Heracles: A Context-Based Multisensor Sensor Data Fusion Algorithm for the Internet of Things

Autor(es)

Delicato, Flavia C. ^[1] ; Vandelli, Tayssa ^[2] ; Bonicea, Mario ^[2] ; Farias, Claudio M. de ^[2]

Afiliação do(s) autor(es)

^[1] Fluminense Fed Univ, Dept Comp Sci, BR-24210310 Niteroi, RJ - Brazil

^[2] Univ Fed Rio de Janeiro, Tercio Pacitti Inst Appl Computat Res, BR-21941916 Rio De Janeiro, RJ - Brazil

• Tipo de documento: Artigo Científico
• Fonte: INFORMATION; v. 11, n. 11 NOV 2020.
• Citações Web of Science: 0

Resumo

In the Internet of Things (IoT), extending the average battery duration of devices is of paramount importance, since it promotes uptime without intervention in the environment, which can be undesirable or costly. In the IoT, the system's functionalities are distributed among devices that (i) collect, (ii) transmit and (iii) apply algorithms to process and analyze data. A widely adopted technique for increasing the lifetime of an IoT system is using data fusion on the devices that process and analyze data. There are already several works proposing data fusion algorithms for the context of wireless sensor networks and IoT. However, most of them consider that application requirements (such as the data sampling rate and the data range of the events of interest) are previously known, and the solutions are tailored for a single target application. In the context of a smart city, we envision that the IoT will provide a sensing and communication infrastructure to be shared by multiple applications, that will make use of this infrastructure in an opportunistic and dynamic way, with no previous knowledge about its requirements. In this work, we present Heracles, a new data fusion algorithm tailored to meet the demands of the IoT for smart cities. Heracles considers the context of the application, adapting to the features of the dataset to perform the data analysis. Heracles aims at minimizing data transmission to save energy while generating value-added information, which will serve as input for decision-making processes. Results of the performed evaluation show that Heracles is feasible, enhances the performance of decision methods and extends the system lifetime. (AU)

• Processo FAPESP: 15/24144-7 - Tecnologias e soluções para habilitar o paradigma de nuvens de coisas
• Beneficiário: José Neuman de Souza
• Modalidade de apoio: Auxílio à Pesquisa - Temático