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.     

Atomic-scale simulations for lithium dendrite growth driven by strain gradient

Dendrite formation is a major obstacle, e.g., capacity loss and short circuit, to the next-generation high-energy-density lithium (Li)-metal batteries. The development of successful Li dendrite mitigation strategies is impeded by an insufficient understanding in Li dendrite growth mechanisms. The Li-plating-induced internal stress in Li-metal and its effects on dendrite growth have been widely studied, but the underlying microcosmic mechanism is elusive. In the present study, the role of the plating-induced stress in dendrite formation is analyzed through first-principles calculations and ab initio molecular dynamic (AIMD) simulations. It is shown that the deposited Li forms a stable atomic nanofilm structure on the copper (Cu) substrate, and the adsorption energy of Li atoms increases from the Li-Cu interface to the deposited Li surface, leading to more aggregated Li atoms at the interface. Compared with the pristine Li-metal, the deposited Li in the early stage becomes compacted and suffers the in-plane compressive stress. Interestingly, there is a giant strain gradient distribution from the Li-Cu interface to the deposited Li surface, making the deposited atoms adjacent to the Cu surface tend to press upwards with perturbation and causing the dendrite growth. This provides an insight into the atomicscale origin of Li dendrite growth, and may be useful for suppressing the Li dendrite in Li-metal-based rechargeable batteries.     

用标准件对梯度磁场定标

就标准厚度卡片在霍尔传感器的定标方面的应用作了有益的探讨。在纵向测量微小长度时,霍尔片处于磁场边缘位置,其对磁场的梯度更大,即灵敏度更高,且靠中心位置的线性更好。     

三维位势问题的梯度边界积分方程的新解法

三维位势问题的边界元分析中,关于坐标变量的边界位势梯度的计算是一个困难的问题. 已有一些方法着手解决这个问题,然而,这些方法需要复杂的理论推导和大量的数值计算. 本文提出求解一般边界位势梯度边界积分方程的辅助边值问题法. 该方法构造了与原边界值问题具有相同解域的辅助边值问题,该辅助边值问题具有已知解,因此通过求解此辅助边值问题,可获得梯度边界积分方程对应的系统矩阵,然后将此系统矩阵应用于求解原边值问题,求解过程非常简单,只需求解一个线性系统即可获得原边值问题的解. 值得注意的是,在求解原边值问题时,不再需要重新计算系统矩阵,因此辅助边值问题法的效率并不很差. 辅助边值问题法避免了强奇异积分的计算,具有数学理论简单、程序设计容易、计算精度高等优点,为坐标变量梯度边界积分方程的求解提供了一个新的途径. 3个标准的数值算例验证了方法的有效性.      

Skyrmion transport driven by pure voltage generated strain gradient

The magnetic skyrmion transport driven by pure voltage-induced strain gradient is proposed and studied via micromagnetic simulation. Through combining the skyrmion with multiferroic heterojunction, a voltage-induced uniaxial strain gradient is adjusted to move skyrmions. In the system, a pair of short-circuited trapezoidal top electrodes can generate the symmetric strain. Due to the symmetry of strain, the magnetic skyrmion can be driven with a linear motion in the middle of the nanostrip without deviation. We calculate the strain distribution generated by the trapezoidal top electrodes pair, and further investigate the influence of the strain intensity as well as the strain gradient on the skyrmion velocity. Our findings provide a stable and low-energy regulation method for skyrmion transport.     

A volatolomic approach using cerumen as biofluid to diagnose bovine intoxication by Stryphnodendron rotundifolium

An innovative volatolomic approach employs the detection of biomarkers present in cerumen (earwax) to identify cattle intoxication by Stryphnodendron rotundifolium Mart., Fabaceae (popularly known as barbatimão). S. rotundifolium is a poisonous plant with the toxic compound undefined and widely distributed throughout the Brazilian territory. Cerumen samples from cattle of two local Brazilian breeds (‘Curraleiro Pé-Duro’ and ‘Pantaneiro’) were collected during an experimental intoxication protocol and analyzed using headspace (HS)/GC–MS followed by multivariate analysis (genetic algorithm for a partial least squares, cluster analysis, and classification and regression trees). A total of 106 volatile organic metabolites were identified in the cerumen samples of bovines. The intoxication by S. rotundifolium influenced the cerumen volatolomic profile of the bovines throughout the intoxication protocol. In this way, it was possible to detect biomarkers for cattle intoxication. Among the biomarkers, 2-octyldecanol and 9-tetradecen-1-ol were able to discriminate all samples between intoxicated and nonintoxicated bovines. The cattle intoxication diagnosis by S. rotundifolium was accomplished by applying the cerumen analysis using HS/GC–MS, in an easy, accurate, and noninvasive way. Thus, the proposed bioanalytical chromatography protocol is a useful tool in veterinary applications to determine this kind of intoxication.     

卷积神经网络用于近红外光谱古筝面板木材分级

目前,我国乐器制作行业在古筝面板用木材等级的筛选上主要依赖于技师主观评判,但此法缺少科学理论的依据,效率低,客观性及出材率的提高等方面受到限制,无法满足乐器市场的大量需求。实现古筝面板用木材快速、智能化的分级工作是一个急需解决的课题。近红外光谱非常适用于测量含氢的有机物质。古筝面板木材主要化学成分的化学键均由含氢基团组成,不同等级板材的化学成分存在差异,这些差异反映在近红外光谱中,为判断木材等级提供了可能。同时卷积神经网络对非线性数据具有较强的特征提取能力,所以提出一种应用卷积神经网络模型对光谱数据进行分析的方法,进而判别木材的等级。应用了Savitzky Golay一阶、二阶微分两种预处理方法和核主成分分析、连续投影算法两种数据压缩方法,通过所设计的卷积神经网络模型以样本识别准确率和模型构建过程中的损失值作为判定指标选出最佳预处理和数据压缩方法。为了提高模型提取分析光谱数据的能力和避免过拟合现象,应用了多通道卷积核、批量归一化和early stopping策略,将通过两层卷积层提取的特征信息送入全连接层,从而充分提取剩余信息,通过Softmax函数获得板材的最终预测等级,从而确定了最终模型。最终Savitzky Golay一阶微分和核主成分分析为最佳数据处理方法,同时得出用于区分不同等级的古筝面板用木材的主要关键谱带,分别为1 163~1 243, 1 346~1 375和1 525~1 584 nm。将该模型应用于测试集样本,古筝面板用木材的等级识别准确率为95.5%。实验结果表明所提出的方法可以高效地处理光谱数据,有效识别区分不同等级的古筝面板用木材的关键特征,从而为广阔的乐器市场提供一定的技术支持。     

语音通信降噪研究

语音通信系统中，语音通过信道传输将不可避免地引入码间串扰和信号畸变，同时受到噪声污染。本文在分析自适应盲均衡算法CMA(constant modulus algorithm）和改进盲均衡算法的基础上，考虑到自适应盲均衡技术在语音噪声控制方面能力有限，将自适应盲均衡技术与小波包掩蔽阈值降噪算法联合使用，形成一种基带语音增强新方法。仿真试验结果显示自适应盲均衡技术可以使星座图变得清晰而紧凑，有效减小误码率。研究证实该方法在语音信号ISI和畸变严重情况下，在白噪及有色噪声不同的噪声环境中都具有稳定的降噪能力，消噪同时可获得汉语普通话良好的听觉效果。     

一阶最优性条件研究

本对由Botsko的关于多变量函数取极值的一阶导数检验条件定理^[1]进行了分析研究，给出了更实用而简捷的差别条件。最后，举出若干例子予以说明。