Murad Ali Khan is a machine learning and data engineering researcher currently pursuing an integrated Ph.D. in the Department of Computer Engineering at Jeju National University, Republic of Korea. He also holds contributions within the Department of Electronics Engineering, indicating a multidisciplinary technical foundation.

Khan has made significant contributions to materials science data analysis through advanced imputation techniques. Notably, he proposed an optimized K‑Nearest Neighbors (KNN) imputation framework integrated with deep neural networks, demonstrating a substantial improvement in R² performance—from ~0.746 with traditional methods to ~0.973 with his enhanced approach. His work, “Enhancing Material Property Predictions through Optimized KNN Imputation and Deep Neural Network Modeling,” was published in IGMin Research (June 2024) and is indexed as DOI 10.61927/igmin197.

Building on his expertise in imputation, Khan examined missing EEG amplitude data in clinical datasets through a transformer‑based model, resulting in improved accuracy in handling complex sequential biomedical data. In addition, his research extends to anomaly detection in clinical rehabilitation data, proposing heuristic–stochastic hybrid frameworks—leveraging optimal k‑means clustering and interquartile range filtering followed by AutoML regression—to enhance predictive robustness.

Beyond these areas, Khan explores spam detection in app reviews using machine learning, contributing to systems that discern genuine user feedback in app marketplaces. His prolific publishing record across multiple high‑impact venues highlights his multidisciplinary competence spanning machine learning, data engineering, biomedical informatics, and materials science.

At Jeju National University, Khan continues to advance in-depth research at the intersection of AI and engineering, aiming to translate complex data challenges into robust, real‑world solutions.

Murad Ali Khan’s research interests lie at the intersection of machine learning, data engineering, and computational modeling, with a focus on solving real-world challenges across domains like materials science, biomedical informatics, and smart systems. He specializes in missing data imputation, employing techniques such as enhanced K-Nearest Neighbors (KNN), deep neural networks, and transformer-based architectures to improve data reliability and predictive accuracy. His work extends to anomaly detection, particularly in clinical rehabilitation datasets, where he integrates hybrid heuristic-stochastic models for robust outlier filtering and forecasting. Khan is also engaged in developing intelligent models for spam detection, user sentiment analysis, and EEG signal modeling, using advanced regression and classification methods. With a strong foundation in AI model optimization, AutoML frameworks, and feature engineering, he aims to build scalable, domain-agnostic solutions. His multidisciplinary approach reflects a commitment to bridging computational intelligence with practical applications in engineering and health technologies.