Concerning the problems of large number of parameters, poor real-time performance and low accuracy of traffic sign recognition algorithms based on deep learning, an improved traffic sign recognition algorithm based on YOLO v3 was proposed. First, the depthwise separable convolution was introduced into the feature extraction layer of YOLO v3, as a result, the convolution process was decomposed into depthwise convolution and pointwise convolution to separate intra-channel convolution and inter-channel convolution, thus greatly reducing the number of parameters and the calculation of the algorithm while ensuring a high accuracy. Second, the Mean Square Error (MSE) loss was replaced by the GIoU (Generalized Intersection over Union) loss, which quantified the evaluation criteria as a loss. As a result, the problems of MSE loss such as optimization inconsistency and scale sensitivity were solved. At the same time, the Focal loss was also added to the loss function to solve the problem of severe imbalance between positive and negative samples. By reducing the weight of simple background classes, the new algorithm was more likely to focus on detecting foreground classes. The results of applying the new algorithm to the traffic sign recognition task show that, on the TT100K (Tsinghua-Tencent 100K) dataset, the mean Average Precision (mAP) of the algorithm reaches 89%, which is 6.6 percentage points higher than that of the YOLO v3 algorithm; the number of parameters is only about 1/5 of the original YOLO v3 algorithm, and the Frames Per Second (FPS) is 60% higher than YOLO v3 algorithm. The proposed algorithm improves detection speed and accuracy while reducing the number of model parameters and calculation.

A method was proposed by combining the global and local path planning algorithms for the problems of slow iteration and not good path in mobile robot path planning under complex environment. Firstly, the synchronous bidirectional A ^* algorithm was used for the pheromone optimization of ant colony algorithm, and the transition probability and pheromone update mechanism of ant colony algorithm were improved, so that the global optimization of the algorithm was faster and the path length of the mobile robot was shortened. Furthermore, the static path was used to initialize the pigeon inspired optimization algorithm. Secondly, the improved pigeon inspired optimization algorithm was used for the local path planning of the mobile robot. The simulated annealing criteria were introduced to solve the local optimum problem, and the logarithmic S-type transfer function was used to optimize the step size of the number of pigeons, so as to better avoid the collision with dynamic obstacles. Finally, the cubic B-spline curve was used to smooth and replan the route. Simulation results indicate that the algorithm can generate smooth paths with short length and small evaluation value in both global static and local dynamic phases, and converge quickly, which is suitable for mobile robot to travel in dynamic and complex environments.

To limit the number of components in the protection switching process and to accordingly reduce the protection cost, a new reliable Wave Division Multiplexing/Time Division Multiplexing Passive Optical Network (WDM/TDM-PON) architecture with cost-efficient hybrid protection was proposed. Firstly, the logic decision unit, protection path control unit and backup transceiver unit were designed in Optical Line Terminal (OLT) to only switch failure components to their backups in Wave Division Multiplexing (WDM) segment. Secondly, by employing the cross bus structure in Time Division Multiplexing (TDM) segment, fast protection switching was achieved in a distributed manner. According to the analytic results of the hybrid protection, the proposed architecture can provide fast and full protection in recovery time of 1.5 to 2.4 ms against Feed Fiber (FF), Distribution Fiber (DF) and Last Mile Fiber (LMF) failures. Certainly, the proposed architecture can also significantly reduce the protection overhead, and achieve great scalability.

When urban waterlogging disasters occur, the scientific deployment of rescue resources can improve the efficiency of urban emergency rescue, and minimize disaster losses. In view of the fact that urban routes are affected by terrain, road conditions and the seriousness of waterlogging, the authors introduced the connected coefficient and the unblocked coefficient, so as to better reflect the urban route conditions and waterlogging disaster. Considering that the ant colony algorithm has some disadvantages, such as slow convergence, easy to fall into local optimum, by randomly selecting the affected areas and introducing a pheromone update operator strategy the ant colony algorithm was improved, which is used to solve the route optimization model. Empirical analysis shows that the improved ant colony algorithm of solving urban waterlogging rescue route optimization has better result.

Concerning the problem that how to initialize the weights of deep neural networks, which resulted in poor solutions with low generalization for spam filtering, a classification method of Deep Belief Net (DBN) was proposed based on the fact that the existing spam classifications are shallow learning methods. The DBN was pre-trained with the greedy layer-wise unsupervised algorithm, which achieved the initialization of the network. The experiments were conducted on three datesets named LinsSpam, SpamAssassin and Enron1. It is shown that compared with Support Vector Machines (SVM) which is the state-of-the-art method for spam filtering in terms of classification performance, the spam filtering using DBN is feasible, and can get better accuracy and recall.

The thorough research on ant colony algorithm points out that the ant colony algorithm has superiority in solving large nonlinear optimization problem. Through careful analysis of the deficiencies that genetic algorithm and particle swarm algorithm solve the problem of vehicle dispatching system, based on the advantage of ant colony algorithm and the own characteristics of vehicle dispatching system, the basic ant colony algorithm was improved in the paper, and the algorithm framework was created. Based on the linear programming theory, the article established mathematical model and operation objectives and constraints for vehicle dispatching system, and got the optimal solution of vehicle dispatching system problem with the improved ant colony algorithm. According to the optimal solution and the dispatching criterion real-time scheduling was achieved. The article used Java language to write a simulation program for comparing the improved particle swarm optimization algorithm and ant colony algorithm. Through the comparison, it is found a result that the improved ant colony algorithm is correct and effective to solve the vehicle dispatching optimization problem.

This paper described an outdoor Global Positioning System (GPS) navigation algorithm for the blind by analyzing the GPS trajectory data received by the embedded platform Windows CE. Based on the data analysis of GPS trajectory, the algorithm introduced a method for the judgment of turning points and turning directions. During practical navigation, the blind can use the real-time voice prompt information for walking guidance. The experimental results show that the judgment of turning points can be realized in this algorithm effectively, and navigation information is effective and practical on helping users arrive at destinations safely and accurately.

The topological property among stroke segments was analyzed. Image of handwritten Chinese character is transformed to geometric graphics, and the graphics was composed of some styles of Chinese character strokes with fault tolerance in different positions. Procedure neural network was applied to extract complex strokes of handwritten Chinese character. The style, number and number of joint and crossover of complex strokes were accumulated, and a kind of characteristic knowledge database table of handwritten Chinese characters was constructed. Handwritten Chinese character in SCUT-IRAC-HCCLIB were tested, and this method can simplify the recognition process, as well as has a high recognition rate.