Using Smart Virtual-Sensor Nodes to Improve the Robustness of Indoor Localization Systems

Abstract

Young, older, frail, and disabled individuals can require some form of monitoring or assistance, mainly when critical situations occur, such as falling and wandering. Healthcare facilities are increasingly interested in e-health systems that can detect and respond to emergencies on time. Indoor localization is an essential function in such e-health systems, and it typically relies on wireless sensor networks (WSN) composed of fixed and mobile nodes. Nodes in the network can become permanently or momentarily unavailable due to, for example, power failures, being out of range, and wrong placement. Consequently, unavailable sensors not providing data can compromise the system’s overall function. One approach to overcome the problem is to employ virtual sensors as replacements for unavailable sensors and generate synthetic but still realistic data. This paper investigated the viability of modelling and artificially reproducing the path of a monitored target tracked by a WSN with unavailable sensors. Particularly, the case with just a single sensor was explored. Based on the coordinates of the last measured positions by the unavailable node, a neural network was trained with 4 min of not very linear data to reproduce the behavior of a sensor that become unavailable for about 2 min. Such an approach provided reasonably successful results, especially for areas close to the room’s entrances and exits, which are critical for the security monitoring of patients in healthcare facilities.

An Overview of Machine Learning and 5G for People with Disabilities

“…Neural networks can improve home automation, comfort, security [54], and health care for people with disabilities in their smart homes [55]. Neural networks can implement virtual sensors to replace temporarily unavailable physical sensors for indoor localization systems [56]. These systems are helpful for monitoring and assisting people with disabilities during critical situations, such as wandering or falling.…”

“…Dynamic resource sharing among tenants enables more efficient network resource usage but also introduces new problems such as how to guarantee a secure isolation of the slices. Security requirements of specific tenant applications, such as remote vehicular control (for people with disabilities), could restrict how the slices are partitioned, or even prevent the coexistence of network slices that would share the same hardware [56]. Since network slices exchange important information about the network state and the network resources, the higher the number of virtual network functions share between slices, the higher the security risks might be [74].…”

Simulation of Virtual Redundant Sensor Models for Safety-Related Applications

“…In [12][13][14][15][16][17], it is possible to find some interesting applications of virtual sensors in areas such as:…”

“…Traffic-vehicle suspension control by means of virtual sensors based on a neural network to determine the estimate vehicle unsprang mass relative velocity [12]; • Environment-virtual sensing for real-time monitoring of surface and groundwater sources for irrigation purposes [13]; • Health-use of a virtual sensor for safety monitoring of a person's position as a replacement for a real position sensor, provided that the position matches within the active radius of the sensor [14];…”

“…The most essential part of our work was dedicated to the creation of virtual redundant sensor software with support of defined numerical models in Equations ( 1) to (14). In order to enable a flexible simulation, the software client of the virtual redundant sensor supports selection of defined models with its required parameters.…”