Search for: All records

Human activity recognition (HAR) from wearable sensor data has recently gained widespread adoption in a number of fields. However, recognizing complex human activities, postural and rhythmic body movements (e.g., dance, sports) is challenging due to the lack of domain-specific labeling information, the perpetual variability in human movement kinematics profiles due to age, sex, dexterity and the level of professional training. In this paper, we propose a deep activity recognition model to work with limited labeled data, both for simple and complex human activities. To mitigate the intra- and inter-user spatio-temporal variability of movements, we posit novel data augmentation and domain normalization techniques. We depict a semi-supervised technique that learns noise and transformation invariant feature representation from sparsely labeled data to accommodate intra-personal and inter-user variations of human movement kinematics. We also postulate a transfer learning approach to learn domain invariant feature representations by minimizing the feature distribution distance between the source and target domains. We showcase the improved performance of our proposed framework, AugToAct, using a public HAR dataset. We also design our own data collection, annotation and experimental setup on complex dance activity recognition steps and kinematics movements where we achieved higher performance metrics with limited label data compared to simple activity recognition tasks. 

Proper thermal insulation yields optimum energy expenses in buildings by maintaining necessary heat gain or loss through the built envelope. However, improper thermal insulation causes significant energy wastage along with infusing various damages on indoor and outdoor walls of the buildings, for example, damp areas, black stains, cracks, paint bubbles etc. Therefore, it is important to inspect the temperature variations in different areas of the built environments in regular basis. We propose a method for identifying temperature variance in building thermal images based on Symbolic Aggregated Approximation (SAX). Our process helps detect the temperature variation over different image segments and infers the fault prone segments of leakages. We have collected about 50 thermal images associated with different types of wall specific insulation problems in indoor built environment and were able to identify the affected area with approximately 75% accuracy using our proposed method based on temperature variation detection approach. 

Modeling buildings' heat dynamics is a complex process which depends on various factors including weather, building thermal capacity, insulation preservation, and residents' behavior. Gray-box models offer an explanation of those dynamics, as expressed in a few parameters specific to built environments that can provide compelling insights into the characteristics of building artifacts. In this paper, we present a systematic study of Bayesian approaches to modeling buildings' parameters, and hence their thermal characteristics. We build a Bayesian state-space model that can adapt and incorporate buildings' thermal equations and postulate a generalized solution that can easily adapt prior knowledge regarding the parameters. We then show that a faster approximate approach using Variational Inference for parameter estimation can posit similar parameters' quantification as that of a more time-consuming Markov Chain Monte Carlo (MCMC) approach. We perform extensive evaluations on two datasets to understand the generative process and attest that the Bayesian approach is more interpretable. We further study the effects of prior selection on the model parameters and transfer learning, where we learn parameters from one season and reuse them to fit the model in other seasons. We perform extensive evaluations on controlled and real data traces to enumerate buildings' parameters within a 95% credible interval. 

Time series behavior of gas consumption is highly irregular, non-stationary, and volatile due to its dependency on the weather, users' habits and lifestyle. This complicates the modeling and forecasting of gas consumption with most of the existing time series modeling techniques, specifically when missing values and outliers are present. To demonstrate and overcome these problems, we investigate two approaches to model the gas consumption, namely Generalized Additive Models (GAM) and Long Short-Term Memory (LSTM). We perform our evaluations on two building datasets from two different continents. We present each selected feature's influence, the tuning parameters, and the characteristics of the gas consumption on their forecasting abilities. We compare the performances of GAM and LSTM with other state-of-the-art forecasting approaches. We show that LSTM outperforms GAM and other existing approaches, however, GAM provides better interpretable results for building management systems (BMS). 

Air leakages pose a major problem in both residential and commercial buildings. They increase the utility bill and result in excessive usage of Heating Ventilation and Air Conditioning (HVAC) systems, which impacts the environment and causes discomfort to residents. Repairing air leakages in a building is an expensive and time intensive task. Even detecting the leakages can require extensive professional testing. In this paper, we propose a method to identify the leaky homes from a set, provided their energy consumption data is accessible from residential smart meters. In the first phase, we employ a Non-Intrusive Load Monitoring (NILM) technique to disaggregate the HVAC data from total power consumption for several homes. We propose a recurrent neural network and a denoising autoencoder based approach to identify the 'ON' and 'OFF' cycles of the HVACs and their overall usages. We categorize the typical HVAC consumption of about 200 homes and any probable insulation and leakage problems using the Air Changes per Hour at 50 Pa (ACH50) metric in the Dataport datasets. We perform our proposed NILM analysis on different granularities of smart meter data such as 1 min, 15 mins, and 1 hour to observe its effect on classifying the leaky homes. Our results show that disaggregation can be used to identify the residential air-conditioning, at 1 min granularity which in turn helps us to identify the leaky potential homes, with an accuracy of 86%. 

Leaky windows and doors, open refrigerators, unattended appliances, left-on lights, and other sources subtly leak energy accounting for a large portion of waste. Formal energy audits are expensive and time consuming and do not capture many sources of leakage and waste. In this short paper, we present a hybrid IR/RGB imaging system for an end-user to deploy to perform longitudinal detection of energy waste. The system uses a low resolution, 16 x 4 IR camera and a low cost digital camera mounted on a steerable platform to automatically scan a room, periodically taking low resolution IR and RGB images. The system uses image stitching to create an IR/RGB hybrid panoramic image and segmentation to determine temperature extrema in the scanned room. Finally, this data is combined with thermostat set-point information to highlight hot-spots or cold-spots which likely indicate energy leakage or wastage. The system obviates the need for expensive, time-consuming waste detection methods, for professional setup, and for more intrusive instrumentation of the home. 

Providing itemized energy consumption in a utility bill is becoming a priority, and perhaps a business practice in the near term. In recent times, a multitude of systems have been developed such as smart plugs, smart circuit breakers etc., for non-intrusive load monitoring (NILM). They are integrated either with the smart meters or at the plug-levels to footprint appliance-level energy consumption patterns in an entire home environment While deploying the existing technologies in a single home is feasible, scaling these technological advancements across thousands of homes in a region is not realized yet. This is primarily due to the cost, deployment complexity, and intrusive nature associated with these types of real deployment. Motivated by these shortcomings, in this paper we investigate the first step to address scalable disaggregation by proposing a disaggregation mechanism that works on a large dataset to accurately deconstruct the cumulative signals. We propose an iterative noise separation based approach to perform energy disaggregation using sparse coding based methodologies which work at the single ingress point of a home, i.e., at the meter level. We performed a ranked iterative signal removal methodology that effectively isolates appliances' individual signal waveform as noise on an aggregate energy datasets with moderate granularity (1 min). We performed experiments on real dataset and obtained approximately 94% energy disaggregation, i.e., disaggregated appliance-wise signal estimation accuracy. 

To promote energy-efficient operations in residential and office buildings, non-intrusive load monitoring (NILM) techniques have been proposed to infer the fine-grained power consumption and usage patterns of appliances from power-line measurement data. Fine-grained monitoring of everyday appliances (such as toasters and coffee makers) can not only promote energy-efficient building operations, but also provide unique insights into the context and activities of individuals. Current building-level NILM techniques are unable to identify the consumption characteristics of relatively low-load appliances, whereas smart-plug based solutions incur significant deployment and maintenance costs. In this paper, we investigate an intermediate architecture, where smart circuit breakers provide measurements of aggregate power consumption at room (or section) level granularity. We then investigate techniques to identify the usage and energy consumption of individual appliances from such measurements. We first develop a novel correlation-based approach called CBPA to identify individual appliances based on both their unique transient and steady-state power signatures. While promising, CBPA fails when the set of candidate appliances is too large. To further improve the accuracy of appliance level usage estimation, we then propose a hybrid system called AARPA, which uses mobile sensing to first infer high-level activities of daily living (ADLs), and then uses knowledge of such ADLs to effectively reduce the set of candidate appliances that potentially contribute to the aggregate readings at any point. We evaluate two variants of this algorithm, and show, using real-life data traces gathered from 10 domestic users, that our fusion of mobile and power-line sensing is very promising: it identified all devices that were used in each data trace, and it identified the usage duration and energy consumption of low-load consumer appliances with 87% accuracy. 

Fine-grained monitoring of everyday appliances can provide better feedback to the consumers and motivate them to change behavior in order to reduce their energy usage. It also helps to detect abnormal power consumption events, long-term appliance malfunctions and potential safety concerns. Commercially available plug meters can be used for individual appliance monitoring but for an entire house, each such individual plug meters are expensive and tedious to setup. Alternative methods relying on Non-Intrusive Load Monitoring techniques help disaggregate electricity consumption data and learn about the individual appliance's power states and signatures. However fine-grained events (e.g., appliance malfunctions, abnormal power consumption, etc.) remain undetected and thus inferred contexts (such as safety hazards etc.) become invisible. In this work, we correlate an appliance's inherent acoustic noise with its energy consumption pattern individually and in presence of multiple appliances. We initially investigate classification techniques to establish the relationship between appliance power and acoustic states for efficient energy disaggregation and abnormal events detection. While promising, this approach fails when there are multiple appliances simultaneously in `ON' state. To further improve the accuracy of our energy disaggregation algorithm, we propose a probabilistic graphical model, based on a variation of Factorial Hidden Markov Model (FHMM) for multiple appliances energy disaggregation. We combine our probabilistic model with the appliances acoustic analytics and postulate a hybrid model for energy disaggregation. Our approach helps to improve the performance of energy disaggregation algorithms and provide critical insights on appliance longevity, abnormal power consumption, consumer behavior and their everyday lifestyle activities. We evaluate the performance of our proposed algorithms on real data traces and show that the fusion of acoustic and power signatures can successfully detect a number of appliances with 95% accuracy.