Dataset Open Access
Footstep-induced floor vibration sensing has been used in many smart home applications, such as elderly/patient care, health monitoring. However, impact by the deployment environment, the acquired dataset in the different environments might have different characteristics. We utilize structural vibration sensing to acquire the footstep-induced floor vibration dataset under different humans, wearing different shoes, and in different environments. We also utilize wearable accelerometer sensing to capture the footstep event activity as the ground truth of the vibration dataset.
The name format of each variable is as: "People ID_Environment ID_Sensor ID_Lane ID_Shoe ID". In this dataset, we have two human objects, eight environments, four sensors, three lanes, and three different shoes. You can find more details in our published paper.
Each variable is a struct, and it contains four files: (1)'vibration': the raw vibration data (2,3,4)'IMU_X/Y/Z': the raw data of wearable accelerometer sensor.
Currently, we have two papers published using this dataset [1,2].
Zhang, Yue, et al. "AutoQual: task-oriented structural vibration sensing quality assessment leveraging co-located mobile sensing context." CCF Transactions on Pervasive Computing and Interaction (2021): 1-19.
Yu, Tong, et al. "Vibration-Based Indoor Human Sensing Quality Reinforcement via Thompson Sampling." Proceedings of the First International Workshop on Cyber-Physical-Human System Design and Implementation. 2021.