Junhua Zou

  • Citations Per Year
Learn More
Some modern information systems require temporal and privilege consuming usage of digital objects, but usage control model (UCON) can¿t resolve it most conveniently. So in order to meet these requirements, the author introduces a new access control model - times-based usage control (TUCON). First, the paper introduces the TUCON model and then gives the(More)
The amount of digitally available informaition is growing at an exponential rate. Educational resource systems are in widespread use and knowledge develops and spreads rapidly in quality, quantity, profundity and extension. This paper describes a new model of knowledge element to organize knowledge and to share the educational resource, and presents the(More)
Convolutional neural network (CNN) has developed such a large network size in last few years, so reducing the storage requirement without hurting its accuracy becomes necessary. In this paper, in order to reduce the number of high dimensional feature maps in shallow layers, we propose a feature map selection method, which cuts the feature map number by(More)
Knowledge develops and spreads rapidly in quality, quantity, profundity and extension. Recently, many researchers pay increased attention to knowledge elements. Knowledge elements are useful for knowledge management. This paper describes a new model of knowledge element to organize knowledge, presents the description of the model, and demonstrates the(More)
With the rapid development of information technology, educational resource systems are in widespread use. For the reuse and sharing of resources and function modules, this paper designs the framework of a SOA-Based Educational Resource Services System, and presents its implementation. Besides the common characteristics of SOA, the system is flexible and(More)
Convolutional neural network (CNN), as widely applied to vision and speech, has developed lager and lager network size in last few years. In this paper, we propose a CNN feature maps selection method which can simplify CNN structure on the premise of stabilize the classifier performance. Our approach aims to cut the feature map number of the last(More)
We present a feature maps selection method for convolutional neural network (CNN) which can keep the classifier performance when CNN is used as a feature extractor. This method aims to simplify the last subsampling layer of CNN by cutting the number of feature maps with Linear Discriminant Analysis (LDA). It is shown that our method can stabilize the(More)
  • 1