基于GA_XGBoost模型的大学生科研能力预测问题研究

科学评价大学生科研创新能力对我国科研水平的提高具有重要意义.采用机器学习模型来预测大学生科研能力可以起到良好的效果,提出一种GAXGBoost模型来实现对大学生的科研能力预测.此模型是以Xgboost算法为基础,然后充分利用遗传算法的全局搜索能力自动搜索Xgboost最优超参数,避免了人为经验调参不准确的缺陷,最后采用精英选择策略以此确保每一轮都是最佳的进化结果.通过分析表明,所采用的GAXGBoost模型在大学生科研能力预测的结果中具有很高的精度,将此模型与Logistic Regression、Random Forest、SVM等模型进行对比,GAXGBoost模型的预测精度最高.     

Nonlinear vibration response of a complex aeroengine under the rubbing fault

Nonlinear Dynamics - Rolling bearing and squeeze film damper will introduce structural nonlinearity into the dynamic model of aeroengine. Rubbing will occur due to the clearance reduction design of...     

A Note on Quantum Bell Nonlocality and Quantum Entanglement for High Dimensional Quantum Systems

We study the Bell nonlocality of high dimensional quantum systems based on quantum entanglement. A quantitative relationship between the maximal expectation value B of Bell operators and the quantum entanglement concurrence C is obtained for even dimension pure states, with the upper and lower bounds of B governed by C.

     

Characteristics of black carbon aerosol in Jiaxing,China during autumn 2013

We conducted measurements of black carbon（BC） aerosol in Jiaxing,China during autumn from September 26 to November 30,2013.We investigated temporal and diurnal variations of BC,and its correlations with meteorological parameters and other major pollutants.Results showed that hourly mass concentrations of BC ranged from 0.2 to 22.0 μg/m³,with an average of 5.1 μg/m³.The diurnai variation of BC exhibited a bimodal distribution,with peaks at 07:00 and 18:00.The morning peak was larger than the evening peak.The mass percentages of BC in PM_2.5 and PM₁₀ were 7.1%and 4.8%,respectively.The absorption coefficient of BC was calculated to be 44.4 Mm^-1,which accounted for 11.1%of the total aerosol extinction.BC was mainly emitted from local sources in southwestern Jiaxing where BC concentrations were generally greater than 11 μg/m³ during the measurement period.Correlation analysis indicated that the main sources of BC were motor vehicle exhaust,and domestic and industrial combustion.     

Feasibility study on buoyancy–weight ratios of a submerged floating tunnel prototype subjected to hydrodynamic loads

The research progress of a novel traffic solution,a submerged floating tunnel(SFT),is reviewed in terms of a study approach and loading scenario.Among existing publications,the buoyancy-weight ratio(BWR) is usually predefined.However,BWR is a critical structural parameter that tremendously affects the dynamic behaviour of not only the tunnel tube itself but also the cable system.In the context of a SFT prototype(SFTP) project in Qiandao Lake(Zhejiang Province,China),the importance of BWR is illustrated by finite element analysis and subsequently,an optimized BWR is proposed within a reasonable range in the present study.In the numerical model,structural damping is identified to be of importance.Rayleigh damping and the corresponding Rayleigh coefficients are attained through a sensitivity study,which shows that the adopted damping ratios are fairly suitable for SFTP.Lastly,the human sense of security is considered by quantifying the comfort index,which helps further optimize BWR in the SFTP structural parameter design.     

Ratiometric Detection of microRNA Using Hybridization Chain Reaction and Fluorogenic Silver Nanoclusters

miRNA (miR)-155 is a potential biomarker for breast cancers. We aimed at developing a nanosensor for miR-155 detection by integrating hybridization chain reaction (HCR) and silver nanoclusters (AgNCs). HCR serves as an enzyme-free and isothermal amplification method, whereas AgNCs provide a built-in fluorogenic detection probe that could simplify the downstream analysis. The two components were integrated by adding a nucleation sequence of AgNCs to the hairpin of HCR. The working principle was based on the influence of microenvironment towards the hosted AgNCs, whereby unfolding of hairpin upon HCR has manipulated the distance between the hosted AgNCs and cytosine-rich toehold region of hairpin. As such, the dominant emission of AgNCs changed from red to yellow in the absence and presence of miR-155, enabling a ratiometric measurement of miR with high sensitivity. The limit of detection (LOD) of our HCR-AgNCs nanosensor is 1.13 fM in buffered solution. We have also tested the assay in diluted serum samples, with comparable LOD of 1.58 fM obtained. This shows the great promise of our HCR-AgNCs nanosensor for clinical application.     

紫色球杆菌视紫红质光谱特性的机器学习研究

近年来，机器学习等人工智能技术被应用于蛋白质工程，其在蛋白质结构、功能预测、催化活性等研究中具有独特优势。在未知蛋白质结构的情况下，将蛋白质序列和功能特性与机器学习相结合，基于序列-活性关系（innovative sequence-activity relationship，ISAR）算法，将蛋白质氨基酸序列数字化，用快速傅里叶变换（fast four transform，FFT）进行预处理，再进行偏最小二乘回归建模，可在数据集较少情况下拟合得到最佳模型。通过机器学习对紫色球杆菌视紫红质（gloeobacter violaceus rhodopsin，GR）的突变体蛋白质氨基酸序列与光谱最大吸收波长进行建模，获得了最佳模型。用最佳索引LEVM760106建模得到的确定系数R² 为0.944，均方误差E为11.64。用小波变换进行的预处理，其R² 虽也约为0.944，但E大于11.64，不及FFT进行的预处理。方法较好地解决了蛋白质序列与功能特性之间的数学建模问题，在蛋白质工程中可为预测更优的突变体提供支持。     

The Periods of States for Markov Chains in a Random Environment

The periods of states for Markov chains in a random environment are introduced and some properties about periods are investigated. An open problem (Orey, 1991; Problem 1.3.3) is studied under the assumption that states have periods.     

激光能量对反钙钛矿GaCMn_3薄膜结构与物性的影响

本文采用脉冲激光沉积方法在LaAlO3(001)单晶衬底上制备了反钙钛矿GaCMn3薄膜,通过控制制备过程中脉冲激光的能量,研究了不同激光能量条件对GaCMn3薄膜结构与物理性能的影响.分别利用X射线衍射仪、原子力显微镜、超导量子干涉仪和物理性能测试系统,对所制备的薄膜的晶体结构、表面形貌和磁性、电输运性质进行了研究.结果表明,制备的样品均为具有多个晶面取向的反钙钛矿薄膜,且薄膜结构和物性明显随制备激光能量的变化而变化.当激光能量为450mJ时,制备的薄膜多晶面取向性最弱,结晶性和表面形貌最优良.实验所得的薄膜均表现出顺磁-铁磁-反铁磁相转变,然而转变过程比块材较平缓,同时薄膜的电阻率并未表现出块材中的突变特征,我们推测该现象很可能是由衬底的应力及衬底的晶格膨胀对薄膜反常晶格变化的抑制作用造成的.