Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering Journal of Information Technology and Cyber Security
Barkah, Nida Muhliya
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management Electrical & Electronics Engineering

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

Found 2 Documents
Search

 1 
Utilizing Prolog for Automatic Transformation of English Words Barkah, Nida Muhliya; Siregar, Maria Ulfah
Journal of Information Technology and Cyber Security Vol. 2 No. 2 (2024): July
Publisher : Department of Information Systems and Technology, Faculty of Intelligent Electrical and Informatics Technology, Universitas 17 Agustus 1945 Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30996/jitcs.11936

Abstract

Artificial Intelligence is a branch of computer science that focuses on developing systems that emulate human intelligence to execute commands or tasks by applying the concept of automatic reasoning. Automatic reasoning is the ability of a system to draw logical conclusions, make decisions, and solve problems independently, without human intervention, based on provided information or rules. The complexity of grammatical rules in English often causes difficulties in understanding and remembering them, hindering mastery of correct English structures. To address these challenges, this research uses automatic reasoning as the primary foundation for developing automatic transformation systems for English words—specifically, transforming singular nouns into plural forms and adjectives into adverbs of manner. The objective of this research is to apply grammatical rules during word transformation in Prolog. Furthermore, this study tests the effectiveness and accuracy of the process by evaluating the success rate of correct transformations. The system's performance is assessed by comparing the transformed words to their correct plural forms and corresponding adverbs of manner, based on predefined grammatical rules. This research does not involve participants directly but evaluates the system's performance on a set of predefined words. The results demonstrate that the system successfully transformed all tested words with 100% accuracy, effectively altering their structure. This indicates that the system is both effective and reliable for use in English language learning. Additionally, the system's high accuracy in handling various morphological transformations makes it a valuable tool for improving English grammar and writing skills.
Optimization of transfer learning for facial emotion classification on the FER-2013 dataset Barkah, Nida Muhliya; ‘Uyun, Shofwatul
International Journal of Electrical and Computer Engineering (IJECE) Vol 16, No 3: June 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v16i3.pp1213-1226

Abstract

Facial expressions play a key role in non-verbal communication by naturally reflecting human emotions. Facial emotion recognition (FER) using computer vision has gained attention with advances in deep learning. However, deep learning models require large datasets to perform well, posing a challenge for FER tasks with limited data. Transfer learning is a promising approach to address this issue, but a standardized method for FER is yet to be established. This study optimizes three transfer learning models ResNet-50, Inception V3, and Xception on the FER-2013 dataset. Experiments include testing input image sizes, hyperparameter tuning, data augmentation, layer addition, and training methods. Results show each model requires different input sizes for best accuracy. Hyperparameter tuning improves accuracy by 6.35%, 4.69%, and 1.04% for ResNet-50, Inception V3, and Xception, respectively. Augmenting only the disgust class yields better accuracy than augmenting all classes. The freeze fine-tuning method is less effective than fine-tuning alone on datasets with thousands of samples but outperforms the freeze layer method. The best accuracies achieved are 64.89% (ResNet-50), 65.83% (Xception), and 66.40% (Inception V3). These findings provide insights into freeze fine-tuning limitations and guidance for optimizing transfer learning in FER with limited data.
Co-Authors Maria Ulfah Siregar ‘Uyun, Shofwatul