• Luu Van Dai
• Huynh Thanh Hoa

Digital communication systems face growing challenges from data corruption and missing information, which can severely reduce system reliability and performance—particularly in real-time, noise-heavy environments. Traditional error-correction and data-imputation methods often fall short when encountering burst-type errors, structured missingness, or strict latency requirements. To address these limitations, this study introduces a new two-stage framework that integrates CatBoost-driven anomaly detection with MICE-based data reconstruction, offering a unified solution for both erroneous and absent data. The proposed model is validated using real-world data from Smart EV Charging infrastructure, under conditions that emulate practical error patterns. Our experimental evaluation demonstrates significant improvements over leading baseline techniques in detection precision, imputation quality, and computational efficiency. These results highlight the framework’s suitability for deployment in time-critical, resource-limited environments such as edge devices and 5G communication systems.

Machine Learning, Anomaly Detection, Data Recovery, Data Imputation, Digital Communication

"An Innovative Model for Enhancing Data Detection and Recovery within Digital Communication Systems", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 11, page no.f622-f628, November-2025, Available :http://www.jetir.org/papers/JETIR2511593.pdf

"An Innovative Model for Enhancing Data Detection and Recovery within Digital Communication Systems", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 11, page no. ppf622-f628, November-2025, Available at : http://www.jetir.org/papers/JETIR2511593.pdf