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

Abstract

BACKGROUND: For campus workplace secure text mining, robotic assistance with feature optimization is essential. The space model of the vector is usually used to represent texts. Besides, there are still two drawbacks to this basic approach: the curse and lack of semantic knowledge. OBJECTIVES: This paper proposes a new Meta-Heuristic Feature Optimization (MHFO) method for data security in the campus workplace with robotic assistance. Firstly, the terms of the space vector model have been mapped to the concepts of data protection ontology, which statistically calculate conceptual frequency weights by term various weights. Furthermore, according to the designs of data protection ontology, the weight of theoretical identification is allocated. The dimensionality of functional areas is reduced significantly by combining standard frequency weights and weights based on data protection ontology. In addition, semantic knowledge is integrated into this process. RESULTS: The results show that the development of the characteristics of this process significantly improves campus workplace secure text mining. CONCLUSION: The experimental results show that the development of the features of the concept hierarchy structure process significantly enhances data security of campus workplace text mining with robotic assistance.