9 May 2018 Mobile node networks model for the generation of knowledge
Author Affiliations +
Mobile node networks are wireless networks formed by different types of devices (sensors, actuators, drones, servers, etc.) that collect, disseminate, process and store information about the environment. This type of networks allows the development of applications in different fields such as medicine, environmental protection, public transport, industrial control, militia, among others. The processing of information acquired by this type of networks is a complex task mainly for 3 reasons: the heterogeneity of the devices that make up the network, the massive amount of information that can be acquired and stored, and the size of the problem or phenomenon to be studied. Due to these difficulties, different tools and approaches have been developed and proposed to perform the processing, analysis, integration and management of information in mobile node networks (data mining, use of middleware, statistical models, Machine learning, Statistical learning, Deep learning, mobile agents, to mention a few). This paper proposes a model applicable to mobile node networks that allows generating knowledge from the variables acquired from the medium. This model is based on the use of ontologies to identify the components of the networks, the relationship between them and the situation under which they work, to subsequently analyze and process information through a statistical model that provides knowledge according to the context, but also allows to infer and predict behaviors and actions in the phenomenon studied.
Conference Presentation
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Manuel A. Díaz-Casco, Manuel A. Díaz-Casco, Blanca E. Carvajal-Gámez, Blanca E. Carvajal-Gámez, "Mobile node networks model for the generation of knowledge", Proc. SPIE 10651, Open Architecture/Open Business Model Net-Centric Systems and Defense Transformation 2018, 106510I (9 May 2018); doi: 10.1117/12.2304873; https://doi.org/10.1117/12.2304873

Back to Top