Search

Aiming at the problems of poor performance and slow convergence of existing symbiotic organisms search（SOS） algorithm in solving discrete optimization problems such as path planning, this paper proposed the virtual multitask SOS（VMTSOS）. Firstly, according to the bidirectional mapping decoding strategy, the transformation between individual continuous spatial position and discrete city sequence was realized; secondly, the idea of multi-task optimization was introduced to construct a virtual multi-task environment, designed multiple populations to optimize the same task simultaneously, and the stagnation threshold controlled the frequency of information transfer between populations. Once the main population reached the stagnation threshold, some excellent individuals in the auxiliary population were replaced with inferior individuals in the main population; finally, the time and space complexity of VMTSOS was analyzed. Experiment results show that VMTSOS converges rapidly to the current optimal solution of each test case when solving most TSP problems, while VMTSOS with multiple groups assistance mechanisms can greatly reduce the optimal total cost when solving cold chain logistics distribution problems. [ABSTRACT FROM AUTHOR]

Copyright of Automobile Technology & Material is the property of Automobile Technology & Material Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Computer-Aided Design & Computer Graphics / Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao is the property of Gai Kan Bian Wei Hui and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In the field of Neural Machine Translation (NMT), the multi-layer neural network model structure can significantly improve the translation performance. However, the structure of multi-layer neural network has an inherent problem with information transfer degeneracy. To alleviate this problem, this paper proposes an information transfer enhancement method by fusing layers information and sublayers information. By introducing a "retention gate " mechanism to control the fused information transfer weight, which is aggregated wit h the output of the current layer and then serves as the input of the next layer, thus making fuller information transfer between layers. Experiments were carried out on the most advanced NMT model Transformer. Experimental results on the Chinese-English and German English tasks show that our method improves BLEU score by 0. 66, and 0. 42 in comparison to the baseline system. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Signal Processing is the property of Journal of Signal Processing and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Soochow Journal of Economics & Business is the property of Soochow Journal of Economics & Business and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)