The paper presents a definition of a hospitals overall competitiveness and expounds its action mechanism, viz. the government plays a guiding role in competition, which constitutes the means via which the subjects of competition seek survival and development, the key basis for a hospital in working out its strategies, and the driving force for a hospitals development. Then it analyzes the features of and the factors affecting a hospitals overall competitiveness and sets forth the evaluation procedure, viz. establishing an evaluation index system, determining and normalizing the standard value for evaluating each index, giving each index a corresponding weight according to its importance and conducting comprehensive evaluation. Next the paper discusses ways of predicting a hospitals overall competitiveness. The steps include: making clear that the purpose of the prediction is to enhance the competitiveness of the hospital in the future, screening the data, selecting the method of prediction, setting up a mathematical prediction model, conducting prediction with the model and evaluating and modifying the evaluation results.

Traditional EP analysis is developed under the condition that the background noises in EP are Gaussian distributed. Alpha stable distribution, a generalization of Gaussian, is better for modeling impulsive noises than Gaussian distribution in biomedical signal processing. Conventional blind separation and estimation method of evoked potentials is based on second order statistics (SOS). In this paper, we propose a new algorithm based on minimum dispersion criterion and Givens matrix. The simulation experiments show that the proposed new algorithm is more robust than the conventional algorithm.
Algorithms ; Artifacts ; Brain ; physiology ; Electroencephalography ; methods ; Evoked Potentials ; physiology ; Humans ; Normal Distribution ; Signal Processing, Computer-Assisted