Doorway tracking systems track people’s room location by instrumenting the doorways rather than instrumenting the rooms themselves—resulting in fewer sensors and less monitoring while still providing location information on occupants. In this article, we explore what is required to make doorway tracking a practical solution. We break a doorway tracking system into multiple independent design components, including both sensor and algorithmic design. Informed by this design, we construct a doorway tracking system and analyze how different combinations of these design components affect tracking accuracy. We perform a six-day in situ study in a ten-room house with two volunteers to analyze how these design components respond to the natural types and frequencies of errors in a real-world setting. To reflect the needs of different application classes, we analyze these design components using three different evaluation metrics: room accuracy, duration accuracy, and transition accuracy. Results indicate that doorway tracking can achieve 99.5% room accuracy on average in controlled settings and 96% room accuracy in in situ settings. This is contrasted against the 76% in situ setting room accuracy of Doorjamb, a doorway tracking system whose design implements only a limited number of components in our proposed doorway tracking system design space. We describe the differences between the data in the in situ and controlled settings, and provide guidelines about how to design a doorway tracking system for a given application’s accuracy requirements.

In this paper, we consider a variant of the multi-target tracking problem in which the tracking region is divided into zones and targets can only be monitored as they transition between these zones. We call this the transition tracking problem. The key challenge in Transition Tracking is to estimate the number of targets in the tracking region without being able to sense all targets simultaneously. In this paper, we propose an approach to the Transition Tracking problem called TransTrack. Unlike most other tracking algorithms that maximize the likelihood of the sensor data, TransTrack applies penalty functions to find the minimum number of targets that can explain the sensor data. These penalties allow tracks with larger numbers of targets only ifthey have sufficiently fewer errors than other, alternative tracks. To evaluate this approach, we apply TransTrack to a data set containing 3275 transitions between rooms in a home. We observe an average room tracking accuracy of up to 94.5%.

In typical US homes, water heating is the largest energy consumer besides space heating and cooling, and it accounts for approximately 17% of residential energy consumption on average. In this paper, we propose and evaluate a new technique to reduce energy waste due to pipe loss: delivering lower temperature water whenever possible. We created a Smarter Water Heater (SWH) that uses data fusion techniques to infer 1) the fixture being used 2) the mixed water temperature at the fixture 3) the pipe volume for that fixture. After learning a model for each fixture, it solves a control optimization problem to decide when and at what temperature to deliver water to minimize energy use without sacrificing comfort of the user. We evaluated the SWH in three stages. First, we built a physical prototype and measured energy efficiency. We then deployed 18 sensors into a home's piping system for a 50-day in-situ study to stress test the SWH's sensing sub-system. Finally, we collected traces of hot water use from 5 different homes over 10 days each to determine how different water usage habits and piping structures affect energy savings. The results indicate that the SWH reduces total water heating energy by 8--14% with little to no effect on user comfort.

People interact with chairs frequently, making them a potential location to perform implicit health sensing that requires no additional effort by users. We surveyed 550 participants to understand how people sit in chairs and inform the design of a chair that detects heart and respiratory rate from the armrests and backrests of the chair respectively. In a laboratory study with 18 participants, we evaluated a range of common sitting positions to determine when heart rate and respiratory rate detection was possible (32% of the time for heart rate, 52% for respiratory rate) and evaluate the accuracy of the detected rate (83% for heart rate, 73% for respiratory rate). We discuss the challenges of moving this sensing to the wild by evaluating an in-situ study totaling 40 hours with 11 participants. We show that, as an implicit sensor, the chair can collect vital signs data from its occupant through natural interaction with the chair.

Development of smarthome home application depends on the ability to identify resident activity and track occupancy of rooms as people move within a residence. Existing solutions to home activity recognition are evaluated using controlled experiments and having participants maintain logs of daily activities as ground truth. In our study, we evaluate the effectiveness of using mid-range RFID as a research tool to perform in-situ evaluation of smarthome systems. We propose that using bracelets and anklets embedded with passive RFID tags can provide an accurate ground truth system, which can help evaluate the performance of research solutions for smarthomes with higher accuracy - in presence of natural variability of people in activities and movement in homes.

Indoor tracking systems will be an essential part of the home of the future, enabling location-aware and individually-tailored services. However, today there are no tracking solutions that are practical for "every day" use in the home. In this paper, we introduce the Doorjamb tracking system that uses ultrasonic range finders mounted above each doorway, pointed downward to sense people as they walk through the doorway. The system differentiates people by measuring their heights, infers their walking direction using signal processing, and identifies their room locations based on the sequence of doorways through which they pass. Doorjamb provides room-level tracking without requiring any user participation, wearable devices, privacy-intrusive sensors, or high-cost sensors. We create a proof-of-concept implementation and empirically evaluate Doorjamb with experiments that include over 3000 manually-recorded doorway crossings. Results indicate that the system can perform room-level tracking with 90% accuracy on average.