®®®® SIIA Público

Título del libro: Intelligent Data Sensing And Processing For Health And Well-Being Applications
Título del capítulo: Data fusion architecture of heterogeneous sources obtained from a smart desk

Autores UNAM:
GUILLERMO GILBERTO MOLERO CASTILLO;
Autores externos:

Idioma:

Año de publicación:
2018
Palabras clave:

Architecture; Data fusion; Data preprocessing; Data sources; Fusion methods; Smart desk


Resumen:

A context-aware system uses heterogeneous data sources to adapt and provide services to the user according to his needs, localization, or his interaction with the environment. However, the use of heterogeneous sources faces various problems caused by the volume of this data, such as high dimensionality, different formats, missing and repetitive data, and high dispersion, among others. This generates data inconsistency, which must be detected in time to avoid erroneous context analysis. Faced with this, data fusion is currently used, which is the action of integrating diverse sources to be analyzed according to a given context. Nowadays, one area that has benefited from data fusion is the smart desk. These smart desks make use of different sensors that collect heterogeneous data needed to describe patterns, activity, or user behavior. However, current data fusion architectures try to avoid the mentioned problems prior to the fusion and not during the whole process. This work proposes a conceptual design of a data fusion architecture for the extraction, preprocessing, fusion, and load process from diverse data sources. It is planned to implement methods for the extraction, preprocessing, and data fusion according to their nature to homogenize them and maintain the coherence of the data, that is, avoid conflicts, outliers, and disorder during the stages of the entire process. Subsequently, homogenized data can be used in analysis and inferences based on a specific context. © 2018 Elsevier Inc. All rights reserved.


Entidades citadas de la UNAM: