Claim Missing Document
Check
Articles

Found 14 Documents
Search

IMPLEMENTATION OF DECISION TREE AND SUPPORT VECTOR MACHINE ON RAISIN SEED CLASSIFICATION Wardhani Utami Dewi; Khoirin Nisa; Mustofa Usman
AKSIOMA: Jurnal Program Studi Pendidikan Matematika Vol 12, No 1 (2023)
Publisher : UNIVERSITAS MUHAMMADIYAH METRO

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (402.668 KB) | DOI: 10.24127/ajpm.v12i1.6873

Abstract

In everyday life there are many complex and global problems, especially in terms of decision making. Machine learning (ML) which is built from the concepts of computer science statistics and mathematics can automatically solve problems without guidance from ordinary users. Decision tree (DT) and support vector machine (SVM) are two supervised learning methods among several classification algorithms in ML. Both algorithms are the most popular classification techniques due to their ability to change a complex decision-making process into a simple process. In this study, the accuracy of the DT and SVM algorithms is studied on classifying raisin seeds into the Besni class and the Kecimen class based on existing features. The raisin data are divided into training and testing data, and the evaluation of the two methods is done using the testing data. The results of the evaluation are compared based on the accuracy, sensitivity, specificity, and kappa levels of the DT and SVM algorithms. The results on classifying raisin seeds data show that the SVM algorithm is superior to DT, therefor the number of positive observations is more precise in the prediction.
IMPELEMENTASI K-NEAREST NEIGHBORS, DECISION TREE DAN SUPPORT VECTOR MECHINE PADA DATA DIABETES Irfan, Miftahul; Dewi, Wardhani Utami; Nisa, Khoirin; Usman, Mustofa
Jurnal Mahasiswa Ilmu Komputer Vol. 4 No. 2 (2023): Jurnal Mahasiswa Ilmu Komputer October 2023
Publisher : Universitas Muhammadiyah Metro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24127/ilmukomputer.v4i2.4007

Abstract

Diabetes merupakan salah satu penyakit yang menjadi penyebab kematian terbesar didunia. Kasus kematiannya pun tercatat lebih dari 4 juta pada tahun 2019. Diabetes juga dapat menyebabkan timbulnya penyakit lainnya. Bahaya diabetes ini menjadi perhatian khusus WHO. Seiring dengan perkembangan teknologi ini, banyak sekali kolaborasi antara bidang kesehatan, statistic dan computer untuk menanggulangi berbagai macam penyakit. Algortima machine learning menjadi popular dalam proses klasifikasi data dan sudah banyak diterapkan pada data kesehatan. Dengan begitu pada artikel ini akan dilakukan perbandingan algoritma machine learning KNN, Decision Tree, dan SVM untuk melihat algortima mana yang paling cocok untuk klasifikasi data diabetes. Hasil menunjukkan bahwa KNN dan SVM memiliki akurasi yang cukup besar yaitu 81,13%. Sehingga kedua algortima tersebut dapat menjadi rekomendasi proses klasifikasi data diabetes sehingga dapat membantu dokter dalam menanggulangi penyakit diabetes. Hasil ini juga menunjukkan bahwa 8 variabel yang digunakan berpengaruh terhadap resiko diabetes
Sampling Survey Design Presidential Election Quick Count Sumatera Island Dewi, Wardhani Utami; Warsono, Warsono; Nisa, Khoirin
Sciencestatistics: Journal of Statistics, Probability, and Its Application Vol. 1 No. 1 (2023): JANUARY
Publisher : Universitas Muhammadiyah Metro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24127/sciencestatistics.v1i1.3162

Abstract

The number of TPS on the island of Sumatra is very large, in order to save time and money in conducting surveys, a sampling survey design was created. The purpose of this study is to predict the results of the presidential election on the island of Sumatra. The TPS sample frame was obtained in four stages where each stage used a sampling technique, namely the first and second stages used stratified random sampling, the third stage used systematic random sampling, and the last used clusters. The results obtained are with different TPS sample sizes showing the same results. The victory in the presidential election on the island of Sumatra was won by candidate pair number two. Then compared with the overall TPS population in Sumatra. Based on the population, the second candidate pair is also superior. So it can be concluded that the use of a survey sampling design in this study is appropriate in predicting the results of the elected president election.
Log-Linear Model on Categorical Data of HIV Cases Dewi, Wardhani Utami; Warsono, Warsono
Sciencestatistics: Journal of Statistics, Probability, and Its Application Vol. 1 No. 2 (2023): JULY
Publisher : Universitas Muhammadiyah Metro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24127/sciencestatistics.v1i2.5022

Abstract

Categorical data is widely used in social, health, educational and psychological research. A contingency table is a form of presenting this data. One of them is about cases of being infected with the HIV virus. The log-linear model is an alternative for analyzing categorical data. In this study, HIV cases will be analyzed using a log-linear model grouped by gender, age and province. Apart from that, several log-linear models will be formed and the best model will be selected based on the likelihood ratio (G^2) statistical test. According to the results of the analysis and consideration of model complexity, (JK*P, JK*U, P*U) is the best model and fits the data because the p-value = 0.517 is greater than the real level α = 0.05. This means that the interaction between gender, age and province is significant. Studies and explanations about the HIV virus show that individuals between the ages of 25-49 years are more at risk of being infected with the virus. Examined by gender group, women were most infected with the virus, namely 513 people. Apart from that, West Papua is the province with the highest number of HIV infections compared to Maluku and North Maluku
Partial Derivatives of Gompertz, Logistic, and Weibull Non-Linear Growth Models on Confirmed COVID-19 Cases Utami Dewi, Wardhani; Warsono
Sciencestatistics: Journal of Statistics, Probability, and Its Application Vol. 2 No. 1 (2024): JANUARY
Publisher : Universitas Muhammadiyah Metro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24127/sciencestatistics.v2i1.5641

Abstract

. The epidemiological picture of COVID-19 is still unknown, and the number of confirmed cases of COVID-19 varies every day. Researchers have studied COVID-19 a lot, and many of them have used statistical models to estimate the growth of the outbreak. Non-linear statistical models can be used to describe growth behavior, as it varies in time. The aim of this research is to analyze, compare, and find the best model from the Gompertz, Logistic, and Weibull non-linear models. Daily cumulative data on confirmed COVID-19 viruses in Indonesia for 2020-2021 will be used in this research. The results obtained by the Logistic model proved to be very effective in describing the COVID-19 epidemic curve and estimating epidemiological parameters. The Logistic Model provides the best results compared to other growth models applied by Gompertz and Weibull. The R-Square of the logistic model is 0.9990, meaning that the model is able to explain or predict 99.90% of the data and 0.10% is explained by other factors. However, this research cannot explain the turning point of the curve, because there are many factors other than the model. One of them is the nature of the virus carrier from one place to another, then the behavior of the carrier who has not fully implemented the health protocol rules.
Penggunaan ARIMA Box-Jenskin dalam Meramalkan Harga Emas Antam Tahun 2025-2027 di Indonesia Sholiha, Sangidatus; Wardhani Utami Dewi
Sciencestatistics: Journal of Statistics, Probability, and Its Application Vol. 2 No. 2 (2024): JULY
Publisher : Universitas Muhammadiyah Metro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24127/sciencestatistics.v2i2.5958

Abstract

Penelitian ini sangat penting mengingat volatilitas pasar global dan ketidakpastian ekonomi yang semakin meningkat, yang mendorong kebutuhan untuk memiliki alat peramalan yang andal bagi aset-aset lindung nilai seperti emas. Penelitian ini bertujuan untuk meramalkan harga emas Antam di Indonesia untuk periode 2025-2027 menggunakan model ARIMA. Metode kuantitatif dengan desain deret waktu digunakan, dengan data harga emas dari tahun 2021 hingga 2024. Hasil analisis menunjukkan bahwa model ARIMA (1,1,1) adalah yang terbaik dalam meramalkan harga emas Antam, dengan nilai MSE, AIC, dan BIC yang rendah. Peramalan menunjukkan tren kenaikan harga emas dari awal 2025 hingga akhir 2027, mencerminkan kepercayaan pasar terhadap emas sebagai aset lindung nilai yang aman. Kesimpulan dari penelitian ini adalah bahwa peramalan harga emas Antam dapat memberikan wawasan yang penting bagi investor dan pembuat kebijakan untuk merencanakan strategi investasi dan langkah-langkah ekonomi di masa depan. This research is especially important given the increasing global market volatility and economic uncertainty, which drives the need to have reliable forecasting tools for hedging assets such as gold. This research aims to predict the price of Antam gold in Indonesia for the 2025-2027 period using the ARIMA model. A quantitative method with a time series design was used, with gold price data from 2021 to 2024. The analysis results show that the ARIMA (1,1,1) model is the best in estimating Antam's gold price, with MSE, AIC and BIC values ​​that are low . Forecasts show an upward trend in gold prices from the beginning of 2025 to the end of 2027, reflecting market confidence in gold as a safe hedging asset. The conclusion of this research is that Antam's gold price forecasting can provide important insights for investors and policy makers to plan investment strategies and economic steps in the future.
Structural Equation Modeling on Data on Students' Knowledge and Interest in Entrepreneurship in Lampung Sholiha, Sangidatus; Vahia, Ira; Dewi, Wardhani Utami
JTAM (Jurnal Teori dan Aplikasi Matematika) Vol 9, No 1 (2025): January
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/jtam.v9i1.26557

Abstract

Entrepreneurship plays a crucial role in economic growth and reducing unemployment, particularly in regions like Lampung, Indonesia, which face challenges such as limited entrepreneurial resources and low interest in entrepreneurship. This research aims to explore the relationship between entrepreneurial knowledge and entrepreneurial interest among students in Lampung, using Structural Equation Modeling (SEM) for analysis. A quantitative approach with a cross-sectional design was applied, involving 300 students randomly selected using simple random sampling from Lampung. The study focuses on entrepreneurial knowledge as the independent variable and entrepreneurial interest as the dependent variable. Data were collected using a questionnaire and analyzed with R Studio 4.2.1 using the lavaan package for SEM. The results show that entrepreneurial knowledge significantly influences entrepreneurial interest, explaining 86.10% of its variation. These findings suggest that strengthening entrepreneurial knowledge through curriculum development and innovative learning approaches can boost students’ entrepreneurial interest. Higher education institutions in Lampung can improve entrepreneurial education by integrating practical knowledge, case studies, and mentorship programs to foster entrepreneurial attitudes. This research contributes to the growing field of entrepreneurship education and offers actionable insights for policymakers and educators to develop sustainable entrepreneurs in Lampung.
Simulation and Analysis of Gamma Distribution in Assessing Delay Rate Completion of the Curriculum in Schools Sari, Reni Permata; Muhammad Ihsan Dacholfany; Amir Khushk; Wardhani Utami Dewi
Sciencestatistics: Journal of Statistics, Probability, and Its Application Vol. 3 No. 1 (2025): JANUARY
Publisher : Universitas Muhammadiyah Metro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24127/sciencestatistics.v3i1.8158

Abstract

Completion of the curriculum on time is one of the important indicators of the success of the learning process. However, various factors such as material difficulty and external distractions often cause delays in curriculum completion. This study aims to model the delay in curriculum completion using Gamma distribution, with the research location at SMP Negeri 1 Melinting, East Lampung. Primary data is obtained from schools, while secondary data comes from related literature. This study uses Monte Carlo simulation based on Gamma distribution with the parameters of mean delay () and degree of variance (). The results showed an average delay of about 2.4 weeks, with the Gamma distribution matching the actual data based on the Kolmogorov-Smirnov test. These findings suggest that the Gamma distribution can be an effective prediction tool for modeling curriculum completion delays. Managerial recommendations include the preparation of flexible schedules and the use of simulation models for risk mitigation. This research contributes to education managers in designing better time and resource management strategiesCompletion of the curriculum on time is one of the important indicators of the success of the learning process. However, various factors such as material difficulty and external distractions often cause delays in curriculum completion. This study aims to model the delay in curriculum completion using Gamma distribution, with the research location at SMP Negeri 1 Melinting, East Lampung. Primary data is obtained from schools, while secondary data comes from related literature. This study uses Monte Carlo simulation based on Gamma distribution with the parameters of mean delay () and degree of variance (). The results showed an average delay of about 2.4 weeks, with the Gamma distribution matching the actual data based on the Kolmogorov-Smirnov test. These findings suggest that the Gamma distribution can be an effective prediction tool for modeling curriculum completion delays. Managerial recommendations include the preparation of flexible schedules and the use of simulation models for risk mitigation. This research contributes to education managers in designing better time and resource management strategies
PCA-SVM Classification: Motor Ability of Down Syndrome Based on Education, Economics And Physiotherapy Therapy Bota Muhammad Akbar; Al Um Aniswatun Khasanah; Sangidatus Sholiha; Wardhani Utami Dewi
Journal of Mathematics, Computations and Statistics Vol. 8 No. 1 (2025): Volume 08 Nomor 01 (April 2025)
Publisher : Jurusan Matematika FMIPA UNM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35580/jmathcos.v8i1.7261

Abstract

The classification of motor abilities of individuals with Down Syndrome is essential to identify more effective developmental patterns. However, research that integrates educational, economic, and physiotherapy factors in the classification model is still limited, especially in the application of machine learning-based methods. The purpose of this study is to classify using PCA-SVM on the motor ability of DS based on education, economics, and physiotherapy therapy. PCA is used to reduce the dimensions of the dataset by extracting the main features that have the greatest variation, thereby increasing the efficiency and accuracy of classification. Meanwhile, SVM with Radial Base Function RBF Kernel is applied to build a classification model capable of handling non-linear data and finding optimal hyperplanes as the separation boundary between classes. This study used 50 samples obtained from POTADS in Lampung Province, Indonesia. The results showed that PCA successfully extracted three main components that explained 80.2% of the variance of the data. The SVM model achieved an overall accuracy of 80.2%, with the highest classification success rate at Level 1 (100%) and Level 3 (75%), while Level 2 had some classification errors due to a wider variation in sample characteristics. This study implies that the resulting model can be used to identify individuals at risk of motor difficulties, allowing for earlier and targeted behavior. In addition, the results of this study can be a reference for medical practitioners and educators in developing therapy and education strategies that are more in line with the needs of each individual.
Naïve Bayes Algorithm: Analysis of Student Group Assignment Project Patterns in Mathematics Learning Dewi, Wardhani Utami; Vahlia, Ira; Linuhung, Nego
JTAM (Jurnal Teori dan Aplikasi Matematika) Vol 9, No 3 (2025): July
Publisher : Universitas Muhammadiyah Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31764/jtam.v9i3.30459

Abstract

Effective collaboration in mathematics learning is essential for developing students' critical thinking and problem-solving skills; however, identifying patterns that lead to successful group collaboration remains challenging. This study aims explicitly to identify and classify the patterns of student group assignment completion in the Logic and Sets course using the Naïve Bayes algorithm. Survey data from 65 mathematics education students were analyzed using a quantitative approach and machine learning techniques. Attributes such as group size, task completion time, participation, contribution strategies, and communication effectiveness were collected via structured questionnaires. Data analysis involved preprocessing, model training using Naïve Bayes, and validation through accuracy and posterior probability analysis. Results indicated that the Naïve Bayes model accurately distinguished groups with very good (A) and fairly good (B) performance, achieving 84.62% accuracy. Groups achieving an A grade typically featured balanced participation and open communication strategies, whereas groups graded B exhibited uneven participation and passive members. This research significantly contributes by demonstrating how data-driven predictive analytics can support instructors in monitoring and enhancing collaborative learning processes in mathematics courses. Future research could further refine predictive accuracy by incorporating additional factors such as leadership style and collaborative technologies, potentially integrating the model into learning management systems for real-time evaluation and intervention.