In the traditional medical image fusion, it is necessary to manually set the fusion rules and parameters by using prior knowledge, which leads to the uncertainty of fusion effect and the lack of detail expression. In order to solve the problems, a Computed Tomography (CT)/Magnetic Resonance (MR) image fusion algorithm based on improved Generative Adversarial Network (GAN) was proposed. Firstly, the network structures of generator and discriminator were improved. In the design of generator network, residual block and fast connection were used to deepen the network structure, so as to better capture the deep image information. Then, the down-sampling layer of the traditional network was removed to reduce the information loss during image transmission, and the batch normalization was changed to the layer normalization to better retain the source image information, and the depth of the discriminator network was increased to improve the network performance. Finally, the CT image and the MR image were connected and input into the generator network to obtain the fused image, and the network parameters were continuously optimized through the loss function, and the model most suitable for medical image fusion was trained to generate the high-quality image. The experimental results show that, the proposed algorithm is superior to Discrete Wavelet Transformation (DWT) algorithm, NonSubsampled Contourlet Transform (NSCT) algorithm, Sparse Representation (SR) algorithm and Sparse Representation of classified image Patches (PSR) algorithm on Mutual Information (MI), Information Entropy (IE) and Structural SIMilarity (SSIM). The final fused image has rich texture and details. At the same time, the influence of human factors on the stability of the fusion effect is avoided.

Focusing on the electricity user group feature, a residential electricity consumption analysis method based on geographic regularized matrix factorization in smart grid was proposed to explore the characteristics of electricity users and provide decision support for personalized better power dispatching. In the proposed algorithm, customers were firstly mapped into a hidden feature space, which could represent the characteristics of users' electricity behavior, and then k-means clustering algorithm was employed to segment customers in the hidden feature space. In particular, geographic information was innovatively introduced as a regularization factor of matrix factorization, which made the hidden feature space not only meet the orthogonal characteristics of user groups, but also make the geographically close users mapping close in hidden feature space, consistent with the real physical space. In order to verify the effectiveness of the proposed algorithm, it was applied to the real residential data analysis and mining task of smart grid application in Sino-Singapore Tianjin Eco-City (SSTEC). The experimental results show that compared to the baseline algorithms including Vector Space Model (VSM) and Nonnegative Matrix Factorization (NMF) algorithm, the proposed algorithm can obtain better clustering results of user segmentation and dig out certain power modes of different user groups, and also help to improve the level of management and service of smart grid.

To promote the model reuse efficiency of 3D Computer Aided Design (CAD), aiming at the flaw of semantic expression in previous 3D model retrieval systems, a similarity measure method based on model semantic representation of Web Ontology Language (OWL) was presented. Firstly, 3D CAD master model was transformed into structuralized representation model with class-property feature as its basic semantic object. And then, the feature semantic information for matching two models was extracted from OWL representation model to be a quantitative similarity unit. And a method of total weight combining subgraph isomorphism and Tversky algorithm was proposed for similarity measure. Finally, the experiment verified the feasibility and effectiveness of the proposed method. The comprehensive quantitative assessments of the experiment show that the proposed method makes the evaluation benchmark switch from the object itself to the set of semantic description of two object properties, and can objectively reflect the similar degree of the two contrast models.

 Petri nets, as a practical formal language to describe asynchronous concurrent systems, are widely used in many fields, and its formal analysis methods are convenient for computer aided analysis of complex systems. The classical Petri nets which have simplex place type have some restrictions in many application area. Petri net model with process and control places was introduced in this paper, which improved the modelling ability of Petri net and extends its application areas, and its application based on the logics of routing of railway station was also depicted.