DOI : https://doi.org/10.62527/ijasce.7.1.231

Building Antusiasm Level Detection Model on Online Learning Using YOLOv11 with Hyperparameter Optimation

Hilmi Aziz (1), Siti Yulianti (2), Rianto Rianto (3)
(1) a:1:{s:5:"en_US";s:20:"Siliwangi University";}
(2)
(3)
How to cite (IJASEIT) :
Hilmi Aziz, Yulianti, S., & Rianto, R. (2025). Building Antusiasm Level Detection Model on Online Learning Using YOLOv11 with Hyperparameter Optimation. International Journal of Advanced Science Computing and Engineering, 7(1). https://doi.org/10.62527/ijasce.7.1.231
Citation Format :

This research aims to build an enthusiasm level detection model in online learning using YOLOv11 algorithm with hyperparameter optimization. Facial expression is an indicator to identify the level of enthusiasm in online learning which can be measured by the level of interest in paying attention to the material on the screen. Increasing the number of interest level data classes is done to produce a more complex and accurate assessment of the learner's enthusiasm level. The dataset used comes from FER2013 which contains 7 classes of human emotions and then classified into 5 classes of enthusiasm levels with 1000 images for each class, making a total of 5000 datasets developed from previous related research. Several hyperparameters of the detection model, namely epoch, batch size, and image size are optimized to obtain optimal performance. Before optimization, the model achieved average precision (mAP 50-95) with a value of 95.2% with inference time at 1.7 ms. After optimization, the performance of the model increased to reach an average precision (mAP 50-95) of 97% With inference time 3.1 ms.

I. Burić and A. Moè, “What makes teachers enthusiastic: The interplay of positive affect, self-efficacy and job satisfaction,” Teach Teach Educ, vol. 89, Mar. 2020, doi: 10.1016/j.tate.2019.103008.

M. E. Kret, E. Prochazkova, E. H. M. Sterck, and Z. Clay, “Emotional expressions in human and non-human great apes,” Aug. 01, 2020, Elsevier Ltd. doi: 10.1016/j.neubiorev.2020.01.027.

F. Rahmawati, D. Setiawan, and M. Roysa, “Penyebab Kesulitan Belajar Siswa pada Pembelajaran Daring,” Journal for Lesson and Learning Studies, vol. 4, no. 3, pp. 302–308, 2021, [Online]. Available: https://ejournal.undiksha.ac.id/index.php/JLLS

C. Conrad, Q. Deng, I. Caron, O. Shkurska, P. Skerrett, and B. Sundararajan, “How student perceptions about online learning difficulty influenced their satisfaction during Canada’s Covid-19 response,” British Journal of Educational Technology, vol. 53, no. 3, pp. 534–557, May 2022, doi: 10.1111/bjet.13206.

C. Janiesch, P. Zschech, and K. Heinrich, “Machine learning and deep learning,” Electron Markets, vol. 31, pp. 685–695, Apr. 2021, doi: 10.1007/s12525-021-00475-2/Published.

A. Jaiswal, A. Krishnama Raju, and S. Deb, “Facial emotion detection using deep learning,” in 2020 International Conference for Emerging Technology, INCET 2020, Institute of Electrical and Electronics Engineers Inc., Jun. 2020. doi: 10.1109/INCET49848.2020.9154121.

N. P. Motwani and S. S, “Human Activities Detection using DeepLearning Technique- YOLOv8,” ITM Web of Conferences, vol. 56, p. 03003, 2023, doi: 10.1051/itmconf/20235603003.

A. Awad, M. Hegazy, and S. A. Aly, “Early Diagnoses of Acute Lymphoblastic Leukemia Using YOLOv8 and YOLOv11 Deep Learning Models,” 2024, Accessed: Oct. 30, 2024. [Online]. Available: https://doi.org/10.48550/arXiv.2410.10701

R. Sapkota, Z. Meng, M. Churuvija, X. Du, Z. Ma, and M. Karkee, “Comprehensive Performance Evaluation of YOLO11, YOLOv10, YOLOv9 and YOLOv8 on Detecting and Counting Fruitlet in Complex Orchard Environments,” Jul. 2024, [Online]. Available: http://arxiv.org/abs/2407.12040

N. B. A. Karna, M. A. P. Putra, S. M. Rachmawati, M. Abisado, and G. A. Sampedro, “Toward Accurate Fused Deposition Modeling 3D Printer Fault Detection Using Improved YOLOv8 With Hyperparameter Optimization,” IEEE Access, vol. 11, pp. 74251–74262, 2023, doi: 10.1109/ACCESS.2023.3293056.

Y. Khaireddin and Z. Chen, “Facial Emotion Recognition: State of the Art Performance on FER2013,” May 2021. Accessed: Nov. 20, 2024. [Online]. Available: https://doi.org/10.48550/arXiv.2105.03588

K. Salma and S. Hidayat, “Deteksi Antusiasme Siswa dengan Algoritma Yolov8 pada Proses Pembelajaran Daring,” 2024. [Online]. Available: https://journal.stmiki.ac.id

A. R. Kusumastuti, Y. Kristian, and E. Setyati, “Klasifikasi Ketertarikan Anak PAUD Melalui Ekspresi Wajah Menggunakan Metode CNN,” Jurnal Teknologi Informasi dan Terapan, vol. 7, no. 2, pp. 92–96, Dec. 2020, doi: 10.25047/jtit.v7i2.176.

X. Tao, Z. Zeng, J. Zeng, T. Zhao, and Q. Dai, “Pavement Crack Detection and Identification Based on Improved YOLOv8,” International Journal of Cognitive Informatics and Natural Intelligence, vol. 18, no. 1, 2024, doi: 10.4018/IJCINI.356363.

A. Serikbay, M. Bagheri, A. Zollanvari, and B. T. Phung, “Ensemble Pretrained Convolutional Neural Networks for the Classification of Insulator Surface Conditions,” Energies (Basel), vol. 17, no. 22, p. 5595, Nov. 2024, doi: 10.3390/en17225595.

R. Khanam and M. Hussain, “YOLOv11: An Overview of the Key Architectural Enhancements,” Oct. 2024, [Online]. Available: http://arxiv.org/abs/2410.17725

D. Krstinić, M. Braović, L. Šerić, and D. Božić-Štulić, “Multi-label Classifier Performance Evaluation with Confusion Matrix,” Academy and Industry Research Collaboration Center (AIRCC), Jun. 2020, pp. 01–14. doi: 10.5121/csit.2020.100801.