Correlating Time Series Signals and Event Logs in Embedded Systems.

Kazimierz Krosman,Janusz Sosnowski

doi:10.3390/s21217128

Kazimierz Krosman, Janusz Sosnowski

Open Access

https://doi.org/10.3390/s21217128

Copy DOI

Abstract

In many embedded systems, we face the problem of correlating signals characterising device operation (e.g., performance parameters, anomalies) with events describing internal device activities. This leads to the investigation of two types of data: time series, representing signal periodic samples in a background of noise, and sporadic event logs. The correlation process must take into account clock inconsistencies between the data acquisition and monitored devices, which provide time series signals and event logs, respectively. The idea of the presented solution is to classify event logs based on the introduced similarity metric and deriving their distribution in time. The identified event log sequences are matched with time intervals corresponding to specified sample patterns (objects) in the registered signal time series. The matching (correlation) process involves iterative time offset adjustment. The paper presents original algorithms to investigate correlation problems using the object-oriented data models corresponding to two monitoring sources. The effectiveness of this approach has been verified in power consumption analysis using real data collected from the developed Holter device. It is quite universal and can be easily adapted to other device optimisation problems.

Highlights

Various sensors are widely used in diverse domains and the collected data need quite sophisticated processing for cognitive or reactive activities
In the case of external monitoring of signals, we face the problem of time correlation of the derived time series and other logs generated by the monitored system, usually not synchronised. This problem is neglected in the literature, and we showed its practical importance [2] while analysing time series features at a higher observation level involving data sample aggregation into time series objects
For an analysed time series (TS) sequence composed of three intervals—117 s, 120 s, and 119 s separated by 22 min 25 s and 27 min and 21 s, respectively—we found only 11 sets of similar bags of words that matched with these intervals

Summary

Introduction

Various sensors are widely used in diverse domains and the collected data need quite sophisticated processing for cognitive or reactive activities. This triggered the development of tiny and low-cost devices installed in the field. An important issue is testing and validation of relevant device prototypes in simulation or production environments. This process needs efficient real-time monitoring of the device’s operation. It involves observation of selected physical signals and device and environment states ([1,2] and references therein). From an analytical point of view, this leads to correlation analysis of time series depicting considered signal states and relevant device state/event logs

Objectives

Discussion

Conclusion