Gender Classification of Walkers via Underfloor Accelerometer Measurements

Abstract

The ability to classify the gender of occupants in a building has far-reaching applications including security and retail sales. The authors demonstrate the success of machine learning techniques for gender classification. Highsensitivity accelerometers mounted non-invasively beneath an actual building floor provide the input for these machine learning methods. While other approaches using gait measurements, such as vision systems and wearable sensors, provide the potential for gender classification, they each face limitations. These limitations include an invasion of privacy, occupant compliance, required line of sight, and/or high sensor density. Underfloor mounted accelerometers overcome these limitations. The authors utilize the highly-instrumented Goodwin Hall smart building on the Virginia Tech campus to measure vibrations of the walking surface caused by walkers. In this study, the gait of fifteen individual walkers was recorded as they, alone, walked down the instrumented hallway. Fourteen accelerometers, mounted underneath the walking surface, recorded walking trials with the placement of the sensors unknown to the walker. This work studies Bagged Decision Trees, Boosted Decision Trees, Support Vector Machines (SVMs), and Neural Networks as the machine learning techniques for their ability to classify gender. A tenfold-cross-validation method is used to comment on the validity of the algorithm's ability to generalize to new walkers. This work demonstrates that a gender classification accuracy of 88% is achievable using the underfloor vibration data from the Virginia Tech Goodwin Hall by using Decision Tree approaches.

A Framework for Occupancy Tracking in a Building via Structural Dynamics Sensing of Footstep Vibrations

“…In addition to obvious remedies such as improving sensor density there may be an algorithmic remedy requiring no additional sensor infrastructure. As noted in the introduction, prior literature (Pan et al, 2015;Bales et al, 2016) extracted statistical features from footstep measurements that enable discrimination among individuals beyond the location and time parameters considered in this paper. Additionally, if the algorithms undertake actual tracking of occupants-not just occupancy tracking-the accuracy has the potential to improve, because the algorithms incorporate all information from a set of observed footsteps and per person state variables (e.g., velocity).…”

“…Furthermore, extracting features from the footstep measurements and applying the features to statistical models of human gait shows promise for distinguishing among individuals by their characteristic gait (Pan et al, 2015) or determining gender (Bales et al, 2016).…”

A Review of the Recent Developments in Integrating Machine Learning Models with Sensor Devices in the Smart Buildings Sector with a View to Attaining Enhanced Sensing, Energy Efficiency, and Optimal Building Management

“…In their research, the authors of these papers implement various types of sensors, according to their purposes, namely: indoor sensors [1], occupancy information sensors [1], electricity meters [1,6,44], motion sensors [6,7,30,59,60], item kitchen sensors [6], door sensors [6,59,61,62], temperature sensors [1,2,6,59,63], photosensors [1,3,63], status of water and burner sensors [6,59], acceleration sensors [4,7], Kinect motion sensors [7], modern smartphone sensors [4,7,60], passive radar-based sensors [8], unobtrusive sensors [9,14], infrared sensors [15,30], wireless sensor networks [61,62], accelerometers [5,63], altimeters [63], gyroscopes [63], barometers [63], heart rate monitor [63], embedded sensors [4,…”

“…Assisted living was a strong motivation for using the SVM method with sensor devices in the smart buildings sector; seven of the identified papers focusing on the recognition of human activity did so in order to provide appropriate assisted living [6,14,15,[30][31][32]63], while other papers aimed to achieve assisted living by focusing on human fall detection [7], human behavior recognition [2], assessment of occupancy status information, and identification of human behavior [61]. Other reasons for applying SVM with sensors in smart buildings include measuring the occupancy status of a building's inhabitants in order to improve the energy prediction performance of the building's energy model [1], classifying the gender of occupants [5], forecasting electricity consumption [44], detecting and classifying human behavior with a view to maximizing comfort with optimized energy consumption [52], recognizing household appliances in order to assess their usage and develop habits of power preservation [64], and selecting optimal sensors for use in complex system monitoring problems such as HVAC chillers [65].…”

“…There is an increasing interest in the scientific literature in studies related to these topics; for example, there have been papers focusing on smart buildings [1][2][3][4][5], smart homes [6][7][8][9][10], smart hospitals [11], smart commercial buildings [12,13], sensor devices [9,[14][15][16][17], supervised machine learning models for classification purposes [1,11,[16][17][18] or for regression purposes [19][20][21][22][23], unsupervised machine learning models for clustering purposes [24][25][26], deep learning techniques [18,27,28], human activity recognition and classification with a view to assisted living [15,[29][30][31][32][33][34][35], Internet of Things (IoT) [21,[36][37][38]…”