scholarly journals Supervised Models for Measuring Performance At E-Learning Environmen

2019 ◽  
Vol 8 (11) ◽  
pp. 2792-2797
Keyword(s):  
Big Data ◽  
Student Performance ◽  
Relational Databases ◽  
Prediction Models ◽  
Data Modeling ◽  
Process Data ◽  
Design Data ◽  
Relationship Model ◽  
E Learning ◽  
Entity Relationship

E-learning data becomes ‘Big’ data as it describes a huge volume of both structured and unstructured data. And inherent limitations of relational databases maintained in this context makes difficult to apply and to extract outputs meaningful. Data modeling is also recommended to design data views at various levels either conceptual or physical here. Most of the educational organizations are keen in collecting, storing and analyzing the students’ data because it will add more significant value to the decision making process. Data modeling through entity relationship model or query views plays a important role in dealing with big data due to the fact around 85% of big data is semi structured data. Hence data modeling should be carried out as required by any learning institution needs. Making big data component to reside in the data model is challenging. This paper is to establish data modeling techniques applied to a reasonably ‘big’ data in e-learning. Prediction models generated from this data will be accurate if the training sets and testing sets are governed properly in spite of data size complexity. Student Performance by study credits (partitioned in three classes: low, medium, high ) are classified with respect to their engagement attributes (activity types, sum of clicks made, duration in days) and obtained maximum accuracy 90.923%.

Objects and Domains for Managing Medical Data and Knowledge

1995 ◽  
Vol 34 (01/02) ◽  
pp. 40-46
Author(s):  
G. Wiederhold
Keyword(s):  
Domain Knowledge ◽  
Relational Databases ◽  
Structural Model ◽  
Algebraic Approach ◽  
Object Oriented ◽  
Relationship Model ◽  
Large Systems ◽  
Entity Relationship ◽  
Data Objects ◽  
Matching Rules

Abstract:This paper assesses the object-oriented data paradigm, and describes an algebraic approach which permits the generation of data objects from relational data, based on the knowledge captured in a formal Entity-Relationship model, the Structural Model. The advantage is that now objects can be created that satisfy a variety of particular views, as long as the hierarchies represented by the views are subsumed in the network represented by the overall structural model.The disadvantage of creating view-objects dynamically is that the additional layering has performance implications, so that the speedup expected from object-oriented databases versus relational databases, due to their hierarchical object storage, cannot be realized. However, scalability of systems is increased since large systems tend to have multiple objectives, and hence often multiple valid hierarchical views over the data. This approach has been implemented in the Penguin project, and recently some commercial successors are emerging.In truly large systems new problems arise, namely that now not only multiple views will exist, but also that the domains to be covered by the data will be autonomous and hence heterogeneous. One result is that ontologies associated with the multiple domains will differ as well. This paper proposes a knowledge-based algebra over the ontologies, so that the domain knowledge can be partitioned for maintenance. Only the articulation points, where the domains intersect, have to be agreed upon as defined by matching rules which define the shared ontologies.

scholarly journals Implementasi Big Data Analytical Untuk Perguruan Tinggi Menggunakan Machine Learning

2021 ◽  
Vol 2 (1) ◽  
pp. 77-88
Author(s):  
Rakhmat Purnomo ◽  
Wowon Priatna ◽  
Tri Dharma Putra
Keyword(s):  
Higher Education ◽  
Machine Learning ◽  
Decision Making ◽  
Big Data ◽  
Data Analysis ◽  
Student Performance ◽  
Big Data Analytics ◽  
Big Data Analysis ◽  
Process Data ◽  
Grouping Students

The dynamics of higher education are changing and emphasize the need to adapt quickly. Higher education is under the supervision of accreditation agencies, governments and other stakeholders to seek new ways to improve and monitor student success and other institutional policies. Many agencies fail to make efficient use of the large amounts of available data. With the use of big data analytics in higher education, it can be obtained more insight into students, academics, and the process in higher education so that it supports predictive analysis and improves decision making. The purpose of this research is to implement big data analytical to increase the decision making of the competent party. This research begins with the identification of process data based on analytical learning, academic and process in the campus environment. The data used in this study is a public dataset from UCI machine learning, from the 33 available varibales, 4 varibales are used to measure student performance. Big data analysis in this study uses spark apace as a library to operate pyspark so that python can process big data analysis. The data already in the master slave is grouped using k-mean clustering to get the best performing student group. The results of this study succeeded in grouping students into 5 clusters, cluster 1 including the best student performance and cluster 5 including the lowest student performance

scholarly journals Modeling and Management Big Data in Databases—A Systematic Literature Review

2020 ◽  
Vol 12 (2) ◽  
pp. 634 ◽  
Author(s):  
Diana Martinez-Mosquera ◽  
Rosa Navarrete ◽  
Sergio Lujan-Mora
Keyword(s):  
Big Data ◽  
Literature Review ◽  
Systematic Literature Review ◽  
Digital Libraries ◽  
Data Modeling ◽  
Unstructured Data ◽  
Publication Data ◽  
Data Source ◽  
Research Questions ◽  
Entity Relationship

The work presented in this paper is motivated by the acknowledgement that a complete and updated systematic literature review (SLR) that consolidates all the research efforts for Big Data modeling and management is missing. This study answers three research questions. The first question is how the number of published papers about Big Data modeling and management has evolved over time. The second question is whether the research is focused on semi-structured and/or unstructured data and what techniques are applied. Finally, the third question determines what trends and gaps exist according to three key concepts: the data source, the modeling and the database. As result, 36 studies, collected from the most important scientific digital libraries and covering the period between 2010 and 2019, were deemed relevant. Moreover, we present a complete bibliometric analysis in order to provide detailed information about the authors and the publication data in a single document. This SLR reveal very interesting facts. For instance, Entity Relationship and document-oriented are the most researched models at the conceptual and logical abstraction level respectively and MongoDB is the most frequent implementation at the physical. Furthermore, 2.78% studies have proposed approaches oriented to hybrid databases with a real case for structured, semi-structured and unstructured data.

scholarly journals Enabling deeper learning on big data for materials informatics applications

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Dipendra Jha ◽  
Vishu Gupta ◽  
Logan Ward ◽  
Zijiang Yang ◽  
Christopher Wolverton ◽  
...  
Keyword(s):  
Neural Networks ◽  
Big Data ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Materials Science ◽  
Prediction Models ◽  
Model Performance ◽  
Materials Informatics ◽  
Learning Framework ◽  
Significant Attention

AbstractThe application of machine learning (ML) techniques in materials science has attracted significant attention in recent years, due to their impressive ability to efficiently extract data-driven linkages from various input materials representations to their output properties. While the application of traditional ML techniques has become quite ubiquitous, there have been limited applications of more advanced deep learning (DL) techniques, primarily because big materials datasets are relatively rare. Given the demonstrated potential and advantages of DL and the increasing availability of big materials datasets, it is attractive to go for deeper neural networks in a bid to boost model performance, but in reality, it leads to performance degradation due to the vanishing gradient problem. In this paper, we address the question of how to enable deeper learning for cases where big materials data is available. Here, we present a general deep learning framework based on Individual Residual learning (IRNet) composed of very deep neural networks that can work with any vector-based materials representation as input to build accurate property prediction models. We find that the proposed IRNet models can not only successfully alleviate the vanishing gradient problem and enable deeper learning, but also lead to significantly (up to 47%) better model accuracy as compared to plain deep neural networks and traditional ML techniques for a given input materials representation in the presence of big data.

Sign in / Sign up

Export Citation Format

Share Document