When I commenced my postgraduate study, I learnt more methods in pattern recognition and tried to improve them. By applying manifold learning algorithms to the feature extraction step of hyperspectral image classification, my adviser Prof. Chen and me get some steps forward. These works include a Riemannian manifold learning based kNN classifier, a supervised LLE algorithm and a Riemannian manifold learning revised Maximum Likelihood Estimator. All these three proposed methods yield, although in varying degrees, improvements on the classification accuracy.
My master's thesis is proposed to focus on two parts. The first is of developing the interpretation of Autoencoder, which is considered more scientifical and statistical related; and the second part is about applying the model into hyperspectral classification, which includes more engineering works such as coding and tuning parameters. I will post the manuscript out on this site after I finish it.
Generally speaking, I like doing research and I think I am suited for it. When I was in secondary school, I was a winner of a series of academic Olympics competitions in Math and Physics. In my first year of university studying, I won a Freshman Foundation for research on heating radiators. All these achievements, regardless of their trivialness, have convinced and encouraged me to continue research in my twenties.