Bin Wu
Papers
1
Total Citations
3
H-Index
1
About
Bin Wu is a researcher whose work sits at the intersection of statistical signal processing, Bayesian inference, and adaptive control systems. His most notable contribution centers on the development of fast particle filters — computationally efficient algorithms designed to tackle one of the most challenging problems in dynamic systems: handling abrupt parameter jumps in real-time environments. His 2009 work introduces sophisticated solutions for change-point detection in ARX (AutoRegressive with eXogenous inputs) models, leveraging Bayesian updating frameworks and the AFMM (Adaptive Forgetting through Multiple Models) approach to calculate posterior probabilities across competing model families. This research bridges theoretical probabilistic methods with practical engineering applications, most notably in robotics, where adaptive control under uncertainty is critical for reliable performance. By combining on-line change detection algorithms with particle filtering techniques, Wu's framework enables systems to respond dynamically to structural shifts in underlying model parameters — a capability with broad relevance across control engineering, time-series analysis, and autonomous systems. While his citation record remains early-stage with 3 citations, his methodological contributions represent meaningful advances in sequential Monte Carlo methods applied to adaptive systems, offering a foundation that researchers in Bayesian filtering and intelligent robotics continue to build upon.
Research Focus
Key Achievements
Top Papers
- 1