Many machine learning algorithms can cope well with prediction and classification， but these methods suffer from poor prediction accuracy and F1 score when they are used on medical datasets with small samples and large feature spaces. To improve the accuracy and F1 score of liver transplantation complication prediction， a prediction and classification method of liver transplantation complications based on Transfer Component Analysis （TCA） and Support Vector Machine （SVM） was proposed. In this method， TCA was used for mapping and dimension reduction of the feature space， and the source domain and the target domain were mapped to the same reproducing kernel Hilbert space， thereby achieving the adaptivity of edge distribution. The SVM was trained in the source domain after transferring， and the complications were predicted in the target domain after training. In the liver transplantation complication prediction experiments for complication Ⅰ， complication Ⅱ， complication Ⅲa， complication Ⅲb， and complication Ⅳ， compared with the traditional machine learning and Heterogeneous Domain Adaptation （HDA）， the accuracy of the proposed method was improved by 7.8% to 42.8%， and the F1 score reached 85.0% to 99.0%， while the traditional machine learning and HDA had high accuracy but low recall due to the imbalance of positive and negative samples. Experimental results show that TCA combined with SVM can effectively improve the accuracy and F1 score of liver transplantation complication prediction.

How to present video effectively is the focus and difficulty in the field of multimedia research. A structural description model for video was proposed in this paper. Using the intrinsic structural characteristics of video, the video correlative graph model was constructed, with the shots of video as vertexes of graph, and the similarity between shots as arcs. The spectral properties of video correlative graph were extracted, including the leading eigenvalues, the eigenmode perimeter, eigenmode volume, Cheeger number, inter-mode adjacency matrices and inter-mode edge-distances. Video clustering and video surveillance experiments show the structural description model for video is feasible and effective, and the leading eigenvalues show better performance.

To improve the security of image sharing and encryption, an algorithm which combined the scrambling encryption with sharing technology and pixel diffusion was proposed. Firstly, the Logistic chaotic mapping algorithm was used to generate the parameter of Arnold transform. Secondly, two-dimensional Arnold transform with variable parameters was adopted to scramble pixel positions of the image. Finally, three-dimensional Arnold transform with variable parameters was adopted to diffuse pixel values of the scrambled image, so the image could be decomposed into two images. The experimental results show that the algorithm has a strong sensitive effect on the external keys, resists plaintext attack and differential attack effectively, and possesses favorable avalanche effect. Moreover, there is a close relationship between the internal keys and the original plaintext image.