In the existing optimization of Electric power material Vehicle Routing Problem (EVRP), the objective function is relatively single, the constraints are not comprehensive enough, and the traditional solution algorithms are not efficient. Therefore, a multi-objective routing optimization model and solution algorithm for electric power material distribution based on Deep Reinforcement Learning (DRL) was proposed. Firstly, the electric power material distribution area constraints such as the distribution of gas stations and the fuel consumption of material transportation vehicles were fully considered to establish a multi-objective power material distribution model with the objectives of the minimum total length of the power material distribution routings, the lowest cost, and the highest material demand point satisfaction. Secondly, a power material distribution routing optimization algorithm DRL-EVRP was designed on the basis of Deep Reinforcement Learning (DRL) to solve the proposed model. In the algorithm, the improved Pointer Network (Ptr-Net) and the Q-learning algorithm were combined to form the Deep Q-Network (DQN), which was used to take the sum of the negative value of the cumulative incremental routing length and the satisfaction as the reward function. After DRL-EVRP algorithm was trained and learned, it can be directly used for the planning of electric power material distribution routings. Simulation results show that the total length of the power material distribution routing solved by DRL-EVRP algorithm is shorter than those solved by the Extended Clarke and Wright (ECW) saving algorithm and Simulated Annealing (SA) algorithm, and the calculation time of the proposed algorithm is within an acceptable range. Therefore, the power material distribution routing can be optimized more efficiently and quickly by the proposed algorithm.
The current method of image classification which uses the Speed Up Robust Feature (SURF) is low in efficiency and accuracy. To overcome these shortages, this paper proposed an approach for image classification which uses the statistical features of the SURF set. This approach took all dimensions and scale information of the SURF as independent random variables, and split the data with the sign of Laplace response. Firstly, the SURF vector set of the image was got. Then the feature vector was constructed with the first absolute order central moments and weighted first absolute order central moments of each dimision. Finally, the Support Vector Machine (SVM) accomplished the image classification process with this vector. The experimental results show that the precision of this approach is better than that of the methods of SURF histogram and 3-channel-Gabor texture features by increases of 17.6% and 5.4% respectively. By combining this approach with the HSV histogram, a high-level feature fusion method was got, and good classification performance was obtained. Compared with the fused method of the SURF histogram and HSV histogram, the fused method of 3-channel-Gabor texture features and HSV histogram, and the multiple-instance-learning method based on the model of Bag of Visual Word (BoVW), the fused method of this approach and HSV histogram has better precision with the increases of 5.2%, 6.8% and 3.2% respectively.
This article focused on the mobile sink scheduling problem in Wireless Sensor Networks (WSN). A mobile single-sink scheduling algorithm in wireless sensor networks was proposed based on Linear Programming (LP). Firstly, the problem was mathematically modeled and formulated in time domain, and the problem was re-formulated from time to space domain to reduce the complexity. Then a polynomial-time optimal algorithm was proposed based on linear programming. The simulations confirm the efficiency of the algorithm and the results show that the algorithm can significantly improve the network lifetime of wireless sensor networks.
To deal with the poor performance of word sense disambiguation in parsing, a Chinese phrase parsing approach was proposed based on disambiguation of Chinese part of speech. First, it expanded part of speech of TongYiCi CiLin and then substituted the original words in the training set and test set with semantics codes. In this process, it used part of speech of word for word sense disambiguation. The experimental results on Penn Chinese TreeBank (CTB) show that the proposed method achieves precision rate of 80.30%, recall rate of 78.12%, and F-measure of 79.19%. Relative to the no disambiguation system, the presented approach can effectively improve the performance of phrase parsing.
A storing systematic configuration of spatial metadata based on XDR Schema was proposed and a XML data reduced schema was created. The spatial metadata expressed by XML was mapped to SQL Server 2000 RDBMS. The annotated XDR schema corresponded with XML view, so we could query database using annotated XDR schema and get result in XML form.
An improved genetic algorithm,evolving algorithm GASA was proposed,in which genetic algorithm was combined with simulated annealing algorithm. It avoided the premature convergence problem existed in Genetic Algorithm by useing Boltamann,and enhanced the global convergence. Genetic operators was redesigned, such as selection operator, cross operator and variation operator,on genetic algorithm. New cross operator and variation operator was proposed, which could dynamically regulate genetic operator according to evolving situation of groups. The algorithm was used in the best path problem of emergency decision support system,and it is proved to be reasonable and efficient.