Article Per Year (5 Year)
p-Index From 2021 - 2026
0.835
P-Index
This Author published in this journals
All Journal Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen)
Gunadi Widi Nurcahyo
Universitas Putra Indonesia “YPTK” Padang, Indonesia
Computer Science & IT Control & Systems Engineering

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Penerapan Metode Naïve Bayes Dalam Memprediksi Kepuasan Mahasiswa Terhadap Cara Pengajaran Dosen Putri Ramadani; Gunadi Widi Nurcahyo; Billy Hendrik
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 2 (2024): Edisi April
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i2.361

Abstract

Student satisfaction in higher education is the main focus in improving the quality of education. In the Tridharma paradigm, satisfaction is measured through a comparison of expectations and teaching realization as the main indicator of learning effectiveness. This research method uses Naïve Bayes classification, through the steps of reading training data, calculating prior probabilities, training data probabilities for each category, reading testing data, and calculating final probabilities. This research aims to evaluate student satisfaction with lecturers' teaching at the LP3I Polytechnic, Padang Campus. The data used in this research was 574. The results of research with 574 data (516 training and 58 testing) showed that 52 data (89.648%) stated "Very Satisfied", while 6 data (10.344%) stated "Satisfied". Prediction accuracy reached 98.28%. However, when using the Naïve Bayes method with 574 data (574 training and 574 testing), 397 data (69.078%) stated "Very Satisfied" and 177 data (30.798%) stated "Satisfied". Without the Naïve Bayes method, 402 data (69.948%) stated "Very Satisfied" and 172 data (29.928%) stated "Satisfied". An improvement of 0.87% occurred for the "Very Satisfied" category and -0.87% for "Satisfied". There are no differences in percentages for other categories. From the comparison of results, it can be seen that the Naïve Bayes method is superior in predicting student satisfaction levels compared to calculations without this method. Therefore, it can be concluded that the Naïve Bayes process model is suitable for use as a method for determining good decisions in predictions
Integrasi Knowledge Management System Dan Teknik Knowledge Discovery In Database Dalam Sharing Culture Pada Proses Pembelajaran Berbasis Blended Learning Iswandi Saputra; Sarjon Defit; Gunadi Widi Nurcahyo
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 2 (2024): Edisi April
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i2.385

Abstract

Education is rapidly changing in the digital age, especially with blended learning, which mixes online and in-person classes. This approach is popular because it offers a well-rounded learning experience. However, getting students and teachers to share knowledge remains a challenge. This study looks at how combining Knowledge Management Systems (KMS) and Knowledge Discovery in Databases (KDD) can help improve knowledge sharing in blended learning at universities. By analyzing data from the E-Learning section of UPI YPTK Padang, involving 120 students, the research aims to create more effective learning systems that encourage sharing. It's a step towards better education in the digital era, promoting collaboration and knowledge exchange among students and educators.
Penerapan Jaringan Syaraf Tiruan Dengan Algoritma Backpropagation Untuk Memprediksi Kunjungan Poliklinik (Studi Kasus Di Rumah Sakit Otak Dr. Drs. M. Hatta Bukittinggi) Eka Ramadhani Putra; Gunadi Widi Nurcahyo; Y Yuhandri
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 2 (2024): Edisi April
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i2.354

Abstract

Artificial Neural Networks (ANN) are computational models inspired by the structure and function of biological neural networks. ANN can model and learn complex patterns in data. The Backpropagation algorithm is a training algorithm used to optimize weights and biases in ANN.. Use of Python Applications is a popular form of computing used in the fields of science and engineering, including in the development and implementation of ANN. Python provides powerful library for building, training, and deploying ANNs. This research aims to have the ANN Backpropagation Algorithm train data using previously collected polyclinic visit data so that the ANN can learn to predict the burden of polyclinic visits in the future. The method in this research uses the Backpropagation Algorithm. This method has six stages, namely data input, normalization, training, testing, calculating test accuracy, and prediction. The dataset processed in this research comes from the annual report of Rumah Sakit Otak Dr. Drs. M. Hatta Bukittinggi from 2020 to 2022. The dataset consists of 36 months of visits to the polyclinic. The results of this research use the 3-10-1 pattern and can identify or calculate predictions for the next 5 months, 2547 people, 2506 people, 2463 people, 2482 people, and 2495 people. The percentage of predictions for polyclinic patient visits with an accuracy level of computing time requiring 0.001 seconds, an average error of 8.794%, and an average accuracy of 91.706%. Therefore, this research can be a reference in predicting polyclinic patient visits in the future so that it can be a consideration for hospital management.
Penerapan Algoritma Fuzzy C-Means untuk Clustering Penilaian Laporan Kinerja Dosen pada UIN Imam Bonjol Padang Alvi Dwi Wahyuni; Sarjon Defit; Gunadi Widi Nurcahyo
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 2 (2024): Edisi April
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i2.359

Abstract

-
Penerapan Algoritma K-Means Dalam Pengklasteran Hasil Evaluasi Akademik Mahasiswa Fitri Safnita; Sarjon Defit; Gunadi Widi Nurcahyo
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 2 (2024): Edisi April
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i2.360

Abstract

Several institutions that have utilized computer-based information systems for many years certainly have quite large amounts of data. The data generated and stored in a computer system is designed to be fast and accurate in both operation and administration. This data is designed for reporting and analysis that uses that data. It turns out that there is a lot of data available, with so much data we are increasingly faced with the question, "What knowledge can we gain from this data?" The K-Means algorithm is an iterative clustering algorithm that partitions a data set into a number of clusters that are initially determined. The K-Means algorithm is an iterative clustering algorithm that partitions a data set into a number of clusters that are initially determined. The K-Means algorithm is easy to implement and run, relatively fast, easy to adapt, commonly used in practice. The parameter that must be entered when using the K-Means algorithm is the K value. The K value is generally used based on previously known information regarding how many clusters appear in This research aims to group students based on academic evaluation results. The method used to manage student academic data uses the Data Mining method with the K-Means Clustering Algorithm. The dataset processed in this research comes from the Faculty of Engineering, Informatics Engineering Study Program, Islamic University of Riau. The dataset consists of 180 student data starting from semester 1 to semester 4. The results obtained from this research are in the form of grouping students based on the achievement student cluster, there are 104 students with a percentage of 57.72%, the student cluster with potential for achievement is 62 students with a percentage of 34 .41%, the potentially problematic student cluster has 10 students with a percentage of 5.55%, and the problematic student cluster has 4 students with a percentage of 2.22%. Therefore, it is hoped that the results of this research will provide new knowledge that can be used as a source of information and function as a reference model for academic planners to monitor and predict the development of each student's academic performance.
Co-Authors Alvi Dwi Wahyuni Billy Hendrik Eka Ramadhani Putra Fitri Safnita Iswandi Saputra Putri Ramadani Sarjon Defit Y Yuhandri