Optimized Software Development and Deployment Using WPM: Integrating Machine Learning Models with U-Net-Based Image Enhancement in Cloud-Native Web Architectures
DOI:
https://doi.org/10.15662/IJRAI.2021.0403003Keywords:
weighted product method (WPM), machine learning, U-Net, image enhancement, cloud-native architectures, software development, software deployment, CI/CD, MCDM, DevOps, MLOps, optimization, microservices, image processing, cloud orchestrationAbstract
The convergence of machine learning and cloud-native architectures has redefined modern software development pipelines, enabling intelligent automation, enhanced visual analytics, and adaptive deployment strategies. This research introduces a Weighted Product Method (WPM)-based optimization framework for software development and deployment that integrates machine learning (ML) models with U-Net-based image enhancement techniques in cloud-native web environments. The proposed approach employs WPM as a multicriteria decision-making (MCDM) mechanism to evaluate and balance key performance indicators—including computational efficiency, scalability, latency, and image quality—throughout the software lifecycle. U-Net models, enhanced with transfer learning and attention modules, are integrated into the CI/CD workflow to improve the visual clarity and interpretability of web-based image data, supporting sectors such as healthcare diagnostics, remote sensing, and digital forensics. The cloud-native infrastructure ensures continuous deployment, auto-scaling, and microservice-level resilience, while ML-driven orchestration dynamically optimizes resource allocation. Experimental results validate that the combined WPM–ML–U-Net architecture delivers superior deployment agility, image enhancement accuracy, and operational transparency. This framework establishes a benchmark for intelligent, optimized, and explainable cloud-native software ecosystems that align with modern DevOps and MLOps standards.
References
1. Burns, B., & Oppenheimer, D. (2016). Design patterns for container-based distributed systems. Proceedings of the 8th USENIX Conference on Hot Topics in Cloud Computing (HotCloud), 1–8.
2. Adari, V. K., Chunduru, V. K., Gonepally, S., Amuda, K. K., & Kumbum, P. K. (2020). Explain ability and interpretability in machine learning models. Journal of Computer Science Applications and Information Technology, 5(1), 1-7.
3. R. Sugumar, A. Rengarajan and C. Jayakumar, Design a Weight Based Sorting Distortion Algorithm for Privacy Preserving Data Mining, Middle-East Journal of Scientific Research 23 (3): 405-412, 2015.
4. Dong, C., Loy, C. C., He, K., & Tang, X. (2015). Image super-resolution using deep convolutional networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(2), 295–307.
5. Ghosh, R., Khatua, S., & Misra, S. (2019). Elastic cloud-based computer vision for intelligent image analytics. IEEE Transactions on Cloud Computing, 7(3), 713–725.
6. Kaur, S., & Chana, I. (2016). Cloud-based image processing: State-of-the-art and future directions. Journal of Network and Computer Applications, 63, 68–85.
7. Land, E. H., & McCann, J. J. (1971). Lightness and retinex theory. Journal of the Optical Society of America, 61(1), 1–11.
8. S. T. Gandhi, "Context Sensitive Image Denoising and Enhancement using U-Nets," Computer Science (MS), Computer Science (GCCIS), Rochester Institute of Technology, 2020. [Online]. Available: https://repository.rit.edu/theses/10588/
9. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444.
10. Newman, S. (2015). Building microservices: Designing fine-grained systems. O’Reilly Media.
11. Reddi, V. J., Cheng, C., & Kanev, S. (2020). AI inference at cloud scale: Efficiency, scalability, and performance. IEEE Micro, 40(2), 24–33.
12. Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention (MICCAI) (pp. 234–241). Springer.
13. Satyanarayanan, M. (2017). The emergence of edge computing. Computer, 50(1), 30–39.
14. Tan, M., & Le, Q. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning (ICML), 6105–6114.
15. Zhang, K., Zuo, W., Chen, Y., Meng, D., & Zhang, L. (2017). Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising. IEEE Transactions on Image Processing, 26(7), 3142–3155.
16. Zhang, X., Wang, Q., & Liu, D. (2018). Image deblurring with enhanced U-Net architectures. Signal Processing: Image Communication, 66, 140–149.
17. Begum, R.S, Sugumar, R., Conditional entropy with swarm optimization approach for privacy preservation of datasets in cloud [J]. Indian Journal of Science and Technology 9(28), 2016. https://doi.org/10.17485/ijst/2016/v9i28/93817’
18. Zhao, H., Gallo, O., Frosio, I., & Kautz, J. (2019). Loss functions for image restoration with neural networks. IEEE Transactions on Computational Imaging, 5(1), 47–57.
19. Srinivas Chippagiri, Preethi Ravula. (2021). Cloud-Native Development: Review of Best Practices and Frameworks for Scalable and Resilient Web Applications. International Journal of New Media Studies: International Peer Reviewed Scholarly Indexed Journal, 8(2), 13–21. Retrieved from https://ijnms.com/index.php/ijnms/article/view/294
20. Amuda, K. K., Kumbum, P. K., Adari, V. K., Chunduru, V. K., & Gonepally, S. (2020). Applying design methodology to software development using WPM method. Journal of Computer Science Applications and Information Technology, 5(1), 1–8. https://doi.org/10.15226/2474-9257/5/1/00146
21. Zhou, Z., Siddiquee, M. M. R., Tajbakhsh, N., & Liang, J. (2018). UNet++: A nested U-Net architecture for medical image segmentation. Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, 3–11.
