IRO Journals
Journal of Artificial Intelligence and Capsule Networks

AI-Driven Early Detection and Classification of Skin Diseases Using Deep Learning and Mobile Edge Computing

Open Access
Published: 27 July, 2026
Pages: 224-242
  • Manikandaraja G. , Manikandaraja G.
    Assistant Professor, School of Mechanical Engineering, SRM Institute of Science and Technology, Tiruchirappalli, India
    Assistant Professor, School of Mechanical Engineering, SRM Institute of Science and Technology, Tiruchirappalli, India
  • Hemanth R S. , Hemanth R S.
    UG Student, School of Computer Science and Engineering, SRM Institute of Science and Technology, Tiruchirappalli, India
    UG Student, School of Computer Science and Engineering, SRM Institute of Science and Technology, Tiruchirappalli, India
  • Nihal Bin Anwar Nihal Bin Anwar
    UG Student, School of Computer Science and Engineering, SRM Institute of Science and Technology, Tiruchirappalli, India
    UG Student, School of Computer Science and Engineering, SRM Institute of Science and Technology, Tiruchirappalli, India
view PDF
view PDF

How to Cite

G., Manikandaraja, Hemanth R S., and Nihal Bin Anwar. 2026. “AI-Driven Early Detection and Classification of Skin Diseases Using Deep Learning and Mobile Edge Computing”. Journal of Artificial Intelligence and Capsule Networks 8 (3): 224-42. https://doi.org/10.36548/jaicn.2026.3.005.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Skin Disease Classification
Deep Learning
EfficientNet
MobileNet
Mobile Edge Computing
Explainable Artificial Intelligence
TensorFlow Lite
Dermatological Image Analysis
Telemedicine

Abstract

Skin disorders are experienced by millions of people across the globe, thus, calling for timely and accurate diagnosis in order to ensure proper treatment and good prognosis of the disease. Nevertheless, lack of access to dermatologists in some parts of the world, especially in rural areas and poor regions, often hinders proper and timely diagnosis of the condition. This work proposes an AI-based framework for automatic detection of skin disorders via deep learning and edge computing technology. Grad-CAM powered explainable artificial intelligence makes the model more transparent through region of interest identification in clinical images, whereas the lightweight web application makes predictions along with disease prediction confidence and visualization of diagnosis. Evaluation on HAM10000 and ISIC datasets attained 94.8% accuracy, 93.6% precision, 94.1% recall, 93.8% F1-score, and 95.4% mAP. The proposed solution presents an effective and scalable solution for AI-assisted dermatological diagnosis.

References

  1. Tschandl, Philipp, Cliff Rosendahl, and Harald Kittler. "The HAM10000 Dataset, A Large Collection of Multi-Sources Dermatoscopic Images of Common Pigmented Skin Lesions." Scientific data 2018, vol 5, no. 1: 180161.
  2. Codella, Noel, Veronica Rotemberg, Philipp Tschandl, M. Emre Celebi, Stephen Dusza, David Gutman, Brian Helba et al. "Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (Isic)." arXiv preprint 2019, arXiv:1902.03368.
  3. Saha, Gokul Kumar, S. S. Rai, K. S. Prakasam, and V. K. Gaur. "Submerged Ancient Indian Continent in the Bay of Bengal-Inference from Ambient Noise and Earthquake Tomography." arXiv preprint 2019, arXiv:1907.12036.
  4. Esteva, Andre, Brett Kuprel, Roberto A. Novoa, Justin Ko, Susan M. Swetter, Helen M. Blau, and Sebastian Thrun. "Dermatologist-Level Classification of Skin Cancer with Deep Neural Networks." Nature 2017, vol 542, no. 7639: 115-118.
  5. Haenssle, Holger A., Christine Fink, Roland Schneiderbauer, Ferdinand Toberer, Timo Buhl, Andreas Blum, Aadi Kalloo et al. "Man Against Machine: Diagnostic Performance of a Deep Learning Convolutional Neural Network for Dermoscopic Melanoma Recognition in Comparison To 58 Dermatologists." Annals of oncology 2018, vol 29, no. 8: 1836-1842.
  6. Ronneberger, Olaf, Philipp Fischer, and Thomas Brox. "U-net: Convolutional Networks for Biomedical Image Segmentation." In International Conference on Medical image computing and computer-assisted intervention 2015, 234-241.
  7. Yuan, Yading. "Automatic Skin Lesion Segmentation with Fully Convolutional-Deconvolutional Networks." arXiv preprint 2017, arXiv:1703.05165.
  8. Howard, Andrew, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang et al. "Searching for Mobilenetv3." In Proceedings of the IEEE/CVF international conference on computer vision 2019, 1314-1324.
  9. Tan, Mingxing, and Quoc Le. "Efficientnet: Rethinking Model Scaling for Convolutional Neural Networks." In International conference on machine learning PMLR, 2019, 6105-6114.
  10. Jacob, Benoit, Skirmantas Kligys, Bo Chen, Menglong Zhu, Matthew Tang, Andrew Howard, Hartwig Adam, and Dmitry Kalenichenko. "Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference." In Proceedings of the IEEE conference on computer vision and pattern recognition 2018, 2704-2713.
  11. Kang, Yiping, Johann Hauswald, Cao Gao, Austin Rovinski, Trevor Mudge, Jason Mars, and Lingjia Tang. "Neurosurgeon: Collaborative Intelligence Between the Cloud and Mobile Edge." ACM SIGARCH Computer Architecture News 2017, vol 45, no. 1: 615-629.
  12. Huang, Qicheng, Chenlei Fang, Zeye Liu, Ruizhou Ding, and RD Shawn Blanton. "IPSA: Integer Programming via Sparse Approximation for Efficient Test-Chip Design." In 2019 IEEE 37th International Conference on Computer Design (ICCD) IEEE, 2019, 11-19.
  13. Hinton, Geoffrey, Oriol Vinyals, and Jeff Dean. "Distilling the Knowledge in a Neural Network." arXiv preprint 2015, arXiv:1503.02531.
  14. McMahan, Brendan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. "Communication-Efficient Learning of Deep Networks from Decentralized Data." In Artificial intelligence and statistics Pmlr, 2017, 1273-1282.
  15. Rieke, Nicola, Jonny Hancox, Wenqi Li, Fausto Milletari, Holger R. Roth, Shadi Albarqouni, Spyridon Bakas et al. "The Future of Digital Health with Federated Learning." NPJ digital medicine 2020, vol 3, no. 1: 119.