Search

In order to find out the appropriate measures for soil water preservation and wheat yield increase, a three–year field experiment was conducted in Yuzhou Experimental Station of Water Saving Agriculture in the west of Henan Province, China, during the growing seasons of 2014–2015, 2015–2016 and 2016–2017 to study the effects of different tillage modes and soil mulching measures on dynamics of soil moisture and temperature, photosynthetic characteristics and yield of winter wheat (Triticum aestivum L.). The results showed that straw coverage and film mulching measures under the conventional tillage and no tillage modes increased soil moisture by 4.4%–27.3%,13.4%–41.8% and 6.2%–46.7%, 2.4%–80.2%, respectively. The treatments of soil surface coverage measures under both conventional tillage and no tillage modes at tillering stage increased the temperature of soil layer at 10 cm and 15 cm depth by 9.1%–18.2% and 10.0%–40.0% in 2014–2015, while mulching measures under the conventional tillage obviously increased soil temperature at wintering stage but decreased soil temperature at booting and mature stages in 2016–2017. However, mulching measures under no tillage mode reduced soil temperature in shallower layer during seedling establishment stage in the three–year period of 2014–2017. Moreover, the two mulching measures raised net photosynthetic rate (Pn) and water use efficiency (WUE) of functional leaves under the conventional tillage mode and reduced transpiration rate (Tr) at the filling stage. Except straw coverage measures under no tillage in 2015–2016, the combination of mulching measures under no tillage reduced Pn, Tr and WUE of wheat leaves at filling stage as compared to those without mulching measures. Under the conventional tillage mode, straw coverage increased wheat yield by 6.4%–9.3%, mainly due to the increase in the number of grains per panicle. Under no tillage mode, both straw coverage and mulching measures reduced wheat yield to different extents and film mulching measures was more effective than straw coverage. The combination of conventional tillage and straw mulching resulted in a yield of 8425.9–8888.9 kg hm−2, so this combination was recommended as the optimal treatment under the conditions set in this study.

To deal with the issues like existing common data sparseness in weibo social network and the phenomena of cold start, this paper puts forward a two-stage clustering based on the recommendation algorithm GCCR. The algorithm firstly selects users’ focused nodes which have higher number, so as to extract a dense subset of sparse data, and by using the method of graph paper, similar concerned interested core clustering is formed to this dense subset. Then, it is extracted that weibo content features of seed clustering and the whole data set other users. Then the entire user group is clustered based on content similarity. Finally the clustering results are used in subject recommendation. Through clustering the two phases of dense data subset and the whole data set, the clustering effect of extreme sparse data sets are improved. At the same time, because of fuzziness of graph clustering, this thesis retains a certain diversity in the process of user interest clustering, so as to avoid convergence too fast when cold start. This method is verified through the real social network data, and the experimental results show that this algorithm can effectively solve the problems such as data sparseness and cold start phenomenon.

To improve the search accuracy and diversity of non-dominated sorting genetic algorithm (NSGA-II), an improved algorithm DMNSGA-II referencing to the strategy of differential evolution to strengthen local search is proposed in this paper. The algorithm uses mutation guiding operator and crossover operator of DE to replace crossover operator in NSGA-II to enhance the local search capability and improve search accuracy. while retaining the mutation operator of NSGA-II to improve diversity. We use four benchmark test problems to investigate the performance of the DMNSGA-II algorithm, and simulation results demonstrate that the proposed algorithm can achieve a good overall performance in multi-objective optimization.