**4. Conclusions**

Since existing rotation forest-based techniques fail to take account of the discriminative information of training samples during feature extraction, this paper proposed a semi-supervised rotation forest that uses the weighted semi-supervised local discriminant analysis method to jointly utilize the class discriminative information and local structural information provided by the labeled and unlabeled samples, respectively. The proposed algorithm aims to find the projection directions that provide better class separability, thus enhancing the performance of existing rotation forest algorithms. Furthermore, the proposed algorithm does not need additional parameters compared with the classical rotation forest method, which makes it easy to implement. Experiments have shown that the proposed algorithm outperforms several typical ensemble learning methods. Our future work will aim to reduce the computational time and assemble some other state-of-the-art machine learning algorithms.

**Acknowledgments:** This work was supported by the National Natural Science Foundation of China under Grant 61271348 and 61471148, and in part by the Foundation of Harbin Excellent Scholar under Grant 2015RAXXJ048. The authors would like to thank D. Landgrebe of Purdue University, West Lafayetter, Indiana, for providing the AVIRIS Indian Pines data set; P. Gamba of the University of Pavia, Italy, for providing the Pavia University data sets; and the Hyperspectral Image Analysis group and the NSF-NCALM at the University of Houston for providing the Houston University data set.

**Author Contributions:** Xiaochen Lu and Junping Zhang conceived and designed the experiments; Xiaochen Lu and Tong Li performed the experiments; all authors analyzed the data and reviewed the study; Xiaochen Lu wrote the paper.

**Conflicts of Interest:** The authors declare no conflict of interest.
