Search

Random forests (RF) has been widely used in bioinformatics especially in cancer diagnosis. This paper studies the classification scheme of RF from the viewpoint of adaptive k nearest neighbors, analyzes the information loss in RF, and proposes a new voting method called RF-based potential nearest neighbor which can use the information of OOB samples in each tree and show significant improvement. Comparison result on 6 cancer gene expression datasets demonstrated that RF-PN got better predictive accuracy than RF. [ABSTRACT FROM AUTHOR]

Objective: To develop a shock response spectrum test facility for testing space products in the pyrotechnic environments., Method: The natural frequencies of the resonant plate, a key part of the facility, were calculated with finite element method. The dynamic response of the whole system was simulated when the machine was excited by a real shock generated by a dropping hammer. A shock response spectrum test facility was developed under the guide of the simulation results., Result: The resonant plate drop machine could simulate pyrotechnic shock by adjusting the force, the natural frequencies of the plate and the damping materials above and under the plate., Conclusion: The agreement between the measurement and the simulation indicates that the computer simulation results are reliable. It is feasible to use the resonant plate drop machine to simulate pyrotechnic environment.