D
Dianhui Wang
Researcher at La Trobe University
Publications - 214
Citations - 6390
Dianhui Wang is an academic researcher from La Trobe University. The author has contributed to research in topics: Artificial neural network & Computer science. The author has an hindex of 31, co-authored 198 publications receiving 5150 citations. Previous affiliations of Dianhui Wang include Nanyang Technological University & Northeastern University.
Papers
More filters
Proceedings ArticleDOI
Neural-net based multi-steps nonlinear adaptive model predictive controller design
Dianhui Wang,Tianyou Chai +1 more
TL;DR: This work focuses on the multistep adaptive NMPC controller design using neural-net, initialisation of the multistsep control laws by using one-step ahead predictive control law, linearization of the neural-nets predictor at every operating point, and tuning of the Neural-net predictor through online learning using teacher signals generated by closed-loop system input-output data.
Journal ArticleDOI
On graph modelling, node ranking and visualisation
TL;DR: This paper provides approaches to building a graph from a given set of objects accompanied by their feature vectors, as well as to ranking nodes in the graph, and a method for visualising graphs with ranking nodes.
Proceedings ArticleDOI
Feature Extraction for Face Image Retrieval
Paul C. Conilione,Dianhui Wang +1 more
TL;DR: The aim of this paper is to examine the Eigenpaxel and commonly used Gabor wavelet filter in terms of distinguishing capability and robustness with respect to 12 types of variation of a neutral expression frontal face image for retrieval.
Journal ArticleDOI
Event-Triggered Prespecified Performance Control for Steer-by-Wire Systems With Input Nonlinearity
TL;DR: In this paper , a prescribed tracking performance control problem for uncertain steer-by-wire (SbW) systems with input nonlinearity (including dead-zone and actuator fault) and the limitation of controller-area-network (CAN) bandwidth is addressed.
Proceedings ArticleDOI
Learning pseudo metrics for semantic image clustering
Dianhui Wang,Yong-Soo Kim +1 more
TL;DR: Experiments show that the LPM-based similarity metric can produce better clustering results in terms of both impurity and robustness.