Research Article
Indoor Activity Position and Direction Detection Using Software Defined Radios
@INPROCEEDINGS{10.1007/978-3-030-95593-9_2, author={Ahmad Taha and Yao Ge and William Taylor and Ahmed Zoha and Khaled Assaleh and Kamran Arshad and Qammer H. Abbasi and Muhammad Ali Imran}, title={Indoor Activity Position and Direction Detection Using Software Defined Radios}, proceedings={Body Area Networks. Smart IoT and Big Data for Intelligent Health Management. 16th EAI International Conference, BODYNETS 2021, Virtual Event, October 25-26, 2021, Proceedings}, proceedings_a={BODYNETS}, year={2022}, month={2}, keywords={Artificial intelligence Indoor positioning Human activity recognition Occupancy monitoring}, doi={10.1007/978-3-030-95593-9_2} }- Ahmad Taha
Yao Ge
William Taylor
Ahmed Zoha
Khaled Assaleh
Kamran Arshad
Qammer H. Abbasi
Muhammad Ali Imran
Year: 2022
Indoor Activity Position and Direction Detection Using Software Defined Radios
BODYNETS
Springer
DOI: 10.1007/978-3-030-95593-9_2
Abstract
The next generation of health activity monitoring is greatly dependent on wireless sensing. By analysing variations in channel state information, several studies were capable of detecting activities in an indoor setting. This paper presents promising results of an experiment conducted to identify the activity performed by a subject and where it took place within the activity region. The system utilises two Universal Software Radio Peripheral (USRP) devices, operating as software-defined radios, to collect a total of 360 data samples that represent five different activities and an empty room. The five activities were performed in three different zones, resulting in 15 classes and a(16^t{}^h)class representing the room whilst it is empty. Using the Random Forest classifier, the system was capable of differentiating between the majority of activities, across the 16 classes, with an accuracy of almost(94\%). Moreover, it was capable of detecting whether the room is occupied, with an accuracy of(100\%), and identify the walking directions of a human subject in three different positions within the room, with an accuracy of(90\%).
