Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yuepeng Zhou has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Constructing Cognitive Reasoning and Decision Making Under Attribute Granular Computing Using Fuzzy Petri Nets

    by Ruqi Zhou, Huiyou Chang, Yuepeng Zhou, Jun Xu, Yonghe Lu, Jiali Feng

    From the philosophical point of view, Granular Computing (GrC) attempts to abstract and formalize the way of human cognition to extract a structured thinking mode. Fuzzy Petri Nets (FPNs) have a strong formal description and fuzzy reasoning abilities, which align with human cognitive thinking. However, the traditional FPNs are challenging to describe the following problems: Formally expressing the transformation relations between information granules and information granule levels, and then carrying out formal reasoning and decision-making based on cognitive thinking mode. This paper introduces the qualitative mapping and the qualitative criterion transformation method to explore this problem. Firstly, the problem of attribute information granulation is discussed by using the equivalence relation of attributes. Secondly, qualitative mapping is used to express the transformation relationship between information granules. The transformation relationship between attribute information granule levels is realized by qualitative criterion transformation, and the basic algebraic structure of attribute information granules is given. The basic network elements of FPNs can formally describe the relationships between these information granules. Finally, a cognitive reasoning and decision-making model for the formal description of attribute information granules based on the new FPN is constructed, and the proposed case study verifies the feasibility of the proposed method.


  • Open Access

    Improving the Performance of VGG Through Different Granularity Feature Combinations

    by Yuepeng Zhou, Huiyou Chang, Yonghe Lu, Xili Lu, Ruqi Zhou

    Convolutional neural networks have achieved amazing success in many areas in recent years, and VGG is a widely used convolutional neural network model. However, it has some limitations, such as a large number of parameters, which take up significant memory and thus restrict its application in resource-constrained scenarios such as mobile devices and embedded systems. In convolutional neural network models, the different number of convolutional layers can extract different granularity features, which represent the different levels of importance in the image recognition process. Here, we propose a new VGG architecture with different granularity feature combinations that combine different granularity features from block1, block2, block3, block4, and block5 in VGG. Each block is followed by a local fully connected layer to reduce the dimensionality of the coarse and fine features, and five different granularity features are combined as the input of the first global fully connected layer. By combining the features of different blocks, it can increase information flow from a lower layer directly to a fully connected layer and increase feature reuse without adding too many connections. The addition of five local fully connected layers means an increase in parameters, so we reduce the neuron number in two global fully connected layers to reduce the number of parameters. The well-known datasets CIFAR-10 and MNIST were used to evaluate the network’s classification performance. The experimental results show that the proposed model achieves better training and testing performance than traditional VGGs and reduces the number of parameters.


  • Representation and Reasoning of Fuzzy Knowledge Under Variable Fuzzy Criterion Using Extended Fuzzy Petri Nets

    by Ruqi Zhou, Jiali Feng, Yiqun Chen, Huiyou Chang, Yuepeng Zhou

    Fuzzy knowledge representation and reasoning is one of the key research subjects of artificial intelligence with uncertainty.Currently, Fuzzy Petri Nets (FPNs) cannot describe fuzzy nondeterministic knowledge based on the variable fuzzy criterion clearly. To solve this problem, we present an extended FPN model based on the qualitative mapping and the qualitative criterion transformation. Firstly, the mechanism and the principles of the variable fuzzy criterion under qualitative mapping are introduced. The important theoretical basis of qualitative mapping is detection and integration of perceptual attribute features. Under transition degree function and the qualitative criterion transformation, the qualitative mapping better reflects the cases in which the fuzzy membership criterion is variable. Secondly, we use the characteristics of the qualitative mapping to propose a structure of attribute fuzzy information granule. Based on the logic operation of fuzzy information granule, we re-describe the four fuzzy production rules which are commonly used, and obtain four kinds of fuzzy qualitative judgment rules. They can explicitly express the occurrence process of transition nodes of FPNs, which strengthens the uncertain knowledge representation ability of FPNs. The new method make it easy to construct a learning mechanism based on cognition in FPNs.