新疆阿勒泰地区西部蝗虫发生面积与大气环流特征量指数模型研究(英文)

By analyzing the correlation between the occurrence area of grasshopper and 74 characteristic indexes of atmospheric circulation in western Aletai from 1991 to 2008,the atmospheric circulation factors which had the significant relationship with the occurrence area of grasshopper in different counties were screened.The prediction models for the occurrence area of grasshopper in different counties were established by stepwise regression method,and the models obtained were also tested.These models were subsequently utilized to carry out extended prediction on the occurrence area of grasshopper in different counties of western Aletai from 2009 to 2010.Meanwhile,the relationship between the atmospheric circulation factors and the occurrence area of grasshopper were analyzed.The results provided the theoretical basis for the prediction on grasshopper plague.

A Low-Memory-Requiring and Fast Approach to Cluster Large-Scale Decoy Protein Structures

This work demonstrates the so-called PCAC (Protein principal Component Analysis Clustering) method, which clusters large-scale decoy protein structures in protein structure prediction based on principal component analysis (PCA), is an ultra-fast and low-memory-requiring clustering method. It can be two orders of magnitude faster than the commonlyused pairwise rmsd-clustering (pRMSD) when enormous of decoys are involved. Instead of N(N – 1)/2 least-square fitting of rmsd calculations and N2 memory units to store the pairwise rmsd values in pRMSD, PCAC only requires N rmsd calculations and N × P memory storage, where N is the number of structures to be clustered and P is the number of preserved eigenvectors. Furthermore, PCAC based on the covariance Cartesian matrix generates essentially the identical result as that from the reference rmsd-clustering (rRMSD). From a test of 41 protein decoy sets, when the eigenvectors that contribute a total of 90% eigenvalues are preserved, PCAC method reproduces the results of near-native selections from rRMSD.

High-Resolution Traffic Flow Prediction Model Based on Deep Learning

The time resolution of the existing traffic flow prediction model is too big to be applied to adaptive signal timing optimization.Based on the view of the platoon dispersion model,the relationship between vehicle arrival at the downstream intersection and vehicle departure from the upstream intersection was analyzed.Then,a high-resolution traffic flow prediction model based on deep learning was developed.The departure flow rate from the upstream and the arrival flow rate at the downstream intersection was taking as the input and output in the proposed model,respectively.Finally,the parameters of the proposed model were trained by the field data,and the proposed model was implemented to forecast the arrival flow rate of the downstream intersection.Results show that the proposed model can better capture the fluctuant traffic flow and reduced MAE,MRE,and RMSE by 9.53%,39.92%,and 3.56%,respectively,compared with traditional models and algorithms,such as Robert­son's model and artificial neural network.Therefore,the proposed model can be applied for realtime adaptive signal timing optimization.