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.     

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.     

A DFT study on mechanisms of CO2 coupling with propargylic alcohols using alkali carbonates

The mechanisms of CO₂ coupling with the propargylic alcohol using alkali carbonates M₂CO₃ (M = Li, Na, K, Cs) have been investigated by means of density functional theory calculations. The calculations reveal that the target product tetronic acid (TA) is yielded through two stages: (a) the formation of the α-alkylidene cyclic carbonate (αACC) intermediate via Cs₂CO₃-mediated carboxylative cyclization of the propargylic alcohol with CO₂, and (b) the conversion of the αACC intermediate with Cs₂CO₃ to produce the cesium salt of the TA. Since the overall kinetic barriers for the two stages are comparable and affordable, the excellent chemoselectivity to the TA should be primarily originated from the high thermodynamic stability of the cesium salt of the TA. Moreover, relative to the TA, the possibility to yield the by-product acyclic carbonate can be excluded due to the both kinetics and thermodynamic inferiority. This result is different from the organic base-mediated reaction. Alternatively, our calculations predict that CsHCO₃ together generated with the cesium salt of the TA might also be an available mediating reagent for the incorporation of CO₂ with the propargylic alcohol. Compared to other alkali carbonates M₂CO₃ (M = Li, Na, K), the stronger basicity of Cs₂CO₃ and the lower ionic potential of cesium ion can raise the effective concentration of the αACC intermediate, and thus the conversion of the αACC intermediate into the cesium salt of the TA can be achieved with high yield.     

Concurrent multiresponse non-linear screening: Robust profiling of webpage performance

Profiling engineered data with robust mining methods continues attracting attention in knowledge engineering systems. The purpose of this article is to propose a simple technique that deals with non-linear multi-factorial multi-characteristic screening suitable for knowledge discovery studies. The method is designed to proactively seek and quantify significant information content in engineered mini-datasets. This is achieved by deploying replicated fractional-factorial sampling schemes. Compiled multi-response data are converted to a single master-response effectuated by a series of distribution-free transformations and multi-compressed data fusions. The resulting amalgamated master response is deciphered by non-linear multi-factorial stealth stochastics intended for saturated schemes. The stealth properties of our method target processing datasets which might be overwhelmed by a lack of knowledge about the nature of reference distributions at play. Stealth features are triggered to overcome restrictions regarding the data normality conformance, the effect sparsity assumption and the inherent collapse of the ‘unexplainable error’ connotation in saturated arrays. The technique is showcased by profiling four ordinary controlling factors that influence webpage content performance by collecting data from a commercial browser monitoring service on a large scale web host. The examined effects are: (1) the number of Cascading Style Sheets files, (2) the number of JavaScript files, (3) the number of Image files, and (4) the Domain Name System Aliasing. The webpage performance level was screened against three popular characteristics: (1) the time to first visual, (2) the total loading time, and (3) the customer satisfaction. Our robust multi-response data mining technique is elucidated for a ten-replicate run study dictated by an L₉(3⁴) orthogonal array scheme where any uncontrolled noise embedded contribution has not been necessarily excluded.     

基于电化学老化衰退模型的锂离子动力电池外特性

当前锂离子动力电池电化学模型存在模型复杂、建模难度大、计算效率低、老化评估效果差的问题,本文提出一种考虑电池衰退老化的机理模型(ADME).本文首先通过有限差分法对伪二维(P2D)电化学模型进行离散降阶处理,得到简化伪二维(SP2D)模型.在SP2D模型的基础上,基于阴阳两极发生的副反应导致的衰退老化现象,提出一种考虑电池衰退老化的机理模型.其次,使用多变量偏差补偿最小二乘法实现模型参数辨识.最后通过动力电池衰退老化性能循环实验,对比分析了恒流、脉冲工况下SP2D模型和ADME模型的终端电压输出.结果表明:ADME模型较为简单、计算效率和估算精度高,可以有效评估电池容量老化衰退,得到理想的锂离子动力电池外特性曲线.     

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。