In order to solve the index calculation problems of high complexity, strong completeness and low efficiency in the filed of financial foreign exchange market monitoring, a novel distributed computing framework for foreign exchange market monitoring based on Spark big data structure was proposed. Firstly, the business characteristics and existing technology framework for foreign exchange market monitoring were analyzed and summarized. Secondly, the foreign exchange business features of single-market multi-indicator and multi-market multi-indicator were considered. Finally, based on Spark's Directed Acyclic Graph (DAG) job scheduling mechanism and resource scheduling pool isolation mechanism of YARN (Yet Another Recourse Negotiator), the Market-level DAG (M-DAG) model and the market-level resource allocation strategy named M-YARN (Market-level YARN) model were proposed, respectively. The experimental results show that, the performance of the proposed distributed computing framework for foreign exchange market monitoring improves the performance by more than 80% compared to the traditional technology framework, and can effectively guarantee the completeness, accuracy and timeliness of foreign exchange market monitoring indicator calculation under the background of big data.

Artificial identification of ischemic stroke lesion is time-consuming, laborious and easy be added subjective differences. To solve this problem, an automatic segmentation algorithm based on 3D deep residual network and cascade U-Net was proposed. Firstly, in order to efficiently utilize 3D contextual information of the image and the solve class imbalance issue, the patches were extracted from the stroke Magnetic Resonance Image (MRI) and put into network. Then, a segmentation model based on 3D deep residual network and cascade U-Net was used to extract features of the image patches, and the coarse segmentation result was obtained. Finally, the fine segmentation process was used to optimize the coarse segmentation result. The experiment results show that, on the dataset of Ischemic Stroke LEsion Segmentation (ISLES), for the proposed algorithm, the Dice similarity coefficient reached 0.81, the recall reached 0.81 and the precision reached 0.81, the distance coefficient Average Symmetric Surface Distance (ASSD) reached 1.32 and Hausdorff Distance (HD) reached 22.67. Compared with 3D U-Net algorithm, level set algorithm, Fuzzy C-Means (FCM) algorithm and Convolutional Neural Network (CNN) algorithm, the proposed algorithm has better segmentation performance.

The rapid development of modern market economy is accompanied by higher risks. Forecasting regional investment in advance can find investment risks in advance so as to provide reference for investment decisions of countries and enterprises. Aiming at the lag of statistical data and the complexity of internal relations in macroeconomic forecasting, a prediction method of Long Short-Term Memory based on Weibo Sentiment Analysis (SA-LSTM) was proposed. Firstly, considering the strong timeliness of Weibo texts, a method of Weibo text crawling and sentiment analysis was determined to obtain Weibo text sentiment propensity scores. Then total investment in the region was forecasted by combing with structured economic indicators government statistics and Long Short-Term Memory (LSTM) networks. The experimental results in four actual datasets show that SA-LSTM can reduce the relative error of prediction by 4.95, 0.92, 1.21 and 0.66 percentage points after merging Weibo sentiment analysis. Compared with the best method in the four methods of AutoRegressive Integrated Moving Average model (ARIMA), Linear Regression (LR), Back Propagation Neural Network (BPNN), and LSTM, SA-LSTM can significantly reduce the relative error of prediction by 0.06, 0.92, 0.94 and 0.66 percentage points. In addition, the variance of the prediction relative error is the smallest, indicating that the proposed method has good robustness and good adaptability to data jitter.

In recent years, facial expression recognition has received extensive attention in education, medicine, psychoanalysis and business. Aiming at the problems of not systematic enough and fuzzy concept of facial expression recognition method, the steps and methods of facial expression recognition were reviewed and discussed. Firstly, the commonly used facial expression databases were introduced and the development of facial expression recognition was reviewed. Then, two aspects of facial expression recognition were introduced, such as facial expression coding and facial expression recognition. The four processes of face facial expression recognition were summarized. The classical algorithms, the basic principles of these algorithms and the comparisons of their advantages and disadvantages were summarized emphatically in the two processes of feature extraction and facial expression classification. Finally, the existing problems and possible development trends in the future of the current facial expression recognition were pointed out.

Concerning the cumbersome programming and low efficiency in parallel power iteration clustering algorithm, a new method for power iteration clustering in distributed environment was put forward based on Spark, a general computational engine for large-scale data processing, and its component GraphX. Firstly, the raw data was transformed into an affinity matrix which can be viewed as a graph by using some kind of similarity measure ment method. Secondly, by using vertex-cut technology, the row-normalized affinity matrix was divided into a number of subgraphs, which were stored on different machines of a cluster. Finally, using the in-memory computational framework Spark, several iterations were performed on the subgraphs stored in the cluster to get a cut of the original graph, and each subgraph of the original graph corresponded to a cluster. The experiments were carried out on datasets with different sizes and different number of executors. Experimental results show that the proposed distributed power iteration clustering algorithm has a good scalability, its running time is negatively correlated with the number of executors, the speedup of the algorithm ranges between 2.09 to 3.77 in a cluster of 6 executors compared with a single executor. Meanwhile, compared with the Hadoop-based power iteration clustering version, the running time of the proposed algorithm decreased significantly by 61% when dealing with 40000 pieces of news.

This paper transfered the problem of the 3D craniofacial registration into the one in 2D parameter domain by using surface parameterization. Firstly, six landmarks on the craniofacial surfaces were calibrated according to the physiological characteristics, and the pose and size of the craniofacial surfaces were normalized by projecting the craniofacial surfaces into a unified coordinate system which was determined by using the six landmarks. Secondly, Least Squares Conformal Mapping (LSCM) was performed for a reference craniofacial surface by pinning two outer corners of the eyes, by which the 2D parameters of the six landmarks were computed. Thirdly, any craniofacial surface could be mapped into a 2D domain using LSCM by pinning the six landmarks. Finally, the 3D point correspondences were obtained by mapping the 2D correspondences into the 3D surfaces. To validate the proposed method, the reference model was deformed into the target one by the Thin Plate Spline (TPS) transform with the corresponding vertices being control points, and the average distance between two corresponding point sets after deformation was computed. By the average distance, the proposed method was compared with the principal axes analysis based ICP (Iterative Closest Point) and the random sampling control points based iterative TPS registration methods. The comparison shows that the proposed approach is more accurate and effective.

For the control allocation problem of flexible fly-wing aircraft with multi-control surfaces, the machine vibration force index was put forward to measure the elastic vibration. Total control allocation model was established, the superior performance of the Estimation of Distribution Algorithm (EDA) was used for solving the model. Firstly the rudder structure was designed, the way of work and control capability of every aerodynamic rudder were analyzed, and the rudder functional configuration was built in accordance with the rudder control efficiency of redundant rudder, elevator aileron and aileron rudder in aerodynamic data. During the control allocation, main performance indices of control allocation were analyzed, the overall multi-objective optimal evaluation function was established, which combined with the equality and inequality constraints, and solved by EDA. The true distribution was estimated by establishing a probability model, during the evolutionary process of EDA, the rudder would be allocated according to the deflection efficiency, the optimal solution was got by combining with the optimization function. At last, the impact of aero wing flexibility on static control performance of the system was analyzed. After considering aeroelasticity, the overshoot and transition time are decreases. The flying quality of flying wing aircraft is significantly improved, the system efficiency is improved by at least 10% after optimization. The simulation results show that the EDA can better solve the control allocation problem, and can improve the dynamic quality of the system, verifying the effectiveness of multi-control surfaces to control allocation.

A new algorithm for Boolean operation of two simple polygons based on minimum circle was presented. Polygon P and Q were initialized to counterclockwise direction, and the edges connecting to each intersection point of P and Q were arranged in sequential order. Then, all minimum circles were found using the minimum turning angle rule. These minimum circles were classified according to edges direction in P and Q. Intersection, union, and difference of the two polygons are corresponding to different kinds of minimum circles. The algorithm run in time O((n+m+k)logd) in a worst presented case, where n and m were the vertex numbers of the two polygons respectively, k was the numbers of intersection points, and d was the number of polygon’s monotonic chain. The algorithm has explicit geometric significance, and well resolves the problems in special cases，such as overlapped edges, and operation edges intersection at the vertex of edges.

Due to the limited resource of security chip, the scheme resisting power analysis attack was researched from two aspects of operation efficiency and withstanding multiple power analysis attacks. A scheme based on Signed Double-based Number System (SDBNS) was presented by coding the key renewably and basic point masking algorithm. According to security analysis, the result shows that the scheme could resist multiple power analysis attacks and promote operation efficiency.