Adaptive Machine Learning for Resource-Constrained Environments: A Path toward Sustainable AI
DOI:
https://doi.org/10.15662/IJRAI.2024.0706012Keywords:
Adaptive Machine Learning, Resource-Constrained Environments, Energy Efficiency, Edge Computing, Lightweight Models, Sustainable AIAbstract
The paper concentrates on adaptive machine learning (ML) models targeted at low-power devices, which will turn AI more available and sustainable in resource-limited settings. As the use of AI applications gains more and more popularity in developing areas and edge computing, a lightweight and energy-efficient model is of the primary concern to allow more people to adopt it. This paper examines the different energy-conservation measures, including model pruning, quantization, and edge AI to balance machine learning against accuracy. With the examples of realistic applications, e.g., healthcare diagnostics and smart agriculture, we show how these models can be effectively used within resource-constrained devices. This methodology is based on the assessment of various lightweight models based on performance benchmarks on low-power hardware, energy efficiency, and accuracy. The most important results include that adaptive ML models can achieve substantial energy saving and high-performing results, providing viable solutions to using AI in the low-resource context. These findings substantiate the possibility of sustainable AI to promote technological inclusion on the international scale.
References
1. Abdussalam Elhanashi, Dini, P., Saponara, S., & Zheng, Q. (2024). Advancements in TinyML: Applications, Limitations, and Impact on IoT Devices. Electronics, 13(17), 3562–3562. https://doi.org/10.3390/electronics13173562
2. Akinsuli, O. (2021). The rise of AI-enhanced Ransomware-as-a-Service (RaaS): A new threat frontier. World Journal of Advanced Engineering Technology and Sciences, 1(2), 85–97. https://wjaets.com/content/rise-ai-enhanced-ransomware-service-raas-new-threat-frontier
3. Akinsuli, O. (2022). AI and the Fight Against Human Trafficking: Securing Victim Identities and Disrupting Illicit Networks. Iconic Research And Engineering Journals, 5(10), 287-303.
4. Akinsuli, O. (2023). The Complex Future of Cyberwarfare - AI vs AI. Journal of Emerging Technologies and Innovative Research, 10(2), 957-978.
5. Akinsuli, O. (2024). AI-Powered Supply Chain Attacks: A Growing Cybersecurity Threat. Iconic Research And Engineering Journals, 8(1), 696-708.
6. Akinsuli, O. (2024). AI Security in Social Engineering: Mitigating Risks of Data Harvesting and Targeted Manipulation. Iconic Research And Engineering Journals, 8(3), 665-684.
7. Akinsuli, O. (2024). Securing AI in Medical Research: Revolutionizing Personalized and Customized Treatment for Patients. Iconic Research And Engineering Journals, 8(2), 925-941.
8. Akinsuli, O. (2024). Securing the Driverless Highway: AI, Cyber Threats, and the Future of Autonomous Vehicles. Iconic Research And Engineering Journals, 8(2), 957-970.
9. Akinsuli, O. (2024). Traditional AI vs generative AI: The role in modern cyber security. Journal of Emerging Technologies and Innovative Research (JETIR), 11(7), 431-447. https://www.jetir.org/papers/JETIR2407842.pdf
10. Akinsuli, O. (2024). Using AI to Combat Cyberbullying and Online Harassment in North America (Focus on USA). International Journal of Emerging Technologies and Innovative Research, 11(5), 276-299.
11. Akinsuli, O. (2024). Using Zero Trust Security Architecture Models to Secure Artificial Intelligence Systems. Journal of Emerging Technologies and Innovative Research, 11(4), 349-373.
12. Chawande, S. (2024). AI-driven malware: The next cybersecurity crisis. World Journal of Advanced Engineering Technology and Sciences, 12(01), 542-554. https://doi.org/10.30574/wjaets.2024.12.1.0172
13. Chawande, S. (2024). Insider threats in highly automated cyber systems. World Journal of Advanced Engineering Technology and Sciences, 13(02), 807-820. https://doi.org/10.30574/wjaets.2024.13.2.0642
14. Chawande, S. (2024). The role of Artificial Intelligence in cybersecurity. World Journal of Advanced Engineering Technology and Sciences, 11(02), 683-696. https://doi.org/10.30574/wjaets.2024.11.2.0014
15. El-Amir, H., & Hamdy, M. (2020). Deep Learning Pipeline. Apress. https://doi.org/10.1007/978-1-4842-5349-6
16. Folorunso, A., Olanipekun, K., Adewumi, T., & Samuel, B. (2024). A policy framework on AI usage in developing countries and its impact. Global Journal of Engineering and Technology Advances, 21(01), 154–166. https://doi.org/10.30574/gjeta.2024.21.1.0192
17. Gkontra, P., Quaglio, G., Tselioudis Garmendia, A., & Lekadir, K. (2023). Challenges of Machine Learning and AI (What Is Next?), Responsible and Ethical AI. Springer EBooks, 263–285. https://doi.org/10.1007/978-3-031-36678-9_17
18. Gualdi, F., & Cordella, A. (2021, January 5). Artificial intelligence and decision-making: the question of accountability (T. X. Bui, Ed.). Eprints.lse.ac.uk; IEEE Computer Society Press. https://eprints.lse.ac.uk/110995/
19. Hua, H., Li, Y., Wang, T., Dong, N., Li, W., & Cao, J. (2023). Edge Computing with Artificial Intelligence: A Machine Learning Perspective. ACM Computing Surveys, 55(9), 1–35. https://doi.org/10.1145/3555802
20. Kumar, M., Zhang, X., Liu, L., Wang, Y., & Shi, W. (2020). Energy-Efficient Machine Learning on the Edges. 2020 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), New Orleans, LA, USA, 912-921. https://doi.org/10.1109/IPDPSW50202.2020.00153
21. Kokare, Ashish, et al. (2014). Survey on classification based techniques on non-spatial data. International Journal of Innovative Research in Science, Engineering and Technology, 3(1), 409-413.
22. Lin, Y.-B., Chen, W.-E., & Chang, T. C.-Y. (2023). Moving from Cloud to Fog/Edge: The Smart Agriculture Experience. IEEE Communications Magazine, 61(12), 86-92. https://doi.org/10.1109/MCOM.001.2200633
23. Muvva, S. (2021). Ethical AI and responsible data engineering: A framework for bias mitigation and privacy preservation in large-scale data pipelines. International Journal of Scientific Research in Engineering and Management, 5(9), 1–6. https://doi.org/10.55041/IJSREM10633
24. Pimenow, S., Pimenowa, O., & Prus, P. (2024). Challenges of Artificial Intelligence Development in the Context of Energy Consumption and Impact on Climate Change. Energies, 17(23), 5965. https://doi.org/10.3390/en17235965
25. Pessach, D., & Shmueli, E. (2023). A Review on Fairness in Machine Learning. ACM Computing Surveys, 55(3), 1–44. https://doi.org/10.1145/3494672
26. Truong, H.-L., Truong-Huu, T., & Cao, T.-D. (2022). Making distributed edge machine learning for resource-constrained communities and environments smarter: contexts and challenges. Journal of Reliable Intelligent Environments. https://doi.org/10.1007/s40860-022-00176-3
27. Wesley Hanwen Deng, Manish Nagireddy, Seng, M., Singh, J., Zhiwei Steven Wu, Holstein, K., & Zhu, H. (2022). Exploring How Machine Learning Practitioners (Try To) Use Fairness Toolkits. 2022 ACM Conference on Fairness, Accountability, and Transparency. https://doi.org/10.1145/3531146.3533113
