首页|Semantic sensor data integration for talent development via hybrid multi-objective evolutionary algorithm
Semantic sensor data integration for talent development via hybrid multi-objective evolutionary algorithm
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Wiley
In this work, we propose a new hybridMulti-Objective Evolutionary Algorithm(hMOEA) specifically designed for semantic sensor data integration, targetingtalent development within the burgeoning field of the Semantic Internetof Things (SIoT). Our approach synergizes the capabilities of Multi-ObjectiveParticle Swarm Optimization and Genetic Algorithms to tackle the sophisticatedchallenges inherent in Sensor Ontology Matching (SOM). This innovativehMOEA framework is adapt at discerning precise semantic correlations amongdiverse ontologies, thereby facilitating seamless interoperability and enhancingthe functionality of IoT applications. Central to our contributions are the developmentof an advanced multi-objective optimization model that underpins theSOM process, the implementation of the hMOEA framework which sets a newbenchmark for accurate semantic sensor data integration, and the rigorous validationof hMOEA’s superiority through extensive testing in varied real-worldSOM scenarios. This research not only marks a significant advancement inSOM but also highlights the critical role of cutting-edge SOM methodologiesin educational curricula, for example, the new business subject education proposedby China in recent years, aimed at equipping future professionalswith thenecessary skills to innovate and lead in the SIoT and SWdomains.
semanticontologytalentmulti-objectiveevolutionary
Fang Luo、Ya-Juan Yang、Yu-Cheng Geng
展开 >
Business School, Dongguan CityUniversity, Dongguan, China
Account & Finance School, DongguanCity University, Dongguan, China
NETL
NSTL
Wiley
