Spatial data analysis for intelligent buildings: Awareness of context and data uncertainty

Area of Science:

• Computer Science
• Building Technology
• Data Science

Background:

• Intelligent buildings extensively use Internet-of-Things (IoT) for digital transformation.
• Spatial data analysis in intelligent buildings offers insights for space management and efficiency.
• Existing methods face challenges with complex analytical contexts and data uncertainty.

Purpose of the Study:

• To address challenges in spatial data analysis for intelligent buildings (SDAIB).
• To propose a unified modeling framework for context-aware and uncertainty-aware SDAIB.
• To enable advanced SDAIB applications like hotspot discovery and path planning.

Main Methods:

• Categorization of analytical contexts and spatial data uncertainties in SDAIB.
• Development of a unified modeling framework to handle identified challenges.
• Demonstration of framework application in hotspot discovery, path planning, semantic trajectory generation, and distance monitoring.

Main Results:

• A systematic categorization of SDAIB contexts and uncertainties.
• A unified framework effectively handling spatial data complexity and uncertainty.
• Successful enablement of context-aware and uncertainty-aware SDAIB applications.

Conclusions:

• The proposed framework provides a robust solution for SDAIB challenges.
• Context-aware and uncertainty-aware SDAIB is crucial for intelligent building applications.
• Future research directions align with emerging IoT trends for enhanced SDAIB.