Chapter 35 Robust Occupant Detection Through Step-Induced Floor Vibration by Incorporating Structural Characteristics Mike Lam, Mostafa Mirshekari, Shijia Pan, Pei Zhang, and Hae Young Noh Abstract The objective of this paper is to present an occupant detection method through step-induced structural vibration. Occupant detection enables various smart building applications such as space/energy management. Ambient structural vibration monitoring provides a non-intrusive sensing approach to achieve that. The main challenges for structural vibration based occupant footstep detection include that (1) the ambient structural vibration noise may overwhelm the step-induced vibration and (2) there are various other impulse-like excitations that look similar to footstep excitations in the sensing environment (e.g., door closing, chair dragging, etc.), which increase the false alarm rate for occupant detection. To overcome these challenges, a two-stage step-induced signal detection algorithm is developed to (1) incorporate the structural characteristics by selecting the dominant frequencies of the structure to increase the signal-to-noise ratio in the vibration data and thus improve the detection performance and (2) perform footstep classification on detected events to distinguish step-induced floor vibrations from other impulse excitations. The method is validated experimentally in two different buildings with distinct structural properties and noise characteristics, Carnegie Mellon University (CMU) campus building and Vincentian Nursing Home deployments in Pittsburgh, PA. The occupant footstep detection F1 score shows up to 4X reduction in detection error compared to traditional thresholding method. Keywords Occupant detection • Structural vibration • Wavelet analysis • One-class classification • Natural frequency 35.1 Introduction Accurately detecting occupants is an important starting point for successful analysis of occupant information. Occupant detection has extensive applications in smart infrastructures. For example, detecting occupants can help understand infrastructure utilization and thus improve maintenance schedule and management. Furthermore, the presence and number of occupants can aid HVAC control for energy management purpose. Current indoor occupant detection makes use of several types of sensors, and each has its own benefits and limitations. The main sensor types include cameras, infrared (IR) sensors, radio frequency (RF) sensors, acoustic sensors, and vibration sensors [1–8]. Cameras, IR sensors, and RF sensors require line-of-sights to capture occupants, which introduces difficulty in installation. RF sensors also face the multipath problem, which makes the sensing sensitive to the ambient environment. Acoustic sensors detect occupant presence by their talk or footstep sounds, however such methods are often sensitive to high ambient noise in the sensing environment. In addition, under some scenarios users do not want their images being captured in cameras and their conversations being recorded by microphones due to privacy reasons. The vibration sensors are used for pedestrian spatio-temporal information sensing [9–11], however the application’s performance depends on the footsteps detection performance. We use vibration sensors in this paper to detect occupants due to its non-intrusive deployment nature, which makes the system easy to install and maintain. The main idea of our method is to detect individual occupants through their footstepinduced vibration in the building structure. Challenges for occupant detection through ambient structural vibration sensing are mainly two folds: (1) the ambient structural vibration noise may overwhelm the step-induced vibration signals; and (2) various other impulse excitations in the environment generate vibration signals similar to step-induced signals, thus introduce false alarms (low precision) on footstep-induced vibration detection. M. Lam( ) • M. Mirshekari • H.Y. Noh Department of Civil and Environmental Engineering, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213, USA e-mail: yanpuil@andrew.cmu.edu S. Pan • P. Zhang Department of Electrical and Computer Engineering, Carnegie Mellon University, Building 23, Moffett Field, CA 94035, USA © The Society for Experimental Mechanics, Inc. 2016 M. Allen et al. (eds.), Dynamics of Coupled Structures, Volume 4, Conference Proceedings of the Society for Experimental Mechanics Series, DOI 10.1007/978-3-319-29763-7_35 357
RkJQdWJsaXNoZXIy MTMzNzEzMQ==