Article Per Year (5 Year)
p-Index From 2020 - 2025
0.659
P-Index
This Author published in this journals
All Journal TEKNIK INFORMATIKA Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) JOMLAI: Journal of Machine Learning and Artificial Intelligence
Trianda, Dimas
Unknown Affiliation
Computer Science & IT Engineering

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

Found 3 Documents
Search

 1 
Overview of Infant Nutrition Status Classification with Rough Set Method Napitupulu, Jessica Evonella; Trianda, Dimas; Nababan , Refly Natalius
JOMLAI: Journal of Machine Learning and Artificial Intelligence Vol. 2 No. 3 (2023): September
Publisher : Yayasan Literasi Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55123/jomlai.v2i3.2893

Abstract

Infant growth and development is an important issue that can be known through nutritional status assessment. A measure of the fulfillment of nutrition in children that can be predicted based on their weight. In assessing the nutritional status of infants, there are concerns in the community about nutritional problems that are good to know, many babies are malnourished and also want to know which children whose nutrition is really ideal]. Rough Set Algorithm can be used as a mathematical tool to overcome uncertainty and imprecise information. This study aims to classify the percentage of nutritional status of infants, using Microsoft Excel and Rosetta version 2.0.0.0 for research and data analysis. The research produced 20 rules in the form of rule patterns as a reference for classifying the nutritional status of infants as poor, less, normal and more. Based on the rules generated, it is concluded that the most influential condition attributes in classifying the nutritional status of infants are gender, age, weight, height and gender, weight, height.
Quantum Perceptron: A Novel Approach to Predicting Unemployment Levels in North Sumatra Province Solikhun; Trianda, Dimas
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 8 No 5 (2024): October 2024
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v8i5.5815

Abstract

The application of Quantum Computing to improve the perceptron algorithm in unemployment prediction is a new aspect of this research. This study focuses on unemployment, which is a big challenge for the young generation in Indonesia, especially in the North Sumatra region. This research applies the quantum perceptron method to provide an alternative solution in predicting the unemployment rate. The data used in this analysis comes from the North Sumatra Central Statistics Agency and includes published unemployment rates (TPT) for individuals aged 15 years and over from 2017 to 2023. This research uses seven variables ranging from x1 to x7 to produce accurate data. Quantum perceptron methods offer specific advantages over traditional methods, including higher computing speeds and the ability to handle greater data complexity. This analysis aims to identify unemployment patterns and trends in North Sumatra and provide more accurate predictions by applying the quantum perceptron method. Although the results of this research are still limited to analysis, this research shows promising results and opens up opportunities for further, more in-depth research. This research is limited to predicting unemployment rates in North Sumatra. The use of quantum computing using the quantum perceptron method shows great potential for application to various other socio-economic problems in the future. This research contributes by introducing a new approach that utilizes quantum technology to improve prediction accuracy in economic analysis.
Comparison of Hyperparameter Tuning Methods for Optimizing K-Nearest Neighbor Performance in Predicting Hypertension Risk Trianda, Dimas; Hartama, Dedy; Solikhun, Solikhun
JURNAL TEKNIK INFORMATIKA Vol. 18 No. 1: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v18i1.42260

Abstract

Hypertension is a major cause of cardiovascular disease, making early risk prediction essential. According to WHO, hypertension cases are estimated to reach 1.28 billion by 2023. This study aims to optimize the K-Nearest Neighbor (KNN) algorithm for predicting hypertension risk through hyperparameter tuning. Three methods Grid SearchCV, Bayes SearchCV, and Random SearchCV are compared to determine the best parameter configuration. The dataset, obtained from Kaggle, consists of 520 balanced samples (260 positive and 260 negative) with 18 health-related features such as age, gender, blood pressure, cholesterol, glucose, and others. After preprocessing, the KNN model is tuned using each method by testing combinations of neighbors (k), weight types, and distance metrics. Results show Bayes SearchCV achieved the highest accuracy of 92%, outperforming the baseline KNN model, which had 85% accuracy. The ROC AUC score of 0.96191 also indicates excellent classification performance. In conclusion, Bayes SearchCV significantly improves KNN's predictive ability in hypertension risk classification.
Co-Authors Hartama, Dedy Nababan , Refly Natalius Napitupulu, Jessica Evonella Solikhun Solikhun Solikhun, Solikhun