Computed Tomography （CT） three-dimensional reconstruction technique improves the quality of three-dimensional model by upsampling volume data， and reduces the jagged edges， streak artifacts and discontinuous surface in the model， so as to improve the accuracy of disease diagnosis in clinical medicine. A CT three-dimensional reconstruction algorithm based on super-resolution network was proposed to solve the problem that the model after CT three-dimensional reconstruction remains unclear enough in the past. The network model is a Double Loss Refinement Network （DLRNET）， and the three-dimensional reconstruction of abdominal CT was performed by uniaxial super-resolution. The optimization learning module was introduced at the end of the network model， and besides the calculation of the loss between the baseline image and super-resolution image， the loss between the roughly reconstructed image in the network model and the baseline image was also calculated. In this way， with the force of optimization learning and double loss， the results closer to the baseline image were produced by the network. Then， spatial pyramid pooling and channel attention mechanism were introduced into the feature extraction module to learn the features of vascular tissues with different thickness degrees and scales. Finally， the upsampling method was used to dynamically generate the convolution kernel set， so that a single network model was able to complete the upsampling tasks with different scaling factors. Experimental results show that compared with Residual Channel Attention Network （RCAN）， the proposed network model improves the Peak Signal-to-Noise Ratio （PSNR） by 0.789 dB on average under 2， 3， and 4 scaling factors， showing that the network model effectively improves the quality of CT three-dimensional model， recovers the continuous detail features of vascular tissues to some extent， and has practicability.

Imbalanced data classification is an important research content in machine learning， but most of the existing imbalanced data classification algorithms foucus on binary classification， and there are relatively few studies on imbalanced multi?class classification. However， datasets in practical applications usually have multiple classes and imbalanced data distribution， and the diversity of classes further increases the difficulty of imbalanced data classification， so the multi?class classification problem has become a research topic to be solved urgently. The imbalanced multi?class classification algorithms proposed in recent years were reviewed. According to whether the decomposition strategy was adopted， imbalanced multi?class classification algorithms were divided into decomposition methods and ad?hoc methods. Furthermore， according to the different adopted decomposition strategies， the decomposition methods were divided into two frameworks： One Vs. One （OVO） and One Vs. All （OVA）. And according to different used technologies， the ad?hoc methods were divided into data?level methods， algorithm?level methods， cost?sensitive methods， ensemble methods and deep network?based methods. The advantages and disadvantages of these methods and their representative algorithms were systematically described， the evaluation indicators of imbalanced multi?class classification methods were summarized， the performance of the representative methods were deeply analyzed through experiments， and the future development directions of imbalanced multi?class classification were discussed.

The high resolution in Magnetic Resonance （MR） image slices and low resolution between the slices lead to the lack of medical diagnostic significance of MR in the coronal and sagittal planes. In order to solve the problem， a medical image processing algorithm based on inter-layer interpolation and multi-view fusion network was proposed. Firstly， the inter-layer interpolation module was introduced to cut the MR volume data from three-dimensional data into two-dimensional images along the coronal and sagittal directions. Then， after the feature extraction on the coronal and sagittal planes， the weights were dynamically calculated by the spatial matrix filter and used for upsampling factor with any size to magnify the image. Finally， the results of the coronal and sagittal images obtained in the inter-layer interpolation module were aggregated into three-dimensional data and then cut into two-dimensional images along the axial direction. The obtained two-dimensional images were fused in pairs and corrected by the axial direction data. Experimental results show that， compared with other super-resolution algorithms， the proposed algorithm has improved the Peak Signal-to-Noise Ratio （PSNR） by about 1 dB in ×2， ×3， and ×4 scales. It can be seen that the proposed algorithm can effectively improve the quality of image reconstruction.

Due to high complexity of dark channel prior defogging algorithm, a fast defogging algorithm based on dark channel prior was proposed. Firstly, the computing of the dark channel map was accelerated by blocking the image. Secondly, the block effect was eliminated by using the linear interpolation algorithm to smoothing. Then, the transmission map was acquired by dark channel prior. Finally, a clear and haze-free image would be gotten from the atmospheric scattering model. The experimental results show that the defogging effect of the proposed algorithm can be as good as the original defogging algorithm but the complexity can be reduced effectively. The proposed algorithm needs time about one-tenth of the original algorithm and reaches the requirement of near real-time.

It is difficult for robot to move in wild environment because of pit areas, so a visual coping method was put forward to detect those pit areas. Firstly, according to project requirements, a part of suspected areas with small size were removed, as well as some the suspected areas with edge gradient. Secondly, the oval similarity was calculated to determine gray level segmentation threshold, and the similarity threshold was confirmed by analyzing the oval similarity curve, which was used to separate pit areas from the suspected pit areas. At last, the simulation results on 200 pictures with different angles, scenes and pit umbers show that the proposed method can be applied to extract pit area in complex environment, and is also not sensitive to outline regularity of pit area; besides, it can adapt to complex environment.

To solve the problems of single and low rate of convolutional codes and large loss of data rate in the G3 standard, the low voltage power line carrier communication system model based on Orthogonal Frequency Division Multiplexing (OFDM) in the G3 standard was analyzed, and a designing scheme of forward error correction encoder was presented based on RS encoding, convolutional encoding, puncturing and depuncturing, repetition encoding and two dimensional time and frequency interleaving algorithm. Moreover, a method for raising the code rate by puncturing and depuncturing was mainly introduced. The simulation results show that the rate of convolutional codes is raised from 1/2 to 2/3, the data rate is improved without increasing the complexity of decoding, and the effective and reliable communication can be realized, which means the scheme can be widely used in low voltage Power Line Communication (PLC).

In view of the low delivery ratio of conventional probabilistic routing in opportunistic networks, an improved routing algorithm based on History Meeting Predictability Routing (HMPR) was put forward. The algorithm was primarily based on the contact duration and the meeting frequency of history information of nodes, and predicted the utility of packets successfully delivered to the destination. Through comparing the utility value, nodes could determine packets whether to be forwarded from them to next hop nodes. The simulation results show that, compared with traditional epidemic routing and probabilistic routing, the proposed routing scheme has better performance in the delivery ratio of packets, the average delay time and the average buffer time.

Global System for Mobile Communications for Railway （GSMR） communication system of highspeed railway is vulnerable to the interference of wireless signals of other types. In this paper, the authors analyzed and researched several GSMR interference signals and proposed a new kind of signal separation algorithm based on the multiframe statistical spectrum. The idea of the algorithm was that the interference signal was divided into multiple frames and accumulated to statistical spectrum. If the number of frames was sufficient, its spectral parameter tended to be a constant. The experimental results show that the algorithm can quickly separate the original and interference signals in the case of known original signal spectrum, its effect and versatility is better, and the complexity of the algorithm is less than the traditional method.

In order to selecte the web services which meet the request in the evolution of Web services efficiently , we propose a web services evolution strategy based on hybrid co-evolutionary algorithm. First of all, by means of the improved fuzzy C-means clustering algorithm, we classify the web services unit into groups according to the application, and then making the internal prioritizing for each subgroup using Particle Swarm Optimization with weights. Finally the co-evolution operation will be executed among the particle subgroups so as to fulfil the users requests and select the best Web services evolution combination. The experimental results show that the hybrid co-evolutionary algorithm is superior to the traditional co-evolutionary algorithms not only in stability, but also the operation cost of time, and could provide quality and efficient services to the service requests in the web environment.