Real-time eye tracking technology is the key technology of intelligent eye movement operating system. Compared to the technology based on eye tracker, the technology based on webcam has the advantages of low cost and high universality. Aiming at the low accuracy problem of the existing webcam based algorithms only with the eye image features considered, an optimization technology for eye tracking algorithm with head pose analysis introduced was proposed. Firstly, the head pose features were constructed based on the results of facial feature point tracking to provide head pose context for the calibration data. Secondly, a new similarity algorithm was studied to calculate the similarity of the head pose context. Finally, during the eye tracking, the head pose similarity was used to filter the calibration data, and the data with higher head pose similarity to the current input frame was selected from the calibration dataset for prediction. A large number of experiments were carried out on the data of populations with different characteristics. The comparison experimental results show that compared with WebGazer, the proposed algorithm has the average error reduced by 58 to 63 px. The proposed algorithm can effectively improve the accuracy and stability of the tracking results, and expand the application scenarios of webcam in the field of eye tracking.

Aiming at generalized or fuzzy queries, the content of the returned list of Web search engines is clustered to help users to find the desired information quickly. Generaly, the returned list consists of short texts called snippets carring few information which traditional Term Frequency-Inverse Document Frequency (TF-IDF) feature selection model is not suitable for, so the clustering performance is very low. An effective way to solve this problem is to extend snippets according to a external knowledge base. Inspired by neural network based word presenting method, a new snippet extension approach based on Word2Vec model was proposed. In the model, Top N similar words in Word2Vec model were used to extend snippets and the extended text was able to improve the clustering performance of TF-IDF feature selection. Meanwhile,in order to reduce the impact of noise caused by some common used terms, the term frequency weight in TF-IDF matrix of the extended text was modified. The experiments were conducted on two open datasets OPD239 and SearchSnippets to compare the proposed method with pure snippets, Wordnet based and Wikipedia based feature extensions. The experimental results show that the proposed method outperforms other comparative methods significantly in term of clustering effect.

In order to improve the discriminative ability of dictionary, a dictionary learning algorithm based on Fisher discriminative criterion constraint of the atoms was proposed, which was called Fisher Discriminative Dictionary Learning of Atoms (AFDDL). Firstly, the specific class dictionary learning algorithm was used to assign a class label to each atom, and the scatter matrices of within-class atoms and between-class atoms were calculated. Then, the difference between within-class scatter matrix and between-class scatter matrix was taken as the Fisher discriminative criterion constraint to maximize the differences of between-class atoms. The difference between the same class atoms was minimized when the autocorrelation was reduced, which made the same class atoms reconstruct one type of samples as much as possible and improved the discriminative ability of dictionary. The experiments were carried out on the AR face database, FERET face database, LFW face database and the USPS handwriting database. The experimental results show that, on the four image databases, the proposed algorithm has higher recognition rate and less training time compared with the Label Consistent K-means-based Singular Value Decomposition (LC-KSVD) algorithm, Locality Constrained and Label Embedding Dictionary Learning (LCLE-DL) algorithm, Support Vector Guided Dictionary Learning (SVGDL) algorithm, and Fisher Discriminative Dictionary Learning (FDDL) algorithm. And on the four image databases, the proposed algorithm has higher recognition rate compared with Sparse Representation based Classification (SRC) and Collaborative Representation based Classification (CRC).

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.

Concerning the problem of lacking completeness and accuracy in the individuals inference information and scientificity in the overall integration results, which exists in the process of inferring Conditional Probability Table (CPT) in Bayesian network according to expert knowledge, this paper presented a method based on the Dempster-Shafer/Analytic Hierarchy Process (DS/AHP) to derive optimal conditional probability from the expert inference information. Firstly, the inferred information extraction mechanism was proposed to make judgment objects more intuitive and judgment modes more perfect by introducing the knowledge matrix of the DS/AHP method. Then, the construction process of Bayesian network was proposed following an inference sequence of "anterior to later". Finally, the traditional method and the presented method were applied to infer the missing conditional probability table in the same Bayesian network. The numerical comparison analyses show that the calculation efficiency can be improved and the accumulative total deviation can be decreased by 41% through the proposed method. Meanwhile, the proposed method is illustrated to be scientific, applicable and feasible.

Current modeling methodologies are lack of reusability in business modeling.The relations between patterns and question domains were analyzed,then a process of modeling business based on analysis pattern and business pattern was proposed.An example of business modeling of enterprise equipment management by measurement pattern and resource allocation pattern was given.