A green AI model selection strategy for computer-aided mpox detection.

Ezenkwu, Chinedu Pascal; Stephen, Bliss Utibe-Abasi; Affiah, Iniabasi; Daniel, Betabasi

Abstract

With the recent global surge in mpox (formerly monkeypox) cases, researchers have proposed deep learning technologies for early detection of the disease from skin lesion images. However, many of these researchers follow the current Red AI trend of seeking to improve the performance accuracies of classifiers with no consideration given to the efficiency and environmental-friendliness of their models. This paper proposes a Green AI model selection strategy based on a multi-criteria decision technique, incorporating computational time in identifying the optimal model for final deployment. We have experimented with end-to-end ResNet50, VGG19 and InceptionV3 networks, and the transfer-learning of their pre-trained versions with SVMs. Using our proposed Green AI strategy, we have identified the optimal models based on efficiency and performance. The results have been assessed using expert-level validation. We demonstrate that our proposed method can select the best model. The outcomes of our model selection strategy are similar to experts' choices of the optimal model when presented with both model error and computation time. This paper's contributions are significant, as they support the ongoing call for Green AI, especially within the healthcare sector.

Citation

EZENKWU, C.P., STEPHEN, B.U.-A., AFFIAH, I. and DANIEL, B. 2023. A green AI model selection strategy for computer-aided mpox detection. In Proceedings of the 16th IEEE Africon conference (IEEE AFRICON 2023): advancing technology in Africa towards presence on the global stage, 20-22 September 2023, Nairobi, Kenya. Piscataway: IEEE [online], document number 10293707. Available from: https://doi.org/10.1109/AFRICON55910.2023.10293707

• Conference Name: 16th IEEE Africon conference (IEEE AFRICON 2023): advancing technology in Africa towards presence on the global stage
• Conference Location: Nairobi, Kenya
• Start Date: Sep 20, 2023
• End Date: Sep 22, 2023
• Acceptance Date: May 15, 2023
• Online Publication Date: Oct 31, 2023
• Publication Date: Dec 31, 2023
• Deposit Date: Sep 7, 2023
• Publicly Available Date: Sep 7, 2023
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Series Title: IEEE AFRICON proceedings
• Series ISSN: 2153-0025; 2153-0033
• ISBN: 9798350336221
• DOI: https://doi.org/10.1109/AFRICON55910.2023.10293707
• Keywords: Green artificial intelligence (AI); Environmental computing; Artificial intelligence (AI) in healthcare; Healthcare technologies; Mpox; Artificial intelligence (AI)
• Public URL: https://rgu-repository.worktribe.com/output/2072015