Chinese Word Segmentation （WS） and Part-Of-Speech （POS） tagging can assist other downstream tasks such as knowledge graph construction and sentiment analysis effectively. Existing work typically only uses pure-text information for WS and POS tagging. However， the Web also contains many associated image and video information. Therefore， efforts were made to mine associated clues from this visual information to aid Chinese WS and POS tagging. Firstly， a series of detailed annotation standards were established， and with WS and POS tagging， a multimodal dataset VG-Weibo was annotated using the text and image content from Weibo posts. Then， two multimodal information fusion methods， VGTD （Visually Guided Two-stage Decoding model） and VGCD （Visually Guided Collapsed Decoding model）， with different decoding mechanisms were proposed to accomplish this joint task of WS and POS tagging. Among the above， in VGTD method， a cross-attention mechanism was adopted to fuse textual and visual information and a two-stage decoding strategy was employed to firstly predict possible word spans and then predict the corresponding tags； in VGCD method， a cross-attention mechanism was also utilized to fuse textual and visual information and more appropriate Chinese representation and a collapsed decoding strategy were used. Experimental results on VG-Weibo test set demonstrate that on WS and POS tagging tasks， the F1 scores of VGTD method are improved by 0.18 and 0.22 percentage points， respectively， compared to those of the traditional pure-text method's Two-stage Decoding model （TD）； the F1 scores of VGCD method are improved by 0.25 and 0.55 percentage points， respectively， compared to the traditional pure-text method's Collapsed Decoding model （CD）. It can be seen that both VGTD and VGCD methods can utilize visual information effectively to enhance the performance of WS and POS tagging.

A real-time object detection algorithm YOLO-C for complex construction environment was proposed for the problems of cluttered environment， obscured objects， large object scale range， unbalanced positive and negative samples， and insufficient real-time of existing detection algorithms， which commonly exist in construction environment. The extracted low-level features were fused with the high-level features to enhance the global sensing capability of the network， and a small object detection layer was designed to improve the detection accuracy of the algorithm for objects of different scales. A Channel-Spatial Attention （CSA） module was designed to enhance the object features and suppress the background features. In the loss function part， VariFocal Loss was used to calculate the classification loss to solve the problem of positive and negative sample imbalance. GhostConv was used as the basic convolutional block to construct the GCSP （Ghost Cross Stage Partial） structure to reduce the number of parameters and the amount of computation. For complex construction environments， a concrete construction site object detection dataset was constructed， and comparison experiments for various algorithms were conducted on the constructed dataset. Experimental results demonstrate that the YOLO?C has higher detection accuracy and smaller parameters， making it more suitable for object detection tasks in complex construction environments.

With regard to the characteristics of randomness and fuzziness in service trust under computing environment, and lack of consideration in timeliness and recommend trust, a service trust evaluation method based on weighted multiple attribute cloud was proposed. Firstly, each service evaluation was given weight by introducing time decay factor, the evaluation granularity was refined by trust evaluation from multiple attribute of service, and direct trust cloud could be generated using the weighted attribute trust cloud backward generator. Then, the weight of recommender could be confirmed by similarity of evaluation, and recommended trust cloud was obtained by recommend information. Finally, the comprehensive trust cloud was obtained by merging direct and recommended trust cloud, and the trust rating could be confirmed by cloud similarity calculation. The simulation results show that the proposed method can improve the success rate of services interaction obviously, restrain malicious recommendation effectively, and reflect the situation of service trust under computing environment more truly.

To solve the problem of traditional interpolation and model-based methods usually leading to decrease of the contrast and sharpness of images, a reverse curvature-driven Super-Resolution (SR) algorithm based on Taylor formula was proposed. The algorithm used the Taylor formula to estimate the change trend of image intensity, and then the image edge features were detailed by the curvature of isophote. Gradients were used as constraints to inhibit the jagged edges and ringing effects. The experimental resluts show that the proposed algorithm has obvious advantages over the conventional interpolation algorithm and model-based methods in clarity and information retention, and its result is more in line with human visual effects. The proposed algorithm is more effective than traditional iterative algorithms for reverse diffusion based on Taylor expansion is implemented.

Video key frame reflects the main content of the video sequence. Video key frame extraction is one of the key steps for video content retrieval. Although there are some effective key frame extraction algorithms, these algorithms still have some problems such as heavy load of computing, difficulty in choosing suitable threshold value for different type sequences and limited types of videos. In this paper, a video key frame extraction method based on frame dominant color was proposed. Firstly, every frame was simplified by the dominant color which was obtained by octree structure color quantization algorithm. Secondly, shot boundary was detected according to the color similarity between adjacent frames. Finally, key frames were decided from candidate frames by K-means clustering algorithm. The experimental results show that the proposed method is simpler in computation and requires lower time and space complexity than other key frame extraction methods.

This paper referred to the common routing protocol threats appearing in MANET and analyzed the properties of satellite network to get possible security threats of Location-Assisted On-demand Routing (LAOR) and what to do to make the protocol safer. It used Id-based cryptography to mainly realize mutual authentication between nodes and protection of the integrity of routing control packet by signature using each nodes private key. Finally strand space was used to analyze the improved routing protocol, and proved it satisfied plausible routing, and was secure.

Chinese comparative sentences are more focused in the field of linguistics. Using machine learning methods to identify comparative sentences, however, has only just started. According to the basic principle of the association rules mining algorithm, a method of comparative sentences based on the associated feature vocabulary was proposed. This method regarded word and part of speech as basic elements, defined the connecting way between the table definition core words and interdependent relationship words, and used the Support Vector Machine (SVM) classifier for the identification of comparative sentences. The experimental results show that this method can effectively identify Chinese comparative sentences, and achieves good results in precision, recall and F-measure.

According to the influence of approximate skin color information or complex background, it is hard to get precise gesture contour by hand gesture segmentation, which will have effect on later gesture recognition rate and real-time interaction. Therefore, this paper proposed a gesture recognition method based on the BOF-SVM (Bag Of Features-Support Vector Machine). At first, local invariant features of the gesture images were extracted by the Scale Invariant Feature Transformation (SIFT) algorithm. Then the visual code book was generated by gesture local eigenvector (SIFT descriptors) through K-means clustering. And visual code set of every image got quantized by visual code book. As a result, the characterized vector of gesture images with fixed dimensional was obtained to train multi-class SVM classifier. This method only needed to frame the gesture area instead of segmenting gesture accurately. The experimental results indicate that the average recognition rate of the nine interactive hand gestures based on this method can reach 92.1%. Besides, it has good robustness and efficiency, and can adapt to the changes of environment.

Abstract：To the blemish of PERT in the project plan management, this thesis introduces a kind of optimization arithmetic which is called PSO and offers an advanced technique to PERT on PSO. This technique using the method of treating with the time of the tasks in project and the theory of PSO made a advantage to the traditional PERT. The experimental results show that the technique show a more advantage, more exact ration controlling standard, can get better controlling and regulating ability to the whole project process compared with the traditional PERT.

The KNX/EIB communications protocol, using CSMA/CA mechanism in its link layer to resolve the communication conflicts, has improved the KNX/EIB network conflict prevention capacity. However, it results in the jitter of transmission delay to a great extent, among the same level command frame data. Consequently, the real-time of transmission has been slashed. In this paper, the improved method named KNX/EIB-A was proposed for the real-time of the KNX/EIB without altering the original KNX/EIB protocol, which applied a scheduling program between the application layer and user application program of the KNX/EIB communication protocol, and changed the original distributed equal structure into a master-slave structure, and dispatched the sending of the data frames. Finally, the analysis and realization of the KNX/EIB-A prototype prove that it improves the real-time performance of the protocol by reducing the transmission delay jitter.

Because the algorithm of cloud threshold often generates boundary effect, this paper proposed an improved algorithm based on wavelet transform and homomorphic filter. The image with cloud was decomposed by wavelet transform to find the proper number of demarcation levels. Cloud could be removed by making homomorphic filtering to the higher level coefficients, while giving the lower level detailed coefficients and the approximation coefficients some weight factors respectively. The three parts of coefficients were reconstructed and fused to get processed result. The experimental results indicate that the proposed algorithm can remove the thin cloud cover effectively, maintain the details better and prevent producing the boundaries.