Article Per Year (5 Year)
p-Index From 2019 - 2024
0.61
P-Index
This Author published in this journals
All Journal JOIV : International Journal on Informatics Visualization Jurnal Teknologi Terpadu Jurnal Teknologi Informasi Cyberku
Yonathan Purbo Santosa
Universitas Katolik Soegijapranata
Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Engineering Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Library & Information Science

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Klasterisasi Kecerdasan Majemuk Siswa Berbasis Jaringan Syaraf Kohonen Guna Mendukung Adaptive Elearning Stefanus Santosa; Wiji Lestari Panjidang; Yonathan Purbo Santosa
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 15 No 2 (2019): Jurnal Teknologi Informasi - Jurnal CyberKU Vol. 15, no 2
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (433.09 KB)

Abstract

Learning strategies are often applied without considering the unique and different characteristics of the learner's intelligence. This causes students to have difficulty understanding the material, not focused, bored, decreased motivation, frustration, and various other learning difficulties. The efforts to create student-oriented learning strategies can be done with adaptive elearning. Adaptive elearning system requires recognition function to cluster the intelligence of the learner when learning takes place. This study shows that Kohonen's Artificial Neural Network can be used for mapping students based on multiple intelligences. The results showed that there were 8 clusters with different intelligence compositions. There is no cluster that has a single intelligence. Intrapersonal intelligence is almost owned by 90% of students, while the lowest is visual-spatial intelligence, which is only 23.33%. In order to create a learner-oriented learning process, this clustering method should be embedded in an adaptive elearning system.
Computational of Concrete Slump Model Based on H2O Deep Learning framework and Bagging to reduce Effects of Noise and Overfitting Stefanus Santosa; Yonathan P. Santosa; Garup Lambang Goro; - Wahjoedi; Jamal Mahbub
JOIV : International Journal on Informatics Visualization Vol 7, No 2 (2023)
Publisher : Politeknik Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30630/joiv.7.2.1201

Abstract

Concrete mixture design for concrete slump test has many characteristics and mostly noisy. Such data will affect prediction of machine learning. This study aims to experiment on H2O Deep Learning framework and Bagging for noisy data and overfitting avoidance to create the Concrete Slump Model. The data consists of cement, blast furnace slag, fly ash, water, superplasticizer, coarse aggregate, fine aggregate, age, slump, and compressive strength. A primary data for concrete mixed design using the fine aggregate material from Merapi Volcano, the hills of Muntilan, and Kalioro. The coarse aggregate was obtained from Pamotan, Jepara, Semarang, Ungaran, and Mojosongo Boyolali Central Java. The cement was using Gresik and Holcim product and the water was from Tembalang, Semarang. The experiment model with one input layer with 7 neurons, one hidden layer with 20 neurons, and one output layer with 1 neuron using activation function TanH, with parameter L1=1.0E-5, L2=0.0, max weight=10.0, epsilon=1.0E-8, rho=0.99, and epoch=800 is able to achieve RMSE of 2.272. This result shows that after introducing Bagging, the error can be reduced up to 2.5 RMSE approximately (50% lower) compared to the model without Bagging. The manually tested mixture data was used to model evaluation. The result shows that the model was able to achieve RMSE 0.568. Following this study, this model can be used for further research such as creating slump design practicum equipment/ application software.
Kombinasi Linier Target Data Untuk Regresi Multitarget Menggunakan Principal Component Analysis Yonathan Purbo Santosa
Jurnal Teknologi Terpadu Vol. 9 No. 1 (2023): Juli, 2023
Publisher : LPPM STT Terpadu Nurul Fikri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54914/jtt.v9i1.516

Abstract

Linear regression is a method to predict numbers, a dependent variable (output) based on some independent variables (inputs). The problem with regression is that some data does not fall into linear problems. Based on this problem, RLC was invented to randomly find a correlation between output by projecting the data into the higher dimension. Unfortunately, RLC does not provide ways to inverse the projection, resulting in poor performance results. On top of that, projecting the data into a higher dimension will increase the learning algorithm complexity. Consequently, PCA can solve the problems by projecting the target data into a lower dimension while leaving possibilities for inverse transformation. This research was implemented with the help of the sci-kit-learn library to create and train the regression model and transform the dataset using Python programming language. As a result, for 12 datasets, augmentation using PCA achieved lower error in 7 datasets than RLC, averaging at 0.3270 for augmentation using PCA and 0.4003 for augmentation using RLC.
Co-Authors - Wahjoedi Garup Lambang Goro Jamal Mahbub Stefanus Santosa Stefanus Santosa Wiji Lestari