To address the problems of limited information expression， imbalance， and dynamic spatio-temporal characteristics of accident data， an accident prediction model fusing heterogeneous traffic situations was proposed. In which， the semantic enhancement was completed by the spatio-temporal state aggregation module through traffic events and weather features representing dynamic traffic situations， and the historical multi-period spatio-temporal states of four types of regions （single region， adjacent region， similar region， and global region） were aggregated； the dynamic local and global spatio-temporal characteristics of accident data were captured by the spatio-temporal relation capture module from both micro- and macro-perspectives； and the multi-region and multi-angle spatio-temporal states were further fused by the spatio-temporal data fusion module， and the accident prediction task in the next period was realized. Experimental results on five city datasets of US-Accident demonstrate that the average F1-scores of the proposed model for accident， non-accident， and weighted average samples are 85.6%， 86.4%， and 86.6% respectively， which are improved by 14.4%， 5.6%， and 9.3% in the three metrics compared to the traditional Feedforward Neural Network （FNN）， indicating that the proposed model can effectively suppresses the influence of accident data imbalance on experimental results. Constructing an efficient accident prediction model helps to analyze the safety situation of road traffic， reduce the occurrence of traffic accidents and improve the traffic safety.

In the face of adversarial example attack， deep neural networks are vulnerable. These adversarial examples result in the misclassification of deep neural networks by adding human-imperceptible perturbations on the original images， which brings a security threat to deep neural networks. Therefore， before the deployment of deep neural networks， the adversarial attack is an important method to evaluate the robustness of models. However， under the black-box setting， the attack success rates of adversarial examples need to be improved， that is， the transferability of adversarial examples need to be increased. To address this issue， an adversarial example method based on image flipping transform， namely FT-MI-FGSM （Flipping Transformation Momentum Iterative Fast Gradient Sign Method）， was proposed. Firstly， from the perspective of data augmentation， in each iteration of the adversarial example generation process， the original input image was flipped randomly. Then， the gradient of the transformed images was calculated. Finally， the adversarial examples were generated based on this gradient， so as to alleviate the overfitting in the process of adversarial example generation and to improve the transferability of adversarial examples. In addition， the method of attacking ensemble models was used to further enhance the transferability of adversarial examples. Extensive experiments on ImageNet dataset demonstrated the effectiveness of the proposed algorithm. Compared with I-FGSM （Iterative Fast Gradient Sign Method） and MI-FGSM （Momentum I-FGSM）， the average black-box attack success rate of FT-MI-FGSM on the adversarially training networks is improved by 26.0 and 8.4 percentage points under the attacking ensemble model setting， respectively.

In order to improve the packet loss resilience of Scalable Video Coding (SVC) over communication networks, an efficient Unequal Error Protection (UEP) algorithm for SVC using adaptive genetic algorithm was proposed. A method to encapsulate network abstract layer units according to the feature of the head information of a packet was introduced. Then the problems of pair codes assignment were transformed into the problems of multi-constraint optimization, which could be transformed into unconstrained objective by exploiting penalty function. Therefore, the adaptive genetic algorithm was employed to obtain globally optimal solution. The simulation results reveal that compared with the typical unequal error protection algorithms, the Peak Signal-to-Noise Ratio (PSNR) is improved by 0.8dB-1.95dB, and the proposed algorithm provides substantial improvement for the decoding speed and received video quality over best effort packet networks.

In recent years, research of almost optimal resilient Boolean functions develops rapidly, and it is important to improve the nonlinearity degree of almost optimal functions. Analysis and improvement of an almost optimal function with good performance was given, and an almost optimal function with even variables was constructed using concatenating construction method. A nonlinear optimal function with higher nonlinearity was got while maintaining its resilience and algebraic degree, which improved the performance of the function. And the construction method was also given to construct an elastic Boolean function with high nonlinearity. Analysis shows that the proposed construction method is simple and easy to implement, the nonlinearity is improved with m resilience and unchanged algebraic degree.

Compressed Sensing (CS) theory can reconstruct original images from fewer measurements using the priors of the images sparse representation. The CS theory was applied into the single-image Super-Resolution (SR), and a new reconstruction algorithm based on two-step iterative shrinkage and Total Variation (TV) sparse representation was proposed. The proposed method does not need an existing training set but the single input low resolution image. A down-sampling low-pass filter was incorporated into measurement matrix to make the SR problem meet the restricted isometry property of CS theory, and the TV regularization method and a two-step iterative method with TV denoising operator were introduced to make an accurate estimate of the image's edge. The experimental results show that compared with the existing super-resolution techniques, the proposed algorithm has higher precision and better performance under different magnification level, the proposed method achieves significant improvement (about 4~6dB) in Peak Signal-to-Noise Ratio (PSNR), and the filter plays a decisive role in the reconstruction quality.

The paper briefly introduced the merits and shortcomings of the existing anti-collision algorithms. Based on the idea of Jumping and Dynamic Searching (JDS) algorithm, a Novel JDS (NJDS) algorithm for tags' anti-collision was proposed. The algorithm brought stack into the new jumping before and after searching strategy to reduce the number of collision slots and avoid idle slots. When requested by readers, it adopted dynamic transmission and variable length adjustment strategy, and used the known information remembered by the feedback tags' information to identify the unknown data bits of tags, which reduced the number of search of readers and the transmission of system. The analysis on simulation results indicates that the proposed algorithm performs significantly better than the existing anti-collision algorithms. The transmission is greatly reduced, and throughput of the system has increased significantly.

Weight coefficients should be employed to transform multi-objective problem of hybrid system into a single objective one. In order to avoid setting weight coefficients, a methodological approach based on Strength Pareto Evolutionary Algorithm (SPEA2) was proposed to optimize parameters of constrained Parallel Hybrid Electric Vehicle (PHEV).The Pareto dominance principle was employed to judge candidate solutions and the objective was to minimum fuel consumption and exhaust emissions while ADVISOR was used to simulate the PHEV driving. The optimal results demonstrate that adopting the methodological approach proposed in this paper to optimize parameters of power control strategy and drivetrain has a significant effect on enhancing working efficiency, promoting vehicle performance, decreasing fuel consumption and reducing exhaust emissions of PHEV.