prediction System ◽

Tree Model ◽

Average Accuracy ◽

C4.5 Algorithm ◽

Academic Grades ◽

Decision Tree Method ◽

Tree Method

The application created are used to analyze which thesis preference subject suits students academic performance based on their academic grades. The application also provide online academic consultations features which students can use for their academic consultations. To find their thesis preference, the application use decision tree method with C4.5 algorithm. Testing prediction system using students data from 2012 to 2015 who have found their thesis preference. The value data used is 32 mandatory courses in the Faculty of Information Technology before thesis preference. The application can run , use and perform well in accordance with the design made. Testing is to compare the accuracy of the selected tree model build from training data and the thesis preference students have selected. The average accuracy percentage of this a 72,6227%.

Download Full-text

Fake News (Hoax) Identification on Social Media Twitter using Decision Tree C4.5 Method

Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) ◽

10.29207/resti.v4i4.2125 ◽

2020 ◽

Vol 4 (4) ◽

pp. 711-716 ◽

Cited By ~ 1

Author(s):

Brenda Irena ◽

Erwin Budi Setiawan

Keyword(s):

Social Media ◽

Feature Selection ◽

Decision Tree ◽

Test Data ◽

Information Gain ◽

Training Data ◽

Fake News ◽

Weighting Method ◽

Exchange Information ◽

Test Scenarios

Social media is a means to communicate and exchange information between people, and Twitter is one of them. But the information disseminated is not entirely true, but there is some news that is not in accordance with the truth or often called hoaxes. There have been many cases of spreading hoaxes that cause concern and often harm a particular individual or group. So in this research, the authors build a system to identify hoax news on social media Twitter using the Decision Tree C4.5 classification method to the 50,610 tweet data. What distinguishes this research from some researches before is the existence of several test scenarios, classification only, classification using weighting feature, and also classification using weighting feature and feature selection. The weighting method used is TF-IDF, and the feature selection uses Information Gain. The features used are also generated using n-grams consisting of unigram, bigram, and also trigrams. The final results show that the classification test that uses weighting feature and feature selection produces the best accuracy of 72.91% with a ratio of 90% training data and 10% test data (90:10) and the number of features used is 5000 in unigram features.

Download Full-text

Model Prediksi Awal Masa Studi Mahasiswa Menggunakan Algoritma Decision Tree C4.5

Jurnal Sistem dan Teknologi Informasi (JustIN) ◽

10.26418/justin.v7i4.33163 ◽

2019 ◽

Vol 7 (4) ◽

pp. 272 ◽

Cited By ~ 1

Author(s):

Elsa Paskalis Krisda Orpa ◽

Eva Faja Ripanti ◽

Tursina Tursina

Keyword(s):

Decision Tree ◽

Error Rate ◽

Drop Out

Masa studi mahasiswa merupakan tolak ukur penilaian keberhasilan Program Studi, karena masa studi merupakan salah satu indikator keberhasilan proses belajar mahasiswa. Permasalahan mahasiswa lulus tidak tepat waktu dan mahasiswa drop out (DO) masih menjadi kendala Program Studi saat ini. Tujuan penelitian ini adalah membangun sebuah model untuk prediksi awal masa studi mahasiswa, dimana saat ini implementasinya dilakukan pada Program Studi Informatika Universitas Tanjungpura. Keterlambatan mahasiswa dalam menempuh masa studi disebabkan karena kesulitan data pengetahuan yang terbatas tentang prediksi masa studi. Prediksi adalah suatu kegiatan untuk memperkirakan kejadian yang akan terjadi dimasa depan dengan menggunakan data yang sudah ada. Penggunakan model untuk melakukan prediksi masa studi bisa digunakan untuk menangani masalah kerumitan dan ketepatan hasil prediksi, dengan menggunakan metode pendekatan yang cocok untuk prediksi salah satunya adalah algoritma Decision Tree C4.5. Pengujian sistem yang dilakukan menggunakan Cofusion Matrix, menunjukan bahwa model prediksi yang dibangun menggunakan Decision Tree C4.5 menghasilkan rule yang baik digunakan untuk prediksi masa studi mahasiswa. Karena hasil perhitungan nilai akurasi terhadap prediksi yang dihasilkan dengan kenyataan sebenarnya menunjukan nilai precision, recall dan accuracy rata-rata diatas 50% sedangkan untuk nilai error rate berada dibawah 20% .

Download Full-text

Data Mining Implementation Using Naïve Bayes Algorithm and Decision Tree J48 In Determining Concentration Selection

International Journal of Quantitative Research and Modeling ◽

10.46336/ijqrm.v1i3.72 ◽

2020 ◽

Vol 1 (3) ◽

pp. 123-134

Author(s):

Budiman Budiman ◽

Reni Nursyanti ◽

R Yadi Rakhman Alamsyah ◽

Imannudin Akbar

Keyword(s):

Data Mining ◽

Decision Tree ◽

Naive Bayes ◽

Naïve Bayes ◽

Training Data ◽

Study Program ◽

Data Set ◽

Lower Accuracy ◽

Accuracy Result ◽

Bayes Algorithm

Computerization of society has substantially improved the ability to generate and collect data from a variety of sources. A large amount of data has flooded almost every aspect of people's lives. AMIK HASS Bandung has an Informatic Management Study Program consisting of three areas of concentration that can be selected by students in the fourth semester including Computerized Accounting, Computer Administration, and Multimedia. The determination of concentration selection should be precise based on past data, so the academic section must have a pattern or rule to predict concentration selection. In this work, the data mining techniques were using Naive Bayes and Decision Tree J48 using WEKA tools. The data set used in this study was 111 with a split test percentage mode of 75% used as training data as the model formation and 25% as test data to be tested against both models that had been established. The highest accuracy result obtained on Naive Bayes which is obtaining a 71.4% score consisting of 20 instances that were properly clarified from 28 training data. While Decision Tree J48 has a lower accuracy of 64.3% consisting of 18 instances that are properly clarified from 28 training data. In Decision Tree J48 there are 4 patterns or rules formed to determine concentration selection so that the academic section can assist students in determining concentration selection.

Download Full-text

Prediksi Kelulusan dan Putus Studi Mahasiswa dengan Pendekatan Bertingkat pada Perguruan Tinggi

SIMADA (Jurnal Sistem Informasi & Manajemen Basis Data) ◽

10.30873/simada.v3i2.2359 ◽

2021 ◽

Vol 3 (2) ◽

pp. 140-148

Author(s):

Hermanto Hermanto

Keyword(s):

Data Mining ◽

Decision Tree ◽

Nearest Neighbor ◽

Naive Bayes ◽

Naïve Bayes ◽

Drop Out ◽

Training Data ◽

K Nearest Neighbor ◽

Quality Of Higher Education

Currently, the problem of college failure, its on-time graduation, and the factors that cause it is still an interesting research topic (C. Marquez-Vera, C. Romero and S. Ventura, 2011). This study compares three data mining classification algorithms namely Naive Bayes, Decision Tree and K-Nearest Neighbor to predict graduation and dropout risk for students to improve the quality of higher education and the most accurate algorithms to use Prepare graduation and dropout prediction Student studies. The best algorithm for predicting graduation and dropout is the decision tree with the best accuracy value of 99.15% with a training data ratio of 30%. Keyword : Data Mining; Algoritma Naive Bayes; Decision Tree; K-Nearest Neighbor; Predict Graduation; Drop Out.

Download Full-text

Pemberian Umpan Balik Dalam Meningkatkan Hasil Belajar dan Minat Belajar Mahasiswa

Formatif Jurnal Ilmiah Pendidikan MIPA ◽

10.30998/formatif.v4i3.158 ◽

2015 ◽

Vol 4 (3) ◽

Author(s):

Seruni Seruni ◽

Nurul Hikmah

Keyword(s):

Information Technology ◽

Learning Outcomes ◽

Test Data ◽

Random Sampling ◽

Covariance Matrices ◽

Test Results ◽

Immediate Feedback ◽

Statistics Course ◽

Independent Variable ◽

Descriptive Statistical Analysis

The purpose of this study is to find and analyze the effect of feedback on learning outcomes in mathematics and an interest in basic statistics course. The population in this study are affordable Information Technology Student cademic Year 2012/2013 Semester II Indraprasta PGRI University of South Jakarta. Sample The study sample was obtained through random sampling. This study used an experimental method to the analysis using the MANOVA test. This study has three variables, consisting of: one independent variable, namely the provision of feedback (immediate and delayed), and two dependent variable is the result of interest in the study of mathematics and basic statistics course. The data was collected for the test results to learn mathematics, and a questionnaire for the interest in basic statistics course. Collected data were analyzed using the MANOVA test. Before the data were analyzed, first performed descriptive statistical analysis and test data analysis requirements (test data normality and homogeneity of covariance matrices). The results show that the learning outcomes of interest in mathematics and basic statistics course for students who are given immediate feedback higher than students given feedback delayed.

Download Full-text

Dropout from an internet-delivered CBT Intervention for Adults with Depression and Anxiety: A Qualitative Study (Preprint)

10.2196/preprints.26221 ◽

2020 ◽

Author(s):

Kate Lawler ◽

Caroline Earley ◽

Ladislav Timulak ◽

Angel Enrique ◽

Derek Richards

Keyword(s):

Online Communication ◽

Structured Interview ◽

Routine Care ◽

Drop Out ◽

Group Differences ◽

Dropping Out ◽

Completion Rates ◽

Depression And Anxiety ◽

Lower Treatment ◽

Perceived Change

BACKGROUND Treatment dropout continues to be reported from iCBT interventions and lower completion rates are generally associated with lower treatment effect sizes. However, evidence is emerging to suggest that completion of a pre-defined number of modules is not always necessary for clinical benefit nor considerate of the needs of each individual patient. OBJECTIVE The study aimed to carry out a qualitative analysis of patients’ experiences of an iCBT intervention in a routine care setting in order to achieve a deeper insight into the phenomenon of dropout. METHODS Fifteen purposively sampled participants (8 female) from a larger parent RCT were interviewed via telephone using a semi-structured interview schedule that was developed from the existing literature and research on dropout in iCBT. Data was analysed using the descriptive-interpretive approach. RESULTS The experience of treatment leading to dropout can be understood in terms of ten domains: Relationship to Technology, Motivation to Start, Background Knowledge and Attitudes towards iCBT, Perceived Change in Motivation, Usage of the Programme, Changes due to the Intervention, Engagement with Content, Experience Interacting with the Supporter, Experience of Online Communication and Termination of the Supported Period. CONCLUSIONS Patients who drop out of treatment can be distinguished in terms of their change in motivation: those who felt ready to leave treatment early and those who had negative reasons for dropping out. These two groups of participants have different treatment experiences, revealing potential attributes and non-attributes of dropout. The reported between group differences should be examined further to consider those attributes that are strongly descriptive of the experience and regarded with less importance those that have become loosely affiliated.

Download Full-text

New polyp image classification technique using transfer learning of network-in-network structure in endoscopic images

Scientific Reports ◽

10.1038/s41598-021-83199-9 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Young Jae Kim ◽

Jang Pyo Bae ◽

Jun-Won Chung ◽

Dong Kyun Park ◽

Kwang Gi Kim ◽

...

Keyword(s):

Colorectal Cancer ◽

Transfer Learning ◽

Test Data ◽

State Of The Art ◽

Early Stage ◽

Statistical Significance ◽

Recall Rate ◽

Training Data ◽

Fine Tuning ◽

Accuracy Evaluation

AbstractWhile colorectal cancer is known to occur in the gastrointestinal tract. It is the third most common form of cancer of 27 major types of cancer in South Korea and worldwide. Colorectal polyps are known to increase the potential of developing colorectal cancer. Detected polyps need to be resected to reduce the risk of developing cancer. This research improved the performance of polyp classification through the fine-tuning of Network-in-Network (NIN) after applying a pre-trained model of the ImageNet database. Random shuffling is performed 20 times on 1000 colonoscopy images. Each set of data are divided into 800 images of training data and 200 images of test data. An accuracy evaluation is performed on 200 images of test data in 20 experiments. Three compared methods were constructed from AlexNet by transferring the weights trained by three different state-of-the-art databases. A normal AlexNet based method without transfer learning was also compared. The accuracy of the proposed method was higher in statistical significance than the accuracy of four other state-of-the-art methods, and showed an 18.9% improvement over the normal AlexNet based method. The area under the curve was approximately 0.930 ± 0.020, and the recall rate was 0.929 ± 0.029. An automatic algorithm can assist endoscopists in identifying polyps that are adenomatous by considering a high recall rate and accuracy. This system can enable the timely resection of polyps at an early stage.

Download Full-text