Queen Mary University of London IoT2US (IoT towards Ubiquitous Computing and Science by all) Lab
Objectives: Create an IPS that is unaffected by moving humans, providing more time-invariant location information, unlike Wi-Fi, Bluetooth Method: Use smart phone to create a radiomap of known MF patterns, then detect a new unknown RF pattern & derive the …
Objectives: using deep learning method to predict spatial-temporal distribution of people based on the Call Detail Record (CDR) dataset Method: Use CDR to map the dynamic people density distribution by kernel density estimation (KDE) method, and then input to a …
RTT Measurement Approach An RTT range system requires an initiator to send an FTM request and a responder to respond to it with an acknowledgement (ACK). A complete callback will return four time points t1 ~ t4. The RTT is …
Objectives: use millimetre wave radar to build a HAR system that can recognize human activities and vital signs. Method: Signal processing algorithms (e.g. FFT, Wavelet transform) are used to get feature map and machine learning and deep learning algorithms are …
Objectives: Use UWB to accurately tracking people, and use the seq2seq (RNN) model to classify daily location-driven activities. Method: Four UWB tags are used to built a system and a Kalman filter is used to improve the positioning accuracy Then …
Objectives: Use 2D lidar to track people and recognize location-driven daily activities. Method: A low cost, 2D, rotating Lidar system is used to collect the lidar radial distance and angle data. After converting the raw data to Cartesian coordinates, Hausdorff …