Performance Evaluation of an Active Learning System Using Smartphone: A Case Study for High Level Class

Author(s):  
Noriyasu Yamamoto ◽  
Noriki Uchida
Author(s):  
Peng Lu ◽  
Xiao Cong ◽  
Dongdai Zhou

Nowadays, E-learning system has been widely applied to practical teaching. It was favored by people for its characterized course arrangement and flexible learning schedule. However, the system does have some problems in the process of application such as the functions of single software are not diversified enough to satisfy the requirements in teaching completely. In order to cater more applications in the teaching process, it is necessary to integrate functions from different systems. But the difference in developing techniques and the inflexibility in design makes it difficult to implement. The major reason of these problems is the lack of fine software architecture. In this article, we build domain model and component model of E-learning system and components integration method on the basis of WebService. And we proposed an abstract framework of E-learning which could express the semantic relationship among components and realize high level reusable on the basis of informationized teaching mode. On this foundation, we form an E-learning oriented layering software architecture contain component library layer, application framework layer and application layer. Moreover, the system contains layer division multiplexing and was not built upon developing language and tools. Under the help of the software architecture, we could build characterized E-learning system flexibly like building blocks through framework selection, component assembling and replacement. In addition, we exemplify how to build concrete E-learning system on the basis of this software architecture.


2020 ◽  
Author(s):  
Yaoguang Zhai ◽  
Alessandro Caruso ◽  
Sicun Gao ◽  
Francesco Paesani

<div> <div> <div> <p>The efficient selection of representative configurations that are used in high-level electronic structure calculations needed for the development of many-body molecular models poses a challenge to current data-driven approaches to molecular simulations. Here, we introduce an active learning (AL) framework for generating training sets corresponding to individual many-body contributions to the energy of a N-body system, which are required for the development of MB-nrg potential energy functions (PEFs). Our AL framework is based on uncertainty and error estimation, and uses Gaussian process regression (GPR) to identify the most relevant configurations that are needed for an accurate representation of the energy landscape of the molecular system under exam. Taking the Cs<sup>+</sup>–water system as a case study, we demonstrate that the application of our AL framework results in significantly smaller training sets than previously used in the development of the original MB-nrg PEF, without loss of accuracy. Considering the computational cost associated with high-level electronic structure calculations for training set configurations, our AL framework is particularly well-suited to the development of many-body PEFs, with chemical and spectroscopic accuracy, for molecular simulations from the gas to condensed phase. </p> </div> </div> </div>


2020 ◽  
Author(s):  
Yaoguang Zhai ◽  
Alessandro Caruso ◽  
Sicun Gao ◽  
Francesco Paesani

<div> <div> <div> <p>The efficient selection of representative configurations that are used in high-level electronic structure calculations needed for the development of many-body molecular models poses a challenge to current data-driven approaches to molecular simulations. Here, we introduce an active learning (AL) framework for generating training sets corresponding to individual many-body contributions to the energy of a N-body system, which are required for the development of MB-nrg potential energy functions (PEFs). Our AL framework is based on uncertainty and error estimation, and uses Gaussian process regression (GPR) to identify the most relevant configurations that are needed for an accurate representation of the energy landscape of the molecular system under exam. Taking the Cs<sup>+</sup>–water system as a case study, we demonstrate that the application of our AL framework results in significantly smaller training sets than previously used in the development of the original MB-nrg PEF, without loss of accuracy. Considering the computational cost associated with high-level electronic structure calculations for training set configurations, our AL framework is particularly well-suited to the development of many-body PEFs, with chemical and spectroscopic accuracy, for molecular simulations from the gas to condensed phase. </p> </div> </div> </div>


2018 ◽  
Vol 24 (4) ◽  
pp. 733-754
Author(s):  
Hyeon Woo Lee ◽  
Yoon Mi Cha ◽  
Kibeom Kim Kibeom Kim

2016 ◽  
Author(s):  
S. Asawapayukkul ◽  
R. Laochamroonvorapongse ◽  
M. Pancharoen ◽  
Y. Rattanarujikorn ◽  
V. Tivayanonda ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document