AI-Driven Computational Frameworks: Advancing Edge Intelligence and Smart Systems
DOI:
https://doi.org/10.22399/ijcesen.1165Keywords:
AI-Driven Computational, Neuromorphic Computing, Reinforcement Learning, Privacy-Preserving AI, IoT Optimization, Blockchain SecurityAbstract
The rapid advancements in Artificial Intelligence (AI) and Edge Computing are transforming modern computing paradigms by enabling real-time processing, low-latency decision-making, and enhanced intelligence in smart systems. This paper presents an AI-driven computational framework that integrates Edge Intelligence (EI) with adaptive deep learning models to optimize data processing and decision-making at the edge. The proposed framework employs federated learning, neuromorphic computing, and reinforcement learning-based optimization to improve efficiency, security, and scalability in distributed edge environments.
Key components include lightweight AI models for energy-efficient edge inference, privacy-preserving techniques using homomorphic encryption and blockchain, and self-learning architectures for adaptive real-time analytics. The study evaluates the framework’s performance in diverse applications, including smart healthcare, autonomous vehicles, and industrial IoT, demonstrating significant improvements in computational efficiency, network resilience, and response time compared to traditional cloud-based architectures.
Comprehensive simulations and real-world case studies validate the feasibility and effectiveness of the proposed approach, showing a 35% reduction in latency, a 30% increase in energy efficiency, and a 50% improvement in decision accuracy in edge-enabled smart systems. This research highlights the critical role of AI-driven computational frameworks in advancing next-generation intelligent computing, paving the way for autonomous, secure, and efficient edge-based smart environments.
References
Dong, H.; Yang, G.; Liu, F.; Mo, Y.; Guo, Y. (2017). Automatic brain tumor detection and segmentation using U-Net based fully convolutional networks. In Proceedings of the Annual Conference on Medical Image Understanding and Analysis, Southampton, UK, 9–11 July 2017; pp. 506–517.
Havaei, M.; Davy, A.; Warde-Farley, D.; Biard, A.; Courville, A.; Bengio, Y.; Pal, C.; Jodoin, P.M.; Larochelle, H. (2017) Brain tumor segmentation with deep neural networks. Med. Image Anal. 35;18–31.
Li, H.; Li, A.; Wang, M. (2019). A novel end-to-end brain tumor segmentation method using improved fully convolutional networks. Comput. Biol. Med. 108, 150–160.
Badrinarayanan, V.; Kendall, A.; Cipolla, R. Segnet: (2017). A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39;2481–2495.
Irmak, E. (2021). Multi-Classification of Brain Tumor MRI Images Using Deep Convolutional Neural Network with Fully Optimized Framework. Iran J Sci Technol Trans Electr Eng 45;1015–1036
D. G. Glan and S. S. Kumar, (2018). Brain tumor detection and segmentation using a wrapper based genetic algorithm for optimized feature set, Cluster Computing, 22(1);13369–13380.
M. Angulakshmi and G. G. Lakshmi Priya, (2018). Brain tumor segmentation from MRI using superpixels based spectral clustering, Journal of King Saud University–Computer and Information Sciences, 32(10);1182–1193.
A. C. Jinisha and T. S. S. Rani, “Brain tumor classification using SVM and bag of visual word classifier,” in Proceedings of the 2019 International Conference on Recent Advances in Energy-efficient Computing and Communication (ICRAECC), pp. 1–6, IEEE, Nagercoil, India, March 2019.
M. Khalil, H. Ayad, and A. Adib, (2018). Performance evaluation of feature extraction techniques in MR-brain image classification system, Procedia Computer Science, 127;218–225.
S. González-Villà, A. Oliver, Y. Huo, X. Lladó, and B. A. Landman, (2019). Brain structure segmentation in the presence of multiple sclerosis lesions, NeuroImage: Clinica, 22;101709,
S. M. Kurian, S. J. Devaraj, and V. P. Vijayan, (2021). Brain tumour detection by gamma DeNoised wavelet segmented entropy classifier, CMC-Computers, Materials & Continua, 69(2);2093–2109.
N.Sasirekha .,K R Kashwan, (2016) International Journal of Digital Content Technology and its Applications 10(2);61-77,
N.Sasirekha .,K R Kashwan, (2015) Improved Segmentation of MRI Brain Images by Denoising and Contrast Enhancement, Indian Journal of Science and Technology 8(22) DOI:10.17485/ijst/2015/v8i22/73050
Saeidifar, M., Yazdi, M. & Zolghadrasli, A. (2021) Performance Improvement in Brain Tumor Detection in MRI Images Using a Combination of Evolutionary Algorithms and Active Contour Method. J Digit Imaging 34, 1209–1224
Shivhare, S.N., N. Kumar, and N. Singh, (2019). A hybrid of active contour model and convex hull for automated brain tumor segmentation in multimodal MRI. Multimedia Tools and Applications, 78(24);34207-34229.
Maheshwari, R. U., Jayasutha, D., Senthilraja, R., & Thanappan, S. (2024). Development of Digital Twin Technology in Hydraulics Based on Simulating and Enhancing System Performance. Journal of Cybersecurity & Information Management, 13(2).
Paulchamy, B., Uma Maheshwari, R., Sudarvizhi AP, D., Anandkumar AP, R., & Ravi, G. (2023). Optimized Feature Selection Techniques for Classifying Electrocorticography Signals. Brain‐Computer Interface: Using Deep Learning Applications, 255-278.
Paulchamy, B., Chidambaram, S., Jaya, J., & Maheshwari, R. U. (2021). Diagnosis of Retinal Disease Using Retinal Blood Vessel Extraction. In International Conference on Mobile Computing and Sustainable Informatics: ICMCSI 2020 (pp. 343-359). Springer International Publishing.
Maheshwari, U. Silingam, K. (2020). Multimodal Image Fusion in Biometric Authentication. Fusion: Practice and Applications,79-91. DOI: https://doi.org/10.54216/FPA.010203
R.Uma Maheshwari (2021). ENCRYPTION AND DECRYPTION USING IMAGE PROCESSING TECHNIQUES. International Journal of Engineering Applied Sciences and Technology, 5(12);219-222
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
