SECOE: Alleviating Sensors Failure in Machine Learning-Coupled IoT Systems

TL;DR

SECOE is a proactive ensemble-based method designed to improve the robustness of IoT machine learning applications against multiple sensor failures, maintaining accuracy despite data stream interruptions.

Contribution

This paper introduces SECOE, a novel ensemble technique that leverages sensor correlations to handle concurrent sensor failures in IoT ML systems, which is a significant advancement over existing imputation methods.

Findings

SECOE maintains high prediction accuracy during sensor failures.

The ensemble size is minimized by exploiting sensor correlations.

Experimental results confirm SECOE's robustness across multiple datasets.

Abstract

Machine learning (ML) applications continue to revolutionize many domains. In recent years, there has been considerable research interest in building novel ML applications for a variety of Internet of Things (IoT) domains, such as precision agriculture, smart cities, and smart manufacturing. IoT domains are characterized by continuous streams of data originating from diverse, geographically distributed sensors, and they often require a real-time or semi-real-time response. IoT characteristics pose several fundamental challenges to designing and implementing effective ML applications. Sensor/network failures that result in data stream interruptions is one such challenge. Unfortunately, the performance of many ML applications quickly degrades when faced with data incompleteness. Current techniques to handle data incompleteness are based upon data imputation ( i.e., they try to fill-in missing data). Unfortunately, these techniques may fail, especially when multiple sensors' data streams become concurrently unavailable (due to simultaneous sensor failures). 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 (i.e., the training set omits corresponding values). 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 three distinct datasets. The experimental findings reveal that SECOE effectively preserves prediction accuracy in the presence of sensor failures.