An improved ensemble learning machine for biological activity prediction of tyrosine kinase inhibitors

Boosting is one of the most important strategies in ensemble learning because of its ability to improve the stability and performance of weak learners. It is nonparametric, multivariate, fast and interpretable but is not robust against outliers. To enhance its prediction accuracy as well as immunize it against outliers, a modified version of a boosting algorithm (AdaBoost R2) was developed and called AdaBoost R3. In the sampling step, extremum samples were added to the boosting set. In the robustness step, a modified Huber loss function was applied to overcome the outlier problem. In the output step, a deterministic threshold was used to guarantee that bad predictions do not participate in the final output. The performance of the modified algorithm was investigated with two anticancer data sets of tyrosine kinase inhibitors, and the mechanism of inhibition was studied using the relative weighted variable importance procedure. Investigating the effect of base learner's strength reveals that boosting is only successful using the classification and regression tree method (a weak to moderate learner) and does not have a significant effect using the radial basis functions partial least square method (a strong base learners). Copyright © 2015 John Wiley & Sons, Ltd.     

Induction of decision trees using genetic programming for modelling ecotoxicity data: adaptive discretization of real-valued endpoints

Recent literature has demonstrated the applicability of genetic programming to induction of decision trees for modelling toxicity endpoints. Compared with other decision tree induction techniques that are based upon recursive partitioning employing greedy searches to choose the best splitting attribute and value at each node that will necessarily miss regions of the search space, the genetic programming based approach can overcome the problem. However, the method still requires the discretization of the often continuous-valued toxicity endpoints prior to the tree induction. A novel extension of this method, YAdapt, is introduced in this work which models the original continuous endpoint by adaptively finding suitable ranges to describe the endpoints during the tree induction process, removing the need for discretization prior to tree induction and allowing the ordinal nature of the endpoint to be taken into account in the models built.     

基于图像处理的闸机口跳闸事件检测算法

文中提出了一种基于图像处理的闸机口跳闸事件检测方法。首先,利用模板匹配的方法进行预处理,得到闸门图像匹配率;其次,根据跳闸事件的连贯性特点,提取一段连续时间序列的匹配率作为分类特征;最后,采取基于最小错误率的贝叶斯分类方法对这段时间序列特征向量进行分类。实验表明,该算法可以有效的检测出闸机口的跳闸事件,具有实时性好、不需要额外的传感器、成本低的优点,具有较好的工程应用前景。     

基于改进极根学习机的回转窑煅烧带温度预测方法

针对传统算法预测回转窑煅烧带温度存在精度低、速度慢的问题,提出了基于改进极限学习机(ELM)的回转窑煅烧带温度预测方法。对ELM输入权值矩阵定义了变换系数,采用黄金分割法在给定区间内搜寻变换系数的最佳值,改进了ELM网络参数的确定方式,弥补了随机确定输入权值并且不作调整的缺陷,在保证ELM训练速度的前提下提高预测精度、减小模型随机性。实验结果表明,改进的ELM预测精度高、训练速度快、模型性能优,可满足工况恶劣的回转窑的生产需要。     

基于MetropolisQ学习的蜂窝网络在线信道分配

针对现有的蜂窝网络的在线动态分配模型具有的信道需求量大、呼叫动态变化时阻塞率高和收敛速度慢的缺点,设计了一种基于MetropoisQ学习的蜂窝网络的在线信道分配方法。首先,在考虑同信道限制、邻居信道限制和同小区限制的基础上,设计了在线信道分配的数学模型,然后在Q-Learning算法基础上的设计了一种基于资格迹的Q(λ)算法实现信道的在线分配,为了进一步提高收敛速度,采用Metropois规则对算法中动作的选择方式进行改进,实现探索和利用的平衡。为了验证文中方法,采用Matlab工具上进行实验,仿真实验结果表明文中方法能实现蜂窝通信网络的在线信道分配,且与其它方法比较,具有较少的信道需求量、较低的阻塞率和收敛速度,较其它方法具有较大优越性。     

结合PBL课例的无机化学线下对分课堂教学设计与实践*

以原电池一节教学设计为例,探索了将PBL课例融入对分课堂教学模式。教学实践表明,新教学模式激发了学生的学习兴趣,提高了学生学习的积极性和主动性,提升了课程教学效果,达到了课程教学目标。对PBL课例与对分课堂有机融合的全新课堂教学模式的建设与发展进行了展望。     

基于深度学习理论的有机合成课程教学改革

有机合成既是有机化学学习中的一个独立构成部分,也是安排于有机化学课程之中的重要学习主题。在目前的有机合成课程教学中,教师的自觉性引导不足,学生容易陷入浅层学习状态,导致教学效果不佳。结合有机化学学科特点,从有机合成课程教学现状出发,围绕深度学习教学设计的四要素——深度学习目标、挑战性学习主题、深度学习活动、持续性评价,以典型的教学片段为例阐述深度学习理论在教学实践中的应用,为相关教学工作提供参考。     

基于深度学习的“实验方案设计”主题式复习教学——以“阿司匹林的制备和提纯”为例

针对实验方案设计题的得分率分析和教学现状,基于课程标准、教材、真题和文献研究,构建“阿司匹林的制备和提纯”深度学习主题模型。通过设计制备和提纯阿司匹林的实验方案,构建实验方案设计的思维模型,并以制备七水合硫酸锌为例内化思维模型,在解决真实、复杂的问题过程中实现核心知识结构化,生成指向深度学习的主题式复习教学流程。     

基于奥苏贝尔学习理论对人教版和鲁科版高中化学教材“化学键”的比较及建议

以奥苏贝尔学习理论为基础,比较人教版与鲁科版化学教材“化学键”内容,对教材的引言、正文编排顺序、正文内容组织、正文栏目、插图、习题等进行分析,并从奥苏贝尔学习理论角度阐述教材编写及教学建议。