Aiming at the problems of low hardware resource utilization and high latency of Convolutional Neural Network （CNN） when performing inference on heterogeneous platforms， a self-adaptive partitioning and scheduling method of CNN inference model was proposed. Firstly， the key operators of CNN were extracted by traversing the computational graph to complete the adaptive partition of the model， so as to enhance the flexibility of the scheduling strategy. Then， based on the performance measurement and the critical path-greedy search algorithm， according to the sub-model running characteristics on the CPU-GPU heterogeneous platform， the optimal running load was selected to improve the sub-model inference speed. Finally， the cross-device scheduling mechanism in TVM （Tensor Virtual Machine） was used to configure the dependencies and running loads of sub-models in order to achieve adaptive scheduling of model inference， and reduce the communication delay between devices. Experimental results show that on GPU and CPU， compared to the method optimized by TVM operator， the proposed method improves the inference speed by 5.88% to 19.05% and 45.45% to 311.46% with no loss of model inference accuracy.

Concerning of the problems of high cost and unstable detection results of the traditional malicious code detection methods， a multi-neural network malicious code detection model based on depthwise separable convolution was proposed. By using the Depthwise Separable Convolution （DSC）， SENet （Squeeze-and-Excitation Network） channel attention mechanism and Grey Level Co-occurrence Matrix （GLCM）， three lightweight neural networks were connected with GLCM in parallel to detect malicious code families and their variants， then the detection results of multiple strong classifiers were fused via Naive Bayes classifier to improve the detection accuracy while reducing the computational cost. Experimental results on the hybrid dataset of MalVis + benign data show that the proposed model achieved the accuracy of 97.43% in the detection of malicious code families and their variants， which was 6.19 and 2.29 percentage points higher than those of ResNet50 and VGGNet models respectively， while its parameter quantity is only 68% of that of ResNet50 model and 13% of that of VGGNet model. On malimg dataset， the detection accuracy of this model achieved 99.31%. In conclusion， the proposed model has good detection effect with reduced parameters.

Accurate segmentation of the polyp region in the colonoscopic images can assist doctors in diagnosing intestinal diseases. However， the structure information of polyp region is missing in the down sampling process， and the existing methods have the problems of over segmentation and under segmentation.Aiming at the problems above， a Fusing Filter enhancement and Reverse attention segmentation Network （FFRNet） was proposed. Firstly， Filter Enhancement Module （FEM） was added to the skip-connection to enhance the structure information of local lesion region in the down-sampling features. Secondly， the global features were obtained by aggregating the shallow features. Finally， Multiscale reverse Attention Fusion Mechanism （MAFM） was adopted in the up-sampling process， by combining the global features and up-sampling features to generate the reverse attention weight， the polyp region information was mined in the features layer by layer， and the relationship between the target region and the boundary was established by the guidance network to improve the integrity of the model on polyp region segmentation. On Kvasir and CVC-ClinicDB datasets， compared with Uncertainty Augmented Context Attention Network （UACANet）， FFRNet has Dice Similarity Coefficient （DSC） increased by 0.22% and 0.54% respectively. Experimental results show that FFRNet can effectively improve the accuracy of polyp image segmentation and has good generalization ability.

In massive Multiple-Input Multiple-Output （MIMO） systems， Minimum Mean Square Error （MMSE） detection algorithm has the problems of poor adaptability， high computational complexity and low efficiency on the reconfigurable array structure. Based on the reconfigurable array processor developed by the project team， a parallel mapping method based on MMSE algorithm was proposed. Firstly， a pipeline acceleration scheme which could be highly parallel in time and space was designed based on the relatively simple data dependency of Gram matrix calculation. Secondly， according to the relatively independent characteristic of Gram matrix calculation and matched filter calculation module in MMSE algorithm， a modular parallel mapping scheme was designed. Finally， the mapping scheme was implemented based on Xilinx Virtex-6 development board， and the statistics of its performance were performed. Experimental results show that， the proposed method achieves the acceleration ratio of 2.80， 4.04 and 5.57 in Quadrature Phase Shift Keying （QPSK） uplink with the MIMO scale of \mathrm{128} \times \mathrm{4} ， \mathrm{128} \times \mathrm{8} and \mathrm{128} \times \mathrm{16} ， respectively， and the reconfigurable array processor reduces the resource consumption by 42.6% compared with the dedicated hardware in the \mathrm{128} \times \mathrm{16} massive MIMO system.

The traditional image encryption with scrambling-diffusion structure is usually divided into two independent steps of scrambling and diffusion， which are easy to be cracked separately， and the encryption process has weak nonlinearity， resulting in poor security of the algorithm. Therefore， a scrambling diffusion synchronous image encryption algorithm with strong nonlinearity was proposed. Firstly， a new sine-cos chaotic mapping was constructed to broaden the range of control parameters and improve the randomness of sequence distribution. Then， the exclusive-OR sum of plaintext pixels and chaotic sequence was used as the initial chaotic value to generate chaotic sequence， and this chaotic sequence was used to construct the network structures of different pixels of different plaintexts. At the same time， the diffusion value was used to dynamically update the network value to make the network dynamic. Finally， the single pixel serial scrambling-diffusion was used to generate cross-effect between scrambling and diffusion，and the overall synchronization of scrambling and diffusion， so as to effectively resist separation attacks. In addition， the pixel operations were transferred according to the network structure， which made the serial path nonlinear and unpredictable， thereby ensuring the nonlinearity and security of the algorithm. And the adjacent node pixels sum was used to perform dynamic diffusion in order to improve the correlation of the plaintext. Experimental results show that the proposed algorithm has high encryption security， strong plaintext sensitivity， and is particularly effective in anti-statistical attack， anti-differential attack and anti-plaintext attack.

In an Executable and Linkable Format (ELF) executable program, Global Offset Table (GOT) was used to store the absolute addresses of library functions. But in Linux operation system, GOT dereference and GOT overwrite are two common vulnerability exploit methods. Through analyzing the GOT feature, a protection method for GOT based on address randomization and segment isolation was proposed and implemented. With modifying the ELF loader program, all sections which pointed to the GOT were loaded into random memory addresses. Using segment isolation technology, all instructions with reference to GOT used a new segment register. The experimental results prove that the proposed method can not only defense against the exploit method of GOT effectively, but also has a very low cost of average 2.9 milliseconds.

In view of the problems that the traditional general graph matching search is inefficient, and refractive index data cannot be positioned fast in large data environment, a distributed massive molecular retrieval model based on consistent Hash function was established. Combined with the characteristics of molecular storage structures, to improve retrieval efficiency of molecules, the continuous refractive index was discretized by fixed width algorithm to establish high-speed Hash index, and the distributed massive retrieval system was realized. The size of dataset was effectively reduced, and Hash collision was handled according to the visiting frequency. The experimental results show that, in the chemical data containing 200 thousand structures of molecules, the average time of this method is about five percent of the traditional general graph matching search. Besides, the model has the steady performance with high scalability. It is applicable to retrieve high-frequency molecules in accordance with refractive index under the environment of massive data.

Concerning the problem of topics mining and its corresponding public emotion analysis, an analytical method for public emotion evolution was proposed based on Probabilistic Latent Semantic Analysis (PLSA) model. In order to find out the evolutional patterns of the topics, the method started with extracting the subtopics on time series by making use of PLSA model. Then, emotion feature vectors represented by emotion units and their weights which matched with the topic context were established via parsing and ontology lexicon. Next, the strength of public emotion was computed via a fine-grained dimension and the holistic public emotion of the issue. In this case, the method has a deep mining into the evolutional patterns of public emotion which were finally quantified and visualized. The advantage of the method is highlighted by introducing grammatical rules and ontology lexicon in the process of extracting emotion units, which was conducted in a fine-grained dimension to improve the accuracy of extraction. The experimental results show that this method can gain good performance on the evolutional analysis of topics and public emotion on time series and thus proves the positive effect of the method.

For improving the accuracy and validity of social E-commerce recommendation services, a trust-aware collaborative filtering recommendation method was proposed with considering the factors that influence the trust relationship of users in social E-commerce, such as transaction evaluation score, transaction frequency, transaction amount, direct trust and recommended reputation. The belief factor was introduced to compute the trust relationship of social E-commerce users, the cosine similarity method was used to calculate the similarity of the users, the harmonic factor was used to synthesize the influence of the trust relationship and similarity on the users, the Mean Absolute Error (MAE), rating coverage and user coverage were used as the evaluation indexes. The experimental results show that the accuracy of the trust-aware collaborative filtering method is superior to the traditional collaborative filtering method and the regularized matrix factorization based collaborative filtering recommendation method in that the MAE reduces to 0.162, and the rating coverage and user coverage rise to 77% and 80% respectively. This proves that the trust-aware collaborative filtering method can solve the problem of recommending the commodities with less transaction evaluation.

To solve the synchronization problem of audio and video, an improved algorithm of audio-video synchronization coding based on H.264 inter-frame prediction was proposed. The algorithm introduced the concept of variable code length. The audio encoding data was divided into several code groups, and each code group had 2 or 3 bits of embedded data. In the stage of H.264 inter-frame prediction, the mappings between various variable size blocks and the data of code groups were based on formula. The coding method was dynamically determined for the macro block modes coding according to embedded data, and a proposed decoding method could extract the corresponding data according to the mapping relationship. Finally, the 4×4 macro block mode was used to indicate the end of the audio data.The experimental results show that the proposed algorithm enables the Peak Signal-to-Noise Ratio (PSNR) of video samples to reduce by 0.031dB, the bit rate to increase by 5.16% and the overhead to increase by 1.97%, but the embedded audio data can be correctly and completely extracted. Therefore,the algorithm can implement the synchronization of audio and video coding while increasing the data embedding capacity, maintaining the quality of video, ensuring the correctness and completeness of the data.

The Camshift algorithm based on color-kernel can effectively track objects in a simple background, but it is easy to be interfered by illumination variation or the similar color object in the background. To improve the algorithms ability to respond to illumination variation, a multi-feature adaptive fusion scheme based on color, shape and texture was proposed. And further improvements have been proposed through modifying feature histogram and setting a reasonable search region to solve the problem of similar background. The experimental results show that the improved algorithm has higher tracking accuracy than traditional algorithm in the scene with illumination variation or similar background.

A new method was presented to calculate two dimentional numerical integration based on Particle Swarm Optimization （PSO） with a constriction factor, named PSO-CF. PSO-CF algorithm selected some initial partition points randomly in the domain,and used the constriction factor to update the velocity,then the particles would move towards better position.This algorithm evaluated particles by fitness value based on the four vertices, four interior points and the center point of every small rectangle after partition, it optimized the particles through repeated iteration. For the opitimal particle, PSO-CF algorithm used the composite four interior points to calculate two dimentional numerical integration. The experimental results show that integral precision is higher,and this method is effective.

As the unsteady bandwidth of mobile channel and the limited coverage of wireless Wi-Fi point, a wireless video transmission system based on adaptive choice of CDMA1X, 3G-EVDO and Wireless Local Area Network (WLAN) was proposed. The adaptive choice algorithm includs: adaptive access of multiple networks, dynamic switch of wireless heterogeneous networks and adaptive choice of homogeneous networks. The presented method can achieve high quality and reliable transmission.

On the heterogeneous architecture of multi-core Central Processing Unit (CPU) and Graphic Processing Unit (GPU), the Open Multi-Processing (OpenMP) and the programming interfaces of Compute Unified Device Architecture (CUDA) were used to implement a molecular dynamics simulation program based on AMBER force field. In order to efficiently use computer processing power, the program was divided into different parts which were processed by CPU single-thread, CPU multi-thread and GPU multi-thread respectively. The experimental results show that compared with the optimized CPU-based implementations, the heterogeneous parallel computing model based on multi-core CPU-GPU gets powerful performance advantage. Especially, the calculations of forces, which account for more than 90% of processing time, get at most 12 times faster than CPU-based implementations while being implemented on GPU.

On the basis of studying Support Vector Machine (SVM) theory, a soft-sensor controlling method based on Support Vector Machine wass presented. In order to solve the problem of getting the important parameter that is hard to be measured online and has long time-delay, a soft-sensor controlling method based on support vector machine was presented. In the control process, modeling techniques have been studied intensively, and then RBF kernel function was chosen to establish an exact support vector machine model. On the background of quality control in a company, the online estimate of output value was realized. Under the circumstance of changing and choosing different parameters and through a lot of research and simulation, a relatively better generalization result model was established.