Comparison of FA-SSD: Performance of Feature Extractors VGG-19, MobileNetV3, and ResNet-152 for Human Body Temperature Prediction

Authors

  • Ridho Sholehurrohman Universitas Lampung
  • Akmal Junaidi Universitas Lampung
  • Hamzah hanif Universitas Lampung
  • Favorisen Rosyking Lumbanraja Universitas Lampung
  • Muhammad Reza Habibi Department of Computer Science and Electrical Engineering, Kumamoto University

DOI:

https://doi.org/10.25077/TEKNOSI.v12i2.2026.300-311

Keywords:

FA-SSD, VGG-19, MobileNetV3, ResNet-152, Body Temperature Prediction

Abstract

Body temperature is a critical health indicator, and non-contact thermal imaging-based prediction systems are essential for early detection of infectious diseases. This study compares the performance of three FA-SSD (Feature Fusion and Spatial Attention-Based Single Shot Detector) models with different feature extractors—VGG-19, MobileNetV3, and ResNet-152—for face detection and body temperature prediction using thermal images. A subset of 520 thermal facial images from the Comprehensive Facial Thermal Dataset was used, with 80% for training, 10% for validation, and 10% for testing. Model performance was evaluated using Generalized Intersection over Union (GIoU) for detection accuracy, and Mean Absolute Error (MAE) with Mean Absolute Percentage Error (MAPE) for temperature prediction accuracy. The results showed that no single model excelled in all metrics. ResNet-152 achieved the highest average GIoU, indicating superior object detection performance. VGG-19 delivered the lowest average MAE of 0.451°C and MAPE of 1.278%, making it the best for temperature prediction. MobileNetV3 achieved the lowest minimum MAE of 0.000050°C but showed higher average errors and validation fluctuations. In conclusion, VGG-19 is recommended for clinical temperature accuracy, ResNet-152 for robust detection, and MobileNetV3 for edge deployment.

References

N. I. D. Zaman, Y. W. Hau, M. C. Leong, et al., "A review on the significance of body temperature interpretation for early infectious disease diagnosis," Artificial Intelligence Review, vol. 56, pp. 15449–15494, 2023, doi: 10.1007/s10462-023-10528-x..

S. Mirjalali, S. Peng, Z. Fang, C.-H. Wang, S. Wu, "Wearable sensors for remote health monitoring: Potential applications for early diagnosis of Covid-19," Advanced Materials Technologies, vol. 7, no. 1, p. 2100545, 2022, doi: 10.1002/admt.202100545.

X. Rong, L. Yang, H. Chu, M. Fan, “Effect of delay in diagnosis on transmission of COVID-19,” Mathematical Biosciences and Engineering, vol. 17, no. 3, pp. 2725–2740, 2020, doi: 10.3934/mbe.2020149.

L. Evangelisti, E. De Cristo, S. Monteleone, C. Guattari, P. Gori, I. Pini, T. de Rubeis, D. Ambrosini, "A New Customized Measurement System for a Non-Contact, Enhanced Thermometric Method," Energies, vol. 18, p. 1537, 2025, doi: 10.3390/en18061537.

K. C. Lee, Y. P. Lin, Y. L. Tzeng, et al., "The impact of age on comparative diagnostic accuracy of temporal artery thermometers and non-contact infrared thermometers for fever detection: a systematic review and meta-analysis," BMC Infectious Diseases, vol. 25, p. 31, 2025, doi: 10.1186/s12879-024-10332-0.

R. Hirani, et al., "Artificial Intelligence and Healthcare: A Journey through History, Present Innovations, and Future Possibilities," Life, vol. 14, no. 557, pp. 1–25, 2024, doi:10.3390/life14050557.

A. Al Kuwaiti, et al., "A Review of the Role of Artificial Intelligence in Healthcare," Journal of Personalized Medicine, vol. 13, p. 951, 2023, doi:10.3390/jpm13060951.

A. A. Khan, A. A. Laghari, S. A. Awan, "Machine Learning in Computer Vision: A Review," EAI Endorsed Transactions on Scalable Information Systems, vol. 8, p. e4, 2021, doi:10.4108/eai.21-4-2021.169418.

Juhartini, D. Arwidiyarti, Desmiwati, “Single Shot Multibox Detector (SSD) in Object Detection: A Review”, IJACI, vol. 1, no. 2, pp. 118–127, Jul. 2025, doi:10.71129/ijaci.v1i2.pp118-127.

W. Liu, “SSD: Single Shot MultiBox Detector,” in Proceedings of the European Conference on Computer Vision (ECCV), 2016, pp. 1–17, doi:10.1007/978-3-319-46448-02.

J.S. Lim, M. Astrid, H. J. Yoon, S. I. Lee, “Small Object Detection using Context and Attention,” 2019, pp. 4321–4330, doi: 10.48550/arXiv.1912.06319.

D. Jiang, B. Sun, S. Su, Z. Zuo, P. Wu, X. Tan, “FASSD: A Feature Fusion and Spatial Attention-Based Single Shot Detector for Small Object Detection,” Electronics, vol. 9, no. 1536, pp. 1–20, 2020, doi:10.3390/electronics9091536.

G. Meena, K. K. Mohbey, A. Indian, S. Kumar, "Sentiment Analysis from Images using VGG-19 based Transfer Learning Approach," Procedia Computer Science, vol. 204, pp. 411–418, 2022, doi:10.1016/j.procs.2022.08.050.

M. Z. Khaliki, M. S. Bajarslan, "Brain tumor detection from images and comparison with transfer learning methods and 3-layer CNN," Scientific Reports, vol. 14, p. 2664, 2024, doi:10.1038/s41598-024-52823-9.

T. Shahriar, “Comparative analysis of lightweight deep learning models for memory-constrained devices,” 2025, doi:10.48550/arXiv.2505.03303.

S. G. Mohammad, A. E. A. Ali, M. M. Saeid, "Optimization MobileNetV3-small Model for Diabetic Foot Ulcers Classification," International Journal of Intelligent Engineering & Systems, vol. 18, no. 9, 2025, doi: 0.22266/ijies2025.1031.51.

D. Saha, M. P. Mangukia, A. Manickavasagan, "Real-Time Deployment of MobileNetV3 Model in Edge Computing Devices Using RGB Color Images for Varietal Classification of Chickpea," Applied Sciences, vol. 13, p. 7804, 2023, doi:10.3390/app13137804.

H. Wang, V. Bhaskara, A. Levinshtein, et al., "Efficient Super-Resolution Using MobileNetV3," in Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 2020, vol. 12537, doi:10.1007/978-3-030-67070-2_5.

S. Athisayamani, R. S. Antonyswamy, V. Sarveshwaran, M. Almeshari, Y. Alzamil, V. Ravi, “Feature Extraction Using a Residual Deep Convolutional Neural Network (ResNet-152) and Optimized Feature Dimension Reduction for MRI Brain Tumor Classification,” Diagnostics, vol. 13, no. 4, 2023, doi:10.3390/diagnostics13040668.

M. K. Panda, B. N. Subudhi, T. Veerakumar, V. Jakhetiya, “Modified ResNet-152 network with hybrid pyramidal pooling for local change detection,” IEEE Trans. Artif. Intell., vol. 5, no. 4, pp. 1599–1612, Apr. 2024, doi:10.1109/TAI.2023.3299903.

S. Basodi, C. Ji, H. Zhang, Y. Pan, "Gradient Amplification: An Efficient Way to Train Deep Neural Networks," Big Data Mining and Analytics, vol. 3, no. 3, pp. 196–207, 2020, doi:10.26599/BDMA.2020.9020004.

A. Abuhussein, M. F. Darwish, A. Darwish, and A. E. Hassanien, "Comprehensive Facial Thermal Dataset," Mendeley Data, V1, 2024. doi: 10.17632/8885sc9p4z.1.

H. Rezatofighi, et al., "Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression," Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 658-666, doi:10.1109/CVPR.2019.00075.

Q. Tang, H. Qiang, Y. Tian, X. Feng, W. Hao, M. Xie, “ATDIOU: Arctangent Differential Loss Function for Bounding Box Regression,”

Sensors, vol. 26, p. 1545, 2026, doi:10.3390/s26051545.

B. Han, Q. Tang, J. Song, Z. Wang, Y. Yang, “GAOC: A Gaussian Adaptive Ochiai Loss for Bounding Box Regression,” Sensors, vol. 26, p. 368, 2026, doi:10.3390/s26020368.

D. Chicco, M. J. Warrens, G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation.” PeerJ Computer Science, vol. 7, p.e623, 2021, doi:10.7717/peerj-cs.623.

S. M. Robeson, and C. J. Willmott, “Decomposition of the mean absolute error (MAE) into systematic and unsystematic components," PLoS ONE, vol. 18, no. 2, 2023, doi:10.1371/journal.pone.0279774.

K. Warneke, S. D. Siegel, J. Afonso, et al., “What the mean absolute percentage error (MAPE) should adopt from Bland–Altman analyses,” German Journal of Exercise and Sport Research, 2025, doi:10.1007/s12662-025-01084-3.

Downloads

Submitted

2026-07-02

Accepted

2026-08-20

Published

2026-08-28

How to Cite

[1]
R. Sholehurrohman, A. Junaidi, H. hanif, F. Rosyking Lumbanraja, and M. Reza Habibi, “Comparison of FA-SSD: Performance of Feature Extractors VGG-19, MobileNetV3, and ResNet-152 for Human Body Temperature Prediction”, TEKNOSI, vol. 12, no. 2, pp. 300–311, Aug. 2026.

Similar Articles

1 2 > >> 

You may also start an advanced similarity search for this article.