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. High-sensitivity accelerometers mounted noninvasively 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 paper, the gait of 15 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 paper studies bagged decision trees, boosted decision trees, support vector machines, 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 paper 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.

Mechanical waves are induced in solids due to the system’s coupling with an external excitation. Depending upon the nature of the resulting displacement and phase difference between the vibrating particles at a particular frequency, the mechanical waves can be classified as standing waves, traveling waves or a combination of the two. This study focuses on the identification of these different forms of mechanical waves and discusses methods that can be suitably used for their classification. The Hilbert and Fourier methods of classification were validated using experimental results and then compared against each other. The experimental and theoretical analysis of mechanical waves was conducted on a beam with free-free boundary conditions excited by piezoelectric elements.

Mechanical waves can be broadly categorized into traveling waves and standing waves. In this study, the nature of the waves in a finite solid medium is investigated to reveal the excitation parameters that influence their behavior. Theoretical and experimental analysis is conducted to find the conditions for generating traveling waves using piezoelectric ceramics as the actuation agent in piezo-structural-coupled systems. A continuous electromechanical model is developed in order to predict the structural dynamics and is validated through experiments. The results from this study provide the fundamental physics behind the generation of mechanical waves and their propagation through finite mediums.

The present work explores the generation of two-dimensional steady-state flexural waves that are non-reflective on a thin rectangular plate with free boundary conditions when excited by two macro-fiber composites (MFCs). The voltage signals to the MFCs have a frequency lying halfway between two adjacent resonant frequencies with a phase difference of $90\circ$ . Locations of MFCs and frequencies of actuation are varied to study the response of the plate due to these forces. A finite element plate model is developed and updated based on experimental modal tests on the plate. This model is able to predict up to the 40th damped eigenvalue with a maximum error of 2.5% and match mode shapes accurately, with a lowest Modal Assurance Criterion value of 0.92. Numerical simulations of traveling waves have been carried out and are compared with experimental results. Preliminary results show that the location of the MFCs and the frequency of excitation have an effect on the type and the quality of the traveling waves. These results shall lay the foundation for an exhaustive analysis of planar traveling waves in plates.

Gait analysis is an invaluable tool in diagnosing and monitoring human health. Current techniques often rely on specialists or expensive gait measurement systems. There is a clear space in the field for a simple, inexpensive, quantitative way to measure various gait parameters. This study investigates if useful quantitative gait parameters can be extracted from floor acceleration measurements produced by the input of foot falls. A total of 17 participants walked along a 115-ft-long hallway while underfloor mounted accelerometers measured the vertical acceleration of the floor. Signal-energy-based algorithms detect the heel strike of each step during trials. From the detected footsteps, gait parameters such as the average stride length, the time between steps, and the step signal energy were calculated. In this study, a single accelerometer was shown to be enough to detect steps over a 115-ft corridor. Distributions for all gait parameters measured were generated for each participant, showing a normal distribution with low standard deviation. The success of gait analysis using underfloor accelerometers presents possibilities in the widespread adaptation of gait measurements. The ease of installation and operation offers an opportunity to gather long-term gait measurements. Such data will augment current gait diagnostic approaches by filling the gaps between specialist visits.

Indoor localization by means of GNSS or a cellular-based method is known to be difficult. Potentially, other wireless technologies could address the technical requirements, but they usually imply the end user must carry a device compatible with this additional technology too. In this paper we investigate the feasibility of collecting vibration sensor readings within a building to locate pedestrians by their footsteps. Vibration propagation in buildings is markedly different than radio wave propagation in free space, thus prompting one to question the suitability of conventional positioning algorithms for this task. We presents the results of experiments conducted with actual measurements from an instrumented, smart building. We expect such buildings to become more prevalent in the future thanks to the technical advances and cost reductions provided by the Internet-of-Things (IoT). The promising initial findings indicate that time-difference-of-arrival, within a limited spatial extent, could be a viable localization technique, and these results encourage further research into vibration-based indoor localization.