scholarly journals Predicting Student Achievement Based on Temporal Learning Behavior in MOOCs

2019 ◽  
Vol 9 (24) ◽  
pp. 5539 ◽  
Author(s):  
Shaojie Qu ◽  
Kan Li ◽  
Bo Wu ◽  
Shuhui Zhang ◽  
Yongchao Wang
Keyword(s):  
Neural Network ◽  
Data Mining ◽  
Student Achievement ◽  
Short Term Memory ◽  
Online Courses ◽  
Educational Data Mining ◽  
Prediction Method ◽  
Learning Processes ◽  
Achievement Prediction ◽  
Temporal Learning

With the development of data mining technology, educational data mining (EDM) has gained increasing amounts of attention. Research on massive open online courses (MOOCs) is an important area of EDM. Previous studies found that assignment-related behaviors in MOOCs (such as the completed number of assignments) can affect student achievement. However, these methods cannot fully reflect students’ learning processes and affect the accuracy of prediction. In the present paper, we consider the temporal learning behaviors of students to propose a student achievement prediction method for MOOCs. First, a multi-layer long short-term memory (LSTM) neural network is employed to reflect students’ learning processes. Second, a discriminative sequential pattern (DSP) mining-based pattern adapter is proposed to obtain the behavior patterns of students and enhance the significance of critical information. Third, a framework is constructed with an attention mechanism that includes data pre-processing, pattern adaptation, and the LSTM neural network to predict student achievement. In the experiments, we collect data from a C programming course from the year 2012 and extract assignment-related features. The experimental results reveal that this method achieves an accuracy rate of 91% and a recall of 94%.

scholarly journals Student-Performulator: Student Academic Performance Using Hybrid Deep Neural Network

2021 ◽  
Vol 13 (17) ◽  
pp. 9775
Author(s):  
Bashir Khan Yousafzai ◽  
Sher Afzal ◽  
Taj Rahman ◽  
Inayat Khan ◽  
Inam Ullah ◽  
...  
Keyword(s):  
Neural Network ◽  
Data Mining ◽  
Student Performance ◽  
Performance Prediction ◽  
Deep Neural Network ◽  
Short Term Memory ◽  
Educational Data Mining ◽  
Attention Mechanism ◽  
Feature Representation ◽  
Superior Performance

Educational data generated through various platforms such as e-learning, e-admission systems, and automated result management systems can be effectively processed through educational data mining techniques in order to gather highly useful insights into students’ performance. The prediction of student performance from historical academic data is a highly desirable application of educational data mining. In this regard, there is an urgent need to develop an automated technique for student performance prediction. Existing studies on student performance prediction primarily focus on utilizing the conventional feature representation schemes, where extracted features are fed to a classifier. In recent years, deep learning has enabled researchers to automatically extract high-level features from raw data. Such advanced feature representation schemes enable superior performance in challenging tasks. In this work, we examine the deep neural network model, namely, the attention-based Bidirectional Long Short-Term Memory (BiLSTM) network to efficiently predict student performance (grades) from historical data. In this article, we have used the most advanced BiLSTM combined with an attention mechanism model by analyzing existing research problems, which are based on advanced feature classification and prediction. This work is really vital for academicians, universities, and government departments to early predict the performance. The superior sequence learning capabilities of BiLSTM combined with attention mechanism yield superior performance compared to the existing state-of-the-art. The proposed method has achieved a prediction accuracy of 90.16%.

scholarly journals Tinjauan Pustaka Sistematis: Implementasi Metode Deep Learning pada Prediksi Kinerja Murid

2021 ◽  
Vol 10 (2) ◽  
pp. 131-138
Author(s):  
Muhammad Haris Diponegoro ◽  
Sri Suning Kusumawardani ◽  
Indriana Hidayah
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Data Mining ◽  
Deep Learning ◽  
Deep Neural Network ◽  
Short Term Memory ◽  
State Of The Art ◽  
Educational Data Mining ◽  
Short Term ◽  
Long Short Term Memory

Pemanfaatan machine learning yang merupakan salah satu implementasi dalam bidang artificial intelligence telah merambah ke berbagai bidang, salah satunya adalah bidang pendidikan. Dengan menggunakan kombinasi teknik machine learning, statistik, dan basis data, dapat dilakukan educational data mining untuk mengetahui pola yang ada dalam suatu dataset tertentu. Salah satu penggunaan educational data mining adalah untuk melakukan prediksi kinerja murid. Hasil dari prediksi kinerja murid dapat digunakan sebagai salah satu instrumen untuk melakukan monitoring dan evaluasi terhadap proses pembelajaran sehingga dapat membantu menentukan langkah-langkah lanjutan dalam rangka meningkatkan proses pembelajaran. Makalah ini bertujuan untuk mengetahui state of the art implementasi deep learning yang merupakan bagian dari machine learning pada konteks educational data mining, khususnya mengenai prediksi kinerja murid. Pada makalah ini disajikan systematic literature review untuk mengetahui variasi teknik atau algoritme deep learning yang digunakan beserta kinerja yang dicapai. Dari dua puluh publikasi ilmiah yang ditelusuri, rata-rata kinerja yang dicapai dalam melakukan prediksi adalah 89,85%. Mayoritas teknik yang digunakan adalah Deep Neural Network (DNN), Recurrent Neural Network (RNN), dan Long Short-Term Memory (LSTM) dengan fitur data demografis, perilaku, dan akademis.

scholarly journals Multimodal Learning Analytics and Education Data Mining: using computational technologies to measure complex learning tasks

2016 ◽  
Vol 3 (2) ◽  
pp. 220-238 ◽  
Author(s):  
Paulo Blikstein ◽  
Marcelo Worsley
Keyword(s):  
Data Mining ◽  
Learning Analytics ◽  
Online Courses ◽  
Educational Data Mining ◽  
Multimodal Learning ◽  
Learning Tasks ◽  
Education Data ◽  
Multimodal Learning Analytics ◽  
High Degree ◽  
Learning Analysis

New high-frequency multimodal data collection technologies and machine learning analysis techniques could offer new insights into learning, especially when students have the opportunity to generate unique, personalized artifacts, such as computer programs, robots, and solutions engineering challenges. To date most of the work on learning analytics and educational data mining has been focused on online courses and cognitive tutors, both of which provide a high degree of structure to the tasks, and are restricted to interactions that occur in front of a computer screen. In this paper, we argue that multimodal learning analytics can offer new insights into students’ learning trajectories in more complex and open-ended learning environments. We present several examples of this work and its educational application.

scholarly journals Deep Learning Algorithmic Approach for Operational Anomaly Based Intrusion Detection System in Wireless Sensor Networks

2021 ◽  
Author(s):  
Ashwini Bhaskar Abhale ◽  
S S Manivannan
Keyword(s):  
Neural Network ◽  
Data Mining ◽  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Short Term Memory ◽  
Detection System ◽  
Short Term ◽  
Term Memory ◽  
Deep Convolution Neural Network ◽  
Long Short Term Memory

Abstract Because of the ever increasing number of Internet users, Internet security is becoming more essential. To identify and detect attackers, many researchers utilized data mining methods. Existing data mining techniques are unable to provide a sufficient degree of detection precision. An intrusion detection system for wireless networks is being developed to ensure data transmission security. The Network Intrusion Detection Algorithm (NIDS) uses a deep classification system to classify network connections as good or harmful. Deep Convolution Neural Network (DCNN), Deep Recurrent Neural Network (DRNN), Deep Long Short-Term Memory (DLSTM), Deep Convolution Neural Network Long Short-Term Memory (DCNN LSTM), and Deep Gated Recurrent Unit (DGRU) methods that use NSLKDD data records to train models are proposed. The experiments were carried out for a total of 1000 epochs. During the experiment, we achieved a model accuracy of more than 98 percent. We also discovered that as the number of layers in a model grows, so does the accuracy.

Sign in / Sign up

Export Citation Format

Share Document