Design of Characteristic Curriculum on Software Engineering Major for Undergraduate-Graduate Education

The concept of“New Engineering”has put forward new challenges to the talents cultivation of universities.Due to some problems of the traditional Software Engineering curriculum,e.g.separated design at undergraduate-level and graduate-level courses,poor curriculum structure,lacking of industry characteristics.This paper proposes an integrated undergraduate-graduate education curriculum for Software Engineering Major,which is based on Software Engineering specialty knowledge system(C-SWEBOK)and focuses on the current national strategic demands.Additionally,the curriculum combines with the University’s transportation characteristics,and fuses the discipline of Software Engineering and Intelligent Transportation.The multi-level curriculum designed in this paper is with reasonable structure,complete system,progressive content,and salient feature,which provides the strong support for cultivating high-qualified software talents in line with national strategies and industry needs.

Knowledge Reasoning Method Based on Deep Transfer Reinforcement Learning:DTRLpath

In recent years,with the continuous development of deep learning and knowledge graph reasoning methods,more and more researchers have shown great interest in improving knowledge graph reasoning methods by inferring missing facts through reasoning.By searching paths on the knowledge graph and making fact and link predictions based on these paths,deep learning-based Reinforcement Learning(RL)agents can demonstrate good performance and interpretability.Therefore,deep reinforcement learning-based knowledge reasoning methods have rapidly emerged in recent years and have become a hot research topic.However,even in a small and fixed knowledge graph reasoning action space,there are still a large number of invalid actions.It often leads to the interruption of RL agents’wandering due to the selection of invalid actions,resulting in a significant decrease in the success rate of path mining.In order to improve the success rate of RL agents in the early stages of path search,this article proposes a knowledge reasoning method based on Deep Transfer Reinforcement Learning path(DTRLpath).Before supervised pre-training and retraining,a pre-task of searching for effective actions in a single step is added.The RL agent is first trained in the pre-task to improve its ability to search for effective actions.Then,the trained agent is transferred to the target reasoning task for path search training,which improves its success rate in searching for target task paths.Finally,based on the comparative experimental results on the FB15K-237 and NELL-995 datasets,it can be concluded that the proposed method significantly improves the success rate of path search and outperforms similar methods in most reasoning tasks.

Diffserv AQM algorithm for edge and core routers

The existing active queue management （AQM） algorithm acts on subscribers and edge routers only, it does not support differentiate-serve （Diffserv） quality of service （QoS）, while the existing diffserv QoS has not considered the link capacities between edge routers and connected core routers. When a core router in a two layers’ network experiences congestion, the connected edge routers have no ability to adjust their access data rates. Thus, it is difficult to achieve the congestion control for the large scale network with many edge routers and core routers. To solve these problems, two difffserve AQM algorithms are proposed for the congestion control of multilayer network. One diffserv AQM algorithm implements fair link capacities of edge routers, and the other one implements unequal link capacities of edge routers, but it requires the core routers to have multi-queues buffers and Diffserv AQM to support. The proposed algorithms achieve the network congestion control by operating AQM parameters on the conditions of proposed three theorems for core and edge routers. The dynamic simulation results demonstrate the proposed control algorithms for core and edge routers to be valid.

Genetic Diversity of Clover by SRAP

In the present study,genetic diversity and genetic relationship of 11materials including red clover ( Trifolium pretense L.),white clover ( T.repen L.) and alsike clover ( T.hybridum L.) and leaf-type variants of white clover were investigated by SRAP (sequence related amplified polymorphism).Forty SRAP primers were screened,and 792 reliable bands were amplified,among which 426 (53.8%) were polymorphic.The number of polymorphic bands per pair of primers ranged from 3 to 38 with an average of 10.6.SRAP cluster analysis showed that the similarity coefficients between white clover materials were from 0.465 to 0.997 with an average of 0.812,indicating that there was certain genetic diversity among white clover.Specific bands appeared in white clover variants,indicating that there were certain differences in DNA sequence between normal while clover plants and their leaf-type variants.The similarity coefficients between red clover materials were from 0.457 to 0.827 with an average of 0.597,indicating that the different red clover germplasms had genetic diversity at the DNA molecular level.The results also showed that the genetic relationship of the alsike clover with the red clover was closer than that with the white clover.This study shows that SRAP technique can be effectively used for the analysis on interspecific and intraspecific relationship,germplasm resource identification and genetic diversity of clover.

Effects of Seed Viability and Number of Generations on Genetic Integrity of Soybean Germplasm Zhonghuang 18 by AFLP Markers

The seeds of a soybean cultivar Zhonghuang 18 were subjected to accelerated aging for 0(population G_0-1), 112(population G_0-2), 154(population G_0-3) and 196 d(population G_0-4), whose germination percentage was found to be 98.0%, 95.0%, 81.0%, and 79.0%, respectively. Then, the four populations were regenerated twice in the field. The first descendant populations were marked as G_1-1, G_1-2, G_1-3 and G_1-4, and the second were marked as G_2-1, G_2-2, G_2-3 and G_2-4, respectively. The genetic variation between the control population(G_0-1) and the experimental populations was analyzed using 12 AFLP primer combinations. The results showed that there was no significant difference in genetic similarity between the 11 experimental populations and the control population G_0-1. The genetic similarity between population G_2-4 and G_0-1 was still as high as 0.933 3, indicating that the F_2 generation of the population whose germination percentage was only 79.0% still had a high genetic similarity to the control population. The results of t-tests revealed that the populations G_1-1, G_2-1, G_1-2 and G_2-2 showed no significant difference from the control population G_0-1 in effective number of alleles per locus(Ae), genetic diversity index(H) and Shannon's diversity index(I), while these indices of populations G_0-3, G_0-4, G_1-3, G_1-4, G_2-3 and G_2-4 were significantly reduced. χ~2 tests indicated that the populations G_1-1 and G_2-1 showed little difference, and the populations G_0-2, G_0-3, G_0-4, G_1-2, G_1-3, G_1-4, G_2-2, G_2-3, and G_2-4 showed great difference in allele frequency distribution from the control population G_0-1, and the difference was greater when the seed viability was lower. Compared with the control population G_0-1, the number of rare alleles(Nr) of the populations G_0-2, G_1-1, G_2-1, G_1-2 and G_2-2 showed no significant difference, while that of the populations G_0-3, G_0-4, G_1-3, G_1-4, G_2-3 and G_2-4 declined obviously. These results revealed that compared with the control population, the genetic diversity and Nr for the descendant populations of the populations with 98.0% and 95.0% germination percentages did not change significantly, but declined greatly for the descendant populations of the populations with 81.0.% and 79.0% percentages. The results suggested that the decline in seed viability has a greater impact than the number of generations on genetic structure of soybean germplasm. So, it is suggested that soybean seed with an initial germination percentage of 98.0% should be regenerated before its germination percentage declines to 81.0%.

Effects of Seed Vitality and Regeneration on Genetic Integrity in Soybean by SSR Markers

The seeds of Zhonghuang 18 were selected as a test material,and subjected to artificial aging treatment(0,112,154 and 196 d),obtaining four 4 populations,i.e.,G_0-1,G_0-2,G_0-3 and G_0-4,the germination rates of which were 98.0%,95.0%,81.0%and 79.0%,respectively.The four populations were reproduced twice in field,giving four populations of the first reproduced generation G_1-1,G_1-2,G_1-3 and G_1-4 and four populations of the second reproduced generation G_2-1,G_2-2,G_2-3 and G_2-4.The results showed that the number of alleles(Ae)per locus and genetic identity of all the treatment populations did not change significantly compared with the control population G_0-1,and population G_0-4 still shared 0.996 2 genetic identity with the control population,indicating that the genetic identity between the population with a germination rate of 79.0%and the control population was still high.The results of t test showed that populations G_0-2,G_1-1 and G_2-1 showed number of alleles per locus(A),genetic diversity index(H)and Shannon index without significantly differences from the control population G_0-1;populations G_1-2 and G_2-2 had the number of alleles per locus(A)significantly decreased;and the above genetic diversity parameters of populations G_0-3,G_0-4,G_1-3,G_1-4,G_2-3 and G_2-4 decreased significantly or very significantly.The results ofχ~2test showed that there were almost no differences in the allelic frequency distribution between populations G_0-2,G_1-1 and G_2-1 and the control populaiton G_0-1;and populations G_0-3,G_0-4,G_1-2,G_1-3,G_1-4,G_2-2,G_2-3and G_2-4 differed in allele frequency distribution,and the lower the vitality level,the greater the differences.Compared with the control population G_0-1,populations G_0-2,G_1-1 and G_2-1 had no significant changes in number of rare alleles,while populations G_0-3,G_0-4,G_1-2,G_2-2,G_1-3,G_1-4,G_2-3 and G_2-4 decreased significantly in number of rare alleles.The above results showed that compared with the control population,the progeny populations reproduced from the population with a germination rate of 98.0%had significant changes in genetic diversity and number of rare alleles,while the values of the progeny populations reproduced from populations having germination rates of 81.0%and 79.0%,respectively,decreased significantly,and the number of alleles per locus and number of rare alleles of the progeny populations reproduced from the population with a germination rate of 95.0%began to decrease.The decline in viability has a greater effect on the genetic structure of soybean germplasm populations than reproduction generation.It is recommended that the germination rate standard for regeneration of soybean germplasm with an initial germination rate of 98.0%should not be lower than 81.0%.

Establishment and Operation of Crop Genebank in Shandong Province

Shandong Province has abundant and diverse crop germplasm resources, but it is in lack of unified and effective preservation and management, leading to the decline and even extinction of many rare germplasm resources. In this study, the necessity for the establishment of crop genebank in Shandong Province was briefly described. In addition, the type, functions and technical indicators, as well as the operation of the crop genebank were introduced comprehensively to provide a reference for the establishment of genebank by other units or organizations.

Four-layer cache strategy of edge computing in education environment

The rapid development of MEC and 5G technology has aroused huge repercussions and aroused the attention of education and industry.The storage of educational resources,energy consumption and delays in use have become urgent issues.In response to the above problems,this paper proposes a three-tier education network model and abstracts the network modeling.At the same time,the DQN method in reinforcement learning is used to solve the modeling method and simulation.Finally,the simulation results show that this method can effectively improve the cache hit rate and reduce the network load.

HIT-SEDAES: An integrated software environment for simulation experiment design, analysis and evaluation

Simulation is a powerful technique in evaluating and improving the performance of complex systems.In order to improve the efficiency of simulation experiment design,analysis and evaluation,auxiliary tools are required.Unfortunately,existing tools are usually not meeting the requirements of simulation.Moreover,the restricted interfaces,reusability and expandability influence their efficiency to a certain extent.In this paper,an integrated software environment,HIT-SEDAES,is designed for solving these problems.A process model of simulation experiment design,analysis and evaluation is introduced to guide the development of the software environment.And several solutions are proposed to solve key problems in this development.Finally,an application is used to illustrate how the software environment works for the problems of model validation,effectiveness evaluation and performance analysis.