Mehrtash Harandi
Papers
1
Total Citations
2
H-Index
1
About
Mehrtash Harandi is a leading researcher in machine learning, computer vision, and anomaly detection, with a particular focus on industrial applications and time series analysis. His work bridges the gap between theoretical advances and practical deployment, notably through the development of STAD-FEBTE, a shallow yet powerful framework for time series anomaly detection that integrates automatic feature engineering, class balancing, and tree-based ensembles. This framework, demonstrated in a 2023 industrial case study, addresses the critical need for reliable monitoring in multi-sensor systems, where undetected anomalies can lead to faulty products, production shutdowns, or catastrophic failures. With over 2 citations on this specific work and a broader portfolio of highly cited papers, Harandi’s contributions have significantly impacted both academic research and real-world engineering. His expertise in designing robust, interpretable models for high-stakes environments underscores his role as a key innovator in applied machine learning, making his work essential reading for students and practitioners seeking to deploy trustworthy AI in industrial settings.
Research Focus
Key Achievements
Top Papers
- 1