M
Mengjie Zhang
Researcher at Victoria University of Wellington
Publications - 848
Citations - 23125
Mengjie Zhang is an academic researcher from Victoria University of Wellington. The author has contributed to research in topics: Genetic programming & Feature selection. The author has an hindex of 52, co-authored 776 publications receiving 15953 citations. Previous affiliations of Mengjie Zhang include Southern University of Science and Technology & Wellington Management Company.
Papers
More filters
Journal ArticleDOI
A Survey on Evolutionary Computation Approaches to Feature Selection
TL;DR: This paper presents a comprehensive survey of the state-of-the-art work on EC for feature selection, which identifies the contributions of these different algorithms.
Journal ArticleDOI
Particle Swarm Optimization for Feature Selection in Classification: A Multi-Objective Approach
TL;DR: The experimental results show that the two PSO-based multi-objective algorithms can automatically evolve a set of nondominated solutions and the first algorithm outperforms the two conventional methods, the single objective method, and the two-stage algorithm.
Book ChapterDOI
Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation
TL;DR: A new model called Deep Reconstruction-Classification Network (DRCN), which jointly learns a shared encoding representation for two tasks: supervised classification of labeled source data, and unsupervised reconstruction of unlabeled target data, is designed.
Proceedings ArticleDOI
Domain Generalization for Object Recognition with Multi-task Autoencoders
TL;DR: In this article, a multi-task autoencoder (MTAE) is proposed to transform the original image into analogs in multiple related domains, which are then used as inputs to a classifier.
Journal ArticleDOI
Particle swarm optimisation for feature selection in classification
TL;DR: Experiments on twenty benchmark datasets show that PSO with the new initialisation strategies and/or the new updating mechanisms can automatically evolve a feature subset with a smaller number of features and higher classification performance than using all features.