Application of Computational Intelligence to Improve Education in Smart Cities

Area of Science:

• Educational Technology
• Computational Intelligence
• Data Science

Background:

• Universal access to quality education remains a global challenge, particularly in developing nations.
• Effective strategies are needed to enhance educational quality and student outcomes.
• Personalized learning approaches can support educators in student guidance.

Purpose of the Study:

• To present a computational intelligence model for developing student knowledge profiles.
• To assist educators in making informed decisions for student orientation and strategic planning.
• To establish key performance indicators for monitoring educational objectives.

Main Methods:

• Application of data mining and data science techniques.
• Utilizing random forest for classification and prediction.
• Employing graph description for data visualization and recommendation systems.

Main Results:

• Development of a student knowledge profiling model.
• Identification of correlations within educational data.
• A predictive model for student performance was established.
• Generated recommendations for educational stakeholders.

Conclusions:

• Computational intelligence offers a viable approach to enhance educational decision-making.
• Student knowledge profiling can lead to more effective student guidance.
• The model provides tools for monitoring and improving educational strategies.