Browsing by Author "Che, Zhen-Hua"

Now showing 1 - 2 of 2

AN INTERACTIVE PERSPECTIVE MODEL BASED ON AHP AND 0-1 IP FOR THE STAFF JOB ROTATION OF NURSES IN LARGE-SCALE HOSPITALS
(2011-02-01)
Che, Zhen-Hua
;
Kuo, Han-Yuan
;
Che, Zhen-Guo
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
Job rotation is an efficient approach to training staff nurses in diversified skills, enabling them to be more capable of taking care of their patients. This paper focuses on application research that emphasizes the development of a new systematic approach to accomplishing job rotation for staff nurses in a large-scale hospital system with branches located in different geographical areas. The proposed approach is based on the analytic hierarchy process (A HP) methodology and 0-1 integer programming (IP) for implementing job rotation with multiple factors and interactive perspectives. The A HP method is employed to assess and set the weights for each nurse candidate and job/department candidate. The 0-1 IP model applies these weights to find an optimal rotation plan. The results show that the proposed approach is able to help decision makers provide feasible and quality solutions for achieving job rotation in a hospital system.
FEED-FORWARD NEURAL NETWORKS TRAINING: A COMPARISON BETWEEN GENETIC ALGORITHM AND BACK-PROPAGATION LEARNING ALGORITHM
(2011-10-01)
Che, Zhen-Guo
;
Chiang, Tzu-An
;
Che, Zhen-Hua
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
This study discusses the advantages and characteristics of the genetic algorithm and back-propagation neural network to train a feed-forward neural network to cope with weighting adjustment problems. We compare the performances of a back-propagation neural network and genetic algorithm in the training outcomes of three examples by referring to the measurement indicators and experiment data. The results show that the back-propagation neural network is superior to the genetic algorithm. Also, the back-propagation neural network has faster training speed than the genetic algorithm. However, the back-propagation neural network has the shortcoming of overtraining, while the genetic algorithm does not. The experiment result proves that the back-propagation neural network yields better outcomes than the genetic algorithm.