The Automated Essay Scoring (AES) technology can automatically analyze and score the essay, and has become one of the hot research problems in the application of natural language processing technology in the education field. Aiming at the current AES methods that separate deep and shallow semantic features, and ignore the impact of multi-level semantic fusion on essay scoring, a neural network model based on Multi-Level Semantic Features (MLSF) was proposed for AES. Firstly, Convolutional Neural Network (CNN) was used to capture local semantic features, and the hybrid neural network was used to capture global semantic features, so that the essay semantic features were obtained from a deep level. Secondly, the feature of the topic layer was obtained by using the essay topic vector of text level. At the same time, aiming at the grammatical errors and language richness features that are difficult to mine by deep learning model, a small number of artificial features were constructed to obtain the linguistic features of the essay from the shallow level. Finally, the essay was automatically scored through the feature fusion. Experimental results show that the proposed model improves the performance significantly on all subsets of the public dataset of the Kaggle ASAP (Automated Student Assessment Prize) champion, with the average Quadratic Weighted Kappa (QWK) of 79.17%, validating the effectiveness of the model in the AES tasks.

As a key module of the question answering system, question classification is also a key factor that restricts the retrieval efficiency of the question answering system. Aiming at the problems of complicated semantic information and large differences of user questions in agricultural question answering system, in order to meet the needs of users to quickly and accurately obtain classification results of common crop disease questions, the question classification model of common crop disease question answering system based on Bidirectional Encoder Representations from Transformers (BERT) was constructed. Firstly, the question dataset was preprocessed. Then, Bidirectional-Long Short Term Memory (Bi-LSTM) self-attention network classification model, Transformer classification model and BERT-based fine-tuning classification model were constructed respectively, and the three models were used to extract information of questions and train question classification model. Finally, the BERT-based fine-tuning classification model was tested and the impact of dataset size on classification results was explored. The experimental results show that, the BERT-based fine-tuning common crop disease question classification model has the classification accuracy, precision, recall, weighted harmonic mean of accuracy and recall higher than those of the Bi-LSTM self-attention network classification model and the Transformer classification model by 2-5 percentage points respectively. On Common Crop Disease Question Dataset (CCDQD), it can obtain the highest accuracy of 92.46%, precision of 92.59%, recall of 91.26%, and weighted harmonic mean of accuracy and recall of 91.92%. The BERT-based fine-tuning classification model has advantages of simple structure, few parameters and fast speed, and can efficiently classify common crop disease questions accurately. So, it can be used as the question classification model for the common crop disease question answering system.

Simultaneous Localization and Mapping (SLAM) is a key technology for robots to realize autonomous navigation in unknown environments. Aiming at the poor real-time performance and low accuracy of the commonly used RGB-Depth (RGB-D) SLAM system, a new RGB-D SLAM system was proposed to further improve the real-time performance and accuracy. Firstly, the Oriented FAST and Rotated BRIEF (ORB) algorithm was used to detect the image feature points, and the extracted feature points were processed by using the quadtree-based homogenization strategy, and the Bag of Words (BoW) was used to perform feature matching. Then, in the stage of system camera pose initial value estimation, an initial value which was closer to the optimal value was provided for back-end optimization by combining the Perspective n Point (P nP) and nonlinear optimization methods. In the back-end optimization, the Bundle Adjustment (BA) was used to optimize the initial value of the camera pose iteratively for obtaining the optimal value of the camera pose. Finally, according to the correspondence between the camera pose and the point cloud map of each frame, all the point cloud data were registered in a coordinate system to obtain the dense point cloud map of the scene, and the octree was used to compress the point cloud map recursively, so as to obtain a 3D map for robot navigation. On the TUM RGB-D dataset, the proposed RGB-D SLAM system, RGB-D SLAMv2 system and ORB-SLAM2 system were compared. Experimental results show that the proposed RGB-D SLAM system has better comprehensive performance on real-time and accuracy.

Focusing on the precise definition of information measures for interval-valued fuzzy soft sets, the distance measure, the similarity measure, the entropy measure, the inclusion measure, and the subsethood measure of interval-valued fuzzy soft sets were introduced. A series of formulae of information measures were presented, and their transformation relationships were discussed. Then, combining the characteristics of interval-valued fuzzy soft sets, a clustering algorithm based on similarity measure was explored. It emphasized the clustering of similar level knowledge of experts who gave the evaluation of objects. Meanwhile, the computational complexity of the algorithm was discussed. Finally, a practical example was given to prove that the proposed algorithm can effectively handle the clustering problem of experts.

The effect of the existing Total Variation (TV) method for image denoising is not ideal, and it is not good at keeping the characteristics of image edge and texture details. A new method of image denoising based on rational-order differential was proposed in this paper. First, the advantages and disadvantages of the present image denoising methods of TV and fractional differential were discussed in detail, respectively. Then, combining the model of TV with fractional differential theory, the new method of image denoising was obtained, and a rational differential mask in eight directions was drawn. The experimental results demonstrate that compared with the existing denoising methods, Signal Noise Ratio (SNR) is increased about 2 percents, and the method retains effectively the advantages of integer and fractional differential methods, respectively. In aspects of improving significantly high frequency of image and keeping effectively the details of image texture, it is also an effective, superior image denoising method. Therefore, it is an effective method for edge detection.

Opportunistic network routing algorithm based on geographic location information in DIrection based Geographic routing scheme (DIG) has the problems of large delay and low success rate, which is due to that DIG algorithm makes the waiting time of the data in the cache too long and cannot guarantee the data-carrying node move to the destination node. To solve these problems, Geographic Routing algorithm based on Directional Data Transmission (GRDDT) was proposed. The algorithm used a new data forwarding mechanism and a more effective use of the neighbor list information, effectively avoiding the appearance of the above circumstances, so as to reduce data packet transmission delay and to improve the success rate. OPNET simulation results show that, the performance of transmission delay and success rate of GRDDDT algorithm are improved compared with DIG.

Intensity inhomogeneity often exists in Magnetic Resonance (MR) images, which is due to the smooth bias field caused by the deficiency of the device. Traditional intensity-based segmentation algorithms often assume the uniform intensity belonging to the object and background, respectively. Therefore, these algorithms fail to successfully segment image with intensity inhomogeneity. This paper proposed a local region fitting model for simultaneous segmentation and bias correction. The model is built based on the intensity property in the local region to build an energy function with respect to the intensity, bias field function and the region indicating function. Then, this energy function was optimized with respect to the intensity, bias field and the indicating function, respectively. The segmentation and bias field estimation would be conducted simultaneously finally. The experimental results on the real MR brain images demonstrate the advantages of the proposed method over variational level set approach.

An improved Differential Evolution (DE) algorithm was proposed to solve the problem of premature convergence and improve the computational efficiency of DE. Firstly, different strategies with different parameter values were adopted to enrich the population diversity. Secondly, a new evaluation index was established to determine the suitable combination to match different phases of the search process. Finally, the evolution process was divided into many subprocesses to eliminate the negative effect of the previously selected combination. The contrast experimental results on ten classical Benchmark functions show that the proposed algorithm has a relatively better performance.

Concerning that the lesion areas of leukoaraiosis in Magnetic Resonance (MR) image present hyper intense signal on T ₂ flair sequence, a level set segmentation method based on C-V model was proposed. First, the C-V model was improved to avoid the re-initialization; second, the Otsu threshold method was used for image's pre-segmentation, and then the image's pre-segmentation result was directly used as the initial contour for the improved C-V model; finally, the segmentation result was obtained by curve evolution. The results show that the proposed segmentation method can get better separation effects, and realize fast auto-segmentation. It has certain application value for clinical diagnosis and prognosis on leukoaraiosis.

According to the problem that Glowworm Swarm Optimization (GSO) cannot acquire solutions exactly and converge slowly in the later period for solving the multimodal function，an improved GSO algorithm combined with luciferinfactor, which can adaptively adjust step, was proposed. The simulation results show that the improved Self-Adaptive Step Glowworm Swarm Optimization (ASGSO) can search for global optimization more quickly and precisely.

A robust image-adaptive public watermarking technique based on discrete wavelet transform(DWT) was proposed in this paper.By taking full advantage of the masking characteristics of the human visual system(HVS),a binary watermark was embedded into the host image by modifying different wavelet subbands coefficients that were corresponded.The blind watermark was realized as the original image don’t be needed when extracting watermark.Modifying some parameters could get a best point.The experimental results show that the proposed algorithm provides higher embedding capacity and robust to common image processing operations and geometric distortions.So a conclusion can be made that the proposed technique is practical.

A distributed, scalable, and self -organized model HMCON（Hierarchical Multicast Overlay Network) was presented based on two-layer P2P network. This model balanced the load on every participant by delivering the source signal on several complementary multicast trees. This forest of trees could significantly improve the quality of communication. The simulation results on NS-2 using ITU-T E-Model verify the effectiveness of HMCON.

This paper introduced a scheme of spam E-mail filtering system which works before mail server independently. This spam filtering system includes E-mail capturing module, E-mail filtering module, database and administrant module. This paper recommended the E-mail filtering module which adopts the heuristic filtering technique based on the Bayesian Statistic method detailedly. Finally,a testing result of the system was given in this paper.