Hyperparameter on-line learning of stochastic resonance based threshold networks

Aiming at training the feed-forward threshold neural network consisting of nondifferentiable activation functions, the approach of noise injection forms a stochastic resonance based threshold network that can be optimized by various gradient-based optimizers. The introduction of injected noise extends the noise level into the parameter space of the designed threshold network, but leads to a highly non-convex optimization landscape of the loss function. Thus, the hyperparameter on-line learning procedure with respective to network weights and noise levels becomes of challenge. It is shown that the Adam optimizer, as an adaptive variant of stochastic gradient descent, manifests its superior learning ability in training the stochastic resonance based threshold network effectively. Experimental results demonstrate the significant improvement of performance of the designed threshold network trained by the Adam optimizer for function approximation and image classification.     

基于深度学习的中医古文献临床经验抽取

中医古文献蕴藏着丰富的临床经验，是古代中医在行医过程中对临床诊疗的经验性总结，体现了中医学形成和发展的理论框架和思想基础.然而这些宝贵的临床经验不仅量大，而且分散在不同的文献中，使得中医从业者手工很难快速全面地获取它们，文献检索工具也只能提供文档级别的信息筛选，无法为这种细粒度的信息获取提供支持.此外，古汉语相对于现代汉语的不同特点也限制了主流文本分析工具的使用效果.为此本文提出面向临床经验获取的中医古文献信息抽取任务，用于识别古文献中描述临床经验的文本片段，手工标注了样本数据用于这种抽取模型的训练和测试，并设计了基于深度学习的序列标注器用于完成该任务.考虑到标注数据量小可能带来的过度拟合问题，本文引入对抗训练和虚拟对抗训练来增强模型的泛化能力.一系列充分的实验验证了模型的有效性，表明利用信息抽取技术从古文献获取中医临床经验具有可行性，为这一新的信息抽取任务提供了有希望的研究基线和可复用的标注数据集.     

基于不确定控制理论的最优策略研究

本文在不确定理论的框架下,研究一类带背景状态变量的最优控制模型.在乐观值准则下,利用不确定动态规划的方法,证明了不确定最优性原则,得到最优性方程.作为应用,求解一个固定缴费(DC)型养老金的最优投资策略问题,在乐观值准则下,以工资变量为背景状态变量,建立养老金模型.通过求解不确定最优性方程得到最优投资策略和最优支付率.     

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.     

高职生“学习参与度”对创新创业核心素养的影响机制研究

通过对523名高职学生进行实地调研,探析“学习参与度”对学生创新创业核心素养的影响机制。结果显示:课程建设、教师引导、资源支持对学习心理参与度影响显著;教师引导、资源支持、社会实践对学习行为参与度影响显著。学习参与度显著影响创业意识、创新精神、创业能力。提出优化对策:重视学生创新创业核心素养的培养;提高学生创新创业学习参与度;人际互动提升学习心理参与度;协同培育提高学习行为参与度。     

Prediction of the drag reduction effect of pulsating pipe flow based on machine learning

Prediction of drag reduction effect caused by pulsating pipe flows is examined using machine learning. First, a large set of flow field data is obtained experimentally by measuring turbulent pipe flows with various pulsation patterns. Consequently, more than 7000 waveforms are applied, obtaining a maximum drag reduction rate and maximum energy saving rate of 38.6% and 31.4%, respectively. The results indicate that the pulsating flow effect can be characterized by the pulsation period and pressure gradient during acceleration and deceleration. Subsequently, two machine learning models are tested to predict the drag reduction rate. The results confirm that the machine learning model developed for predicting the time variation of the flow velocity and differential pressure with respect to the pump voltage can accurately predict the nonlinearity of pressure gradients. Therefore, using this model, the drag reduction effect can be estimated with high accuracy.     

钩形弯交叉口信号协同控制优化方法研究

针对车辆在钩形弯交叉口与相邻常规交叉口间的整体运行特性，建立了各条车道的车辆平均延误计算模型。以各交叉口的周期时长和相位绿灯时间为约束，钩形弯交叉口与相邻常规交叉口间的车辆平均延误最小为目标，建立了信号协同配时方案。以位于苏州市高新区内有轨电车沿线的两个相邻交叉口为例，采用实际数据验证所建立的方法，并设置钩形弯渠化方案。将设置的钩形弯交叉口与其相邻常规交叉口的信号协同作为改进方法，在VISSIM软件中对比分析改进方案与现状方案的车辆延误指标。实验结果表明，钩形弯交叉口与相邻常规交叉口的信号协同优化方法可有效提高交叉口的通行能力，尤其是干道直行机动车的通行能力，可降低车辆的平均延误。     

基于LQG控制的整车8-DOF系统振动分析

建立了整车8-DOF系统动力学模型,考虑了主动悬架控制,并增设了主动座椅控制,设计了车辆主动悬架系统的LQG控制器。基于Matlab仿真平台建立了整车8-DOF系统动力学仿真模型,对所得最优控制策略下的动态响应进行了仿真验证。仿真结果表明:为了改善人椅系统质心及车身质心的跳振性能需要在一定程度上弱化各轮轮胎动位移性能。从控制效能上来看,该最优控制器能够满足各行驶状态下对悬架性能的要求,改善了车辆的行驶平顺性。     

Wave-based vibration control of large cable net structures

Large cable net structures have been widely applied in aerospace engineering due to the feature of light-weight, high packaging efficiency, and high thermal stability. Structural vibrations induced by a variety of disturbances are inevitable in the space environment, resulting in the requirement of effective vibration control strategies for large cable net structures. Since the large cable net structures have many closely spaced vibrational modes in the range of low frequencies, traditional modal based control may cause modal truncation and spillover problems. In this paper, a wave-based boundary control strategy is adopted and its effectiveness to control the vibration of cable net structures is investigated, by transfer function analysis and numerical methods. It is found that the structural vibration can be absolutely resisted by applying the wave-based boundary controllers onto all the exterior nodes, when disturbances come from the external boundaries of the cable net. Our results in this paper can provide a theoretical basis for the vibration control of large cable net structures.     

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。