SECOE: Alleviating Sensors Failure in Machine Learning-Coupled IoT Systems
Yousef AlShehri, Lakshmish Macheeri Ramaswamy · 2022
Internet of Things (IoT) domains are characterized by continuous streams of data originating from diverse, geographically distributed sensors. Sensor/network failures that result in data stream interruptions is a major challenge in applying ML techniques to IoT domains. Unfortunately, the performance of many ML applications quickly degrades when faced with data incompleteness. With the aim of building robust IoT-coupled ML applications, this paper proposes SECOE – a unique, proactive approach for alleviating potentially simultaneous sensor failures. The fundamental idea behind SECOE is to create a carefully chosen ensemble of ML models in which each model is trained assuming a set of failed sensors. SECOE includes a novel technique to minimize the number of models in the ensemble by harnessing the correlations among sensors. We demonstrate the efficacy of the SECOE approach through a series of experiments involving two distinct datasets.