Shida He, Fei Guo, Quan Zou* and Hui Ding Pages 1 - 20 ( 20 )
Aims: Find a way to reduce the dimensionality of the dataset.
Background: Dimensionality reduction is the key issue of the machine learning process. It doesn’t only improve the prediction performance, but also could recommend the intrinsic features and help to explore the biological expression of the machine learning “black box”.
Objective: A variety of feature selection algorithms are used to select data features to achieve dimensionality reduction.
Methods: First, MRMD2.0 integrated 7 different popular feature ranking algorithms with PageRank strategy. Second, optimized dimensionality was detected with forward adding strategy.
Result: We have achieved good results in our experiments.
Conclusion: Several works have been tested with MRMD2.0. It showed the well performance. Otherwise, it also can draw the performance curves according to the feature dimensionality. If users want to sacrifice accuracy for fewer features, they can select the dimensionality from the performance curves.
Other: We developed friendly python tools together with web server. The users could upload their csv, arff or libsvm format files. Then the web server would help to rank features and find the optimized dimensionality.
Bioinformatics, Feature ranking, Feature selection, machine learning, PageRank, reduction
College of Intelligence and Computing, Tianjin University, Tianjin, College of Intelligence and Computing, Tianjin University, Tianjin, Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu, Center for Informational Biology, University of Electronic Science and Technology of China, Chengdu