Behnam Khojasteh
Papers
2
Total Citations
12
H-Index
2
About
Behnam Khojasteh is a rising researcher in multimodal sensing and surface recognition, with a focus on haptic-auditory signal processing. His work centers on developing robust, data-driven methods to classify physical surfaces using machine learning, particularly through the application of the kernel two-sample test and maximum mean discrepancy (MMD). Khojasteh’s major contributions include pioneering approaches that reduce reliance on human expertise and extensive parameter tuning in surface classification, instead leveraging statistical tests to compare multimodal data distributions. His 2023 paper on multimodal multi-user surface recognition and his 2024 study on degrading haptic-auditory signals through bandwidth and noise each have garnered 6 citations, demonstrating early impact in this niche field. Notably, his research addresses practical challenges in robotics and human-computer interaction, such as how tool-material interactions can be optimally captured for reliable recognition. Khojasteh’s work is particularly relevant for students and researchers interested in the intersection of tactile sensing, auditory analysis, and efficient machine learning, offering a path toward more autonomous and adaptable recognition systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2