scholarly journals Determining patterns of student graduation using a bi-level learning framework

2021 ◽  
Vol 10 (4) ◽  
pp. 2201-2211
Author(s):  
Lalida Nanglae ◽  
Natthakan Iam-On ◽  
Tossapon Boongoen ◽  
Komkrit Kaewchay ◽  
James Mullaney
Keyword(s):  
Student Performance ◽  
Learning Style ◽  
Data Science ◽  
Real Data ◽  
Classification Models ◽  
Group Approach ◽  
Effective Learning ◽  
Learning Framework ◽  
Education Data ◽  
Student Graduation

The practice of data science, artificial intelligence (AI) in general, has expanded greatly in terms of both theoretical and application domains. Many existing and new problems have been tackled using different reasoning and learning methods. These include the research subject, generally referred to as education data mining (or EDM). Among many issues that have been studied in this EMD community, student performance and achievement provide an interesting, yet useful result to shaping effective learning style and academic consultation. Specific to this work at Mae Fah Luang University, the pattern of students’ graduation is determined based on their profile of performance in different categories of courses. This course-group approach is picked up to generalize the framework for various undergraduation programmes. In that, a bi-level learning method is proposed in order to predict the length of study before graduation. At the first tier, clustering is applied to derive major types of performance profiles, for which classification models can be developed to refine the prediction further. With the experiments on a real data collection, this framework usually provides accurate predictive outcomes, using several conventional classification techniques.

Evaluating Impacts of Performance Funding Policies on Student Outcomes in Higher Education

2014 ◽  
Vol 655 (1) ◽  
pp. 185-208 ◽  
Author(s):  
Amanda Rutherford ◽  
Thomas Rabovsky
Keyword(s):  
Postsecondary Education ◽  
Student Performance ◽  
Student Outcomes ◽  
Performance Funding ◽  
Systematic Research ◽  
Link State ◽  
Education Data ◽  
Funding Policies ◽  
Student Graduation ◽  
Public Colleges And Universities

Concerns about performance and cost efficiency have taken center stage in discussions about the funding and oversight of public universities in recent years. One of the primary manifestations of these concerns is the rise of performance funding policies, or policies that seek to directly link state appropriations to the outcomes institutions generate for students. Despite the popularity of these policies, relatively little systematic research examines their effect on student outcomes at public colleges and universities. We use data collected from the Integrated Postsecondary Education Data System (IPEDS) to analyze the effectiveness of performance funding policies as a mechanism for improving student graduation, persistence, and degree attainment in more than 500 postsecondary institutions in all fifty states over a span of 18 years. We find that current performance funding policies are not associated with higher levels of student performance and that these policies may in fact contribute to lower performance over a longer period of time. However, more recent policies linked to institutional base funding may produce some likelihood of long-term improvement and require additional research.

scholarly journals Record linkage of routine data with cohorts’ data of infants under European and Portuguese law

2020 ◽  
Vol 30 (Supplement_5) ◽  
Author(s):  
J Doetsch ◽  
I Lopes ◽  
R Redinha ◽  
H Barros
Keyword(s):  
Big Data ◽  
Data Processing ◽  
Data Protection ◽  
Record Linkage ◽  
Data Science ◽  
Personal Data ◽  
Routine Data ◽  
Cohort Data ◽  
Education Data ◽  
Explicit Consent

Abstract The usage and exchange of “big data” is at the forefront of the data science agenda where Record Linkage plays a prominent role in biomedical research. In an era of ubiquitous data exchange and big data, Record Linkage is almost inevitable, but raises ethical and legal problems, namely personal data and privacy protection. Record Linkage refers to the general merging of data information to consolidate facts about an individual or an event that are not available in a separate record. This article provides an overview of ethical challenges and research opportunities in linking routine data on health and education with cohort data from very preterm (VPT) infants in Portugal. Portuguese, European and International law has been reviewed on data processing, protection and privacy. A three-stage analysis was carried out: i) interplay of threefold law-levelling for Record Linkage at different levels; ii) impact of data protection and privacy rights for data processing, iii) data linkage process' challenges and opportunities for research. A framework to discuss the process and its implications for data protection and privacy was created. The GDPR functions as utmost substantial legal basis for the protection of personal data in Record Linkage, and explicit written consent is considered the appropriate basis for the processing sensitive data. In Portugal, retrospective access to routine data is permitted if anonymised; for health data if it meets data processing requirements declared with an explicit consent; for education data if the data processing rules are complied. Routine health and education data can be linked to cohort data if rights of the data subject and requirements and duties of processors and controllers are respected. A strong ethical context through the application of the GDPR in all phases of research need to be established to achieve Record Linkage between cohort and routine collected records for health and education data of VPT infants in Portugal. Key messages GDPR is the most important legal framework for the protection of personal data, however, its uniform approach granting freedom to its Member states hampers Record Linkage processes among EU countries. The question remains whether the gap between data protection and privacy is adequately balanced at three legal levels to guarantee freedom for research and the improvement of health of data subjects.

scholarly journals Supervised dimensionality reduction for big data

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Joshua T. Vogelstein ◽  
Eric W. Bridgeford ◽  
Minh Tang ◽  
Da Zheng ◽  
Christopher Douville ◽  
...  
Keyword(s):  
Dimensionality Reduction ◽  
Data Science ◽  
Real Data ◽  
Low Rank ◽  
Conditional Moment ◽  
Desktop Computer ◽  
Reduction Techniques ◽  
Reduction Methods ◽  
The Individual ◽  
Low Dimensional

AbstractTo solve key biomedical problems, experimentalists now routinely measure millions or billions of features (dimensions) per sample, with the hope that data science techniques will be able to build accurate data-driven inferences. Because sample sizes are typically orders of magnitude smaller than the dimensionality of these data, valid inferences require finding a low-dimensional representation that preserves the discriminating information (e.g., whether the individual suffers from a particular disease). There is a lack of interpretable supervised dimensionality reduction methods that scale to millions of dimensions with strong statistical theoretical guarantees. We introduce an approach to extending principal components analysis by incorporating class-conditional moment estimates into the low-dimensional projection. The simplest version, Linear Optimal Low-rank projection, incorporates the class-conditional means. We prove, and substantiate with both synthetic and real data benchmarks, that Linear Optimal Low-Rank Projection and its generalizations lead to improved data representations for subsequent classification, while maintaining computational efficiency and scalability. Using multiple brain imaging datasets consisting of more than 150 million features, and several genomics datasets with more than 500,000 features, Linear Optimal Low-Rank Projection outperforms other scalable linear dimensionality reduction techniques in terms of accuracy, while only requiring a few minutes on a standard desktop computer.

scholarly journals Online Learning in Nutrition and Dietetics: Student Performance and Attitudes

2005 ◽  
Author(s):  
Dominic Upton
Keyword(s):  
Student Performance ◽  
Learning Style ◽  
Independent Learning ◽  
Online Course ◽  
Traditional Lecture ◽  
Innovative Method ◽  
Traditional Lectures ◽  
On Line ◽  
Dietetic Students ◽  
Nutrition And Dietetics

Context: Behavioural studies can form an essential component of the Nutrition and Dietetics undergraduate degree. Aims: This study aimed to firstly produce on-line teaching material in Behavioural studies suitable for undergraduate Nutrition and Dietetic students. Secondly, to explore students’ views on the online material, and record their performance when taught through this innovative method. Methods: Nutrition and Dietetics students completed an online health psychology/sociology module and their performance compared to students who completed a traditional lecture based course. Student evaluations of the online course were also recorded. Findings: Results suggested that students taught through on-line medium performed no differently to those taught through “traditional lectures”. Students appeared to enjoy the material although there was some reluctance to develop an independent learning style. Conclusion: It was apparent that material has to be developed that can both engage and motivate learners, thereby further developing independent learning, and that this may have to be tailored dependent on a number of student factors.

scholarly journals Data for Students: The Potential of Data and Analytics for Student Success

2020 ◽  
Author(s):  
Katherine Leu
Keyword(s):  
Student Success ◽  
Financial Aid ◽  
Postsecondary Education ◽  
Data Analytics ◽  
Data Science ◽  
Postsecondary Institutions ◽  
College Completion ◽  
Ethical Challenges ◽  
Education Data ◽  
Data Linkages

Postsecondary education is awash in data. Postsecondary institutions track data on students’ demographics, academic performance, course-taking, and financial aid, and have put these data to use, applying data analytics and data science to issues in college completion. Meanwhile, an extensive amount of higher education data are being collected outside of institutions, opening possibilities for data linkages. Newer sources of postsecondary education data could provide an even richer view of student success and improve equity. To explore this potential, this brief describes existing applications of analytics to student success, presents a framework to structure understanding of postsecondary data topics, suggests potential extensions of these data to student success, and describes practical and ethical challenges.

scholarly journals Deep Learning Framework to Detect the False Analysis of a Product given by Robots and Malicious Users

2019 ◽  
Vol 8 (6S4) ◽  
pp. 689-692
Keyword(s):  
Signs And Symptoms ◽  
Fine Tuning ◽  
Product Evaluations ◽  
Data Set ◽  
Learning Framework ◽  
Education Data ◽  
High Level ◽  
Future Work ◽  
Product Ranking ◽  
Convolution Function

Product evaluations are precious for upcoming clients in supporting them make choices. To this, numerous mining techniques have been proposed, wherein judging a evaluation sentence’s orientation (e.g. Outstanding or bad) is considered as one of their key worrying conditions. Lately, deep studying has emerged as a powerful technique for fixing sentiment kind issues. A neural network intrinsically learns useful instance routinely without human efforts. But, the fulfilment of deep getting to know pretty is primarily based totally on the supply of big-scale education data. We recommend a unique deep studying framework for product review sentiment classification which employs prevalently to be had rankings as susceptible supervision signs and symptoms. The framework consists of steps: (1) studying a high level representation (an embedding region) which captures the general sentiment distribution of sentences thru score facts; (2) such as a class layer-on top of the embedding layer and use labelled sentences for supervised fine-tuning. We discover styles of low stage community structure for modelling evaluation sentences, specifically, convolution function extractors and prolonged brieftime period memory. To have a take a look at the proposed framework, we gather a data set containing 1.1M weakly classified evaluate sentences and eleven, 754 labelled review sentences from Amazon. Experimental effects display the efficacy of the proposed framework and its superiority over baselines. In this future work todetect false reviews given by robots or by malicious people by taking amount, sometimessome companies may hire people to boost their product ranking higher by assigning fake rating and this malicious people or robots give continuous ranking or review to such product and we can detect such fake rating by analysingratingandremove suchfake rating to give only genuine reviews to users.

Knowledge Discovery for Large Databases in Education Institutes

2017 ◽  
pp. 27-110
Author(s):  
Robab Saadatdoost ◽  
Alex Tze Hiang Sim ◽  
Hosein Jafarkarimi ◽  
Jee Mei Hee
Keyword(s):  
Higher Education ◽  
Data Mining ◽  
Decision Making ◽  
Knowledge Discovery ◽  
Learning Style ◽  
Science Research ◽  
Data Set ◽  
Use Of Data ◽  
Education Data ◽  
Decision Making System

This project presents the patterns and relations between attributes of Iran Higher Education data gained from the use of data mining techniques to discover knowledge and use them in decision making system of IHE. Large dataset of IHE is difficult to analysis and display, since they are significant for decision making in IHE. This study utilized the famous data mining software, Weka and SOM to mine and visualize IHE data. In order to discover worthwhile patterns, we used clustering techniques and visualized the results. The selected dataset includes data of five medical university of Tehran as a small data set and Ministry of Science - Research and Technology's universities as a larger data set. Knowledge discovery and visualization are necessary for analyzing of these datasets. Our analysis reveals some knowledge in higher education aspect related to program of study, degree in each program, learning style, study mode and other IHE attributes. This study helps to IHE to discover knowledge in a visualize way; our results can be focused more by experts in higher education field to assess and evaluate more.

A Literature Review on Thyroid Hormonal Problems in Women Using Data Science and Analytics

2021 ◽  
pp. 416-428
Author(s):  
R. Suganya ◽  
Rajaram S. ◽  
Kameswari M.
Keyword(s):  
Machine Learning ◽  
Literature Review ◽  
Data Science ◽  
Learning Algorithms ◽  
Research Literature ◽  
Machine Learning Algorithms ◽  
Thyroid Disorder ◽  
Classification Models ◽  
Indian Women ◽  
Using Data

Currently, thyroid disorders are more common and widespread among women worldwide. In India, seven out of ten women are suffering from thyroid problems. Various research literature studies predict that about 35% of Indian women are examined with prevalent goiter. It is very necessary to take preventive measures at its early stages, otherwise it causes infertility problem among women. The recent review discusses various analytics models that are used to handle different types of thyroid problems in women. This chapter is planned to analyze and compare different classification models, both machine learning algorithms and deep leaning algorithms, to classify different thyroid problems. Literature from both machine learning and deep learning algorithms is considered. This literature review on thyroid problems will help to analyze the reason and characteristics of thyroid disorder. The dataset used to build and to validate the algorithms was provided by UCI machine learning repository.

COGNITIVE, AFFECTIVE AND CONATIVE MODEL FOR ANALYSING HIGHER EDUCATION STUDENTSq

2017 ◽  
Vol 10 (13) ◽  
pp. 133
Author(s):  
Priyaadharshini Manickavasag ◽  
Swati S Surwade
Keyword(s):  
Higher Education ◽  
Learning Environment ◽  
Student Performance ◽  
Learning Style ◽  
Management System ◽  
Research Work ◽  
Personalized Learning ◽  
Three Dimensions ◽  
Learning Abilities ◽  
Learning Platform

Many models are used in recent years to analyze behavior of the students in the higher education. Analyzing the learning style and student performance in academic studies are very essential to enhance their performance. This research work is focused on analyzing the learners behavior using three dimensions, i.e., cognitive, affective, and conative model. In this paper, we used Moodle learning management system which is a learning platform to create a personalized learning environment and to track learning abilities using activities. This model will be helpful to study the cognitive, conative, and emotions of students. 

Sign in / Sign up

Export Citation Format

Share Document