4,720 Hits in 5.9 sec

RHEM: A Robust Hybrid Ensemble Model for Students' Performance Assessment on Cloud Computing Course

Sapiah Sakri, Ala Saleh
2020 International Journal of Advanced Computer Science and Applications  
, and Rotation Forestwhich produced 16 new hybrid ensemble classifier models.  ...  The research aim is to propose a robust hybrid ensemble model (RHEM) that can warn at-risks students (on Cloud Computing course) of their likely outcomes at the early semester assessment.  ...  The questionnaire was designed to include students' demographic and students' motivational behaviour questions for the course cloud computing.  ... 
doi:10.14569/ijacsa.2020.0111150 fatcat:yq2lrf6f3vb5rh7vrtpgfccfga

Comparative Analysis for Boosting Classifiers in the Context of Higher Education

Eslam Abou Gamie, Samir Abou El-Seoud, Mostafa A. Salama
2020 International Journal of Emerging Technologies in Learning (iJET)  
The approaches in this work implements the divide and conquer algorithm on feature set of an educational data set to enhance the analysis and prediction accuracy.  ...  This type of analysis serves in predicting students' scores, in alerting students-at-risk, and in managing the degree of stu-dent engagement to educational system.  ...  Ensemble with Boosting model The main model in this paper is ensemble model with boosting as shown on figure 1. The approach starts by categorizing the OULAD education dataset into four groups.  ... 
doi:10.3991/ijet.v15i10.13663 fatcat:jygdesihzje7bans4sgbnx4vli

A Review of Recommender Systems for Choosing Elective Courses

Mfowabo Maphosa, Wesley Doorsamy, Babu Paul
2020 International Journal of Advanced Computer Science and Applications  
Recommender systems have their origins in commerce and are used in other sectors such as education. Recommender systems offer an alternative to the use of human advisors.  ...  These articles show that several recommender systems approaches and data mining algorithms are used to achieve the task of recommending elective courses.  ...  to an online or a blended approach.  ... 
doi:10.14569/ijacsa.2020.0110933 fatcat:fmkt3krswjdt3g3vaahxooavye

A Hybrid Approach using Ontology Similarity and Fuzzy Logic for Semantic Question Answering [article]

Monika Rani, Maybin K. Muyeba, O. P. Vyas
2017 arXiv   pre-print
In this paper, our objective is to present a hybrid approach for a Semantic question answering retrieval system using Ontology Similarity and Fuzzy logic.  ...  One of the challenges in information retrieval is providing accurate answers to a user's question often expressed as uncertainty words.  ...  Conclusion and Future Work We have proposed a hybrid approach for Semantic question answering based on Semantic Fuzzy ontology for retrieval systems.  ... 
arXiv:1709.09214v2 fatcat:w3snfi2m3zg53lr2mwqxuayece

A matter of presence: A qualitative study on teaching individual and collective music classes

Andrea Schiavio, Michele Biasutti, Dylan van der Schyff, Richard Parncutt
2018 Musicae Scientiae  
Adopting an approach based on grounded theory, two interrelated themes were identified in the raw data: teaching issues and professional development.  ...  onto the learners, giving rise to a hybrid extended system that fosters a shared sense of responsibility, where pedagogical dynamics are functionally distributed across the whole group.  ...  Data analysis The participants' answers were analysed by two of the present authors using an inductive method framed within the approach known as grounded theory (Oktay, 2012; Rostvall & West 2003; Stebbins  ... 
doi:10.1177/1029864918808833 fatcat:i2zntc6dfzda7gusekyg652tzq

Intelligent Decision Support System for Predicting Student's E-Learning Performance Using Ensemble Machine Learning

Farrukh Saleem, Zahid Ullah, Bahjat Fakieh, Faris Kateb
2021 Mathematics  
The model performance has shown remarkable improvement using ensemble approaches.  ...  The integration of the ML models has improved the prediction ratio and performed better than all other ensemble approaches.  ...  Another experiment using an ensemble meta-based approach integrated the ensemble technique with other classification models.  ... 
doi:10.3390/math9172078 fatcat:li5ckuchrrah3pnyfp5kxaw4gm


Hiba Al Sghaier
2020 International Journal of Engineering Technologies and Management Research  
In [35] , a hybrid machine learning technique and a new feature selection method is used to examine an automated bug triaging system.  ...  The student can add one or more questions and assign set points for it, when other students answer the questions, then points will be assigned to the student's account.  ... 
doi:10.29121/ijetmr.v7.i6.2020.694 fatcat:blgkpwyb3zfxtckv4nn3733nei

Fake Reviews Detection through Ensemble Learning [article]

Luis Gutierrez-Espinoza and Faranak Abri and Akbar Siami Namin and Keith S. Jones and David R. W. Sears
2020 arXiv   pre-print
The application of a number of ensemble learning-based approaches to a collection of fake restaurant reviews that we developed show that these ensemble learning-based approaches detect deceptive information  ...  Motivated by the recent trends in ensemble learning, this paper evaluates the performance of ensemble learning-based approaches to identify bogus online information.  ...  There are three main approaches for developing an ensemble learner [13] : • Boosting, often uses homogeneous-base models trained sequentially; • Bagging, which often uses homogeneous-base models trained  ... 
arXiv:2006.07912v1 fatcat:k6w6oero6bh2zhdhch56hwcujq

Predicting Student Academic Performance with Ensemble Classification Method on Imbalanced Educational Data

2019 International journal of recent technology and engineering  
At present universities and colleges are mainly focusing to improve the academic performance of the students.  ...  The original data set with the re-sampling method with the proposed method achieved maximum precision values at a learning rate 0.3 with an accuracy rate of 98.36%.  ...  After, an ensemble based progressive prediction framework has been developed to employ the student developing performance into prediction. M. Sagar et al.  ... 
doi:10.35940/ijrte.d7741.118419 fatcat:vgaxazi5svggzb5ov2mfzdonli


Anbarasi M.S.
2018 International Journal of Advanced Research in Computer Science  
Therefore the strategies like anonymization, randomization are used to attain the intention.  ...  Our challenge initiates with cleaning and preprocessing followed by ensemble classification and proceeded with perturbation to attain the goal.  ...  [3] In this paper they have elaborated the hybrid approach combining suppression and perturbation for Privacy Preserving data mining takes care of these requirements.  ... 
doi:10.26483/ijarcs.v9i2.5777 fatcat:zu4xrcfas5hnjoj4zvqfdbfw3y

Ensemble Learning Using Fuzzy Weights to Improve Learning Style Identification for Adapted Instructional Routines

Christos Troussas, Akrivi Krouska, Cleo Sgouropoulou, Ioannis Voyiatzis
2020 Entropy  
model (FSLSM) using ensemble classification.  ...  cognitive characteristics (i.e., prior academic performance categorized using fuzzy weights), and solely four questions pertaining to the FSLSM dimensions, to identify the learning style.  ...  In [14] , the authors present an automatic approach for detecting students' learning style based on web usage mining; specifically, the students' log files were classified using clustering algorithms  ... 
doi:10.3390/e22070735 pmid:33286506 fatcat:br4zz3gdvrg2bbrlcmhylowmie

Imbalanced Ensemble Classifier for Learning from Imbalanced Business School Dataset

Tanujit Chakraborty
2019 International journal of mathematical, engineering and management sciences  
Experimental evidence is also provided using Indian business school dataset to evaluate the outstanding performance of the proposed imbalanced ensemble classifier.  ...  This paper proposes an imbalanced ensemble classifier which can handle the imbalanced nature of the dataset and achieves higher accuracy in case of the feature selection (selection of important characteristics  ...  In response to this question, we proposed an ensemble classifier for feature selection cum classification problems which can be used to solve the imbalanced business school dataset problem.  ... 
doi:10.33889/ijmems.2019.4.4-068 fatcat:w7peaq5fnvei7bz2tstojlkkfe

Employability and related context prediction framework for university graduands: a machine learning approach

Manushi P. Wijayapala, H. L. Premaratne, I. T. Jayamanne
2018 The International Journal on Advances in ICT for Emerging Regions  
More importantly, this study utilizes several types of Sampling (Oversampling, Undersampling) and Ensemble (Bagging, Boosting, RF) techniques as well as a newly proposed hybrid approach to overcome the  ...  under the ROC curve interpretation as an 'Excellent' experiment, while a C4.5 Decision Tree model under Ensemble approach has been selected as the best model of the remaining module (Salary Prediction  ...  Hence in this hybrid approach, oversampling was used as the sampling technique to apply on Ensemble approaches.  ... 
doi:10.4038/icter.v9i2.7181 fatcat:7cmseqx6crgsjd2eylwakk6kzi

Job Recommender Systems: A Review [article]

Corné de Ruijt, Sandjai Bhulai
2021 arXiv   pre-print
Using existing recommender taxonomies, we split this large class of hybrids into subcategories that are easier to analyse.  ...  With respect to the type of models used in JRS, authors frequently label their method as 'hybrid'. Unfortunately, they thereby obscure what these methods entail.  ...  Although multiple hybrid approaches can be used to resolve this problem, perhaps the most direct approach is to use switching hybrids.  ... 
arXiv:2111.13576v1 fatcat:hlm2dowihjd33p55jgexueefbq

Physics Pre-service Teachers' Approaches to Scientific Investigations by Data Exploration

Thomas Schubatzky, Benjamin Bock, Claudia Haagen-Schützenhöfer
2020 Eurasia Journal of Mathematics, Science and Technology Education  
In this article we provide exploratory insights into the strategies students use.  ...  Findings show that the pre-service teachers follow three different approaches: some always start their investigations with a research question, some switch between exploratory and targeted investigations  ...  We have chosen a contextoriented approach, using a real-world scenario that is relevant to students.  ... 
doi:10.29333/ejmste/8536 fatcat:t3mljwtyz5d2ra5hyeh6ebym4a
« Previous Showing results 1 — 15 out of 4,720 results