Binary Classifiers for Data Integrity Detection in Wearable IoT Edge Devices

Arlene John,Rajesh C Panicker,Yong Lian,Deepu John,Barry Cardiff

doi:10.1109/ojcas.2020.3009520

Abstract

This paper presents a comparison of several artificial intelligence (AI) based binary classifiers for detecting the integrity of data obtained from Internet of Things (IoT) enabled wearable sensors. Detecting the integrity of data at the network edge facilitates the elimination of corrupted or unusable data, which translates to a lower amount of data stored and transmitted. This reduces the storage and power requirements of IoT devices without a reduction in functionality. In this work, we explore several machine learning-based classifiers to check the integrity of electrocardiogram (ECG) data. The feature vectors are derived from low complexity kurtosis and skewness based Signal Quality Indices (SQIs). From the experiments, it is found that a bagged ensemble of 3 neural networks achieves the highest detection accuracy of 99.47%. We also estimated the complexity and power consumed by the various classifier implementations and classifier fusion implementations. The energy consumed by the ensemble classifier was estimated to be around 0.039 nJ.

Highlights

H EALTHCARE expenditure is increasingly becoming the most significant component in the national spending of many countries
The method discussed is found to be suitable for improving the quality of ECG signals obtained from wearable Internet of Things (IoT) devices based on performance accuracy as well as computational complexity
2 signal quality indicators, namely kSQI and sSQI-with each of them calculated for 3 non-overlapping windows of the record were used as features for classification and an ensemble of neural networks were found to perform best in-terms-of all performance parameters considered

Summary

Introduction

H EALTHCARE expenditure is increasingly becoming the most significant component in the national spending of many countries. Real-time monitoring of physiological data using Internet of Things (IoT) enabled wearable sensors is widely touted as an effective way to address this issue by healthcare researchers, clinical practitioners, and academia. Long-term monitoring of the data acquired from IoT sensors, using machine learning (ML) techniques in cloud servers, can facilitate early detection such that proactive actions can be initiated. The PhysioNet/Computation in Cardiology Challenge 2011 (CinC) attempted to address this issue by developing efficient real-time algorithms to run on a smartphone that can provide useful feedback to the user while acquiring an ECG signal [1]. Many SoCs possess enough computing capacity to perform complex computations on the devices itself, enabling computation at the edge of the network.

Methods

Results

Conclusion