TY - GEN
T1 - Indoor Activity Position and Direction Detection Using Software Defined Radios
AU - Taha, Ahmad
AU - Ge, Yao
AU - Taylor, William
AU - Zoha, Ahmed
AU - Assaleh, Khaled
AU - Arshad, Kamran
AU - Abbasi, Qammer H.
AU - Imran, Muhammad Ali
N1 - Publisher Copyright:
© 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.
PY - 2022
Y1 - 2022
N2 - 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 16t 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 %.
AB - 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 16t 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 %.
KW - Artificial intelligence
KW - Human activity recognition
KW - Indoor positioning
KW - Occupancy monitoring
UR - https://www.scopus.com/pages/publications/85125231149
U2 - 10.1007/978-3-030-95593-9_2
DO - 10.1007/978-3-030-95593-9_2
M3 - Conference contribution
AN - SCOPUS:85125231149
SN - 9783030955922
T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
SP - 15
EP - 27
BT - Body Area Networks. Smart IoT and Big Data for Intelligent Health Management - 16th EAI International Conference, BODYNETS 2021, Proceedings
A2 - Ur Rehman, Masood
A2 - Zoha, Ahmed
PB - Springer Science and Business Media Deutschland GmbH
T2 - 16th EAI International Conference on Body Area Networks, BODYNETS 2021
Y2 - 25 December 2021 through 26 December 2021
ER -