Meta-Heuristic Feature Optimization for ontology-based data security in a campus workplace with robotic assistance

Area of Science:

• Computer Science
• Information Security
• Artificial Intelligence

Background:

• Campus workplace secure text mining requires effective feature optimization.
• Traditional vector space models for text representation have limitations, including the curse of dimensionality and lack of semantic knowledge.
• Robotic assistance is crucial for implementing advanced text mining techniques in secure environments.

Purpose of the Study:

• To propose a novel Meta-Heuristic Feature Optimization (MHFO) method for enhancing data security in campus workplace text mining.
• To address the drawbacks of traditional text representation methods by integrating semantic knowledge and data protection ontologies.
• To improve the efficiency and accuracy of secure text mining processes with robotic assistance.

Main Methods:

• Mapping terms from the space vector model to data protection ontology concepts.
• Calculating conceptual frequency weights and allocating theoretical identification weights based on ontology designs.
• Integrating semantic knowledge and combining standard frequency weights with ontology-based weights to reduce dimensionality.
• Utilizing robotic assistance for feature optimization in text mining.

Main Results:

• The developed MHFO method significantly improves the characteristics of secure text mining processes in campus workplaces.
• Dimensionality reduction was achieved by effectively combining different weighting strategies.
• Enhanced feature optimization led to more robust data security.

Conclusions:

• The experimental results confirm that the MHFO method, incorporating concept hierarchy structures, significantly enhances data security in campus workplace text mining.
• The integration of semantic knowledge and ontology-based weighting provides a more effective approach to secure text mining.
• The findings support the use of robotic assistance and advanced feature optimization for improving data security in academic and professional environments.