scholarly journals Towards a provenance-enabled, reproducible, and extensible machine learning platform by integrating databases, web services, containers, and code repositories in a loosely coupled manner

2021 ◽  
Keyword(s):  
Machine Learning ◽  
Web Services ◽  
Loosely Coupled ◽  
Learning Platform

scholarly journals Multi-Agent System Observer: Intelligent Support for Engaged E-Learning

Electronics ◽  
2021 ◽  
Vol 10 (12) ◽  
pp. 1370
Author(s):  
Igor Vuković ◽  
Kristijan Kuk ◽  
Petar Čisar ◽  
Miloš Banđur ◽  
Đoko Banđur ◽  
...  
Keyword(s):  
Machine Learning ◽  
Machine Learning Algorithms ◽  
Intelligent Support ◽  
Course Success ◽  
States Of Emergency ◽  
Learning Platform ◽  
Rapid Spread ◽  
E Learning ◽  
Multi Agent ◽  
Observer System

Moodle is a widely deployed distance learning platform that provides numerous opportunities to enhance the learning process. Moodle’s importance in maintaining the continuity of education in states of emergency and other circumstances has been particularly demonstrated in the context of the COVID-19 virus’ rapid spread. However, there is a problem with personalizing the learning and monitoring of students’ work. There is room for upgrading the system by applying data mining and different machine-learning methods. The multi-agent Observer system proposed in our paper supports students engaged in learning by monitoring their work and making suggestions based on the prediction of their final course success, using indicators of engagement and machine-learning algorithms. A novelty is that Observer collects data independently of the Moodle database, autonomously creates a training set, and learns from gathered data. Since the data are anonymized, researchers and lecturers can freely use them for purposes broader than that specified for Observer. The paper shows how the methodology, technologies, and techniques used in Observer provide an autonomous system of personalized assistance for students within Moodle platforms.

scholarly journals A machine learning platform for the discovery of materials

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Carl E. Belle ◽  
Vural Aksakalli ◽  
Salvy P. Russo
Keyword(s):  
Machine Learning ◽  
Density Functional ◽  
Gw Approximation ◽  
Dft Methods ◽  
Functional Theory ◽  
Unit Cell Size ◽  
Learning Platform ◽  
Photovoltaic Materials ◽  
Wide Range ◽  
Quantum Espresso

AbstractFor photovoltaic materials, properties such as band gap $$E_{g}$$ E g are critical indicators of the material’s suitability to perform a desired function. Calculating $$E_{g}$$ E g is often performed using Density Functional Theory (DFT) methods, although more accurate calculation are performed using methods such as the GW approximation. DFT software often used to compute electronic properties includes applications such as VASP, CRYSTAL, CASTEP or Quantum Espresso. Depending on the unit cell size and symmetry of the material, these calculations can be computationally expensive. In this study, we present a new machine learning platform for the accurate prediction of properties such as $$E_{g}$$ E g of a wide range of materials.

Design and Implementation of Network Management Architecture for Wireless Sensor Networks

2012 ◽  
Vol 433-440 ◽  
pp. 3895-3899 ◽  
Author(s):  
Ray I Chang ◽  
Chi Cheng Chuang
Keyword(s):  
Web Services ◽  
Network Management ◽  
Service Oriented Architecture ◽  
Wireless Sensor ◽  
Memory Space ◽  
Loosely Coupled ◽  
Sensor Platforms ◽  
Management Architecture ◽  
Service Oriented ◽  
Network Management Architecture

Traditional NM (Network Management) techniques can not be applied on WSN (Wireless Sensor Network) due to its features of low computing ability, tiny memory space, and limited energy. A new NMA (Network Management Architecture) for WSN is needed. In this paper, we design a loosely coupled NMA of WSN based on SOA (Service-Oriented Architecture), and have well defined NM interfaces. Finally, we develop a SOA platform for WSN operations according to the NMA. Based on SOA platform, users can compose and use various NM Web Services by internet depending on their requirements. Heavy tasks which need a great deal of computing resources and storage are executed on the SOA platform. Thus, energy consumption and node computation can be decreased. Moreover, external applications use Web Services to integrate SOA platform for WSN. It lowers the difficulty in integrating different sensor platforms and heterogeneous devices.

A Machine Learning Platform for the Discovery of Materials

2020 ◽  
Author(s):  
Carl Belle ◽  
Vural Aksakalli ◽  
Salvy Russo
Keyword(s):  
Machine Learning ◽  
Function Theory ◽  
Gw Approximation ◽  
Dft Methods ◽  
Materials Properties ◽  
Unit Cell Size ◽  
Learning Platform ◽  
Photovoltaic Materials ◽  
Wide Range ◽  
New Machine

Abstract For photovoltaic materials, properties such as band gap E g are critical indicators of the material's suitability to perform a desired function. Calculating E g is often performed using Density Function Theory ( DFT ) methods, although more accurate calculation are performed using methods such as the GW approximation. DFT software often used to compute electronic properties includes applications such as VASP , CRYSTAL, CASTEP or Quantum Expresso . Depending on the unit cell size and symmetry of the material, these calculations can be computationally expensive. In this study, we present a new machine learning platform for the accurate prediction of properties such as E g of a wide range of materials.

Service Discovery Framework for Distributed Embedded Real-Time Systems

2014 ◽  
pp. 126-147 ◽  
Author(s):  
Furkh Zeshan ◽  
Radziah Mohamad ◽  
Mohammad Nazir Ahmad
Keyword(s):  
Web Services ◽  
Real Time ◽  
Context Awareness ◽  
Service Discovery ◽  
Low Cost ◽  
High Volume ◽  
Heterogeneous Environments ◽  
Real Time Systems ◽  
Loosely Coupled ◽  
Time Systems

Embedded systems are supporting the trend of moving away from centralised, high-cost products towards low-cost and high-volume products; yet, the non-functional constraints and the device heterogeneity can lead to system complexity. In this regard, Service-Oriented Architecture (SOA) is the best methodology for developing a loosely coupled, dynamic, flexible, distributed, and cost-effective application. SOA relies heavily on services, and the Semantic Web, as the advanced form of the Web, handles the application complexity and heterogeneity with the help of ontology. With an ever-increasing number of similar Web services in UDDI, a functional description of Web services is not sufficient for the discovery process. It is also difficult to rank the similar services based on their functionality. Therefore, the Quality of Service (QoS) description of Web services plays an important role in ranking services within many similar functional services. Context-awareness has been widely studied in embedded and real-time systems and can also play an important role in service ranking as an additional set of criteria. In addition, it can enhance human-computer interaction with the help of ontologies in distributed and heterogeneous environments. In order to address the issues involved in ranking similar services based on the QoS and context-awareness, the authors propose a service discovery framework for distributed embedded real-time systems in this chapter. The proposed framework considers user priorities, QoS, and the context-awareness to enable the user to select the best service among many functional similar services.

Service-Oriented Agents and Meta-Model Driven Implementation

2005 ◽  
pp. 270-291 ◽  
Author(s):  
Yinsheng Li ◽  
Hamada Ghenniwa ◽  
Weiming Shen
Keyword(s):  
Web Services ◽  
Software Agents ◽  
Software Modeling ◽  
Semantic Description ◽  
Implementation Framework ◽  
Meta Model ◽  
Model Driven ◽  
Loosely Coupled ◽  
Dynamic Composition ◽  
Service Oriented

Current efforts have not enforced Web services as loosely coupled and autonomous entities. Web services and software agents have gained different focuses and accomplishments due to their development and application backgrounds. This chapter proposes service-oriented agents (SOAs) to unify Web services and software agents. Web services features can be well realized through introducing software agents’ sophisticated software modeling and interaction behaviors. We present a natural framework to integrate their related technologies into a cohesive body. Several critical challenges with SOAs have been addressed. The concepts, system and component structures, a meta-model driven semantic description, agent-oriented knowledge representation, and an implementation framework are proposed and investigated. They contribute to the identified setbacks with Web services technologies, such as dynamic composition, semantic description, and implementation framework. A prototype of the proposed SOAs implementation framework has been implemented. Several economic services are working on it.

Improvement of Self-Assessment Effectiveness by Activity Monitoring and Analysis

2012 ◽  
pp. 1779-1798
Author(s):  
Dumitru Dan Burdescu ◽  
Marian Cristian Mihaescu
Keyword(s):  
Machine Learning ◽  
Open Source ◽  
Input Data ◽  
Software System ◽  
Business Logic ◽  
Self Assessment ◽  
Student Activities ◽  
Learning Platform ◽  
Engineering Department ◽  
E Learning

Self-assessment is one of the crucial activities within e-learning environments that provide learners with feedback regarding their level of accumulated knowledge. From this point of view, the authors think that guidance of learners in self-assessment activity must be an important goal of e-learning environment developers. The scope of the chapter is to present a recommender software system that runs along the e-learning platform. The recommender software system improves the effectiveness of self-assessment activities. The activities performed by learners represent the input data and the machine learning algorithms are used within the business logic of the recommender software system that runs along the e-learning platform. The output of the recommender software system is represented by advice given to learners in order to improve the effectiveness of self-assessment process. The methodology for obtaining improvement of self-assessment is based on embedding knowledge management into the business logic of the e-learning platform. Naive Bayes Classifier is used as machine learning algorithm for obtaining the resources (e.g., questions, chapters, and concepts) that need to be further accessed by learners. The analysis is accomplished for disciplines that are well structured according to a concept map. The input data set for the recommender software system is represented by student activities that are monitored within Tesys e-learning platform. This platform has been designed and implemented within Multimedia Applications Development Research Center at Software Engineering Department, University of Craiova. Monitoring student activities is accomplished through various techniques like creating log files or adding records into a table from a database. The logging facilities are embedded in the business logic of the e-learning platform. The e-learning platform is based on a software development framework that uses only open source software. The software architecture of the e-learning platform is based on MVC (model-view-controller) model that ensures the independence between the model (represented by MySQL database), the controller (represented by the business logic of the platform implemented in Java) and the view (represented by WebMacro which is a 100% Java open-source template language).

Sign in / Sign up

Export Citation Format

Share Document