Article Per Year (5 Year)
p-Index From 2020 - 2025
0.444
P-Index
This Author published in this journals
All Journal Jurnal Riset Informatika EVOLUSI : Jurnal Sains dan Manajemen
Siti Ernawati
Unknown Affiliation
Computer Science & IT

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

Found 2 Documents
Search

 1 
OPTIMASI PARAMETER PSO BERBASIS SVM UNTUK ANALISIS SENTIMEN REVIEW JASA MASKAPAI PENERBANGAN BERBAHASA INGGRIS Risawati Risawati; Siti Ernawati; Ina Maryani
Evolusi : Jurnal Sains dan Manajemen Vol 8, No 2 (2020): Jurnal Evolusi 2020
Publisher : Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/evolusi.v8i2.9248

Abstract

AbstractAs technology advances, many airline service users provide reviews of what they feel while using these services which are written through internet media, such as websites and social media. Currently, a lot of research is being done to analyze someone's review or opinion. This research teaches Support Vector Machine (SVM) as a method for processing data and optimizes Particle Swarm Optimization (PSO) as feature selection to improve. The parameters used in the SVM are the values of C and Epsilon while the parameters used in the PSO are the Population Size and Inertia Weight values. PSO was able to optimize the SVM model with the value of the SVM model before the implementation of the PSO feature selection was 84.25% and after the implementation of the PSO feature selection it increased to 87.39%. The increase in the value increase was 3.14%. AbstrakSeiring dengan kemajuan teknologi, banyak pengguna jasa maskapai penerbangan memberikan review mengenai apa yang dirasakan selama menggunakan jasa tersebut yang dituliskan melalui media internet, seperti situs web ataupun media sosial. Saat ini banyak penelitian yang terus dilakukan untuk menganalisis review atau pendapat seseorang.  Penelitian ini mengusulkan Support Vector Machine (SVM) sebagai metode untuk memproses data dan mengoptimasi Particle Swarm Optimization (PSO) sebagai seleksi fitur agar akurasi meningkat. Parameter yang digunakan pada SVM adalah nilai C dan Epsilon sedangkan parameter yang digunakan pada PSO adalah nilai Population Size dan Inertia Weight. PSO mampu mengoptimasikan model SVM dengan nilai akurasi model SVM sebelum diterapkannya seleksi fitur PSO adalah sebesar 84,25% dan setelah diterapkannya seleksi fitur PSO akurasi meningkat menjadi 87,39%. Terdapat kenaikan akurasi sebesar 3.14%. Keywords: Optimasi Parameter; PSO; SVM; Jasa Maskapai Penerbangan.
Machine Learning for Stroke Prediction: Evaluating the Effectiveness of Data Balancing Approaches Muhamad Indra; Siti Ernawati; Ilham Maulana
Jurnal Riset Informatika Vol. 6 No. 4 (2024): September 2024
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34288/jri.v6i4.344

Abstract

Stroke occurs due to disrupted blood flow to the brain, either from a blood clot (ischemic) or a ruptured blood vessel (hemorrhagic), leading to brain tissue damage and neurological dysfunction. It remains a leading cause of death and disability worldwide, making early prediction crucial for timely intervention. This study evaluates the impact of data balancing techniques on stroke prediction performance across different machine learning models. Random Forest (RF) consistently achieves the highest accuracy (98%) but struggles with precision and recall variations depending on the balancing method. Decision Tree (DT) and K-Nearest Neighbors (KNN) benefit most from SMOTE and SMOTETomek, improving their F1-scores (11.21% and 9.18%), indicating better balance between precision and recall. Random Under Sampling enhances recall across all models but reduces precision, leading to lower overall predictive reliability. SMOTE and SMOTETomek emerge as the most effective balancing techniques, particularly for DT and KNN, while RF remains the most accurate but requires further optimization to improve precision and recall balance.
Co-Authors Ilham Maulana Ina Maryani Muhamad Indra Risawati Risawati