IoT-Based Sensor Systems for Intelligence in Transportation, Healthcare and Natural Gas Detection

Abstract

In the last decade, significant advances have been made to enhance the deployment of sensors. Everything from novel manufacturing technologies (including additive manufacturing techniques) to topologies to material systems.Here we are defining the utility of a sensor as the ability to provide intelligence. Intelligence comes from collecting data , extracting information , which comes from data analytics, and interpreting the information is what we are calling intelligence . Many tools are available, even off-the-shelf capabilities, which include machine learning, artificial intelligence, and even sets of toolboxes in MatLab that have changed the way we obtaining intelligence.In order to obtain viable data, integrity on the collection of the data becomes important. Collection can be done by assigning IP addresses to sensors, on-board data storage and/or Internet of things-type (IoT-type) platforms that have really enabled the utilization of sensors to explode. The challenge is always about obtaining intelligence.This paper introduces the concept of SensorComm’s emission monitoring solution, Wi-NOx™. Wi-NOx™ is an IoT-based real-time NOx emission monitoring system. Installed at the tailpipe, it provides key stakeholders with real-time business intelligence by capturing the pollution footprint of vehicles. Operational efficiencies of up to 15% include fuel savings, predictive maintenance, and performance optimization, all obtained through analytics. This system was developed to monitor emissions from vehicles, more recently modified to monitor patients remotely for healthcare applications, and now to monitor natural gas for oil & gas applications.This talk will discuss the systems strategy for data surety, data analytics, and examples of the intelligence extracted specifically from an application.This material is based upon work supported by the U.S. Department of Energy, National Energy Technology Office program under Award Number DE-FOA-0031864, and by the National Science Foundation under Grant No. 1632498. Figure 1