Article Per Year (5 Year)
p-Index From 2020 - 2025
0.444
P-Index
This Author published in this journals
All Journal Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Indonesian Applied Physics Letters
Fitri Noor Febriana
Unknown Affiliation
Chemical Engineering, Chemistry & Bioengineering Computer Science & IT Electrical & Electronics Engineering Engineering Materials Science & Nanotechnology Physics

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

Found 2 Documents
Search

 1 
Theoretical Study of the Stability of Acetylcholine Based on Molecular Orbital Theory using Density Functional Theory Fitri Noor Febriana; Vera Khoirunisa; Wun Fui Mark-Lee; Febdian Rusydi
Indonesian Applied Physics Letters Vol. 3 No. 1 (2022): June
Publisher : Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/iapl.v3i1.39777

Abstract

Some molecules in nature have a positive or negative charge. One such molecule is acetylcholine. Acetylcholine is a positively charged molecule that is responsible for Alzheimer's disease. This study evaluated acetylcholine through six simple molecules based on the ionization potential and the HOMO-LUMO gap obtained from the density functional theory calculation. The calculation results showed that the ionization potential and the HOMO-LUMO gap could explain the stability of acetylcholine and the six other molecules. As a result, acetylcholine has the same properties as five other simple molecules. Meanwhile, one other molecule has the opposite properties to acetylcholine.
Benchmarking Machine Learning Paradigms for Resume Screening on Imbalanced Data Fitri Noor Febriana; Ira Puspitasari
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 6 (2025): December 2025 (in progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i6.7123

Abstract

Manual resume screening is an inefficient and bias-prone process, yet comprehensive benchmarks of machine learning models on imbalanced, real-world recruitment data remain scarce. This study addresses this gap by benchmarking seven models from classical, ensemble, and deep learning paradigms for automated resume classification. Using a private dataset of 2,483 resumes across 24 job categories, this study evaluates the models with distinct TF-IDF and BERT embedding feature pipelines and an adaptive strategy for handling class imbalance (Class Weights, SMOTE, SMOTEENN). The results showed that the XGBoost model achieved the highest performance (weighted F1-score of 0.779), followed by the highly competitive BERT (F1 0.728) and Random Forest (F1 0.711) models. Despite these methods, all models struggled with extreme minority classes, confirming data scarcity as a primary limitation. This study provides a valuable benchmark and an evidence-based framework for HR practitioners, highlighting the critical trade-off between predictive performance (XGBoost), interpretability (Random Forest), and semantic capability (BERT). The findings conclude that the primary challenge is data representation, steering future work towards data augmentation and fairness audits.
Co-Authors Febdian Rusydi Ira Puspitasari Vera Khoirunisa Wun Fui Mark-Lee