Claim Missing Document
Check
Articles

Found 5 Documents
Search

Diabetes risk prediction using logistic regression model Rassiyanti, Linda; Farid, Fajri; Pitri, Rizka
Desimal: Jurnal Matematika Vol. 8 No. 1 (2025): Desimal: Jurnal Matematika
Publisher : Universitas Islam Negeri Raden Intan Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24042/djm.v8i1.26493

Abstract

This study aims to analyze the factors that contribute to diabetes using the logistic regression method. The data used in this study include variables of number of pregnancies, glucose levels, blood pressure, skin thickness, insulin levels, body mass index (BMI), family history of diabetes, and age. The logistic regression model was applied to determine the effect of each variable on the likelihood of a person having diabetes. Evaluation of model performance was carried out using the ROC (Receiver Operating Characteristic) curve, and the results obtained showed an AUC value of 0.8391, which indicated a very good classification ability of the model. The results of the analysis showed that the number of pregnancies, glucose levels, blood pressure, BMI, and family history of diabetes had a significant effect on the risk of diabetes.
Factor Analysis for Increasing Reading Literacy in Indonesia Pitri, Rizka; Sofia, Ayu
Parameter: Journal of Statistics Vol. 2 No. 2 (2022)
Publisher : Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Tadulako

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22487/27765660.2022.v2.i2.15898

Abstract

Low interest in reading is a problem for our nation that must be solved, because Indonesia to occupy second position from bottom in terms of literacy. Most of the provinces in Indonesia are at low literacy activity levels and none of the provinces are included in the high literacy activity level. The lack of interest in reading can be influenced by many factors. Access of supporting resource where people get literacy materials, such as libraries, bookstores, and mass media, how people to get the information technology, and media devices to access literacy materials are the factor that can be affect the interest of reading. Literacy is one of the important cultures for a country. That is because the culture is able to influence the intelligence and well-being of a country's life. So the study aims to see what factors affect to increasing the literacy reading in the provinces in Indonesia. This study uses k-means clustering before applying factor analysis. Based on k-means clustering, two clusters are formed and showed one of the cluster showed that the second cluster is the provinces that have the highest number of library’s facilities. In addition based on the analysis factor in each cluster, two factors were formed, namely the standard factor for reading literacy levels and supporting the facilities for reading literacy. It can be concluded that the way to increase reading literacy in two clusters of the area in Indonesia are by increasing the standard of reading literacy level and supporting the facilities for reading literacy.
IMPLEMENTATION OF THE K-MEDOIDS METHOD IN CLUSTERING HUMAN DEVELOPMENT INDEXES IN INDONESIA Erda, Gustriza; Usdika, Radhiatul Khaira; Pitri, Rizka; Erda, Zulya
Parameter: Journal of Statistics Vol. 3 No. 2 (2023)
Publisher : Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Tadulako

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22487/27765660.2023.v3.i2.16906

Abstract

The Human Development Index (HDI), which takes into account three fundamental aspects of human existence, a long and healthy life, knowledge, and a reasonable level of living, is one tool used to assess the effectiveness of human progress. Clustering provinces based on the human development index is important so that development disparities can be identified and help identify provinces with high, medium or low levels of development. The purpose of this study was to use the k-medoids approach to perform a cluster analysis of HDI in Indonesia based on life expectancy, average years of schooling, expected years of schooling, and expenditure per capita adjusted for 2022. The analysis indicate that two clusters were created: cluster 1 had a high human development index, while cluster 2 had a low human development index. More provinces belonged to cluster 1 than cluster 2 suggesting that human development index in Indonesia in 2022 was largely in the high category
SENTIMENT ANALYSIS OF REVIEW DATA OF THE RUANGGURU ONLINE LEARNING APPLICATION USING THE C5.0 ALGORITHM Izzah, Nurul; Nur'eni; Pitri, Rizka
Parameter: Journal of Statistics Vol. 3 No. 2 (2023)
Publisher : Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Tadulako

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22487/27765660.2023.v3.i2.16919

Abstract

Sentiment analysis is process to determine the sentiment of a person that is manifested in the form of text. Internet users write their opinions and everything that concerns them in the google play store review column. Moreover, when the world of education could not carry out face-to-face learning due to the covid-19 pandemic, learning turned to e-learning applications. Through this innovation, many pros and cons flow from the community with the existence of Ruangguru online learning application in the world of education. This research was conducted with the aim of determining word cloud visualization and the accuracy of the results of sentiment analysis of review data on the Ruangguru application using the C5.0 algorithm. The word cloud visualization results are dominated by word such as “paham”, “bagus”, “mudah”, “suka”, “langganan”, “seru”, “nyaman”, “senang”, “menarik”, “keren”, “lancar”, “sukses”. This shows that Ruangguru Application is a good application because it is dominated by positive sentiment words which means that users find it helpful and easy to understand the learning material in Ruangguru. The results of the Confusion Matrix show that the model successfully classifies 0.8557 or 85.57% of the data correctly from all test data
EFFECTIVENESS OF INTERACTIVE MULTIMEDIA ARTICULATE STORYLINE 3 USING PAIRED SAMPLE T-TESTS Pitri, Rizka
Parameter: Journal of Statistics Vol. 4 No. 1 (2024)
Publisher : Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Tadulako

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22487/27765660.2024.v4.i1.17084

Abstract

In facing the era of globalization, especially in the field of education, the government must improve and prepare a better government system. Therefore, efforts are needed to be made, one of which is by increasing basic abilities in the mathematics. The lack of innovation in the process of learning mathematics makes students feel bored with the material provided. Therefore, students often get mathematics score below the graduate competency standards and even fail. Based on these facts, it is necessary to develop interactive multimedia learning innovations in mathematics by creating interactive multimedia using articulate storyline 3 in mathematics learning. So the research was conducted on the effectiveness of interactive multimedia using storyline articulation 3 using paired sample t-tests. This research was using 166 students of class X SMAN 4 Kotabumi. This study aims to see the efficiency of interactive multimedia articulating storyline 3 on understanding concepts and increasing students' academic scores in mathematics. Based on the results of the paired sample t-test, the p-value is 0.000, which is less than the 0.05 significance level. So it can be concluded that the application of multimedia articulate storyline 3 is efficient in increasing students' understanding of mathematical concepts and academic values.