TY - JOUR
T1 - Software-Defined Radio-Based Contactless Localization for Diverse Human Activity Recognition
AU - Saeed, Umer
AU - Shah, Syed Aziz
AU - Khan, Muhammad Zakir
AU - Alotaibi, Abdullah Alhumaidi
AU - Althobaiti, Turke
AU - Ramzan, Naeem
AU - Imran, Muhammad Ali
AU - Abbasi, Qammer H.
PY - 2023/4/13
Y1 - 2023/4/13
N2 - This article presents a study on contactless localization for activity recognition based on radio frequency (RF) sensing. The focus of this study is on the quantitative analysis of the collected data, which is in the form of channel state information (CSI). The proposed method utilizes a software-defined radio (SDR) system in combination with an ensemble learning technique to localize and identify daily living activities such as leaning, sitting, standing, and walking. Specifically, an SDR device, a universal software radio peripheral (USRP) model X300/X310, is utilized to collect data on the aforementioned activities. The data is collected from an empty space and a participant performing daily living activities in different territories. The acquired data is labeled based on the region, zone, and performed activity. The CSI data is subsequently preprocessed and fed into an ensemble-based machine-learning algorithm for classification. Furthermore, the stability analysis of the proposed method is performed to evaluate its reliability and robustness. The performance of the algorithm is evaluated using various metrics, including a confusion matrix, accuracy, cross-validation score, and training time (Shah et al., 2017 and Taylor et al., 2020). The results demonstrate that the proposed ensemble-based approach achieves a high accuracy of up to 90% in activity recognition, highlighting the effectiveness of the proposed method in contactless localization for activity recognition.
AB - This article presents a study on contactless localization for activity recognition based on radio frequency (RF) sensing. The focus of this study is on the quantitative analysis of the collected data, which is in the form of channel state information (CSI). The proposed method utilizes a software-defined radio (SDR) system in combination with an ensemble learning technique to localize and identify daily living activities such as leaning, sitting, standing, and walking. Specifically, an SDR device, a universal software radio peripheral (USRP) model X300/X310, is utilized to collect data on the aforementioned activities. The data is collected from an empty space and a participant performing daily living activities in different territories. The acquired data is labeled based on the region, zone, and performed activity. The CSI data is subsequently preprocessed and fed into an ensemble-based machine-learning algorithm for classification. Furthermore, the stability analysis of the proposed method is performed to evaluate its reliability and robustness. The performance of the algorithm is evaluated using various metrics, including a confusion matrix, accuracy, cross-validation score, and training time (Shah et al., 2017 and Taylor et al., 2020). The results demonstrate that the proposed ensemble-based approach achieves a high accuracy of up to 90% in activity recognition, highlighting the effectiveness of the proposed method in contactless localization for activity recognition.
KW - Ensemble learning
KW - human activity recognition
KW - indoor localization
KW - radio frequency (RF) sensing
KW - software-defined radio (SDR)
KW - universal software radio peripheral (USRP)
UR - http://www.scopus.com/inward/record.url?scp=85153505258&partnerID=8YFLogxK
U2 - 10.1109/jsen.2023.3265867
DO - 10.1109/jsen.2023.3265867
M3 - Article
SN - 1530-437X
VL - 23
SP - 12041
EP - 12048
JO - IEEE Sensors Journal
JF - IEEE Sensors Journal
IS - 11
ER -