First-arrival picking is an essential step in seismic data processing， which can directly affect the accuracy of normal moveout correction， static correction and velocity analysis. At present， affected by background noise and complex near-surface conditions， the picking accuracies of the existing methods are reduced. Based on this， a First-arrival automatic Picking algorithm based on Clustering and Local linear regression （FPCL） was proposed. This algorithm was implemented in two stages： pre-picking and fine-tuning. In the pre-picking stage， the k-means technique was firstly used to find first-arrival cluster. Then the Density-Based Spatial Clustering of Applications with Noise （DBSCAN） technique was used to pick first-arrivals from the cluster. In the fine-tuning stage， the local linear regression technique was used to fill in missing values， and the energy ratio minimization technique was used to adjust error values. On two seismic datasets， compared with Improved Modified Energy Ratio （IMER） method， FPCL had the accuracy increased by 4.00 percentage points and 3.50 percentage points respectively； compared with Cross Correlation Technique （CCT）， FPCL had the accuracy increased by 38.00 percentage points and 10.25 percentage points respectively； compared with Automatic time Picking for microseismic data based on a Fuzzy C-means clustering algorithm （APF）， FPCL had the accuracy increased by 34.50 percentage points and 3.50 percentage points respectively； compared with First-arrival automatic Picking algorithm based on Two-stage Optimization （FPTO）， FPCL had the accuracy increased by 5.50 percentage points and 16.25 percentage points respectively. The above experimental results show that FPCL is more accurate.

Concerning the problems of the difficulties in obtaining， the limitation of labels， and the high cost of labeling of shale gas reservoir data， a Multi-standard Active query Multi-label Learning （MAML） algorithm was proposed. First of all， with the consideration of the informativeness and representativeness of the samples， the preliminary processing was performed on the samples. Secondly， the sample richness constraints including attribute differences and label richness were added， on this basis， the valuable samples were selected and the labels of these samples were queried. Finally， a multi-label learning algorithm was used to predict the labels of the remaining samples. Through experiments on eleven Yahoo datasets， the MAML algorithm was compared with popular multi-label learning algorithms and active learning algorithms， and the superiority of the MAML algorithm was proved. Then， the experiments were extended to four real shale gas well logging datasets. In these experiments， compared with the multi-label learning algorithms： Multi-Label Multi-Label K-Nearest Neighbor （ML-KNN）， BackPropagation for Multi-Label Learning （BP-MLL）， multi-label learning with GLObal and loCAL label correlation （GLOCAL） and active learning by QUerying Informative and Representative Examples （QUIRE）， the MAML algorithm improved the average prediction accuracy of comprehensive quality of shale gas reservoirs by 45 percentage points， 68 percentage points， 68 percentage points， and 51 percentage points， respectively. The practicability and superiority of the MAML algorithm in the prediction of shale gas reservoir sweet spots are fully proved by these experimental results.

Some researchers suggest replacing concept lattices with concept sets in recommendation field due to the high time complexity of concept lattice construction. However， the current studies on concept sets do not consider the role of approximate concepts. Therefore， approximate concepts were introduced into recommendation application， and a genetic algorithm based Approximate Concept Generation Algorithm （ACGA） and the corresponding recommendation scheme were proposed. Firstly， the initial concept set was generated through the heuristic method. Secondly， the crossover operator was used to obtain the approximate concepts by calculating the extension intersection set of any two concepts in the initial concept set. Thirdly， the selection operator was used to select the approximate concepts meeting the conditions according to the similarity of extensions and the relevant threshold to update the concept set， and the mutation operator was adopted to adjust the approximate concepts without meeting the conditions to meet the conditions according to the user similarity. Finally， the recommendation to the target users was performed according to the neighboring users’ preferences based on the new concept set. Experimental results show that， on four datasets commonly used by recommender systems， the approximate concepts generated by ACGA algorithm can improve the recommendation effect， especially on two movie scoring datasets， compared with Probabilistic Matrix Factorization （PMF） algorithm， ACGA algorithm has the F1-score， recall and precision increased by nearly 78%， 104% and 57% respectively； and compared with K-Nearest Neighbor （KNN） algorithm， ACGA algorithm has the precision increased by nearly 12%.

To improve the performance of k-Nearest Neighbor (kNN) model on class-imbalanced data, a new kNN classification algorithm was proposed. Different from the traditional kNN, for the learning process, the majority set was partitioned into several clusters by using partitioning method (such as K-Means), then each cluster was merged with the minority set as a new training set to train a kNN model, therefore a classifier library was constructed consisting of serval kNN models. For the prediction, using a partitioning method (such as K-Means), a model was selected from the classifier library to predict the class category of a sample. By this way, it is guaranteed that the kNN model can efficiently discover local characteristics of the data, and also fully consider the effect of imbalance of the data on the performance of the classifier. Besides, the efficiency of kNN was also effectively promoted. To further enhance the performance of the proposed algorithm, Synthetic Minority Over-sampling TEchnique (SMOTE) was applied to the proposed algorithm. Experimental results on KEEL data sets show that the proposed algorithm effectively enhances the generalization performance of kNN method on evaluation measures of recall, g-mean, f-measure and Area Under ROC Curve (AUC) on majority set partitioned by random partition strategy, and it also shows great superiority to other state-of-the-art methods.

In order to improve the retrieval efficiency of massive medical images, a new medical image retrieval system was proposed based on distributed Hadoop to solve the low efficiency of medical image retrieval system based on single node. Firstly, the features of medical image were extracted by using Brushlet transform and Local Binary Pattern (LBP) algorithm, and the feature database was stored in the Hadoop Distributed File System (HDFS). Secondly, the Map was used to match the features of retrieval images and medical images in the library, and the matching results of the Map task were collected and sorted by the Reduce function. Finally, the optimum results of medical image retrieval were obtained according to the ordering. The test results show that, compared with other medical image retrieval systems, the proposed system reduces the time of image storage and retrieval, and improves the image retrieval speed.

Locally Weighted Naive Bayes (LWNB) is a good improvement of Naive Bayes (NB) and Discriminative Frequency Estimate (DFE) remarkably improves the generalization accuracy of Naive Bayes. Inspired by LWNB and DFE, this paper proposed Gradually Contracting Spaces (GCS) algorithm to learn parameters of Naive Bayes. Given a test instance, GCS found a series of subspaces in global space which contained all training instances. All of these subspaces contained the test instance and any of them must be contained by others that are bigger than it. Then GCS used training instances contained in those subspaces to gradually learn parameters of Naive Bayes (NB) by Modified version of DFE (MDFE) which was a modified version of DFE and used NB to classify test instances. GSC trained Naive Bayes with all training data and achieved an eager version, which was the essential difference between GSC and LWNB. Decision tree version of GCS named GCS-T was implemented in this paper. The experimental results show that GCS-T has higher generalization accuracy compared with C4.5 and some Bayesian classification algorithms such as Naive Bayes, BaysianNet, NBTree, Hidden Naive Bayes (HNB), LWNB, and the classification speed of GCS-T is remarkably faster than LWNB.

At present, most of the privacy protection schemes are based on sophisticate zero-knowledge protocol or bilinear mapping computation, so their efficiency is low. In order to address this problem, an anonymous negotiation credentials scheme was proposed based on ring signature. On the foundation of anonymous credentials framework, an efficient discrete logarithm based ring signature scheme was constructed to protect the negotiation credentials, compared with two schemes proposed by ZHANG, et al. (ZHANG MING-WU, YANG BO, ZHU SHENG-LIN, et al. Policy-Based Signature Scheme for Credential Privacy Protecting in Trust Negotiation. Journal of Electronics & Information Technology, 2009(1): 224-227) and LIU, et al. (LIU BAILING, LU HONGWEI, ZHAO YIZHU. An efficient automated trust negotiation framework supporting adaptive policies. Proceedings of the Second International Workshop on Education Technology and Computer Science. Washington, DC: IEEE Computer Society, 2010: 96-99) the proposed scheme is more efficient.

Given that the original maximum flow algorithm set a fixed edge capacity to each edge, which caused poor quality and improper size of communities, this paper proposed an improved algorithm for mining Web communities. The algorithm considered the differences between edges in terms of importance, and assigned different capacities to different edges by transforming the significant measurements of pages evaluated by weighted PageRank algorithm to edge-transferring probability scores to measure the importance of edges, and assigning them to corresponding edges as their capacities. The experimental results show that the improved maximum flow algorithm improves the quality of Web community effectively.

The paper defined fractal art based on the essential theory of fractal-chaos, expressed structural means of fractal figures in line with its track and distribution, and made use of these methods to construct a series of M-J fractal-chaos figures, showing the beautiful fine structure of the fractal set. The paper provided a definitely new view and an application base for applying fractal-chaos theory and technique in the area of digital media.

An efficient way calling masking to prevent DPA(Differential Power Analysis) attacks was introduced,and the modified simple fixed-value masking method was spreaded to fixed-value masking method to prevent SODPA(Second-order Differential Power Analysis).

MBSA(Map-based BitSet Associaition Rule) algorithm was presented which used TreeMap class and a compressed BitSet class in Java to store Boolean values. MBSA algorithm scanned the transaction database only once and further database scans were replaced by BitSet logical AND operation, which efficiently speeded up the computation. MBSA algorithm had been applied to mine the association rules of red, green and blue bands associated with crop yield from remote sensing image of crop. It is useful for improve crop production.

A PDAS(Pattern Discovery and Analyzing System) structure for finding user access patterns was designed according to characteristics of Web information. Based on association rule theory, the processing models and algorithms of single-user k-sequence frequent access patterns were presented. Experiments show that frequent access patterns mined by algorithms can assist decision-making to some extent.