Painting image sentiment prediction is a research hotspot in affective computing. At present, there are few sources of abstract paintings and a small sample size; most of its sentiment analysis uses low-level features of the image, and the accuracy is not high. To resolve these problems, a sentiment prediction of small sample abstract painting image based on feature fusion was proposed. First, the relationship between the basic elements of abstract painting (point, line, plane and color) and human emotions in abstract art theory was analyzed, and according to these theories, the low-level features of abstract painting image were quantified. Second, the transfer learning algorithm was adopted to obtain the parameters from large sample data in the pre-training network, and these parameters were transferred to the target model, and then the target model was fine-tuned on the small sample data to obtain the high-level features of the image. Finally, the low-level and high-level features were fused linearly, and the multi-class Support Vector Machine (SVM) was used to achieve the sentiment prediction of abstract painting image. The experiments were carried out on three small sample abstract painting datasets, and the proposed method was compared with the methods of directly using low-level features. The results show that the classification accuracy of the proposed algorithm is improved, confirming its effectiveness in sentiment research of small sample abstract painting.

The advent of big data era elicits the importance of visualization. As an import data analysis method, visual analytics explores the cognitive ability and advantages of human beings, integrates the abilities of human and computer, and gains insights into big data with human-computer interaction. In view of the characteristics of large amount of data, high dimension, multi-source and multi-form, the visualization method of large scale data was discussed firstly: 1) divide and rule principle was used to divide big problem into a number of smaller tasks, and parallel processing was used to improve the processing speed; 2) the means of aggregation, sampling and multi-resolution express were used to reduce data; 3) multi-view was used to present high dimensional data. Then, the visualization process of flow data was discussed for the two types of flow data, which were monitoring and superposition. Finally, the visualization of unstructured data and heterogeneous data was described. In a word, the visualization could make up for the disadvantages and shortcomings of computer automatic analysis, integrate computer analysis ability and human perception of information, and find the information and wisdom behind big data effectively. However, the research results of this theory are very limited, and it is faced with the challenge of large scale, dynamic change, high dimension and multi-source heterogeneity, which are becoming the hot spot and direction of large data visualization research in the future.

In order to further improve the resolution of existing image super-resolution methods, a High-performance Deep Convolution neural Network (HDCN) was proposed to reconstruct a fixed-scale super-resolution image. By cascading several HDCN models, the problem that many traditional models could not upscale images in alternative scale factors was solved, and a deep edge filter in the cascade process was introduced to reduce cascading errors, and highlight edge information, High-performance Cascade Deep Convolutional neural Network (HCDCN) was got. The super-resolution image reconstruction experiment was carried out on high-performance cascade deep convolution neural network (HCDCN) model on Set5 and Set14 datasets. The experimental results prove the effectiveness of introducing the deep edge-aware filter. By comparing the performance evaluation results of HCDCN method and other image super-resolution reconstruction method, the superior performance of HCDCN method is demonstrated.

A computational method utilizing divide-and-conquer and incremental computation was proposed to calculate the structure of attribute granule of an inseparable information system. Firstly, the rule that how the structure of attribute granule of an information system changed when new Functional Dependency (FD) was added to the functional dependency set of an information system was studied and the increment theorem of information system structure was proved. Secondly, by removing a part of the functional dependency, an inseparable information system could become a separable information system and the structure of the separable information system was calculated by using decomposition theorem. Thirdly, the removed functional dependency was added to the separable information system and the structure of the original information system was calculated by using increment theorem. Lastly, the algorithm to calculate the structure of attribute granule of inseparable information system was given and its complexity was analyzed. The complexity of the direct calculation of the structure of attribute granule of information system was O(n×m×2ⁿ), and the proposed method could reduce the complexity to below O(n×k×2ⁿ)(k<m), and when k=1,2, the complexity could be reduced to O(n₁×m₁×2^n₁)+O(n₂×m₂×2^n₂)(n=n₁+n₂,m=m₁+m₂). The theoretical analysis and practical calculation demonstrate that the proposed method can effectively reduce the computational complexity of the structure of attribute granule of an inseparable information system.

Based on functional dependency over the attributes, the concept of attribute information granule of information system was proposed, and a method to calculate the structure of attribute granule of separable information system was given. Firstly, the separability of information system was defined, and it was proved that if an information system is separable, the structure of attribute granule of the system can be decomposed into the Cartesian product of the structures of attribute granules of its sub-systems. Secondly, the method to judge the separability of an information system and the decomposition algorithm of information system were given. Lastly, the complexity of the proposed method was analyzed. And the analysis result demonstrates that the complexity of the direct calculation of the structure of attribute granule of information system is O(2ⁿ), and the proposed method can reduce it to O(2^n₁+2^n₂+…+2^n_k) where n=n₁+n₂+…+n_k. The theoretical analysis and example show that the method is feasible.

In order to solve the problems of digital image encryption algorithm including scheme complexity and poor security, a DNA fusion image encryption algorithm based on chaotic system was proposed. Firstly, the image was scrambled by Baker transform to obtain the DNA sequence. Then, Logistic map was used to generate chaotic sequence. Finally, the DNA sequence was encrypted. The method has good sensitivity to initial values and strong ability of anti-statistical and anti-differential attacks. The simulation results show that the algorithm is not only simple, but also has good encryption effect and high security.

Considering the problems caused by the traditional association rules visualization approaches, including being unable to display the frequent pattern and relationships of items, unitary express, especially being not conducive to represent multi-schema association rules, a new visualizing algorithm for multi-valued association rules mining was proposed. It introduced the redefinition and classification of multi-valued attribute data by using conceptual lattice and presented the multi-valued attribute items of frequent itemset and association rules with concept lattice structure. This methodology was able to achieve frequent itemset visualization and multi-schema visualization of association rules, including the type of one to one, one to many, many to one, many to many and concept hierarchy. At last, the advantages of these new methods were illustrated with the help of experimental data obtained from demographic data of a province, and the source data visualization, frequent pattern and association relation visual representation of the demographic data were also achieved. The practical application analysis and experimental results prove that the schema has more excellent visual effects for frequent itemset display and authentical multi-schema association rules visualization.

For the poor readability and understandability with the existing display form for genealogical data, this paper presented visualization for genealogical data with metagraph. In the metagraph representation of genealogy, the generating set comprised of all persons in the family; each edge represented only "parents-child" relationship. An edge in the metagraph representation of genealogy was a pair consisting of an invertex and an outvertex, the invertex consisted of two nodes of the marital relationship, and the outvertex represented a single child node set. The experimental results show that the number of the edges in the metagraph form is almost half of common form in the case of the same data, and the visualizing effect is significantly improved. At the same time, the proposed methodology has a guiding role in the mathematical modeling of genealogy, the research of genealogy visualization and the improvement of genealogical information system.

Concerning the MPC8247 target system based on PowerPC, the device tree was discussed and an embedded Linux system was developed, including the transplant and deployment of U-Boot, Linux kernel, Device Tree Blob (DTB) and Ramdisk file system. The actual operation of the system shows that the device tree file is correct, and the system design is rational and efficient.

The existing methods of malware feature selection and reduction methods were studied. Current attribute reduction methods of malware do not take advantage of the information of feature selection evaluation function. So a method was proposed to order all features based on their value of information gain and their size, and used attributes order reduction method to get a reduction. An analysis of spatial and temporal complexity was given, and the overall design was given. Test results show that the application of attributes order reduction can obtain fewer reduction results in less time, and get higher classification accuracy using the reduction result.

In the existing heterogeneous Wireless Sensor Network (WSN) architecture, various data link layers lack a common structure. To solve this problem, the concept of attribute assembly layer was proposed. Based on the modeling and simulation platform of Ptolemy Ⅱ, the authors modeled the attribute assembly layer and the data link layer respectively, and then put forward an adaptive architecture for WSN. In the attribute assembly layer, the attribute factory was designed to classify various prototypes of communication protocols and encapsulate upper applications, while the assembly factory was designed to generate packet headers and distribute packets to different networks. This architecture unifies the data link layers for heterogeneous networks, and it is well compatible with the existing platforms, communication protocols and network mechanisms. What's more, it can be applied to potential communication protocols and mechanisms. The experimental results show that the communication systems based on this architecture have low memory occupation and time cost, and also have good adaptive capacity.

Research and design of three generation file system for smart card on flash memory were made, introducing log technology and power failure protection to assure smart cards file system reliability, data consistency and integrality. Memory space was assigned according to byte. Mechanisms of valid space collection and reuse improve the using rate of memory space. Technology of wear leveling and page mapped prolong the flash storage life-span, and the design of efficiency memory management improves the rate of data retrieval. Consequently, the whole performance of smart card is strengthened. The simulation makes sure the file system fit 3G EVDO card.

A conception of missile intelligent fault diagnosis technology based on artificial immune system was presented,the fault diagnosis cell model and the fault diagnosis gene model were analyzed.How to create and evolve the fault diagnosis gene model was introduced,and the intelligent fault diagnosis principle based on artificial immune system was discussed.

The intelligence and human-computer interaction of existing answering system are not good enough. To overcome the shortages, this paper presented a complete intelligent question answering System (IQAS) implementation. To enhance the veracity of matching between question from student and questions in database, the algorithm of question similarity was researched. By using auto segmenting algorithm, question similarity transformed the relativity of collections. A good study model was found to optimize segmenting weights from BP model, a supervised-machine learning task. Test results show that the algorithm can help IQAS improve veracity and intelligence and has practical value.