Academic Performance Prediction Based on Multisource, Multifeature Behavioral Data

1 Crore Projects is the best project center to get your IEEE 2021 Java Projects. We have 1000 plus project domains and six years of experience. We deliver your project on time at an affordable cost.

The Objective of The Project:

The main aim of the project is to develop a robust academic performance prediction model, to gain an in depth insight into student behavioral patterns and potentially help students to optimize their interactions with the university

Abstract:

• To identify the real-world campus dataset of college students that aggregates multisource behavioral data covering not only online and offline learning but also behaviors inside and outside of the classroom.
• The features representing dynamic changes in temporal lifestyle patterns are extracted by the means of long short-term memory.
• The machine learning-based classification algorithms are developed to predict academic performance
• The visualized feedback enabling students to potentially optimize their interactions with the university and achieve a study-life balance is designed.

System Analysis:

Existing system :

• In the existing system, the student predictions based on academic performance not all kinds of behavioral activities.
• The features and predictions are only based on the online metrics.
• The prediction of the student's academic performance with low accuracy.

Proposed system:

• In our Proposed system, robust academic performance and the student behavioral patterns, that potentially help students to optimize their interactions with the university.
• This is used to develop not only academic performance, it includes Students personality, Personal status, Lifestyle Behaviors and Learning Behaviors .
• The features and predictions in not only online, they also predict the offline basis with high accuracy.

Advantages:

• It is very useful to analyze the particular student's entire performance.
• The predicted academic performance is high accuracy.

Algorithms:

Machine learning:

Machine learning is a type of artificial intelligence that allows software applications to become more accurate at predicting outcomes without being explicitly programmed to do so. Machine learning algorithms use historical data as input to predict new output values.

Random forest:

Random forest is a flexible, easy-to-use machine learning algorithm that produces, even without hyper-parameter tuning, a great result most of the time.

K Nearest Neighbour

K nearest   KNN is used for both classification and regression Its purpose is to use a database in which the data points are separated into several classes to predict the classification of a new sample point.

Cross validation: 

      Cross-validation is a technique for evaluating ML models by training several ML models on subsets of the available input data and evaluating them on the complementary subset of the data. Use cross-validation to detect overfitting,  failing to generalize a pattern.

System Architecture of Machine Learning:

Modules:

This project has two  modules:

 Admin module 

•      Data module 
•      Prediction module 
•      Feedback module

 User module

Admin Module:

1.Login 

2. Upload two types of the dataset Student dataset--->upload the backend once upload the dataset not reset again. Book dataset 

3. View all datasets for student details---> view here student login, search, view details... A student once login our college website login count has automatically incremented the particular student id. 

Now see here abhinaya login=15, search=16, views=2 all are increment here... Notes this...

 4. Classification of the different types of behaviors students predicts the CNN algorithm. Three type of student behavior are classification them 

1.Beginner level 

2. Middle level 

3. High level

5. Search, login browser details show here -->view here the academic performance of above 60 % student details 

6. Overall--->view here overall behavior student details

 1. High level -->above 80 

2. Middle level--->above 60 

3. Low level or beginner-->40

 This method can predict the student behavior's 

7. Graph: overall behavior of student detail-wise show here result..

User Module:

• Login-->Student here login from student id and student name stored to back end
• After student login, their website login count is auto-increment here
• search here book--->reference book--->also search count is increment 
• view our history here

Software Requirements:

• System                 : Pentium IV 2.4 GHZ
•  Hard disk               : 1 Gb. 
• Mouse                     : logiTech.
•  Ram                       : 2 Gb.
•  Operating system   : Windows XP. 
• Coding language :  Java 
• Data base         :  MYSQL

Conclusion:

• Our project is to develop a robust academic performance prediction model, to gain an in-depth insight into student behavioral patterns for offline, online and potentially help students to improve the performance. 
• The machine learning is successfully done the predictions of the students academic and behaviors from the online and offline.

Reference:

• S. P. Gilbert, and C. C. Weaver, “sleep quality and academic performance in university students: A wake-up call for college psychologists,” journal of college student psychotherapy, vol. 24, no. 4, pp. 295-306, 2010. 
• Z. Liu, C. Yang, L. S. Rüdian, S. Liu, L. Zhao, and T. Wang, “temporal emotion-aspect modeling for discovering what students are concerned about in online course forums,” interactive learning environments, vol. 27, pp. 598-627, 2019.
•  B. Kim, B. Vizitei, and V. Ganapathi, “gritnet: student performance prediction with deep learning,” in proc. Of the 11th international conference on educational data mining, buffalo, NY, USA, 2018, pp. 625-629.