The current reversible data hiding algorithms in encrypted domain have the problems that the ciphertext images carrying secret have poor fault tolerance and disaster resistance after embedding secret data， once attacked or damaged， the original image cannot be reconstructed and the secret data cannot be extracted. In order to solve the problems， a new reversible data hiding algorithm in encrypted domain based on secret image sharing was proposed， and its application scenarios in cloud environment were analyzed. Firstly， the encrypted image was divided into n different ciphertext images carrying secret with the same size. Secondly， in the process of segmentation， the random quantities in Lagrange interpolation polynomial were taken as redundant information， and the mapping relationship between secret data and each polynomial coefficient was established. Finally， the reversible embedding of the secret data was realized by modifying the built-in parameters of the encryption process. When k ciphertext images carrying secret were collected， the original image was able to be fully recovered and the secret data was able to be extracted. Experimental results show that， the proposed algorithm has the advantages of low computational complexity， large embedding capacity and complete reversibility. In the （3，4） threshold scheme， the maximum embedding rate of the proposed algorithm is 4 bit per pixel （bpp）， and in the （4，4） threshold scheme， the maximum embedding rate of the proposed algorithm is 6 bpp. The proposed algorithm gives full play to the disaster recovery characteristic of secret sharing scheme. Without reducing the security of secret sharing， the proposed algorithm enhances the fault tolerance and disaster resistance of ciphertext images carrying secret， improves the embedding capacity of algorithm and the disaster recovery ability in the application scenario of cloud environment， and ensures the security of carrier image and secret data.

The diversity between base classifiers and the accuracy of single base classifiers itself are two important factors that affect the generalization performance of ensemble system. Aiming at the problem that the diversity and accuracy are difficult to balance, a selective ensemble algorithm for gene expression data based on Diversity and Accuracy of Weighted Harmonic Average (D-A-WHA) was proposed. The Kernel Extreme Learning Machine (KELM) was used as the base classifier, and the diversity and accuracy of base classifiers were adjusted by D-A-WHA measure. Finally, a set of classifiers with high accuracy and high diversity with other base classifiers were selected to ensemble. The experimental results on UCI gene dataset show that compared with traditional Bagging, Adaboost and other ensemble algorithms, the classification accuracy and stability of the selective ensemble algorithm based on D-A-WHA measure are improved significantly,and it can be applied to the classification of cancer gene expression data effectively.

Since it was not ideal for Extreme Learning Machine (ELM) to deal with non-linear data, and the parameter randomization of ELM was not conducive for generalizing the model, an improved version of ELM algorithm was proposed. The parameters of ELM were optimized by Adaptive Chaotic Particle Swarm Optimization (ACPSO) algorithm to increase the stability of the algorithm and improve the accuracy of ELM for gene expression data classification. The simulation experiments were carried out on the UCI gene data. The results show that Adaptive Chaotic Particle Swarm Optimization-Extreme Learning Machine (ACPSO-ELM) has good stability and reliability, and effectively improves the accuracy of gene classification over existing algorithms, such as Detecting Particle Swarm Optimization-Extreme Learning Machine (DPSO-ELM) and Particle Swarm Optimization-Extreme Learning Machine (PSO-ELM).

Considering the problem that the abnormal features have great similarity so that simple structure and high precision modeling cannot be achieved, a control chart pattern recognition method based on Kernel Principal Component Analysis (KPCA) and neural network was proposed. Firstly, the kernel method was used to translate the nonlinear feature into a higher dimensional linear feature space. Secondly this feature was projected to lower dimensional feature space. Finally the BP neural network classifier was introduced to identify the control chart pattern. This method was verified through stochastic simulation. The result demonstrates that the model can cluster each control chart pattern effectively and improve recognition accuracy.