Indoor Navigation and Neural Networks – An IOTC or Internet of Things Cloud

October 2, 2013

in innovation, IoT Internet of Things, Location & Context, Mobility, Strategic Foresight

LocationThere will soon be a very nice business in installing Bluetooth LE networks in retail stores that are tightly planned (example supermarket planograms). The installation will involve making sure there are no dead zones, while the consultants tie in the backend product services with the product localization maps. Then the environment can become alive and personalized to you.

“In this paper, a low-cost Bluetooth based localization system has been proposed. We introduced a novel approach based on multiple neural networks. The most suitable one is automatically selected and loaded by the system depending on user orientation, estimated with a compass. In this way, the system copes with the power absorption of the human body, achieving higher accuracy. In fact, taking into account the user orientation during both training phase and use, we proved that the indoor user tracking improves significantly. Using a few basestations and common office devices such as a laptop and a PDA, we obtained results significantly better than the current state of the art, where Bluetooth systems are usually limited to room level localization [10, 11]. Our results show that the system could be employed in a navigation task, where high degree of confidence on the localization is necessary to reach the expected destination. 90% of precision and 0.5 meters of accuracy were achieved during a walk along the corridor. Moreover a recovery system able to improve system performance in case of base stations failure has been implemented. It increases the accuracy of the system from 48% to 74% even when only 60% of the original deployed nodes are active.” 

I started looking for information like this after thinking about triangulation and how just a few Bluetooth LE beacons could help you map out a detailed area and the route that a person was taking and what they might be passing/seeing along that route. What intrigued me about the above was that the compass, and no doubt other motion sensors, will assist in improving accuracy to 0.5 meters.

In a highly planned retail environment, the products won’t need complex tags for the environment to come alive. It will just require a customer motivated to use the retailer’s App.

Separately, I’m beginning to consider this as an IOTC or Internet of Things Cloud, where the things themselves have no real intelligence, rather exist in a localized cloud which is simply accessed by walking around, fueled by a database on what’s currently in-stock.


Previous post:

Next post: