Claim Missing Document
Check
Articles

Aplikasi Data Mining Menggunakan Algoritme C4.5 untuk Memprediksi Ketepatan Lulus Mahasiswa Berdasarkan Faktor Demografi Diva Devina; Ahmad Afif Supianto; Welly Purnomo
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 6 (2019): Juni 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (907.403 KB)

Abstract

Students who graduate not on time are a problem that is still often found in the college academic environment. This was also found in the UB Information Systems study program, wherein 2015-2018 there were 241 students accepted each year on average, while the average student graduated around 130 students. Based on the information, students who graduated and students received were not balanced. So that it can be said that there are still many students who are active and have completed their study period of more than 8 semesters or graduated not on time, this can be detrimental to both students and study programs. Therefore we need a step to help the problem of student graduation accuracy, namely by making predictions using data mining. By utilizing one of the data mining methods namely Decision Tree C4.5, which will later produce a rule in the form of a decision tree. The data used in the data mining process only uses demographic (non-academic) data from students to find out whether the demographics influence the graduation accuracy of students, after that the data is processed using Weka CLI. The results of the algorithm evaluation carried out using the confussion matrix obtained an accuracy rate of 80.4714%. Information about predictions of student graduation accuracy is displayed in the form of a dashboard to make it easier for Kaprodi SI as user. System tested using black-box testing and System Usability Scale (SUS), with the results of valid black-box testing as needed, while the SUS test gets results 67.5.
Analisis Sentimen Evaluasi Kinerja Dosen menggunakan Term Frequency-Inverse Document Frequency dan Naive Bayes Classifier Sri Wulan Utami Vitandy; Ahmad Afif Supianto; Fitra Abdurrachman Bachtiar
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 6 (2019): Juni 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (560.926 KB)

Abstract

Effective and efficient in teaching can help students achieve maximum results. An evaluation is needed to improve the quality of learning and academic standardization, also it can improve the quality of the student. Therefore, the Information Systems Department always evaluates performance using questionnaires and filled by students at the end of each semester. The results of the suggestion column can be sentiment analysis to find out whether the suggestion is positive, negative or neutral. The classifier is a method that can classify data into several classes. Naive Bayes Classifier can be used to classify opinions into positive, negative and neutral classes. The comment data was collected 3502 comments which were divided into 3 semesters. Then, this comment data processed in preprocessing, weighting TF-IDF and classification using Naive Bayes Classifier. The test result on 4 parameters resulted in an accuracy of 80,1%, Precision 80,3%, Recall 80,3% and F1-Score 80%. The results of Usability testing obtained an average value of SUS Score of 75. So it can be concluded that the Dashboard is included in the Acceptance category and in the rating of "Good"
Analisis Sentimen Opini Mahasiswa Terhadap Saran Kuesioner Penilaian Kinerja Dosen dengan Menggunakan TF-IDF dan K-Nearest Neighbor Nur Shafiya Nabilah Salam; Ahmad Afif Supianto; Andi Reza Perdanakusuma
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 6 (2019): Juni 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (850.128 KB)

Abstract

Faculty of Computer Science on the University of Brawijaya evaluates lecturer performance every semester and the evaluation program was carried out by the Quality Assurance Unit (UJM) Team. UJM Team does the evaluation by distributing questionnare within the Student Academic Information System (SIAM). There were two section on the questionnaire, multiple choice section and the comment section. After collecting data, UJM Team processed the data from the comment section manually. The comment section contained student's perspective of the lecturer performance, which has never been processed to date to be used as an evaluation material. Therefore, this study is performed to assist UJM Team to process the data from the comment section using Sentiment Analysis on sentence level with K-Nearest Neighbor classification method. Out of 2210 opinion data from students of the Information Technology Study Program analyzed from three semester period in the Even Semester 2016/2017, Odd Semester 2017/2018, and Even Semester 2017/2018, the classification result in an average accuracy of 81%. The result of this study is a list of opinions and bar chart showing the frequency of opinions that have been classified and will be displayed as a dashboard. This data opinions can also be filterred by lecturer's subjects and his/her name.
Aplikasi Data Mining untuk Memprediksi Mahasiswa Berpotensi Drop Out menggunakan Algoritme K-Nearest Neighbor (K-NN) Mardiani Putri Agustini; Ahmad Afif Supianto; Welly Purnomo
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 6 (2019): Juni 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (476.111 KB)

Abstract

Drop out is a problem related to the success of student learning. This problem has also happened in Information System study program at Brawijaya University. The results of interviews were conducted with the Head of the Information System Study Program that there was a drop out every year. The existence of students who drop out can cause a decrease in the quality of higher education. Therefore, as handling of these problems needs a system that capable to help make decisions to predict on students who have the potential to drop out so prevention can be done. This system is expected to be able to help the Brawijaya Information System Study Program in making decisions, become the material for early evaluation and provide early treatment for students who have the potential to drop out. One technique for predicting is to use data mining. Classification using K-Nearest Neighbor (K-NN) algorithm is one of data mining method that can be used to predict student drop out potential. The results of processing with the help of Weka tool found the best proximity value using the K-NN algorithm is k=5. The results of evaluating algorithms obtained using confusion matrix have an accuracy rate of 99.2337%. The AUC value result of ROC curve shows a value of 0.8918. The level of usability testing generated by utilizing SUS is 67.
Aplikasi Data Mining menggunakan Algoritme Naive Bayes untuk Memprediksi Ketepatan Waktu Lulus Mahasiswa Riska Agustia; Ahmad Afif Supianto; Niken Hendrakusma Wardani
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 7 (2019): Juli 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (507.107 KB)

Abstract

The graduation rate for each student is different, timely and not on time. What can be an obstacle is if there are many students who graduate not on time. Based on data in 2018 on the official website of the Faculty of Computer Science, Universitas Brawijaya, the average student admission of Information Systems every year is approximately 227 students, while for the average student graduating annually around 134 students. So based on these data, an application is needed that is able to help decision makers to predict earlier students who have the potential to pass on time so that further action can be given. The process of predicting the timeliness of graduating students will be done using the Naive Bayes algorithm. The system implementation will utilize the Laravel framework and Weka simple CLI. The output generated from the system is in the form of a dashboard visualization with a chart containing graduation information, a form to create a model, information from the model that has been made, and a form that can be used by the Head of the SI Department to predict the timeliness of graduating students. The results of the evaluation and validation of the Naive Bayes algorithm resulted in an accuracy value of 88.6076% and an AUC of 0.9558. The results of testing the system using black-box testing shows that the system is valid according to defined requirements. While for usability testing with the System Usability Scale produces a value of 67.5 which is classified as an Adjective rating Good.
Aplikasi Data Mining menggunakan Algoritme C4.5 untuk Memprediksi Mahasiswa Berpotensi Drop Out Izza Isma; Ahmad Afif Supianto; Andi Reza Perdanakusuma
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 7 (2019): Juli 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (818.501 KB)

Abstract

Higher education is the organizer of academic education for students where the quality of a college can be seen from the high level of success of students and the low failure rate of students. One indicator of student failure is a drop out case where it is also experienced by the study program Information System of the Faculty of Computer Science, University of Brawijaya. Based on the results of the interview obtained information that every year there are students of Information Systems who resign. The case certainly needs to be considered so as not to reduce the quality of education and university accreditation. So based on these problems a system is needed that is able to be a decision support to detect students who have the potential to drop out so that further action can be given. C4.5 algorithm is one of the algorithms in data mining that can be used to predict students who have the potential to drop out by generating rule in form of decision tree. The attributes used consist of academic data and student demographics of the study program Information Systems. The results from the calculation of confussion matrix are an accuracy rate of 98.85%. Meanwhile, based on the ROC curve, the AUC value is 0.8462. The output of this study is to make predictive applications for students who have the potential to drop out for the study program Information System by applying the C4.5 algorithm for the mining process on a system developed in the form of a website-based dashboard. Usability testing using the System Usability Scale (SUS) is 67.5 which is included in the adjective rating Good category and the acceptability level of users is included in the Marginal-High category.
Pengembangan Aplikasi Media Pembelajaran Berbasis Website Untuk Materi Laju Reaksi di Tingkat SMA (Studi Pada SMA Brawijaya Smart School Malang) Ignatius Chandra Christian; Ahmad Afif Supianto; Retno Indah Rokhmawati
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 7 (2019): Juli 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1131.613 KB)

Abstract

One of the difficult material at the senior high school is the Reaction Rate, because students need to understand the factors that affect the Reaction Rate that are difficult if only explained verbally without being followed by practice. The problem is demonstrate the affect of the Reaction Rate requires time and effort. Learning books are considered to be lacking in representing factors of the reaction rate effectively. The teacher also has difficulty knowing the gap in understanding between students. Based on these problems, a learning media application is needed that can help teachers demonstrate the Reaction Rate material, know the level of understanding of students, are easily accessible and attract students' interest in learning. The methodology in this research uses Extreme Programming (XP) with the aim of covering all needs and changes in user needs. The design of the application is object oriented using the Model-View-Controller (MVC) design pattern.. The process of implementing the application is done using the CodeIgniter framework. Furthermore, the developed application was tested using the Basis-Path Testing and Compatibility Testing method to determine the level of successful implementation and User Acceptance Testing to determine user acceptance of the application. The results of the research indicate that the website-based Reaction Rate learning media application can accommodate needs and is easy to use by both teachers and students. Extreme Programming (XP) methodology is quite suitable to cover all needs, but for segmentation of learning media is less suitable because more changes occur in the user interface aspects.
Peramalan Hasil Penjualan Perhiasan Emas Menggunakan Metode Exponential Smoothing (Studi Kasus: Toko Emas Rejeki Baru Sumenep) Risqi Auliatin Nisyah; Nurul Hidayat; Ahmad Afif Supianto
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 7 (2019): Juli 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1037.077 KB)

Abstract

Gold is a precious metal which is one of the important roles in people's daily lives. Gold jewelry is usually sold in large places such as markets to small shops. The rise and fall of the sales of gold obtained by the seller is difficult to predict, one of the contributing factors is the uncertain gold price following the fluctuation of the rupiah exchange rate against the dollar. Though knowing the results of future sales can help the seller to know the benefits and losses in the coming period. Therefore, it takes a system that functions to do forecasting to find out the results of automatic gold sales with the Exponential Smoothing method which is one of the forecasting methods that can perfect a forecasting result by smoothing on past values ​​that function to produce forecasting values. Then, error evaluation of forecasting results was performed with Mean Absolute Percentage Error (MAPE). The lowest MAPE results obtained were located in the SES method when the parameter α = 0.4 with a value of 56.64. Based on the MAPE value that has been obtained using the three methods on Exponential Smoothing, the results obtained above 50, then the Exponential Smoothing method is not suitable to be used to calculate forecast sales of gold.
Sistem Prediksi Penerimaan SNMPTN menggunakan Algoritme Decision Tree C4.5 Dityo Kukuh Utomo; Ahmad Afif Supianto; Welly Purnomo
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 9 (2019): September 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (464.268 KB)

Abstract

Seleksi Nasional Masuk Perguruan Tinggi Negeri (SNMPTN) is a selection of tertiary education based on the grade of subjects which each year experiences an increase in the number of participants so that they have a high level of competition. Counseling guidance teacher has the duty to predict student acceptance in attending SNMPTN. Problems arise when the number of students conducting guidance increases as the SNMPTN registration time approaches. Therefore, we need a system that can predict the likelihood of students being accepted through the SNMPTN pathway to ease the burden on counseling guidance teachers. One prediction algorithm is decision tree C4.5 that makes decision tress to describe rules. The data used comes from the value of subjects belonging to SMA Negeri 3 Malang alumni who have attended SNMPTN from 2016-2018 with a total of 681 data for the Natural Sciences majors and 90 data for the Social Sciences majors along with a list of students graduating SNMPTN in the same year. From the value data and the list of students passing the SNMPTN, the attribute used is only the attribute value of the subjects used in the 2019 SNMPTN along with the status of graduating or not students in joining the SNMPTN. The system is built in the form of a website that utilizes WEKA CLI for the prediction process. The black box testing-validation results show the use case and system functions are matched or valid. The system usability level generated by utilizing the system usability scale is 87.5 which is included in the "acceptable" category
Sistem Pendukung Keputusan untuk Penentuan Dosen Pembimbing Skripsi menggunakan Algoritme Winnowing-Weighted Product Rizka Awaliyah Nurul Putri; Ahmad Afif Supianto; Welly Purnomo
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 9 (2019): September 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (386.826 KB)

Abstract

In order to complete their thesis, students need a supervisor. Thesis supervisor plays an important role as a good facilitator, motivator, and director so that the thesis can be completed and ready to be tested. The inappropriate determination of supervisors can hamper the student's thesis guidance and work process. For this reason, an effective system to reccomend thesis supervisors for students is needed to minimize errors that may occur in the determination of the thesis supervisor. The recommendations given are not only based on personal knowledge, but also consider lecturers' researches, KJFD, majors, quotas, positions, and lecturer workload. The lecturer research data used was obtained from Google Scholar, functional position data was obtained from forlap.risetdikti.go.id, and the department data, quota, and lecturer workload were obtained from the Information Systems Management, IT Infrastructure and Public Relations of Faculty of Computer Science (PSIK). The validation test results show that the system built was in accordance with the requirements defined. The usability test results that utilize the System Usability Scale (SUS) show the system usability level is 90% which means system is in the acceptable category..
Co-Authors Abdul Harris Wicaksono Achmad Firmansyah Sulaeman Adhitya Pratama Wijayakusuma Adinugroho, Sigit Admaja Dwi Herlambang Afrizal Aminulloh Ahmad Fairuzabadi Aldous Elpizochari Ammar Burhanuddin Sayuti Anam, Syaiful Andi Reza` Perdanakusuma Anggie Tamara Blanzesky Annisa Salamah Rahmadhani Arief Andy Soebroto Bayu Rahayudi Beta Deniarrahman Hakim Bilal Benefit Candra Dewi Carlista Naba Chandra Ayu Anindya Putri Dewa Ayu Anggi Gharbelasari Dian Eka Ratnawati Dito William Hamonangan Gultom Dityo Kukuh Utomo Diva Devina Djoko Pramono Entra Betlin Ladauw Fadhyl Farhan Alghifari Fawwaz Roja Mahardika Febrian Pandu Widhianto Feri Setyo Efendi Fitra Abdurrachman Bachtiar Fitra Abdurracman Bachtiar Galih Wisnu Murti Gede Jaya Widhi Aryadi Hafizh Yuwan Fauzan Haryo Setowibowo Herman Tolle Hilmi Rezkian Aziz Dama Ignatius Chandra Christian Imaning Dyah Larasati Indra Ekaristio P Indriati Indriati Iqbal Setya Nurfimansyah Izza Isma Komang Candra Brata Lestari, Retno Linda Pratiwi Lutfi Fanani Lutfi Putra Gusrinda Mardiani Putri Agustini Maulana Aditya Rahman Mira Wahyu Kusumawati Mochamad Bachtiyar Eko Cahyo Putro Mochammad Izzuddin Mohammad Birky Auliya Akbar Mohammad Malik Abdul Azis Muhammad Aminul Akbar Muhammad Hasan Johan Alfarizi Muhammad Tanzil Furqon Nabila Divanadia Luckyana Nanang Yudi Setiawan Nanda Samsu Dhuha Ni Wayan Surya Wardhani Niken Asih Laras Ati Niken Hendrakusma Wardani Novira Azpiranda Nur Aenun Marjan Nur Laita Rizki Amalia Nur Sa'diyah Nur Shafiya Nabilah Salam Nurul Hidayat Onky Prasetyo Phat Prapawichar Puras Handharmahua Rafid Agung Pradana Retno Indah Rokhmawati Ridhoyanti Hidayah Ridwan Sofian Rifaldi Raya Rifky Yunus Krisnabayu Riska Agustia Risqi Auliatin Nisyah Rizka Awaliyah Nurul Putri Rosa Nur Madinah Rudi Gunawan Ryan Dwi Pambudi Santi Yunika Sufiana Satrio Agung Wicaksono Satrio Hadi Wijoyo Sri Wulan Utami Vitandy Tibyani Tibyani Tri Berlian Novi Ulfatun Nadifa Vito Ramadhan Welly Purnomo Widhy Hayuhardhika Nugraha Putra Willy Aditya Nugraha Windarwati, Heni Dwi Yusi Tyroni Mursityo Yustinus Radityo Pradana