Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Unisda Journal of Mathematics and Computer Science (UJMC)
Puce Angreni
Universitas Jenderal Soedirman
Computer Science & IT Education Mathematics

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

Found 2 Documents
Search

 1 
Evaluasi Metode Inisialisasi pada Model Pemulusan Eksponensial melalui Data IPM Banyumas Raya Melda Juliza; Novita Eka Chandra; Felinda Arumningtyas; Puce Angreni
UJMC (Unisda Journal of Mathematics and Computer Science) Vol. 12 No. 1 (2026): Unisda Journal of Mathematics and Computer Science
Publisher : Mathematics Department, Faculty of Sciences and Technology Unisda Lamongan

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The forecasting accuracy of exponential smoothing models is significantly influenced by the determination of initial values (initialization). This study aims to evaluate the performance of initialization methods for Brown’s Double Exponential Smoothing model using Human Development Index (HDI) data from the Banyumas Raya region for the period 2010-2025. The research stages included identifying data patterns, constructing models using both simple initialization and optimal initialization with numerical optimization, performing the Ljung-Box test for residual diagnostics, and comparing model accuracy. Evaluation results indicate that the Brown model using the optimal initialization method effectively captures trend patterns. The application of optimal initialization consistently improved model accuracy across all regencies. The highest error improvement was observed in Banyumas Regency (28.65%), followed by Cilacap (28.29%), Banjarnegara (24.77%), and Purbalingga (22.89%). Based on these results, the optimal initialization model was used to project HDI values for the next three periods, revealing a sustained upward trend. In conclusion, determining initial values is a crucial component that alongside smoothing parameter optimization must be seriously considered when developing forecasting models.
Perbandingan Model Klasifikasi Multikelas Tingkat Depresi Mahasiswa dengan Skor PHQ-9 Felinda Arumningtyas; Puce Angreni; Lutfiah Maharani Siniwi
UJMC (Unisda Journal of Mathematics and Computer Science) Vol. 12 No. 1 (2026): Unisda Journal of Mathematics and Computer Science
Publisher : Mathematics Department, Faculty of Sciences and Technology Unisda Lamongan

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Depression is one of the most common mental health disorders among university students and may adversely affect academic performance and social functioning. The severity of depression can be assessed using the Patient Health Questionnaire-9 (PHQ-9), which classifies individuals into several levels of depression severity. This study aims to compare several machine learning models for multiclass classification of student depression levels based on PHQ-9 scores. The study employed the PHQ-9 Student Depression Dataset consisting of 682 student records. Predictor variables included age, gender, the nine PHQ-9 items, sleep quality, study pressure, and financial pressure. The models evaluated were Logistic Regression, Decision Tree, Random Forest, Support Vector Machine (SVM), and XGBoost. Model performance was assessed using accuracy, precision, recall, and F1-score metrics. The results indicate that XGBoost achieved the best performance, with an accuracy of 78,10%, macro precision of 0,77, macro recall of 0,77, and macro F1-score of 0,77. These findings demonstrate that XGBoost provides relatively good performance in the multiclass classification of student depression levels. This study suggests that machine learning approaches have the potential to support the identification of depression severity among university students.
Co-Authors Felinda Arumningtyas Lutfiah Maharani Siniwi Melda Juliza Novita Eka Chandra