Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : INFORMAL: Informatics Journal

Optimasi Algoritma XGBoost Classifier Menggunakan Hyperparameter Gridesearch dan Random Search Pada Klasifikasi Penyakit Diabetes Ginanjar Abdurrahman; Hardian Oktavianto; Mukti Sintawati
INFORMAL: Informatics Journal Vol 7 No 3 (2022): Informatics Journal (INFORMAL)
Publisher : Faculty of Computer Science, University of Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.19184/isj.v7i3.35441

Abstract

Classification using XGBoost in this study was applied to diabetes data originating from the UCI Machine Learning website. The initial step in this research is to deal with missing values. Missing value is found in several features. These missing values need to be handled otherwise the XGBoost algorithm will not work. Missing value handling is done by adding a meaningful value as a substitute for the missing value. At the time of modeling, the dataset is divided into training data and test data. The training data used is 80% of the number of patients, while the test data is 20%. In this study, the dataset that had imputed missing values was subjected to three treatments, first without hyperparameters, secondly hyperparameter tuning using gridsearch, and third hyperparameter tuning using random search. In the first treatment, classification using XGBoost without hyperparameters obtained a negative log loss value of 25%, which means that the performance accuracy of the algorithm reaches 75%. As for the second treatment and the third treatment, namely by using gridsearch and random search, it produces the same negative log loss value, which is 5%, which means that the performance of the algorithm reaches 95%. Thus, the performance of gridsearch and random search can significantly increase the accuracy value
Rancang Bangun Aplikasi Smart Kids English Berbasis Mobile Dasuki, Moh; Abdurrahman, Ginanjar
INFORMAL: Informatics Journal Vol 8 No 3 (2023): Informatics Journal (INFORMAL)
Publisher : Faculty of Computer Science, University of Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.19184/isj.v8i3.38420

Abstract

Smart Kids English is a mobile-based learning media application that aims to help teachers and parents accompany children in learning English with different experiences by utilizing technology. The use of learning software is considered more effective because basically children use gadgets more often in their daily activities. Using learning software on gadget devices can also minimize the use of gadgets for unimportant applications such as playing games. The System Development Life Cycle in this research uses the Waterfall method, this method is used by many software developers. This research produces the Smart Kids English application with several basic features such as: pronunciation which is equipped with attractive images. Smart Kids English is equipped with a writing feature to train children in writing English. Smart Kids English is equipped with an animal sounds feature to increase children's insight into recognizing animal sounds in the environment around us. Smart Kids English is also equipped with a practice menu, the aim of which is to sharpen children's memory in remembering the material they have studied.