Article Per Year (5 Year)
p-Index From 2020 - 2025
2.293
P-Index
This Author published in this journals
All Journal Humanitas: Indonesian Psychological Journal Intuisi Psikodimensia: Kajian Ilmiah Psikologi Jurnal Pengukuran Psikologi dan Pendidikan Indonesia (JP3I) Jurnal Psikologi Ulayat: Indonesian Journal of Indigenous Psychology Jurnal Psikologi Ulayat: Indonesian Journal of Indigenous Psychology Jurnal Psikohumanika Buletin Ilmiah Sarjana Teknik Elektro ANIMA Indonesian Psychological Journal Jurnal Penelitian dan Pengukuran Psikologi: JPPP Education and Social Sciences Review International Journal of Applied Business and International Management Journal of International Conference Proceedings Wacana: Journal of the Humanities of Indonesia
Christiany Suwartono
Universitas Katolik Indonesia Atma Jaya
Arts Humanities Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Library & Information Science Neuroscience Physics Public Health Social Sciences

Published : 41 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 41 Documents
Search

 1   2   3   4   5 
Enhancing Facial Emotion Recognition on FER2013 Using Attention-based CNN and Sparsemax-Driven Class-Balanced Architectures Suwartono, Christiany; Bata, Julius Victor Manuel; Airlangga, Gregorius
Buletin Ilmiah Sarjana Teknik Elektro Vol. 7 No. 4 (2025): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v7i4.14510

Abstract

Facial emotion recognition plays a critical role in various human–computer interaction applications, yet remains challenging due to class imbalance, label noise, and subtle inter-class visual similarities. The FER2013 dataset, containing seven emotion classes, is particularly difficult because of its low resolution and heavily skewed label distribution. This study presents a comparative investigation of advanced deep learning architectures against traditional machine-learning baselines on FER2013 to address these challenges and improve recognition performance. Two novel architectures are proposed. The first is an attention-based convolutional neural network (CNN) that integrates Mish activations and squeeze-and-excitation (SE) channel recalibration to enhance the discriminative capacity of intermediate features. The second, FastCNN-SE, is a refined extension designed for computational efficiency and minority-class robustness, incorporating Sparsemax activation, Poly-Focal loss, class-balanced reweighting, and MixUp augmentation. The research contribution is demonstrating how combining attention, sparse activations, and imbalance-aware learning improves FER performance under challenging real-world conditions. Both models were extensively evaluated: the attention-CNN under 10-fold cross-validation, achieving 0.6170 accuracy and 0.555 macro-F1, and FastCNN-SE on the held-out test set, achieving 0.5960 accuracy and 0.5138 macro-F1. These deep models significantly outperform PCA-based Logistic Regression, Linear SVC, and Random Forest baselines (≤0.37 accuracy and ≤0.29 macro-F1). We additionally justify the differing evaluation protocols by emphasizing cross-validation for architectural stability and held-out testing for generalization and note that FastCNN-SE contains ~3M parameters, enabling efficient inference. These findings demonstrate that architecture-level fusion of SE attention, Sparsemax, and Poly-Focal loss improves balanced emotion recognition, offering a strong foundation for future studies on efficient and robust affective-computing systems.
Co-Authors Adishesa, Made Syanesti Agustin, Leonita Dwi Airlangga, Gregorius Amiseso, Cahyo Pratomo Andika Octavianto Anna Marietta da Silva Astuti, Sri Wahyuning Bata, Julius Victor Manuel Benecdita Prihatin Dwi Riyanti Bintamur, Dewa Fajar Cahyo Pratomo Amiseso Clara Moningka Dea Franceline, Dea Dearly, Dearly Dermawan, Sella Devi Wulandari Devina Wicaksana Dewi, Monika Puspa Dicky Sugianto Dih’iyah E. Pratiwi Edwin Adrianta Surijah Efar, Mirna Fadhilah Aziz, Sari Febbealya Cheerson Febbealya Cheerson Fenny Junita Fenny Junita Feny M. Lestari Gevi Khairunnisa Gevi Khairunnisa Grace Indrawati Gracia Tobing, Gracia Gugah Bawono Handayani Sutanto Handoyo, Restu Tri Hutami, Priska Ayuningdiah Ide Bagus Siaputra Juneman Abraham Karitas, Chionia Lidia L. Hidajat Magdalena Halim Magdalena Halim Magdalena Halim Magdalena S. Halim Magdalena S. Halim Mamahit, Aileen P. Marc P. H. Hendriks Meinarno, Eko Aditya Mewengkang, Meirlyn D. Miranti, Indira Mohammad A. G. Priadi Morina Yuandary Anwar, Morina Yuandary NURWAHIDAH NURWAHIDAH Pricillia Putri Pricillia Putri Rahmawati Segara, Sila Restu Tri Handoyo Rocky Roy P. C. Kessels Santoso, Justinus Budi Sjania Malik Soeherman, Sylvia Sri Hapsari Wijayanti Suhendra, Junianawaty Sunu Bagaskara Sutanto, Sandra Handayani Tjung, Yassir Nasanius Veronika Efata Angelina, Veronika Efata Wicaksana, Yosef Arya Wiradhany, Wisnu Yapina Widyawati Yassir Nasanius YENNY YENNY Yudha Gutara, Mohamad Yunita, Erly