Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal RABIT: Jurnal Teknologi dan Sistem Informasi Univrab Akademika
Maria Rosario B
Universitas Dinamika Bangsa
Computer Science & IT Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
ANALISIS KUALITAS WEBSITE SAMSAT JAMBI MENGGUNAKAN METODE DELONE AND MCLEAN Maria Rosario B; Marrylinteri Istoningtyas; Fitria Febrianti
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 6 No 2 (2021): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v6i2.1743

Abstract

The SAMSAT website is an application of information technology that is used to facilitate motorized vehicle users to obtain information related to services provided by the SAMSAT office. Based on the results of the initial questionnaire that the researcher has distributed to 50 respondents, 82% of the respondents stated that the SAMSAT Jambi website has weaknesses, including the website is less attractive in terms of interface and there is an error menu on the website. The purpose of this study is to analyze the level of success of the website SAMSAT Jambi using the Delone and Mclean method and to determine the effect of independent variables (system quality, information quality, service quality) on the dependent variable (use, user satisfaction, net benefits). Data analysis using SEM and SmartPLS software. Based on the results of the data processing of the Jambi community questionnaire, it was found that of the 9 hypotheses proposed in this study, only 7 hypotheses were acceptable including system quality on usage, system quality on user satisfaction, quality of information on usage, quality of information on user satisfaction, use of user satisfaction, use of net benefits, and user satisfaction with net benefits
Evaluasi SMOTE dan SMOTE+Tomek untuk Mengatasi Ketidakseimbangan Kelas pada Prediksi Stunting Balita Berbasis Pembelajaran Mesin Marrylinteri; M. Irwan Bustami; Irawan Irawan; Maria Rosario B; Sansan Rosita
JURNAL AKADEMIKA Vol 18 No 2 (2026): Jurnal Akademika
Publisher : LP2M Universitas Nurdin Hamzah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53564/sajy3k06

Abstract

Class imbalance is a recurring obstacle in machine learning based screening of child nutritional status. This study evaluates and compares the effect of SMOTE and SMOTE+Tomek Links on the classification of toddler nutritional status using K-Nearest Neighbours (KNN) and Random Forest (RF). The data consist of 9,426 anthropometric records with four predictors, labelled into three classes: normal (7,212; 76.51%), moderate stunting (1,612; 17.10%) and severe stunting (602; 6.39%), a majority to minority ratio of about 12:1. Min-Max scaling and resampling were fitted on training data only, inside a pipeline, and the models were assessed on an independent 20% test set (n = 1,886) with stratified 5-fold cross validation. At baseline, RF reached 0.975 accuracy and 0.932 macro-F1, while KNN displayed an accuracy paradox: 0.913 accuracy but only 0.392 recall on severe stunting (47 of 120 cases). SMOTE raised KNN recall to 0.733 and macro-F1 from 0.753 to 0.816. For RF, SMOTE improved both criteria at once: recall rose from 0.825 to 0.908 (99 to 109 cases) and macro-F1 from 0.932 to 0.949. SMOTE+Tomek performed almost identically, removing only 30 of 17,307 training samples. RF with SMOTE is therefore recommended
Co-Authors Fitria Febrianti Irawan Irawan M Irwan Bustami Marrylinteri Marrylinteri Istoningtyas Sansan Rosita