利用无机化学在线课程资源，开展翻转课堂的教学实践

During the years of 2015 to 2018, the inorganic chemistry course in Tianjin University has gradually transited from small private on-line course (SPOC) to flipped classroom. Flipped classroom teaching practices were carried out at more than 30 classes at our university by the sufficient use of on-line course resources. These practices effectively improve the quality of teaching, and greatly solve the problem of poor learning initiative and low participation of the students existing in current traditional teaching model. This article in detail introduces and summarizes the following four aspects, including transition of teaching modes, construction of online resources, online and offline supervising, test scores analysis and teaching thought. The effective ways for flipped classroom mode are discussed to improve students' knowledge and learning ability. And it also provides references for teachers to carry out their classroom teaching reform.     

深度融合云环境自身架构的东西向攻击检测技术研究

随着云和容器等虚拟化技术的不断扩张,云、数据中心和企业网中的东西向流量呈快速增长趋势。如果不采集虚拟网络流量,用户80%的网络流量将呈现“黑盒”状态,无法对云平台内东西向量进行安全管控,在等保2.0云计算安全扩展中明确要求针对虚机之间、宿主机与虚机间的流量需要进行检测和异常告警。本文通过对业内现有东西向流量检测方案进行分析,研究并提出一种与云平台自身架构深度融合且非侵入式的流量获取方式,基于大数据分析和机器学习算法提升攻击检测能力的整体方案,此外还研究了融合过程中与云平台业务自动适配的问题。     

Diagnosis of learner dropout based on learning styles for online distance learning

The amount of data generated by computer systems in Online Distance Learning (ODL) contains rich information. One example of this information we define as the Learner Learning Trail (LLT), which is the sequence of interactions between the students and the virtual environment. Another example is the Learner Learning Style (LLS), which is associated with the student behavior and choices during the learning process. This information can be used to identify learner behavior and learning style. We perceived, after the study of related literature, that the research field of learner diagnosis for ODL does not apply the conjoint use of LLT and LLS. In this article, we propose a model capable of integrating data generated from the behavior of students in ODL with cognitive aspects of them, such as their Learning Styles, by crossing LLT with LLS. We also propose the CPAD method (Collect, Preprocessing, Analysis, Diagnosis), which is implemented by collecting the raw data regarding learning activities, preprocessing the data into structured time sequences, analyzing the sequences regarding the learning styles and using this analysis to diagnose the learner behavior. We selected the dropout to investigate, once the dropout rate in ODL is a real problem in universities around the world. In addition, the dropout is a student decision which can be associated with previous students behaviors. We performed a study with 202 learners to evaluate if learning styles are capable of explaining aspects of the student behavior. The results suggest that Sequential/Global learning style dimension is more capable of explaining the dropout than the other dimensions. Also, we performed four classification experiments to verify how the dimensions of Felder-Silverman Learning Style Model influence the learner diagnosis. We perceived that the Sequential/Global dimension could provide a higher accuracy average with lower variation independently of the diagnosis technique.     

航空公司电子客票航班查询动态缓存系统设计

本文采用机器学习技术实现航空公司电子客票航班查询的动态缓存.针对第三方大量抓取航空公司网站航班数据的问题,进行访问行为分析,建立航班查询缓存模型并进行系统改造,以达到降低查询预订比的效果.     

Learning and approximation by Gaussians on Riemannian manifolds

Learning function relations or understanding structures of data lying in manifolds embedded in huge dimensional Euclidean spaces is an important topic in learning theory. In this paper we study the approximation and learning by Gaussians of functions defined on a d-dimensional connected compact C ^∞ Riemannian submanifold of which is isometrically embedded. We show that the convolution with the Gaussian kernel with variance σ provides the uniform approximation order of O(σ ^s ) when the approximated function is Lipschitz s ∈(0, 1]. The uniform normal neighborhoods of a compact Riemannian manifold play a central role in deriving the approximation order. This approximation result is used to investigate the regression learning algorithm generated by the multi-kernel least square regularization scheme associated with Gaussian kernels with flexible variances. When the regression function is Lipschitz s, our learning rate is (log² m)/m) ^{s/(8 s + 4 d)} where m is the sample size. When the manifold dimension d is smaller than the dimension n of the underlying Euclidean space, this rate is much faster compared with those in the literature. By comparing approximation orders, we also show the essential difference between approximation schemes with flexible variances and those with a single variance. Supported partially by the Research Grants Council of Hong Kong [Project No. CityU 103405], City University of Hong Kong [Project No. 7001983], National Science Fund for Distinguished Young Scholars of China [Project No. 10529101], and National Basic Research Program of China [Project No. 973-2006CB303102].     

Small Data Can Play a Big Role in Chemical Discovery

The chemistry community is currently witnessing a surge of scientific discoveries in organic chemistry supported by machine learning (ML) techniques. Whereas many of these techniques were developed for big data applications, the nature of experimental organic chemistry often confines practitioners to small datasets. Herein, we touch upon the limitations associated with small data in ML and emphasize the impact of bias and variance on constructing reliable predictive models. We aim to raise awareness to these possible pitfalls, and thus, provide an introductory guideline for good practice. Ultimately, we stress the great value associated with statistical analysis of small data, which can be further boosted by adopting a holistic data-centric approach in chemistry.     

关于职业院校PLC课程的教学质量提升策略分析

职业院校毕业的学生其在未来工作中的表现如何在很大程度上取决于职业院校的教学质量如何.本文所提出的一些办法可以调动学生学习的积极性和主动性,实现自主学习,在提升PLC课程教学质量的同时也保障学生良好的学习效果,希望能为今后职业院校PLC课程教学的深入发展奠定良好的基础.     

Assessment model of classroom acoustics criteria for enhancing speech intelligibility and learning quality

In this paper, a new classroom acoustics assessment model (CAAM) based on analytic hierarchy process (AHP) for enhancing speech intelligibility and learning quality is proposed. The model is based on five main criteria that affect the learning process and related to classrooms acoustical properties. These include classroom specifications, noise sources inside and outside the classroom, teaching style, and vocal effort. The priority and weights of these major criteria along with their alternatives are identified using the views of students, staff, education consultants, and expertise by using a developed questionnaire, and the AHP methodology. This model can be considered as a helpful framework enabling universities decision makers to take effective decisions on classroom acoustics treatment issues. It also provides colleges’ higher authorities the suitable guidelines that help for determining necessary requirements that help to raise the quality and efficiency of the educational environment; in order to reach an excellent learning environment; and hence increasing students learning outcomes.     

改进人工蜂群算法优化ELM分类模型

针对极限学习机(Extreme Learning Machine,ELM)参数优化问题,提出改进人工蜂群算法(Improvement Artificial bee colony, IABC)优化ELM分类模型。算法采用解更新策略池代替固定不变的更新策略,将邻域搜索自适应化;优化侦察蜂搜索方式,利用Kent映射产生均匀性更优的初始随机数序列。在分类数据集中,将IABC-ELM分类模型同ELM、PSO-ELM分类模型进行对比实验。实验中,IABC-ELM模型取得了最佳的分类结果,得到了最低的输出权重范数。结果表明,IABC-ELM模型分类效果显著优于对比模型,证实了IABC算法优化ELM分类模型的有效性和优越性。     

基于模糊多核学习的改进支持向量机算法研究

针对传统SVM对噪声点和孤立点敏感的问题,以及不能解决样本特征规模大、含有异构信息、在特征空间中分布不平坦的问题,将模糊隶属度融入多核学习中,提出了一种模糊多核学习的方法。通过实验验证了模糊多核学习比传统SVM、模糊支持向量机以及多核学习具有更好的分类效果,从而验证了所提方法能够有效的克服传统SVM对噪声点敏感以及数据分布不平坦的问题。