2690-6791ISSN (Online)
2769-786XISSN (Print)
Volume 16 , Issue 2 , PP: 82-101, 2025 | Cite this article as | XML | Html | PDF | Full Length Article
Deepa Devasenapathy 1 * , Krishna Bhimaavarapu 2 , Prem Kumar Sholapurapu 3 , S. Sarupriya 4
Doi: https://doi.org/10.54216/JISIoT.160207
This research creates an innovative EfficientNet-B7-based Facial Expression Recognition model that delivers maximum accuracy performance for detecting emotions. Successful classification performance benefits substantially from EfficientNet-B7's application of compound scaling techniques which balances the entire network dimensions depth width and resolution. The characteristic distinctive to EfficientNet-B7 over standard architectural models involves its dual capability to perform accurate computations at reduced complexity levels. The model receives evaluation using KDEF at high-resolution as well as FER2013 at low-resolution through usage of SGD, Adam, and RMSprop optimizers. Experimental tests confirmed that EfficientNet-B7 operates with RMSprop optimizer to recognize emotions on KDEF at 91.78% accuracy superior to ResNet152's highest recorded accuracy of 88.77%. Performance levels declined to 57.56% on FER2013 because low-resolution images represent a great challenge to the model. Internal Batch Normalization (IBN) enters the model as an issue solution to halt gradient descent problems, which results in better model training stability and enhanced accuracy-loss patterns. The research demonstrates that FER performance benefits greatly when EfficientNet-B7 works in combination with IBN for high-resolution image processing. The research proves that EfficientNet-B7 stands as a reliable FER solution that shows potential usage in affective computing and human-computer interaction domain.
Facial Expression Recognition , Convolutional Neural Networks , EfficientNet-B7 , Image Classification , Batch Normalization (IBN) , KDEF Dataset , FER2013 Dataset , Neural Network Optimization , , Deep Learning
[1] K. Wiley, Y. Dimitriadis, and M. Linn, “A human-centred learning analytics approach for developing contextually scalable K-12 teacher dashboards,” Brit. J. Educ. Technol., vol. 55, no. 3, pp. 845–885, May 2024.
[2] V. A. Bhagyalakshmi L., P. S. and S. S. K., “Review of Detecting Diabetes Mellitus and Diabetic Retinopathy Using Tongue Images and Its Features,” Res. J. Pharm. Biol. Chem. Sci., vol. 8, no. 2, pp. 378–386, Apr. 2017.
[3] S. Hemalatha et al., “A Development of 5G Technology in Cloud Computing and its Optimization Technique,” in Proc. 4th Int. Conf. Adv. Comput. Innov. Technol. Eng. (ICACITE), 2024, pp. 372–377, doi: 10.1109/ICACITE60783.2024.10617049.
[4] S. Devi, L. Bhagyalakshmi, and S. S. K., “Enhancing the Performance of Wireless Sensor Networks through Clustering and Joint Routing with Mobile Sink,” Int. J. Eng. Adv. Technol., vol. 8, no. 6, pp. 323–327, 2019.
[5] V. Roy et al., “Reinforcement Learning for Real-time ICU Patient Management in Critical Care,” in Proc. Int. Conf. Syst. Comput. Autom. Netw. (ICSCAN), 2023.
[6] L. Bhagyalakshmi et al., “Improving Spectral Efficiency and Coverage Capacity of 5G Networks: A Review,” Adv. Math. Sci. J., vol. 9, no. 6, pp. 3387–3397, 2020.
[7] J. Ogier du Terrail et al., “Federated learning for predicting histological response to neoadjuvant chemotherapy in triple-negative breast cancer,” Nat. Med., vol. 29, pp. 1–9, Jan. 2023, doi: 10.1038/s41591-022-02155.
[8] C. Saillard et al., “Pacpaint: a histology-based deep learning model uncovers the extensive intratumor molecular heterogeneity of pancreatic adenocarcinoma,” Nat. Commun., vol. 14, no. 3459, pp. 1–12, Jun. 2023, doi: 10.1038/s41467-023-3459.
[9] E. Jothi et al., “Distributed Generation Planning in Multi-Energy Microgrids,” E3S Web Conf., vol. 540, 2024, doi: 10.1051/e3sconf/202454010017.
[10] V. Roy et al., “An Advance Implementation of Machine Learning Techniques for the Prediction of Cervical Cancer,” in Proc. 3rd IEEE Int. Conf. ICT Bus. Ind. Gov. (ICTBIG), 2023, doi: 10.1109/ICTBIG59752.2023.10456347.
[11] A. R. Aravind et al., “A Way of Optimization of Wireless Sensor Network using TSCH,” in Proc. 4th Int. Conf. Adv. Comput. Innov. Technol. Eng. (ICACITE), 2024, pp. 326–330, doi: 10.1109/ICACITE60783.2024.10616840.
[12] R. Maruthamuthu et al., “A Way to Design Fog Computing Model for 5G Network using Vanet,” in Proc. 4th Int. Conf. Adv. Comput. Innov. Technol. Eng. (ICACITE), 2024, pp. 431–435, doi: 10.1109/ICACITE60783.2024.10617287.
[13] S. K. Yadav et al., “Hybrid Cloud Surveillance in Smart Grids: Optimising Solar Power with Dual-Mode Control,” E3S Web Conf., vol. 540, 2024, doi: 10.1051/e3sconf/202454010020.
[14] R. Singh et al., “Machine Learning Applications in Energy Management Systems for Smart Buildings,” E3S Web Conf., vol. 540, 2024, doi: 10.1051/e3sconf/202454008002.
[15] V. Roy and S. Shukla, “Effective EEG Motion Artifacts Elimination Based on Comparative Interpolation Analysis,” Wireless Pers. Commun., vol. 97, pp. 6441–6451, 2017.
[16] N. Misra et al., “Wall-Climbing Robots: Optimising Adsorption and Novel Suction Techniques,” E3S Web Conf., vol. 540, 2024, doi: 10.1051/e3sconf/202454013011.
[17] R. Padmavathy et al., “Enhancing Power Grid Resilience against Cyber Threats in the Smart Grid Era,” E3S Web Conf., vol. 540, 2024, doi: 10.1051/e3sconf/202454010021.
[18] V. Rawat et al., “Optimising Solar Energy: An Evaluation of IoT-Based Solar Panel Monitoring Systems,” E3S Web Conf., vol. 540, 2024, doi: 10.1051/e3sconf/202454008005.
[19] R. Vaish et al., “Automated Smart Crop Protection Utilising IoT: A Comprehensive Review,” E3S Web Conf., vol. 540, 2024, doi: 10.1051/e3sconf/202454013012.
[20] R. Kashyap et al., “Deep Learning’s Role in Advancing Gastroenterology and Digestive Health,” in Proc. 3rd IEEE Int. Conf. ICT Bus. Ind. Gov. (ICTBIG), 2023, doi: 10.1109/ICTBIG59752.2023.10455988.
[21] V. Balmiki et al., “Perspective-smart energy management system using machine learning,” E3S Web Conf., vol. 540, 2024, doi: 10.1051/e3sconf/202454008007.
[22] K. P. Manikandan et al., “Industry 5.0 based on Hybrid and Nonlinear Systems in Robustness,” Int. J. Intell. Syst. Appl. Eng., vol. 12, no. 12s, pp. 223–230, 2024.
[23] E. Sudha et al., “A Review of Smart Grid Management Systems Using Machine Learning Algorithms for Efficient Energy Distribution,” E3S Web Conf., vol. 540, 2024, doi: 10.1051/e3sconf/202454008009.
[24] S. Srinivasan et al., “Decision Support System based on Industry 5.0 in Artificial Intelligence,” Int. J. Intell. Syst. Appl. Eng., vol. 12, no. 15s, pp. 172–178, 2024.
[25] S. Tiwari et al., “Cross-Lingual Transfer Learning in RNNs for Enhancing Linguistic Diversity in Natural Language Processing,” in Proc. Int. Conf. Adv. Comput. Res. Sci. Eng. Technol. (ACROSET), Indore, India, 2024, pp. 1–6.
[26] M. X. Raajini and G. Rajesh, “Meta-Heuristic Solution for Route Optimization in Underwater Wireless Sensor Networks for Marine Applications,” J. Sci. Ind. Res., vol. 83, no. 4, pp. 405–413, 2024, doi: 10.56042/jsir.v83i4.2936.
[27] T. Ramesh et al., “A Comprehensive Evaluation of Deep Learning based Melanoma Detection and Classification Scheme,” in Proc. 2nd Int. Conf. Intell. Innov. Technol. Comput. Electr. Electron. (ICIITCEE), 2024, doi: 10.1109/IITCEE59897.2024.10467850.
[28] J. U. Maheswari et al., “Data Privacy and Security in Cloud Computing Environments,” E3S Web Conf., vol. 399, 2023, doi: 10.1051/e3sconf/202339904040.
[29] M. Preetha et al., “A Zigbee Garbage Bin Monitoring system with IoT,” E3S Web Conf., vol. 399, 2023, doi: 10.1051/e3sconf/202339904052.
[30] D. Kirubakaran et al., “Driving into the Future: The Role of IoT in Smart Vehicle Automation,” E3S Web Conf., vol. 399, 2023, doi: 10.1051/e3sconf/202339904045.
