S PRAR: A novel relational association rule mining classification model applied for academic performance prediction

Czibula, Gabriela; Mihai, Andrei; Crivei, Liana Maria

doi:10.1016/j.procs.2019.09.156

Cited by 41 publications

(42 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Similarly, the precision and recalls of HLVQ 1 are 0.891 and 0.942 hence the f‐measure is 0.915. The observed results of precision and recall value of the S PRAR 2 are 0.875 and 0.905 consequently the f‐measure is 0.889. The above statistical analysis results prove that the MSFMDDCN‐LSTM technique outperforms well in the student academic performance prediction than the existing classifiers.…”

Section: Methodsmentioning

confidence: 81%

“…The different recall outcomes are obtained for all the classifiers. The comparative analysis proves that the average recall value gets increased by 5%, 11%, and 12% using the MSFMDDCN‐LSTM technique than the HLVQ 1 and S PRAR, 2 student performance prediction 21 model. By considering dataset 3, the recall value of MSFMDDCN‐LSTM technique is increased by 5%, 8%, and 10% when compared to HLVQ 1 and S PRAR, 2 student performance prediction 21 model.…”

Section: Methodsmentioning

confidence: 91%

“…In this section, an experimental evaluation of MSFMDDCN‐LSTM and two existing methods HLVQ, 1 S PRAR, 2 student performance prediction model 21 is implemented with WEKA open‐source tool. To perform the experiments, three different datasets are used namely the student dataset (D 1 ) and Student Academics Performance Dataset (D 2 ) taken from the https://archive.ics.uci.edu/ml/datasets/Student%2BAcademics%2BPerformance, Students' Academic Performance Dataset (https://www.kaggle.com/aljarah/xAPI-Edu-Data) (D 3) .…”

Section: Methodsmentioning

confidence: 99%

“…After obtaining the 10 results, the proposed values are compared to the existing results. As a result, the average precision of the MSFMDDCN‐LSTM is improved by 8%,13%, and 14% when compared to HLVQ 1 and S PRAR, 2 student performance prediction model 21 respectively. By applying dataset 3, the average precision of MSFMDDCN‐LSTM is enhanced by 10%, 15%, and 13% as compared to HLVQ 1 and S PRAR, 2 student performance prediction model 21 respectively.…”

Section: Methodsmentioning

confidence: 99%

See 3 more Smart Citations

Minkowski Sommon Feature Map‐based Densely Connected Deep Convolution Network with LSTM for academic performance prediction

Ramanathan

Balasubramanian

2021

Concurrency and Computation

View full text Add to dashboard Cite

Summary Student academic performance prediction plays a major role in the current educational systems to improve the quality of education. The conventional single classifier‐based predictive analysis is not efficient to provide accurate results. In this paper, a novel technique called Minkowski Sommon Feature Map Densely connected Deep Convolution Network with LSTM (MSFMDDCN‐LSTM) is introduced to predict the academic performance of students with higher accuracy and lesser time consumption. The MSFMDDCN‐LSTM technique uses a densely connected deep convolution network to learn the given input for accurate prediction. The student activities are collected and stored in the organization dataset. The MSFMDDCN‐LSTM technique starts with the data collection followed by performing the attributes selection and classification. The collected data are given to input layer to predict the students' academic achievement at the end of study program. Secondly, the importance of numerous dissimilar attributes or “features” is considered for student performance prediction using steepest descent Minkowski sommon mapping. After that, the classification is performed using LSTM to classify the input instances for accurate prediction. Finally, the classification results are observed in the output layer. The quantitative outcomes inferred that MSFMDDCN‐LSTM technique performs well in terms of achieving higher precision, recall, f‐measure, and lesser time consumption than the state‐of‐the‐art methods.

show abstract

Section: Methodsmentioning

confidence: 81%

Section: Methodsmentioning

confidence: 91%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Minkowski Sommon Feature Map‐based Densely Connected Deep Convolution Network with LSTM for academic performance prediction

Ramanathan

Balasubramanian

2021

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…To redress the space issue, they confined the size of the dataset through putting away and using the latest or most critical examples. The authors of [5] proposes a new model, called Students Performance prediction using Relational Association Rules (S PRAR) to predict the final grade of a student using relational association rules. In this, the datasets contain the grades of students in the first, second and third semesters at Babes-Bolyai University.…”

Section: Related Workmentioning

confidence: 99%

Enhance the Educational Outcome in Higher Educational Institutes through Deep Neural Network

2020

IJATCSE

View full text Add to dashboard Cite

Nowadays, the main aim of every engineering college or university is the improvement of the educational outcome. The student's academic performance mainly impacts the educational outcome of any college. Measuring students' performance is a challenging issue that can help students and teachers to keep track progress of student performance and there by mentoring less performance students to obtain the highest grade in their final exams. The present work will help in predicting the performance of every student within 2 weeks of 16 weeks instruction period using previous outcome in various examinations and some additional parameters also effects the students' academic performance such as attendance, health issues, etc. Based on the predicted results student can be monitored to improve his/her abilities. To achieve this, this study proposes a deep multilayer feed forward neural network (MFFNN) model. The proposed model is used to predict the performance of every individual for a single subject or a course with high accuracy. In this paper, a dataset is generated based on the previous exam grades and a set of handcrafted features of students. The results indicate the proposed MFFNN model achieves an accuracy of 89.19% -93.89 %. The proposed model outperforms the support vector machine. While the support vector machine achieves 76.71% -88.6%. This study makes an open door for recognizing students who may graduate with poor outcomes or may not graduate at all, and also to assist intuitions and instructors for early intervention.

show abstract

Teaching‐Learning Process and Brain‐Computer Interaction Using ICT Tools

Raja

Sahu²,

Pathak³

2021

Cognitive Behavior and Human Computer Interaction Based on Machine Learning Algorithm

View full text Add to dashboard Cite

S PRAR: A novel relational association rule mining classification model applied for academic performance prediction

Cited by 41 publications

References 11 publications

Minkowski Sommon Feature Map‐based Densely Connected Deep Convolution Network with LSTM for academic performance prediction

Minkowski Sommon Feature Map‐based Densely Connected Deep Convolution Network with LSTM for academic performance prediction

Enhance the Educational Outcome in Higher Educational Institutes through Deep Neural Network

Teaching‐Learning Process and Brain‐Computer Interaction Using ICT Tools

Contact Info

Product

Resources

About