Hae Young Noh

BOES: Building Occupancy Estimation System using sparse ambient vibration monitoring

In this paper, we present a room-level building occupancy estimation system (BOES) utilizing low-resolution vibration sensors that are sparsely distributed. Many ubiquitous computing and building maintenance systems require fine-grained occupancy knowledge to enable occupant centric services and optimize space and energy utilization. The sensing infrastructure support for current occupancy estimation systems often requires multiple intrusive sensors per room, resulting in systems that are both costly to deploy and difficult to maintain. To address these shortcomings, we developed BOES. BOES utilizes sparse vibration sensors to track occupancy levels and activities. Our system has three major components. 1) It extracts features that distinguish occupant activities from noise prone ambient vibrations and detects human footsteps. 2) Using a sequence of footsteps, the system localizes and tracks individuals by observing changes in the sequences. It uses this tracking information to identify when an occupant leaves or enters a room. 3) The entering and leaving room information are combined with detected individual location information to update the room-level occupancy state of the building. Through validation experiments in two different buildings, our system was able to achieve 99.55% accuracy for event detection, less than three feet average error for localization, and 85% accuracy in occupancy counting.

Use of Wavelet-Based Damage-Sensitive Features for Structural Damage Diagnosis Using Strong Motion Data

This paper introduces three wavelet-based damage-sensitive features (DSFs) extracted from structural responses recorded during earthquakes to diagnose structural damage. Because earthquake excitations are nonstationary, the wavelet transform, which represents data as a weighted sum of time-localized waves, is used to model the structural responses. These DSFs are defined as functions of wavelet energies at particular frequencies and specific times. The first DSF (DSF1) indicates how the wavelet energy at the original natural frequency of the structure changes as the damage progresses. The second DSF (DSF2) indicates how much the wavelet energy is spread out in time. The third DSF (DSF3) reflects how slowly the wavelet energy decays with time. The performance of these DSFs is validated using two sets of shake-table test data. The results show that as the damage extent increases, the DSF1 value decreases and the DSF2 and DSF3 values increase. Thus, these DSFs can be used to diagnose structural damage. The r...

Indoor Person Identification through Footstep Induced Structural Vibration

Person identification is crucial in various smart building applications, including customer behavior analysis, patient monitoring, etc. Prior works on person identification mainly focused on access control related applications. They achieve identification by sensing certain biometrics with specific sensors. However, these methods and apparatuses can be intrusive and not scalable because of instrumentation and sensing limitations. In this paper, we introduce our indoor person identification system that utilizes footstep induced structural vibration. Because structural vibration can be measured without interrupting human activities, our system is suitable for many ubiquitous sensing applications. Our system senses floor vibration and detects the signal induced by footsteps. Then the system extracts features from the signals that represent characteristics of each persons gait pattern. With the extracted features, the system conducts hierarchical classification at an individual step level and then at a trace (i.e., collection of consecutive steps) level. Our system achieves over 83% identification accuracy on average. Furthermore, when the application requires different levels of accuracy, our system can adjust confidence level threshold to discard uncertain traces. For example, at a threshold that allows only most certain 50% traces for classification, the identification accuracy increases to 96.5%.

Characterizing Wave Propagation to Improve Indoor Step-Level Person Localization using Floor Vibration

The objective of this paper is to characterize frequency-dependent wave propagation of footstep induced floor vibration to improve robustness of vibration-based occupant localization. Occupant localization is an essential part of many smart structure applications (e.g., energy management, patient/customer tracking, etc.). Exist- ing techniques include visual (e.g. cameras and IR sensors), acoustic, RF, and load-based approaches. These approaches have many deployment and operational requirements that limits their adaptation. To overcome these limitations, prior work has utilized footstep-induced vibrations to allow sparse sensor configuration and non-intrusive detection. However, frequency dependent propagation characteristics and low signal-to-noise ratio (SNR) of footstep-induced vibrations change the shape of the signal. Furthermore, estimating the wave propagation velocity for forming the multilateration equations and localizing the footsteps is a challenging task. They, in turn, lead to large errors of localization. In this paper, we present a structural vibration based indoor occupant localization technique using improved time-difference-of-arrival between multiple vibration sensors. In particular we overcome signal distortion by decomposing the signal into frequency components and focusing on high energy components for accurate indoor localization. Such decomposition leverages the frequency-specific propagation characteristics and reduces the effect of low SNR (by choosing the components of highest energy). Furthermore, we develop a velocity calibration method that finds the optimal velocity which minimizes the localization error. We validate our approach through field experiments in a building with human participants. We are able to achieve an average localization error of less than 0.21 meters, which corresponds to a 13X reduction in error when compared to the baseline method using raw data.

Occupant traffic estimation through structural vibration sensing

The number of people passing through different indoor areas is useful in various smart structure applications, including occupancy-based building energy/space management, marketing research, security, etc. Existing approaches to estimate occupant traffic include vision-, sound-, and radio-based (mobile) sensing methods, which have placement limitations (e.g., requirement of line-of-sight, quiet environment, carrying a device all the time). Such limitations make these direct sensing approaches difficult to deploy and maintain. An indirect approach using geophones to measure floor vibration induced by footsteps can be utilized. However, the main challenge lies in distinguishing multiple simultaneous walkers by developing features that can effectively represent the number of mixed signals and characterize the selected features under different traffic conditions. This paper presents a method to monitor multiple persons. Once the vibration signals are obtained, features are extracted to describe the overlapping vibration signals induced by multiple footsteps, which are used for occupancy traffic estimation. In particular, we focus on analysis of the efficiency and limitations of the four selected key features when used for estimating various traffic conditions. We characterize these features with signals collected from controlled impulse load tests as well as from multiple people walking through a real-world sensing area. In our experiments, the system achieves the mean estimation error of ±0.2 people for different occupant traffic conditions (from one to four) using k-nearest neighbor classifier.

Step-level person localization through sparse sensing of structural vibration

We describe a step-level indoor localization system which uses the ground vibration induced by human footsteps. Indoor localization is important for various smart building applications, including resources arrangement optimization, patient/customer tracking, etc. Geophones are used to measure the ground vibrations and time difference of arrival (TDoA) for different sensors are used to solve the multilateration localization problem. The advantages of this system include its sparsity and also its stability over time. Lesser dependency on instrument people is another upside of this system. The results of pilot tests show that this system can be successfully used for indoor localization.

Robust Occupant Detection Through Step-Induced Floor Vibration by Incorporating Structural Characteristics

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.

MyoVibe: vibration based wearable muscle activation detection in high mobility exercises

Skeletal muscles are activated to generate the force needed for movement in most high motion sports and exercises. However, incorrect skeletal muscle activation during these sports and exercises, can lead to sub-optimal performance and injury. Existing techniques are susceptible to motion artifacts, particularly when used in high motion sports (e.g. jumping, cycling, etc.). They require limited body movement, or experts to manually interpret results, making them unsuitable in sports scenarios. This paper presents MyoVibe, a wearable system for determining muscle activation in high motion exercise scenarios. MyoVibe senses muscle vibration signals obtained from a wearable network of accelerometers to determine muscle activation. By modeling the characteristics of muscles and high motion noise using extreme value analysis, MyoVibe can reduce noise due to high mobility exercises. Our system can predict muscle activation with greater than 97% accuracy in isometric low motion exercise cases, up to 90% accuracy in high motion exercises.

Data-driven forecasting algorithms for building energy consumption

This paper introduces two forecasting methods for building energy consumption data that are recorded from smart meters in high resolution. For utility companies, it is important to reliably forecast the aggregate consumption profile to determine energy supply for the next day and prevent any crisis. The proposed methods involve forecasting individual load on the basis of their measurement history and weather data without using complicated models of building system. The first method is most efficient for a very short-term prediction, such as the prediction period of one hour, and uses a simple adaptive time-series model. For a longer-term prediction, a nonparametric Gaussian process has been applied to forecast the load profiles and their uncertainty bounds to predict a day-ahead. These methods are computationally simple and adaptive and thus suitable for analyzing a large set of data whose pattern changes over the time. These forecasting methods are applied to several sets of building energy consumption data for lighting and heating-ventilation-air-conditioning (HVAC) systems collected from a campus building at Stanford University. The measurements are collected every minute, and corresponding weather data are provided hourly. The results show that the proposed algorithms can predict those energy consumption data with high accuracy.

Burnout: a wearable system for unobtrusive skeletal muscle fatigue estimation

Skeletal muscles are pivotal for sports and exercise. However, overexertion of skeletal muscles causes muscle fatigue which can lead to injury. Consequently, understanding skeletal muscle fatigue is important for injury prevention. Current ways to estimate exhaustion revolve around self-estimation or inference from such sensors as force sensors, electromyography e.t.c. These methods are not always reliable, especially during isotonic exercises. Toward this end, we present Burnout - a wearable system for quantifying skeletal muscle fatigue in an exercise setting. Burnout uses accelerometers to sense skeletal muscle vibrations. From these vibrations, Burnout obtains a region based feature (R- Feature), in the case of this work, the region mean power frequency (R-MPF) gradient to correlate the sensed vibrations to a known ground truth measure of skeletal muscle fatigue, i.e., Dimitrovs spectral fatigue index gradient. We evaluate Burnout on the biceps and quadriceps of 5 healthy participants through four different exercises, collected in a real world environment. Our results show that by using this R-MPF feature on our real world data set, Burnout is able to reduce the error of estimating the ground truth fatigue index gradient by up to 50% on average compared to using the standard MPF feature.