In order to solve the problem of action localization in video, a weakly supervised method based on template matching was proposed. Firstly, several candidate bounding boxes of the action subject position were given on each frame of the video, and then these candidate bounding boxes were connected in chronological order to form action proposals. Secondly, action templates were obtained from some frames of the training set video. Finally, the optimal model parameters were obtained after model training by using action proposals and action templates. In the experiments on UCF-sports dataset, the method has the accuracy of the action classification increased by 0.3 percentage points compared with TLSVM (Transfer Latent Support Vector Machine) method; when the overlapping threshold is 0.2, the method has the accuracy of action localization increased by 28.21 percentage points compared with CRANE method. Experimental results show that the proposed method can not only reduce the workload of dataset annotation, but also improve the accuracy of action classification and action localization.

Aiming at the problem that the sub-health state of subway door is difficult to identify, a sub-health state identification method based on time series data mining was proposed. First of all, the angle, speed and current data of the subway door motor were discretized by combining multi-scale sliding window method and Extension of Symbolic Aggregate approXimation (ESAX) algorithm. And then, the features were obtained by calculating the distances among the templates under the normal state of the subway door, in which the Principal Component Analysis (PCA) was adopted to reduce feature dimension. Finally, combining with basic features, a hierarchical pattern recognition model was proposed to identify the sub-health state from coarse to fine. The real test data of subway door were taken as examples to verify the effectiveness of the proposed method. The experimental results show that the proposed method can recognize sub-health state effectively, and its recognition rate can reach 99%.

In order to resolve the difficulty in changing the monitoring points of the original network after extending the network topology structure, an incremental election algorithm for incremental network monitoring points was proposed. The greedy algorithm was optimized by the proposed algorithm to obtain the approximate solution of fewer vertices, which used the degree of vertices in the network as the greedy-choice strategy for the weak vertex cover of the graph. While calculating incremental network monitoring point set, only the extended network topology was used to obtain the corresponding monitoring point set of the new network. The obtained incremental monitoring points could be directly added to the collection of the original network monitoring points for the new whole network monitoring point set and the cost of rearranging the whole network monitoring points could be reduced. The experiment results show that the number of vertices of the whole monitoring point set obtained by the proposed incremental selection algorithm is basically the same with that of a new monitoring point set generated by recalculating the whole network topology structure in the new network. The proposed algorithm can be effectively applied to the deployment of actual network monitoring points.

Open geospatial consortium Web Services (OWS) are essential parts for the national and global geospatial data infrastructure construction and have been increasingly adopted to publish the geographic data through the Internet for sharing and interoperation. However, these services are widely dispersed and hard to be recovered once they are inaccessible or need long response time. Focusing on the availability and performance of the OWS, a dynamic task-planning model was generated for monitoring OWS. And, a model-based monitoring workflow and an evaluation model were proposed including evaluation factors and weights. Based on the above models, a special prototype was developed to monitor the services statuses dynamically and evaluate performance considering the history accessibility records. An experiment of Web Map Service (WMS) was done to demonstrate the abilities of the developed prototype system.