A Rough Set Based Approach to Find Learners' Key Personality Attributes in an E-Learning Environment

2010 ◽  
pp. 1788-1811
Author(s):  
Qinghua Zheng ◽  
Xiyuan Wu ◽  
Haifei Li
Keyword(s):  
Learning Environment ◽  
Learning Strategies ◽  
Set Theory ◽  
Rough Set ◽  
Research University ◽  
Rough Set Theory ◽  
Personality Characteristic ◽  
E Learning ◽  
Learning Research ◽  
Discriminator Function

One of the challenges in personalized e-learning research is how to find the unique learning strategies according to a learner’s personality characteristic. A learner’s personalitycharacteristic may have many attributes, and all of them may not have equal values. Correlation analysis, regression analysis, discriminator function, and educational psychology have been used to find solutions, but these methods have their shortcomings. This article proposes an improved approach based on rough set theory to find thekey personality attributes and evaluates the importance of these attributes. The approach has been successfully used in the actual e-learning environment for a major research university in China.

scholarly journals Construction Of Opinion Models For E-Learning Courses By Rough Set Theory And Text Mining

2019 ◽  
Vol 8 (6) ◽  
pp. 1107-1111 ◽  
Keyword(s):  
Text Mining ◽  
Set Theory ◽  
Rough Set ◽  
Rough Set Theory ◽  
Attribute Reduction ◽  
Expressive Power ◽  
Machine Learning Techniques ◽  
Decision Attributes ◽  
E Learning ◽  
Lower And Upper Approximations

Extracting knowledge through the machine learning techniques in general lacks in its predictions the level of perfection with minimal error or accuracy. Recently, researchers have been enjoying the fruits of Rough Set Theory (RST) to uncover the hidden patterns with its simplicity and expressive power. In RST mainly the issue of attribute reduction is tackled through the notion of ‘reducts’ using lower and upper approximations of rough sets based on a given information table with conditional and decision attributes. Hence, while researchers go for dimension reduction they propose many methods among which RST approach shown to be simple and efficient for text mining tasks. The area of text mining has focused on patterns based on text files or corpus, initially preprocessed to identify and remove irrelevant and replicated words without inducing any information loss for the classifying models later generated and tested. In this current work, this hypothesis are taken as core and tested on feedbacks for elearning courses using RST’s attribution reduction and generating distinct models of n-grams and finally the results are presented for selecting final efficient model

A Rough Set Theory Approach for Rule Generation and Validation Using RSES

2016 ◽  
Vol 3 (1) ◽  
pp. 55-70 ◽  
Author(s):  
Hemant Rana ◽  
Manohar Lal
Keyword(s):  
Learning Styles ◽  
Learning Style ◽  
Set Theory ◽  
Rough Set ◽  
Rough Set Theory ◽  
Learning Technology ◽  
Theory Approach ◽  
E Learning ◽  
Rough Theory ◽  
Ambiguous Data

Despite significant progress in e-learning technology over previous years, in view of huge sizes of data and databases, efficient knowledge extraction techniques are still required to make e-learning effective tool for delivery of learning. Rough set theory approach provides an effective technique for extraction of knowledge out of massive data. In order to provide effective support to learners, it is essential to know individual style of learning for each learner. For determining learning style of each learner, one is required to extract essentials of style of learning from a large number of parameters including academic background, profession, time available etc. In such scenario, rough theory proves a useful tool. In this paper, a rough set theory approach is proposed for determining learning styles of learners efficiently, so that based on the style, a learner may be provided learning support on the basis of requirement of the learner. These is achieved by eliminating redundant and ambiguous data and by generating reduct set, core set and rules from the given data. The results of this study are validated through RSES software by using same rough set analysis.

scholarly journals E-Learning Attributes Selection Through Rough Set Theory and Data Mining

2019 ◽  
Vol 8 (10) ◽  
pp. 3920-3924
Keyword(s):  
Data Mining ◽  
Set Theory ◽  
Rough Set ◽  
Rough Set Theory ◽  
Search Space ◽  
Primary Objective ◽  
Attribute Selection ◽  
Mining Machine ◽  
Degree Of Satisfaction ◽  
E Learning

Recent research makes wide efforts on attribute selection methods for making effective data preprocessing. The field of attribute selection spreads out both vertical and horizontal, due to increasing demands for dimensionality reduction. The search space is reduced very much by pruning the insignificant attributes. The degree of satisfaction on the selected list of attributes will only be increased through verification of more than one formal channel. In this paper, we look for two completely independent areas like Rough Set theory and Data Mining/Machine Learning Concepts, since both of them have distinct ways of determining the selection of attributes. The primary objective of this work is not only to establish the differences of these two distinct approaches, but also to apply and appreciate the results in e-learning domain to study the student engagement through their activities and the success rate. Hence our framework is based students’ log file on the portal page for elearning courses and results are compared with two different tools WEKA and ROSE for the purpose of elimination of irrelevant attributes and tabulation of final accuracies.

Incremental Learning Researches on Rough Set Theory

2014 ◽  
Vol 1 (1) ◽  
pp. 99-112 ◽  
Author(s):  
Dun Liu ◽  
Decui Liang
Keyword(s):  
Learning Strategies ◽  
Set Theory ◽  
Rough Set ◽  
Incremental Learning ◽  
Rough Sets ◽  
Rough Set Theory ◽  
Dynamic Environment ◽  
Future Research ◽  
Research Directions ◽  
The Status

Rough set theory is an effective tool to deal with information with uncertainty, and has been successfully applied in many fields. Incremental learning as an efficient strategy for data analysis in dynamic environment enables acquiring additional knowledge from new information by using prior knowledge and has drawn the widespread attentions of many scholars. In this paper, the authors discuss the status of incremental learning researches on rough sets and give potential future research directions. The authors first review basic concepts of rough sets and list three variations of information system in the dynamic decision procedures. Then, the authors investigate and summarize the corresponding incremental learning strategies for the three variations with different research viewpoints, respectively. Finally, the authors further tease out the research framework of our work and identify some future possible research directions.

scholarly journals Combining genetic algorithm with machine learning strategies for designing potent antimicrobial peptides

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Kyle Boone ◽  
Cate Wisdom ◽  
Kyle Camarda ◽  
Paulette Spencer ◽  
Candan Tamerler
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
Antimicrobial Peptides ◽  
Learning Strategies ◽  
Set Theory ◽  
Rough Set ◽  
Rational Design ◽  
Design Space ◽  
Rough Set Theory ◽  
Supervised Machine Learning

Abstract Background Current methods in machine learning provide approaches for solving challenging, multiple constraint design problems. While deep learning and related neural networking methods have state-of-the-art performance, their vulnerability in decision making processes leading to irrational outcomes is a major concern for their implementation. With the rising antibiotic resistance, antimicrobial peptides (AMPs) have increasingly gained attention as novel therapeutic agents. This challenging design problem requires peptides which meet the multiple constraints of limiting drug-resistance in bacteria, preventing secondary infections from imbalanced microbial flora, and avoiding immune system suppression. AMPs offer a promising, bioinspired design space to targeting antimicrobial activity, but their versatility also requires the curated selection from a combinatorial sequence space. This space is too large for brute-force methods or currently known rational design approaches outside of machine learning. While there has been progress in using the design space to more effectively target AMP activity, a widely applicable approach has been elusive. The lack of transparency in machine learning has limited the advancement of scientific knowledge of how AMPs are related among each other, and the lack of general applicability for fully rational approaches has limited a broader understanding of the design space. Methods Here we combined an evolutionary method with rough set theory, a transparent machine learning approach, for designing antimicrobial peptides (AMPs). Our method achieves the customization of AMPs using supervised learning boundaries. Our system employs in vitro bacterial assays to measure fitness, codon-representation of peptides to gain flexibility of sequence selection in DNA-space with a genetic algorithm and machine learning to further accelerate the process. Results We use supervised machine learning and a genetic algorithm to find a peptide active against S. epidermidis, a common bacterial strain for implant infections, with an improved aggregation propensity average for an improved ease of synthesis. Conclusions Our results demonstrate that AMP design can be customized to maintain activity and simplify production. To our knowledge, this is the first time when codon-based genetic algorithms combined with rough set theory methods is used for computational search on peptide sequences.

Sign in / Sign up

Export Citation Format

Share Document