An edge intelligence-enhanced quantitative assessment model for implicit working gain under mobile internet of things

Abstract

Edge intelligence refers to a novel operation mode in which intelligent algorithms are implemented in edge devices to break the limitation of computing power. In the context of big data, mobile computing has been an effective assistive tool in many cross-field areas, in which quantitative assessment of implicit working gain is typical. Relying on the strong ability of data integration provided by the Internet of Things (IoT), intelligent algorithms can be equipped into terminals to realize intelligent data analysis. This work takes the assessment of working gain in universities as the main problem scenario, an edge intelligence-enhanced quantitative assessment model for implicit working gain under mobile IoT. Based on fundamental data acquisition from deployed mobile IoT environment, all the distributed edge terminals are employed to implement machine learning algorithms to formulate a quantitative assessment model. The dataset collected from a real-world application is utilized to evaluate the performance of the proposed mobile edge computing framework, and proper performance can be obtained and observed.

Keywords

• edge intelligence
• mobile iot
• quantitative assessment model
• mobile computing
• machine learning