|Title||Indoor Location IoT Analytics “in the wild”: Active and Healthy Ageing Cases|
|Publication Type||Book Chapter|
|Year of Publication||2016|
|Authors||Konstantinidis, Evdokimos, Billis Antonis, Plotegher Leonardo, Conti Giuseppe, and Bamidis Panagiotis|
|Book Title||XIV Mediterranean Conference on Medical and Biological Engineering and Computing, MEDICON|
Early detection of cognitive and physical status deterioration for elderly people has been much dependent on gait analysis lately. However, much of the recent literature fo- cuses on gait analysis methodologies exploiting average speed. This presents a serious constraint when gait analysis is supposed to drive context aware applications. To this end, this work ap- plies density based clustering algorithms on gait and trajectory IoT data recorded from real senior homes ("on the wild"). The indoor analytics client analyzes high density regions rendered from locations in real senior homes facilitated by IoT technology consisting of events describing the seniors’ position. These are collected, analyzed and made available by the indoor analytics client taking into account the available processing resources and configuring itself to deliver the analytics outcome even when it is hosted in hardware with constrained resources. Promising re- sults are obtained by analyzing a whole week's data in two sen- iors’ homes. The algorithm performance and accuracy with re- spect to the number of points included in the analysis are presented and discussed.