Causal Digital Twin from Multi-channel IoT

TL;DR

This paper introduces a novel approach to treat multi-channel IoT sensor data as a single time series using a Structural Vector Autoregressive model and Kalman Filter, enabling causal analysis through Ladder Graph visualizations.

Contribution

It presents the Ladder Graph as a new visualization tool for SVAR estimates and introduces the Causal Digital Twin concept for multi-channel IoT data analysis.

Findings

Ladder Graph effectively visualizes causal relationships in multi-channel data.

The proposed method enables high-order causal inference from IoT sensor data.

Application potential demonstrated across various IoT scenarios.

Abstract

Treating data from each sensor in an IoT installation on its own separately is wasteful. This article shows how to treat them as a multi-channel time series and introduces the State-space model formulation of Structural Vector Autoregressive (SVAR) model and the use of time-varying Kalman Filter for optimal estimation of causal parameters. Ladder graphs are introduced as a powerful visualization tool for SVAR estimates where both instantaneous and lagged causal factors are displayed and interactions analyzed. Ladder Graph IS the Causal Digital Twin (CDT); its use for multiple IoT applications that involve multi-channel time series are explored briefly. The main takeaway is that the NEXT STEP in IoT ML is the utilization of data from multiple sensors collectively as a single multi-channel time series. This article shows the way to do it and extract high-order (causal) information via our ladder graph based Causal Digital Twin.