Citation :

Ramya U, Saraswathi S, "Enhanced Lightweight Deep Learning Framework with Knowledge Distillation and Binary Whale Optimization for Diabetic Foot Ulcer Classification," International Journal of Engineering Trends and Technology (IJETT), vol. 73, no. 12, pp. 280-296, 2025. Crossref, https://doi.org/10.14445/22315381/IJETT-V73I12P123

Abstract

A common hopeless significance of diabetes is Diabetic Foot Ulcers (DFU), which require speedy and accurate analysis to avoid amputation and lower death. Computerized DFU identification has likely ended due to the rapid growth of deep learning; the computational requirements of existing high-performing models limit their application in quantifiable settings with limited resources. To overcome this challenge, this research focuses on addressing a key question: whether a lightweight DFU classification model can be strengthened using knowledge distillation and automated hyperparameter tuning to uphold the performance of the model that is suitable for edge development. This research presents an original, lightweight classification framework that combines the Binary Whale Optimization Algorithm (BWOA) with Knowledge Distillation (KD) to yield an effective and specialized DFU classification system. This technique creates soft probability labels by using a pretrained InceptionV3 model as a teacher. These are motivated by DFU-LWNet, a small convolutional neural network with little parameter overhead, which is a customizable student network. The baseline DFU-LWNet with KD imitates earlier best findings (96.23% accuracy) on experiments with the publicly available DFU Patch Dataset. The proposed model DFU-LWNet-BWOA achieves a significant accuracy gain of 96.8% compared to the previous models, and it also ensures real-time compatibility for the mobile applications by making the consistency of parameter count as 0.5M. This study mainly focuses on the deployable, intelligent, and scalable solution for the DFU model in an experimental setup and ensures the interaction between the model, knowledge distillation, and BWOA optimization.

Keywords

Diabetic Foot Ulcer, DFU-LWNet, Knowledge Distillation, Binary Whale Optimization, DFU Classification.

References

[1] Moi Hoon Yap et al., “Deep Learning in Diabetic Foot Ulcers Detection: A Comprehensive Evaluation,” Computers in Biology and Medicine, vol. 135, pp. 1-17, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Fitri Arnia et al., “Towards Accurate Diabetic Foot Ulcer Image Classification: Leveraging CNN Pre-Trained Features and Extreme Learning Machine,” Smart Health, vol. 33, pp. 1-12, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Kamran Amjad et al., “A Novel Lightweight Deep Learning Framework with Knowledge Distillation for Efficient Diabetic Foot Ulcer Detection,” Applied Soft Computing, vol. 167, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Jinhai Fang et al., “Anomaly Detection of Diabetes Data based on Hierarchical Clustering and CNN,” Procedia Computer Science, vol. 199, pp. 71-78, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[5] André Kharitonov et al., “Literature Survey on Combining Machine Learning and Metaheuristics for Decision-Making,” Procedia Computer Science, vol. 253, pp. 199-208, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Juan Pablo Mesa et al., “Machine-Learning Component for Multi-Start Metaheuristics to Solve the Capacitated Vehicle Routing Problem,” Applied Soft Computing, vol. 173, pp. 1-32, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Dil Bahar, Akshay Dvivedi, and Pradeep Kumar, “Optimizing the Quality Characteristics of Glass Composite Vias for RF-MEMS using Central Composite Design, Metaheuristics, and Bayesian Regularization-Based Machine Learning,” Measurement, vol. 243, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Sulaiman Afolabi et al., “Informatics and Health Predicting Diabetes using Supervised Machine Learning Algorithms on E-Health Records,” Informatics and Health, vol. 2, no. 1, pp. 9-16, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Averina Nurdin et al., “Using Machine Learning for the Prediction of Diabetes with Emphasis on Blood Content,” Procedia Computer Science, vol. 227, pp. 990-1001, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Durga Parkhi et al., “Prediction of Postpartum Prediabetes by Machine Learning Methods in Women with Gestational Diabetes Mellitus,” iScience, vol. 26, no. 10, pp. 1-15, 2023.
[CrossRef] [Google Scholar] [Publisher Link] 

[11] Arinze Nkemdirim Okere et al., “Evaluation of Factors Predicting Transition from Prediabetes to Diabetes among Patients Residing in Underserved Communities in the United States - A Machine Learning Approach,” Computers in Biology and Medicine, vol. 187, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Yitayeh Belsti et al., “Comparison of Machine Learning and Conventional Logistic Regression-based Prediction Models for Gestational Diabetes in an Ethnically Diverse Population; The Monash GDM Machine Learning Model,” International Journal of Medical Informatics, vol. 179, pp. 1-12, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Fang Zhou et al., “A Stepwise Prediction and Interpretation of Gestational Diabetes Mellitus: Foster the Practical Application of Machine Learning in Clinical Decision,” Heliyon, vol. 10, no. 12, pp. 1-11, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Liangjun Jiang et al., “Diabetes Risk Prediction Model based on Community Follow-Up Data using Machine Learning,” Preventive Medicine Reports, vol. 35, pp. 1-16, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Muhammad Exell Febrian et al., “Diabetes Prediction using Supervised Machine Learning,” Procedia Computer Science, vol. 216, pp. 21-30, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Ketan Dhatariya, and Zulfiqarali G. Abbas, “Estimated Costs of Treating Two Standardised Diabetes-Related Foot Ulcers of Different Severity - A Comparison of 7 Global Regions,” Diabetes Research and Clinical Practice, vol. 221, pp. 1-7, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Puneeth N. Thotad, Geeta R. Bharamagoudar, and Basavaraj S. Anami, “Diabetic Foot Ulcer Detection using Deep Learning Approaches,” Sensors International, vol. 4, pp. 1-9, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Shuvo Biswas et al., “DFU_Multinet: A Deep Neural Network Approach for Detecting Diabetic Foot Ulcers through Multi-Scale Feature Fusion using the DFU Dataset,” Intelligence-Based Medicine, vol. 8, pp. 1-12, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Malik Adnan et al., “IDC Pressure Sensors Enabled Smart Footwear System for in Vitro Detection and Monitoring of Diabetic Foot Ulcer,” Sensors and Actuators A: Physical, vol. 388, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Mrinal Kanti Dhar et al., “Fusegnet: A Deep Convolutional Neural Network for Foot Ulcer Segmentation,” Biomedical Signal Processing and Control, vol. 92, pp. 1-17, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[21] Marizuana Mat Daud et al., Revolutionizing Diabetic Foot Ulcer Treatment Prediction: Harnessing the Power of Artificial Intelligence and Transfer Learning, Uncertainty in Computational Intelligence-Based Decision Making: Advanced Studies in Complex Systems, pp. 55-63, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[22] Haidong Ye, and Fang Yao, “Deep Learning-Enhanced MRI for Diabetic Foot Tarsal Bone Lesions and Insulin Injection Behavior Analysis,” Journal of Radiation Research and Applied Sciences, vol. 18, no. 2, pp. 1-10, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[23] N. Christy Evangeline, and S. Srinivasan, “Deep Neural Net for Identification of Neuropathic Foot in Subjects with Type 2 Diabetes Mellitus using Plantar Foot Thermographic Images,” Biomed Signal Process Control, vol. 96, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[24] Andrés Anaya-Isaza, and Martha Zequera-Diaz, “Fourier Transform-Based Data Augmentation in Deep Learning for Diabetic Foot Thermograph Classification,” Biocybernetics and Biomedical Engineering, vol. 42, no. 2, pp. 437-452, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[25] Lit Zhi Chee et al., “Gait Acceleration-Based Diabetes Detection Using Hybrid Deep Learning,” Biomedical Signal Processing and Control, vol. 92, pp. 1-8, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[26] Farman Ali et al., “IP-GCN: A Deep Learning Model for Prediction of Insulin using Graph Convolutional Network for Diabetes Drug Design,” Journal of Computational Science, vol. 81, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[27] Keona Pang, “A Comparative Study of Explainable Machine Learning Models with Shapley Values for Diabetes Prediction,” Healthcare Analytics, vol. 7, pp. 1-11, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[28] Teagan Weatherall, et al., “The Impact of Machine Learning on the Prediction of Diabetic Foot Ulcers - A Systematic Review,” Journal of Tissue Viability, vol. 33, no. 4, pp. 853-863, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[29] Shuvo Biswas et al., “XAI-Fusionnet: Diabetic Foot Ulcer Detection based on Multi-Scale Feature Fusion with Explainable Artificial Intelligence,” Heliyon, vol. 10, no. 10, pp. 1-23, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[30] Jenny Elizabeth Price et al., “Machine Learning Algorithms Mimicking Specialists Decision Making on Initial Treatment for People with Type 2 Diabetes Mellitus in Japan Diabetes Data Management Study (JDDM76),” Diabetes and Metabolic Syndrome: Clinical Research and Reviews, vol. 18, no. 11-12, pp. 1-6, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[31] Lingga Aksara Putra et al., “State Estimation of a Biogas Plant based on Spectral Analysis using a Combination of Machine Learning and Metaheuristic Algorithms,” Applied Energy, vol. 377, pp. 1-15, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[32] Sagarika Mohanty, Bibhudatta Sahoo, and Subham Sai Behera, “An Assessment of Nature-Inspired Metaheuristic Algorithms for Resilient Controller Placement in Software-Defined Networks,” Decision Analytics Journal, vol. 12, pp. 1-18, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[33] Ramandeep Saha, and Somnath Pal, “A Hybrid Metaheuristic Algorithm using Elitist Chemical Reaction Optimization and Learning from Knowledge Assimilation for Improving Rule-based Classification Models,” Procedia Computer Science, vol. 235, pp. 701-712, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[34] Ruben Silva-Tinoco et al., “Improving Foot Ulcer Risk Assessment and Identifying Associated Factors: Results of an Initiative Enhancing Diabetes Care in Primary Settings,” Diabetes Epidemiology and Management, vol. 14, pp. 1-8, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[35] Robert Fitridge et al., “The Intersocietal IWGDF, ESVS, SVS Guidelines on Peripheral Artery Disease in People with Diabetes Mellitus and a Foot Ulcer,” Journal of Vascular Surgery, vol. 78, no. 5, pp. 1101-1131, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[36] Gyeongho Kim et al., “Developing a Data-Driven System for Grinding Process Parameter Optimization using Machine Learning and Metaheuristic Algorithms,” CIRP Journal of Manufacturing Science and Technology, vol. 51, pp. 20-35, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[37] Jaesun Park, Jeahoon Cho, and Kyung-Young Jung, “Nature-Inspired Metaheuristic Optimization Algorithms for FDTD Dispersion Modeling,” AEU - International Journal of Electronics and Communications, vol. 187, pp. 1-18, 2024.
[CrossRef] [Google Scholar] [Publisher Link]