An Intelligent Failure Detection on a Wireless Sensor Network for Indoor Climate Conditions

Abstract

Wireless sensor networks (WSN) involve large number of sensor nodes distributed at diverse locations. The collected data are prone to be inaccurate and faulty due to internal or external influences, such as, environmental interference or sensor aging. Intelligent failure detection is necessary for the effective functioning of the sensor network. In this paper, we propose a supervised learning method that is named artificial hydrocarbon networks (AHN), to predict temperature in a remote location and detect failures in sensors. It allows predicting the temperature and detecting failure in sensor node of remote locations using information from a web service comparing it with field temperature sensors. For experimentation, we implemented a small WSN to test our sensor in order to measure failure detection, identification and accommodation proposal. In our experiments, 94.18% of the testing data were recovered and accommodated allowing of validation our proposed approach that is based on AHN, which detects, identify and accommodate sensor failures accurately.

Decision tree-based radio link failure prediction for 5G communication reliability

“…With 5G applications multiplying by the day, it is essential to predict and forecast the possibilities of failure in radio links to employ measures to solve such disruptions in connectivity. Existing research work for radio link failure prediction considers multiple factors individually, such as signal strength [3], weather phenomenon [4], mobility, realtime data, etc. [5].…”

“…The best accuracy was achieved through KNNs but required extensive data and large computational expenditure. Prone to indoor climate conditions, wireless sensor networks were studied and failures were detected using a newly proposed supervised learning network [4]. Equipped with temperature sensors, this system estimates the temperature in a remote location using the novel model designed.…”

Climate-Aware and IoT-Enabled Selection of the Most Suitable Stone Fruit Tree Variety

“…The system uses supervised learning to predict the temperature; the result is compared with a web service, obtaining an error of approximately 2.1 °C; the model used obtains excellent results but to determine the cooling needs of crops, the error should be lower. In a similar vein, the work proposed by Gutiérrez and Ponce [ 30 ] propose a supervised learning method called artificial hydrocarbon networks (AHN) to predict the temperature at a remote location together with the intelligent detection and identification of possible sensor failures; the behavior of the proposed model should be verified with a network of agro-meteorological stations.…”

Auto-Gerenciamento de Falhas no Contexto de Ambientes Inteligentes e Assistidos: Uma Abordagem Baseada em Redes Bayesianas

“…Uma das características dessas redes é que são propícias a falhas como: quebra, interferência de comunicação por conta de outros elementos no ambiente e falta de energia. Essas falhas comprometem a transmissão e a coleta de informações [Gutiérrez et al 2019], o que resulta na perda da eficiência de seu funcionamento provocando assim um possível problema ao indivíduo que depende do AIA no seu cotidiano. Portanto, dada a natureza sensível dos serviços oferecidos nos AIAs, a detecção e diagnóstico de falhas nessas redes são muito importantes.…”