Abdullah Mueen

University of California, Riverside, University of New Mexico

Papers

Total Citations

449

H-Index

About

Abdullah Mueen is a leading researcher in time series data mining, with a focus on developing efficient algorithms for pattern discovery and classification. His key contributions center on shapelets—small, discriminative subsequences within time series that enable highly interpretable classification and summarization. His seminal 2011 paper, “Logical-shapelets,” introduced a method to extract these local patterns, earning 273 citations and establishing a foundational approach in the field. Mueen also revolutionized the practical use of Dynamic Time Warping (DTW) with his 2016 work, “Extracting Optimal Performance from Dynamic Time Warping,” which proposed optimizations that dramatically reduced DTW’s computational cost from O(n²) to near-linear time, enabling its widespread adoption in data mining, image processing, and industrial applications—a paper cited 161 times. More recently, his 2024 paper on MASS (Mueen’s Algorithm for Similarity Search) provides a fast, exact method for computing distance profiles over time series, further cementing his impact. With over 400 total citations, Mueen’s work has shaped modern time series analysis, making complex tasks like similarity search and classification both scalable and accessible.