An Achievement Prediction Method on the Video Learning Time Based on EKF

AbstractData-driven techniques improve the quality of talent training comprehensively for university by discovering potential academic problems and proposing solutions. We propose an interpretable prediction method for university student academic crisis warning, which consists of K-prototype-based student portrait construction and Catboost–SHAP-based academic achievement prediction. The academic crisis warning experiment is carried out on desensitization multi-source student data of a university. The experimental results show that the proposed method has significant advantages over common machine learning algorithms. In terms of achievement prediction, mean square error (MSE) reaches 24.976, mean absolute error (MAE) reaches 3.551, coefficient of determination ($$R^{2}$$ R 2 ) reaches 80.3%. The student portrait and Catboost–SHAP method are used for visual analysis of the academic achievement factors, which provide intuitive decision support and guidance assistance for education administrators.

Download Full-text

Predicting Student Achievement Based on Temporal Learning Behavior in MOOCs

Applied Sciences ◽

10.3390/app9245539 ◽

2019 ◽

Vol 9 (24) ◽

pp. 5539 ◽

Cited By ~ 5

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%.

Download Full-text

Evaluation of Student Performance with Predicted Learning Curve Based on Grey Models for Personalized Tutoring

International Journal of Emerging Technologies in Learning (iJET) ◽

10.3991/ijet.v14i13.9880 ◽

2019 ◽

Vol 14 (13) ◽

pp. 157

Author(s):

Manqiang Liu ◽

Qingsheng Zhang

Keyword(s):

Learning Curve ◽

Student Performance ◽

Intelligent Tutoring System ◽

Prediction Method ◽

Learning Time ◽

Factors Analysis ◽

Knowledge Component ◽

Grey Models ◽

Practice Opportunities ◽

Learning Factors

Learning time of student is precious, over-practice of target knowledge component wastes student’s time, however, under-practice may mean the student may not grasp target knowledge component properly. To any student, it is helpful if intelligent tutoring system can determine how many practice opportunities needed for mastery of knowledge component. In this paper, to improve student’s learning efficiency, a method of predicted learning curve based on grey models is proposed to determine the counts of practice op-portunity for mastery of knowledge component. The experimental results show that the predicted value on error rate of practice opportunity over knowledge component with the proposed method is much closer to the value of real learning curve than the predicted learning curve produced by learning factors analysis. It implies the proposed prediction method is potential to present reasonable practices for personalized tutoring.

Download Full-text

Accurate language achievement prediction method based on multi-model ensemble using personality factors

Multimedia Tools and Applications ◽

10.1007/s11042-020-09297-4 ◽

2020 ◽

Author(s):

Yuping Lin ◽

Panpan Song ◽

Hong Long

Keyword(s):

Prediction Method ◽

Personality Factors ◽

Model Ensemble ◽

Language Achievement ◽

Achievement Prediction

Download Full-text

Selection of a leading edge noise prediction method for PNoise

The Academic Society Journal ◽

10.32640/tasj.2018.4.214 ◽

2018 ◽

pp. 214-223

Author(s):

AM Faria ◽

MM Pimenta ◽

JY Saab Jr. ◽

S Rodriguez

Keyword(s):

Wind Turbine ◽

Turbine Blades ◽

Prediction Method ◽

Leading Edge ◽

Wind Farms ◽

Broadband Noise ◽

Turbulence Energy ◽

Noise Prediction ◽

Migration Routes ◽

Turbulent Inflow

Wind energy expansion is worldwide followed by various limitations, i.e. land availability, the NIMBY (not in my backyard) attitude, interference on birds migration routes and so on. This undeniable expansion is pushing wind farms near populated areas throughout the years, where noise regulation is more stringent. That demands solutions for the wind turbine (WT) industry, in order to produce quieter WT units. Focusing in the subject of airfoil noise prediction, it can help the assessment and design of quieter wind turbine blades. Considering the airfoil noise as a composition of many sound sources, and in light of the fact that the main noise production mechanisms are the airfoil self-noise and the turbulent inflow (TI) noise, this work is concentrated on the latter. TI noise is classified as an interaction noise, produced by the turbulent inflow, incident on the airfoil leading edge (LE). Theoretical and semi-empirical methods for the TI noise prediction are already available, based on Amiet’s broadband noise theory. Analysis of many TI noise prediction methods is provided by this work in the literature review, as well as the turbulence energy spectrum modeling. This is then followed by comparison of the most reliable TI noise methodologies, qualitatively and quantitatively, with the error estimation, compared to the Ffowcs Williams-Hawkings solution for computational aeroacoustics. Basis for integration of airfoil inflow noise prediction into a wind turbine noise prediction code is the final goal of this work.

Download Full-text