The number of defect region samples is far less than that of the normal region samples in aircraft engine borescope inspection image defect detection task, and the defect samples cannot cover the whole sample space, which result in poor generalization of the detection algorithms. In order to solve the problems, a new interactive data augmentation method based on style transfer technology was proposed. Firstly, background image and defect targets were selected according to the interactive interface, and the informations such as size, angle and position of the target needed to be pasted were specified according to the background image. Then, the style of background image was transferred to the target image through style transfer technology, so that the background image and the target to be detected had the same style. Finally, the boundary of the fusion region was modified by Poisson fusion algorithm to achieve the effect of natural transition of the connected region. Two-class classification and defect detection were conducted to verify the effectiveness of the proposed method. The testers achieve 44.0% classification error rate for the two-class classification on the dataset with real images and augmented images averagely. In the detection task based on Mask Region-based Convolutional Neural Network (Mask R-CNN) model, the proposed method has the Average Precision (AP) of classification and segmentation improved by 99.5% and 91.9% respectively compared to those of the traditional methods.

Focusing on the information asymmetry problem in the process of lending, in order to integrate different data sources and loan default prediction models more effectively, an ensemble learning training method was proposed, which measured the accuracy and the diversity of learners by Area Under Curve (AUC) value and Q statistics, and an ensemble learning training method named TABAQ (Training Algorithm Based on AUC and Q statistics) was implemented. By empirical analyses based on Peer-to-Peer (P2P) loan data, it was found that the performance of ensemble learning was closely related to the accuracy and diversity of the base learners and had low correlation with the number of base learners, and statistical ensemble performed best in all ensemble learning methods. It was also found in the experiments that by integrating the information sources of borrower side and investor side, the information asymmetry in loan default prediction was effectively reduced. TABAQ can combine the advantages of both information sources fusion and ensemble learning. With the accuracy of prediction steadily improved, the number of forecast errors further reduced by 4.85%.

To solve the problems of low precision and poor generalization performance of traditional image segmentation algorithms on the plant images under bias light in plant factory, a method based on neural network and deep learning for accurately segmenting the plant images under artificial bias light in plant factory was proposed. By using this method, the segmentation accuracy on the original test set of bias light plant images is 91.89% and is far superior to that by other segmentation algorithms such as Fully Convolutional Network (FCN), clustering, threshold and region growth. In addition, this method has better segmentation effect and generalization performance than the above methods on plant images under different color lights. The experimental results show that the proposed method can significantly improve the accuracy of plant image segmentation under bias light, and can be applied to practical plant factory projects.

Concerning that current P2P loan default prediction models are limited by the information asymmetry of lenders and borrowers, and do not take differences between loan lenders into account, a P2P loan default prediction model based on Term Frequency-Inverse Document Frequency (TF-IDF) algorithm of information retrieval was proposed. Firstly, based on the investment utility theory, a loan default prediction model was established by using the information such as lender's historical investment profit rate and loan bid interest rate. Secondly, referred to TF-IDF algorithm of information retrieval, loan lender's reverse investment scale factor was constructed to quantify the lender's differences, and the weight factor in the model were optimized. Experimental results show that the prediction effect of this model is better than those of other models on different data sets, its prediction accuracy increases by an average of 6% compared with other models.

Aiming at the problem of personal privacy protection in Internet car rental scenario, a personal privacy protection mechanism based on blockchain was proposed. Firstly, a framework for personal privacy protection based on blockchain was proposed for solving personal privacy issues exposed in the Internet car rental. Secondly, the design and definition of the model were given by participant profile, database design and performance analysis, and the framework and implementation of the model were expounded from the aspects of granting authority, writing data, reading data and revoking authority. Finally, the realizability of the mechanism was proved by the system development based on blockchain.

Focusing on the issue that edges extracted by state-of-the-art exist some deficiencies including non-continuity, incompleteness, incline, jitter and notches etc., an edge extraction method based on graph theory was proposed, which considered the image as an undirected graph by regarding each pixel as a node and connecting two adjacent nodes in horizontal or vertical direction to constitute a side. The proposed method included three phases:in pixels similarity calculation phase, the weights were given to sides in undirected graph, which represented pixels similarity; in threshold determination phase, the mean of all the weights (the similarity of the whole image) was determined as a threshold; in edge determination phase, when weights on horizontal or vertical sides were smaller than the threshold, the left nodes of horizontal side and the upper nodes of vertical side were retained to constitute edges of the image. The experimental results show that the proposed edge extraction method based on graph theory is suitable for the images with obvious target and background, and can overcome deficiencies including non-continuity, incompleteness, incline, jitter and notches etc., and has anti-noise ability to Speckle noise and Gaussian noise.

To decrease the time of classifier design and training, a new method combining the Clonal Selection Algorithm and K Nearest Neighbor (CSA+KNN) was proposed. Having the image preprocessed and getting the comprehensive features information from geometry and texture feature, the CSA+KNN was used to train and classify the plant leaf samples. The plant leaf database with 100 leaf species was applied to test the proposed algorithm, and the recognition accuracy was 91.37%. Compared with other methods, the experimental results demonstrate the efficiency, accuracy and high training speed of the proposed method, and verify the significance of texture features in leaf recognition. CSA+KNN method broadens the field of plant leaf recognition method, and it can be applied to create digitalized plant specimens museum.

Concerning that the edges of the endocardium and epicardium of the left ventricle in the cardiac Magnetic Resonance Imaging (MRI) images have different directions, a new directional active contour model in curve evolution framework was proposed for segmentation of endocardium and epicardium of the left ventricle. The curve evolution equation included a hybrid geometric flow with edge and region gray characteristics that were obtained from the image itself. The edge-based term in the geometric flow borrowed from extended Dynamic Directional Gradient Vector Flow (DDGVF) with fast marching method was utilized to guide the curve evolution towards the object boundaries with different direction. The region-based term borrowed from Chan-Vese (CV) model was utilized to prevent the curve from leakage under the influence of other edge components. The final curve evolution equation was dealt with level set method. The experimental results for gray and cardiac MRI images show that the proposed method can get better segmentation effects. It has certain application value for realizing myocardium auto-segmentation, evaluation and analysis of heart function based on cardiac MRI images.

The new mechanism of Linux kernel v2.6 - kernel object was analyzed, including the structure, principle and functions of it. A method was provided to simplify the structure of directories.