Juhi Ranjan

An RF doormat for tracking people's room locations

Many occupant-oriented smarthome applications such as automated lighting, heating and cooling, and activity recognition need room location information of residents within a building. Surveillance based tracking systems used to track people in commercial buildings, are privacy invasive in homes. In this paper, we present the RF Doormat - a RF threshold system that can accurately track peoples room locations by monitoring their movement through the doorways in the home. We also present a set of guidelines and a visualization to easily and rapidly setup the RF-Doormat system on any doorway. To evaluate our system, we perform 580 doorway crossings across 11 different doorways in a home. Results indicate that our system can detect doorway crossings made by people with an average accuracy of 98%. To our knowledge, the RF Doormat is the first highly accurate room location tracking system that can be used for long time periods without the need for privacy invasive cameras.

Discerning electrical and water usage by individuals in homes

Energy auditing and feedback is an effective and low cost technique that has the potential to save 20-50% energy in homes. Several new sensing technologies can now detect and disaggregate energy usage in homes at a fixture level, which is helpful for eco-feedback in homes. However, without disaggregating and assigning fixture energy usage to individuals (fixture assignment problem), it is hard for residents to discover individual energy saving actions. In this paper, we explore the hypothesis that fixture assignment can be performed based on coarse-grained room-level location tracking -- even when a fixture is used and multiple people are in the same room. To test this hypothesis, we perform a study with 5 groups of 2 participants each, who lived together for 7-12 days in a test home. We find that fixture assignment can be performed with an average accuracy of 87% using room-level tracking. In comparison, fixture assignment has 12% accuracy with house-level tracking (who is home vs not home) and 97% accuracy with coordinate-level tracking (who is standing at the oven vs fridge).

Object hallmarks: identifying object users using wearable wrist sensors

In order for objects to perform personalized or contextual functions based on identity, they must solve what we call the object user identification problem: understanding who is actually using them. In this paper, we propose a new technique that uses data from wearable wrist sensors to perform object user identification. We hypothesize that objects have unique hallmarks that are imprinted in the hand gestures of its users. By detecting the presence of an objects hallmark in the wrist sensor data, we can identify who used the object. We evaluate this concept with a smart home application: recognizing who is using an object or appliance in a multi-person home by combining smart meter data and wearables. We conduct three different studies with 10 participants: 1) a study with scripted object use 2) a study with high-level tasked activities and unscripted object use, and 3) a 5-day in-situ study. These studies indicate that our approach performs object user identification with an average accuracy of 85--90%.

ThermalSense: determining dynamic thermal comfort preferences using thermographic imaging

We present ThermalSense, a method for dynamically detecting and predicting thermal comfort by using thermographic imaging to look for the physiological markers of vasodilation or vasoconstriction. We describe how ThermalSense can be used to infer how to control heating and cooling systems and reduce energy use while maintaining comfort. We evaluate ThermalSense using a study involving thirty individuals over five weeks in an office building. Our study shows that, on around 40% of occasions, the HVAC system could have expended less energy to achieve comfort. It further demonstrates that thermographic imaging can be used to infer whether heating or cooling must be activated to maintain comfort, with an accuracy of 94-95%.

Towards Occupancy-Driven Heating and Cooling

HVAC systems are eventually needed to maintain comfort for occupants, and as a result sensing and leveraging user context information is critical for the energy-efficient operation of buildings. This article describes an occupancy-driven HVAC control framework for more effective heating and cooling management.

Using mid-range RFID for location based activity recognition

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.

RF-CePal: A universal remote control based on MEMS accelerometer

‘RF-CePal’ is networked sensor device to assist people with restricted finger movements. Many electrical/electronic equipment can be operated using IR based remote control. As these remote controls take user input using push buttons, persons with restricted finger movement (e.g those with cerebral palsy) cannot operate such equipment. Taking advantage of MEMS accelerometer, we recognize gross movements of hand and map them to important functions of the equipment to be operated. We had earlier developed a device in which IR transmitter was integrated in the device along with sensor. However many users have problem pointing it towards the equipment to operate it reliably. In this paper, we report our work on developing a two part networked system communicating via zigbee based wireless link to overcome this difficulty. First part of the device(body device) containing sensor is placed on the body part (e.g hand/wrist) and the other part (base device) is pointing in direction of IR receiver of equipment. Tilt angle of hand is used as input to device (e.g left tilt changes the channel on TV). Based on preliminary trials, we have made design modifications to make the system more suitable and cheaper. This system is now being made available to users.

Towards recognizing person-object interactions using a single wrist wearable device

Activity recognition (AR) is an important part of context-aware applications. In this paper, we focus on an indirect AR method: by sensing the objects that a person is using. Objects that provide functional utility to their user, also indicate the type of activity that their user is doing. For example, the use of a hair dryer indicates that its user is grooming their hair. In this paper, we discuss an approach to sense the objects that the person interacts with, using only a single wearable device on the wrist of the person. Wearable devices typically have an IMU sensor, which can sense several aspects of the persons hand gestures, such as acceleration, and orientation. We collect a dataset of 17 different object interaction gestures using 5 participants in a test home. We evaluate the object gestures using supervised and unsupervised machine learning approaches. Our study reveals that we can recognize object interactions with 83-91% accuracy in the supervised approach, and 58-66% accuracy in the unsupervised approach.

Rethinking the Fusion of Technology and Clinical Practices in Functional Behavior Analysis for the Elderly

Functional assessment is the test of the ability of a person to perform basic self-care activities that are instrumental for living safely and independently in a home. Gerontology classifies these self-care activities as Activities of Daily Living ADL. There exist many clinical and systems measures for performing functional assessment. This paper critically reviews the state of art in these assessments. This paper also talks about the disconnect between the clinical and the technological measures. It also discusses future directions to establish a practical and objective method of conducting functional assessments.

Automatic authentication of smartphone touch interactions using smartwatch

In this demo, we will display a smartphone authentication system that can automatically validate every touch interaction made on a smartphone using a smart watch worn by the phones owner. The IMU sensors on a smart watch monitor the motion of the hand for specific signal characteristics, which is relayed to the phone. If the signal features match certain criteria then the touch is authenticated and the phone responds appropriately. If not, the phones screen remains locked/unresponsive to the touch action. The challenge here is to be able to validate every touch gesture within acceptable limits of human perception.