Search

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.

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. First, 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. Second, 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 redescribe 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 makes it easy to construct a learning mechanism based on cognition in FPNs.

In this paper we propose a quantum convolutional neural network(QCNN) based chaotic metric classification for chaology scaling-down images in the tensorflow quantum framework. The chaology image is properly downscaled with the measurement of spatial occupancy and granularity introduced by fractal dimension and the dimensionality of the overall input space is reduce before it is fed into the QCNNs quantum circuit for state preparation, quantum convolution and quantum pooling. The experimental results show that QCNN, Hybrid QCNN and Hybrid QCNN with multiple quantum filters have achieved relatively high accuracies on more than 94%, and convergence of these three kinds of QCNN classifier has a small fluctuation which indicates that through this scale transformation the discrepancy among the different quantum hybrid classifiers is minimized to some extent.

The model of attribute information granule based on the method of attribute theory and the problem of fuzzification of attribute information granules are discussed. The concept of information granule given by Zadeh can be explained with an attribute and its qualitative mapping operator. Finally, this study also discusses the reasoning of granulation form of attribute fuzzification information which is based on the fuzzy Petri net, with the good formalisation structure of fuzzy Petri net, as well as its asynchronous, concurrency, uncertainty, and other characteristics which is similar to those of human cognitive activities, enabling the fuzzy Petri net to express the basic characteristics of a cognitive system in the form of computing attribute granules. The results of this study can provide a reference for the establishment of the granular logic model in the uncertain problems and a new interpretation framework for revealing the inherent laws of knowledge uncertainty's change with knowledge granularity, and also provides another new possible approach to the establishment of the machine learning model of fuzzy Petri net.

In this paper, a study on the lithium-ion rechargeable battery based on a petroleum coke anode and a polyaniline cathode is introduced. The new battery is different from other lithium-ion rechargeable batteries in which transition metal oxides are used as the cathode materials. During the charging, Li + cations are intercalated in carbon layers and ClO 4 − anions are simultaneously doped on the aniline chain. During discharging, both Li + and ClO 4 − are removed to the electrolyte solution from the anode and cathode, respectively. This battery avoids safety and poor rechargeability problems because there is no dendrite growth and no changes in morphology. Therefore, the new battery possesses good rechargeable and reversible characteristics.

The state-of-the-art of digital home sensor network is analyzed and studied. A classification mining model for digital home sensor network is proposed. The data collected by the sensor network is preprocessed and mined with classification by utilizing the FP-tree algorithm.Based on this, the temperature, humidity and noise data with respect to a certain appliance are mined. An improved Apriori algorithm is applied to mine them with classification and to obtain the frequent item sets, the frequent patterns and the classification rules.The results can support the safe running and energy-efficient control of household appliances.

The aim of this work was to improve the ambient temperature ionic conductivity of poly(ethylene oxide) (PEO) complex electrolytes. The effects of various plasticizers, such as poly(ethylene glycol) (PEG), monomethoxy poly(ethylene glycol) (MMPEG), dimethoxy poly(ethylene glycol) (DMPEG), were examined. Considering the compatibility between the polymer electrolytes and lithium anode, lithium-treated poly(ethylene glycol) (LPEG) was mainly used as the plasticizer blended into the PEO-LiCF 3 SO 3 complex electrolyte. Conductivities of PEO-based polymer electrolytes are enhanced three orders of magnitude at room temperature.