Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{207227,
        author = {Mrs.M.Nandhiya and Dr.C.R Durga devi},
        title = {A Robust Deep Capsule Network for IoT-Enabled Cloud-Based Predictive Analytics},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {3},
        pages = {429-433},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=207227},
        abstract = {Cloud computing offers scalable resources such as storage, networking, analytics, and software services through the internet. Predictive analytics in cloud platforms is widely used to forecast future events from historical data. Existing prediction models often suffer from lower accuracy and high computational complexity when handling large and diverse datasets. This paper presents an IoT-enabled Robust Autoencoded Deep Capsule Network for efficient predictive analytics in cloud environments. The proposed framework integrates preprocessing, feature extraction, classification, and optimization into a unified architecture. IoT sensors continuously gather environmental data and transfer it to the cloud platform for analysis. Missing values and abnormal records are corrected during preprocessing using polynomial imputation and modified Z-score analysis. A robust autoencoder identifies the most relevant features, reducing dimensionality and improving efficiency. Finally, the capsule network applies similarity-based classification to generate accurate prediction results. Experimental evaluation using the Global Air Pollution Dataset demonstrates that the proposed framework achieves superior prediction accuracy, reduced error rate, and lower prediction time compared with existing deep learning approaches.},
        keywords = {IoT, Cloud Computing, Predictive Analytics, Deep Capsule Network, Autoencoder, Feature Selection, Air Pollution Prediction, Machine Learning},
        month = {August},
        }