Search for: All records

We present the design and implementation of RECA, a novel human-centric recommender system for co-optimizing energy consumption, comfort and air quality in commercial buildings. Existing works generally optimize these objectives separately, or by only controlling energy consuming resources within the building without directly engaging occupants. We develop a deep reinforcement learning architecture based on multitask learning, demonstrate how it can be used to jointly learn energy savings, comfort and air quality improvements for different actions, and build a recommender system with humans-in-the-loop. Through real deployments in multiple commercial buildings, we found that RECA has the potential to further reduce energy consumption by up to in energy-focused optimization, improve all objectives by in joint optimization, and improve thermal comfort by up to in comfort and air quality focused optimization, over existing solutions. 

We present SoFIT, an easily-deployed and privacy-preserving camera network system for occupant tracking. Unlike traditional camera network-based systems, SoFIT does not require a person to calibrate the network or provide real-world references. This enables anyone, including non-professionals, to install SoFIT. Once installed, SoFIT automatically localizes cameras within the network and generates the floor map leveraging movements of people using the space in daily life, before using the floor map and camera locations to track occupants throughout the environment. We demonstrate through a series of deployments that SoFIT can localize cameras with less than 4.8cm error, generate floor maps with 85% similarity to actual floor maps, and track occupants with less than 7.8cm error. 

With the recent societal impact of COVID-19, companies and government agencies alike have turned to thermal camera based skin temperature sensing technology to help screen for fever. However, the cost and deployment restrictions limit the wide use of these thermal sensing technologies. In this work, we present SIFTER, a low-cost system based on a RGB-thermal camera for continuous fever screening of multiple people. This system detects and tracks heads in the RGB and thermal domains and constructs thermal heat map models for each tracked person, and classifies people as having or not having fever. SIFTER can obtain key temperature features of heads in-situ at a distance and produce fever screening predictions in real-time, significantly improving screening through-put while minimizing disruption to normal activities. In our clinic deployment, SIFTER measurement error is within 0.4°F at 2 meters and around 0.6°F at 3.5 meters. In comparison, most infrared thermal scanners on the market costing several thousand dollars have around 1°F measurement error measured within 0.5 meters. SIFTER can achieve 100% true positive rate with 22.5% false positive rate without requiring any human interaction, greatly outperforming our baseline [1], which sees a false positive rate of 78.5%. 

In this poster abstract, we present a thermal comfort estimation system using low-cost thermal camera based sensor nodes. This system extracts perspective invariant, non-intrusive thermal measurements, is easily deployable and low-cost, and can incorporate individual thermal feedback for more personalized thermal comfort estimates. In comparison with baseline methods, our system is able to improve thermal comfort estimates on the ASHRAE 7-point thermal sensation scale by up to 64% over baseline methods. 

Energy footprinting has the potential to raise awareness of energy consumption and lead to energy-saving behavior. However, current methods are largely restricted to single buildings; these methods require energy and occupancy monitoring sensor deployments, which can be expensive and difficult to deploy at scale. Further, current methods for estimating energy consumption and population at scale cannot provide fine enough temporal or spatial granularity for a reasonable personal energy footprint estimate. In this work, we present a data-driven system for city-wide estimation of personal energy footprints. This system takes advantage of existing sensing infrastructure and data sources in urban cities to provide energy and population estimates at the building level, even in built environments that do not have existing or accessible energy or population data. 

In commercial buildings, occupant thermal comfort is a key factor that must be optimized to provide a comfortable and productive work environment. However, current methods largely estimate thermal comfort based on preset models which do not incorporate real-time measurements or individual thermal preferences. In this work, we present a scalable system for estimating personalized thermal comfort using low-cost thermal camera based sensor nodes. This system extracts non-intrusive thermal measurements, is robust to different perspectives and environments, is easily deployable and low-cost, and can incorporate individual thermal feedback for more personalized thermal comfort estimates. In comparison with baseline methods, our system is able to improve thermal comfort estimates on the ASHRAE 7-point thermal sensation scale by 64% over baseline methods. 

Energy footprinting has the potential to raise awareness of energy consumption and lead to energy saving behavior. However, current methods are largely restricted to single buildings; these methods require energy and occupancy monitoring sensor deployments, which can be expensive and difficult to deploy at scale. Further, current methods for estimating energy consumption and population cannot provide fine enough temporal or spatial granularity for a reasonable personal energy footprint estimate. In this work, we present CityEnergy, a data-driven system for city-wide estimation of personal energy footprints. CityEnergy takes advantage of existing sensing infrastructure and data sources in urban cities to provide energy and population estimates at the building level, even in built environments that do not have existing or accessible energy or population data. 

In this work, we present recEnergy, a recommender system for reducing energy consumption in commercial buildings with human-in-the-loop. We formulate the building energy optimization problem as a Markov Decision Process, show how deep reinforcement learning can be used to learn energy saving recommendations, and effectively engage occupants in energy-saving actions. is a recommender system that learns actions with high energy saving potential, actively distribute recommendations to occupants in a commercial building, and utilize feedback from the occupants to learn better energy saving recommendations. Over a four week user study, four different types of energy saving recommendations were trained and learned. improves building energy reduction from a baseline saving (passive-only strategy) of 19% to 26%. 

Vehicle flow estimation has many potential smart cities and transportation applications. Many cities have existing camera networks which broadcast image feeds; however, the resolution and frame-rate are too low for existing computer vision algorithms to accurately estimate flow. In this work, we present a computer vision and deep learning framework for vehicle tracking. We demonstrate a novel tracking pipeline which enables accurate flow estimates in a range of environments under low resolution and frame-rate constraints. We demonstrate that our system is able to track vehicles in New York City's traffic camera video feeds at 1 Hz or lower frame-rate, and produces higher traffic flow accuracy than popular open source tracking frameworks.