Back to Table of contents

Primeur weekly 2017-04-03

Focus

Luxembourg capital of supercomputing in Europe ...

Quantum computing

Quantum communication: How to outwit noise ...

Rigetti Computing raises $64 million in Series A and B funding, led by Andreessen Horowitz and Vy Capital ...

Focus on Europe

HPC Summit Week 2017 in Barcelona to gather main HPC stakeholders in Europe ...

Six High Performance Computing centres in the UK to be officially launched ...

It is easier for a DNA knot ...

Prof. Dieter Kranzlmüller is new Chairman of the Board of Directors at Leibniz Supercomputing Centre ...

GW4 world-first ARM based production supercomputer launched at national exhibition in the UK ...

Middleware

New version of Univa Grid Engine 2x faster than Sun Grid Engine 6.2u5 ...

Huawei and Altair sign MoU to jointly pursue High-Performance Computing (HPC) opportunities and build industrial simulation Cloud solutions ...

Hardware

New HPC installation to deploy Asetek liquid cooling solution ...

HPE to acquire Nimble Storage to strengthen leadership in hybrid IT ...

New Supermicro rack scale design brings open management for on-demand Cloud scale data centres ...

Supermicro launches new Intel Optane SSD optimized platforms ...

GBP 3 million awarded to Oxford-led consortium for national machine learning computing facility ...

EPCC invests GB 2.4 million in Tier-2 Cirrus system ...

Eurotech continues to lead innovation in embedded and high-performance computing: New designs featuring 2nd generation Intel Xeon Phi and Intel Atom E39XX ...

Officials dedicate Ohio OSC's newest, most powerful supercomputer ...

USC's Information Sciences Institute tapped to produce computing chips technology ...

Applications

Supercomputer puts Colombia on fast track to designing new HIV drugs, science and engineering discovery ...

SDSC announces Annual Supercomputing & Data Science Workshop ...

IBM patents cognitive system to manage self-driving vehicles ...

Cryo-electron microscopy achieves unprecedented resolution using new computational methods ...

Psychologists enlist machine learning to help diagnose depression ...

A seismic mapping milestone ...

Information storage with a nanoscale twist ...

Nanomagnets for future data storage ...

Researchers shoot for success with simulations of laser pulse-material interactions ...

A system based on data science to predict student dropouts ...

The Cloud

Oracle unveils industry-first Cloud Converged Storage to help organisations bridge on-premises and Oracle Cloud storage ...

A system based on data science to predict student dropouts


31 Mar 2017 Barcelona - There is currently a 30% of student dropout in Europe according to Education at a Glance (EAG). In Spain, these figures are between the 25% and 29%. In order to create a tool aimed at lecturers to assess and improve the academic performance and reduce these levels, a team of the Faculty of Mathematics and Computer Science has published an article in the journalPLoS ONEwhich shows a data analysis system to predict student dropout. This tool is based on science data, that is, machine learning techniques.

The study is signed by the researchers Laura Igual and Eloi Puertas, from the Department of Mathematics and Computer Science of the UB, together with Sergi Rovira, student of the bachelor degree in Computer Engineering of the University of Barcelona. This research is part of the Teaching Innovation Project: "Sistema Intel·ligent de Suport als Tutors a la Universitat de Barcelona" - Intelligent System to Support the Teaching Staff at the University of Barcelona, led by Laura Igual, with the participation of researchers of the Faculty of Mathematics and Computer Science, and from the Faculty of Education. The aim is to develop a tool for the lecturers so they receive recommendations and orientation for the students, and can assess the risk of student dropouts.

"Nowadays the role of the tutor is more important than ever in order to prevent students from leaving the university and improve their academic performance. The research proposes a system based on objective data to take hidden information which is important for the students' academic data and therefore, to help teachers to offer their students a personal and proactive orientation", stated Laura Igual.

In this first stage, the objective of the research was to answer the question "is it possible to predict whether a student will continue the second year at university out of the results from the first academic year?" To carry the analysis out the researchers used data from the first and second academic years in three bachelor degrees: Mathematics, Computer Science and Law. To do so, they applied five different data science algorithms, the best of which has shown a precision of 82%. Both the algorithm and anonymous data are publicly published inPLoS ONE.

The previous studies on university dropouts in this field were focused on statistical models, based on a collection of data - usually through interviews - gathering information on the possible causes of study dropout - motivation, relation with students... Statistical models are based on hypotheses taken from the underlying problems. With this, if students' performance factors change over time the assumptions of a statistical model could be obsolete. "However", continued Laura Igual, " machine learning techniques have a predictive use based on objective data, which makes them more adaptable to new data." However, statistical systems are better to determine the reasons students leave their studies. "But the predictive power of these tools is lower", stated Laura Igual. Also, this new focus will allow the teaching staff to have "warnings" about students before registering, she noted.

This system also allows predicting the grades students can get in future courses, which would allow the teachers to give advice or orientation to students.

Within the teaching innovation project, "the following step is to analyze - from an educational perspective - how to use this tool, how to assess its impact and develop a computer application prototype", concluded the researcher.

S. Rovira, E. Puertas, and L. Igual are the authors of "Data-driven System to Predict Academic Grades and Dropout", published inPLoS ONE, February, 2017 - Doi:10.1371/journal.pone.0171207.

Source: Universidad de Barcelona

Back to Table of contents

Primeur weekly 2017-04-03

Focus

Luxembourg capital of supercomputing in Europe ...

Quantum computing

Quantum communication: How to outwit noise ...

Rigetti Computing raises $64 million in Series A and B funding, led by Andreessen Horowitz and Vy Capital ...

Focus on Europe

HPC Summit Week 2017 in Barcelona to gather main HPC stakeholders in Europe ...

Six High Performance Computing centres in the UK to be officially launched ...

It is easier for a DNA knot ...

Prof. Dieter Kranzlmüller is new Chairman of the Board of Directors at Leibniz Supercomputing Centre ...

GW4 world-first ARM based production supercomputer launched at national exhibition in the UK ...

Middleware

New version of Univa Grid Engine 2x faster than Sun Grid Engine 6.2u5 ...

Huawei and Altair sign MoU to jointly pursue High-Performance Computing (HPC) opportunities and build industrial simulation Cloud solutions ...

Hardware

New HPC installation to deploy Asetek liquid cooling solution ...

HPE to acquire Nimble Storage to strengthen leadership in hybrid IT ...

New Supermicro rack scale design brings open management for on-demand Cloud scale data centres ...

Supermicro launches new Intel Optane SSD optimized platforms ...

GBP 3 million awarded to Oxford-led consortium for national machine learning computing facility ...

EPCC invests GB 2.4 million in Tier-2 Cirrus system ...

Eurotech continues to lead innovation in embedded and high-performance computing: New designs featuring 2nd generation Intel Xeon Phi and Intel Atom E39XX ...

Officials dedicate Ohio OSC's newest, most powerful supercomputer ...

USC's Information Sciences Institute tapped to produce computing chips technology ...

Applications

Supercomputer puts Colombia on fast track to designing new HIV drugs, science and engineering discovery ...

SDSC announces Annual Supercomputing & Data Science Workshop ...

IBM patents cognitive system to manage self-driving vehicles ...

Cryo-electron microscopy achieves unprecedented resolution using new computational methods ...

Psychologists enlist machine learning to help diagnose depression ...

A seismic mapping milestone ...

Information storage with a nanoscale twist ...

Nanomagnets for future data storage ...

Researchers shoot for success with simulations of laser pulse-material interactions ...

A system based on data science to predict student dropouts ...

The Cloud

Oracle unveils industry-first Cloud Converged Storage to help organisations bridge on-premises and Oracle Cloud storage ...