Research

Selected Publications

The full list can be found on my Scholar page

FitNibble

The ultimate goal of automatic diet monitoring systems (ADM) is to make food journaling as easy as counting steps with a smartwatch. To achieve this goal, it is essential to understand the utility and usability of ADM systems in real-world settings. However, this has been challenging since many ADM systems perform poorly outside the research labs. Therefore, one of the main focuses of ADM research has been on improving ecological validity. This paper presents an evaluation of ADM's utility and usability using an end-to-end system, FitNibble. FitNibble is robust to many challenges that real-world settings pose and provides just-in-time notifications to remind users to journal as soon as they start eating. We conducted a long-term field study to compare traditional self-report journaling and journaling with ADM in this evaluation. We recruited 13 participants from various backgrounds and asked them to try each journaling method for nine days. Our results showed that FitNibble improved adherence by significantly reducing the number of missed events (19.6% improvement, p =.0132). Results have shown that participants were highly dependent on FitNibble in maintaining their journals. Participants also reported increased awareness of their dietary patterns, especially with snacking. All these results highlight the potential of ADM in improving the food journaling experience.

FitByte

In an attempt to help users reach their health goals and practitioners understand the relationship between diet and disease, researchers have proposed many wearable systems to automatically monitor food consumption. When a person consumes food, he/she brings the food close to their mouth, take a sip or bite and chew, and then swallow. Most diet monitoring approaches focus on one of these aspects of food intake, but this narrow reliance requires high precision and often fails in noisy and unconstrained situations common in a person's daily life. In this paper, we introduce FitByte, a multi-modal sensing approach on a pair of eyeglasses that tracks all phases of food intake. FitByte contains a set of inertial and optical sensors that allow it to reliably detect food intake events in noisy environments. It also has an on-board camera that opportunistically captures visuals of the food as the user consumes it. We evaluated the system in two studies with decreasing environmental constraints with 23 participants. On average, FitByte achieved 89\% F1-score in detecting eating and drinking episodes.

EarBit

Chronic and widespread diseases such as obesity, diabetes, and hypercholesterolemia require patients to monitor their food intake, and food journaling is currently the most common method for doing so. However, food journaling is subject to self-bias and recall errors, and is poorly adhered to by patients. In this paper, we propose an alternative by introducing EarBit, a wearable system that detects eating moments. We evaluate the performance of inertial, optical, and acoustic sensing modalities and focus on inertial sensing, by virtue of its recognition and usability performance. Using data collected in a simulated home setting with minimum restrictions on participants’ behavior, we build our models and evaluate them with an unconstrained outside-the-lab study. For both studies, we obtained video footage as ground truth for participants activities. Using leave-one-user-out validation, EarBit recognized all the eating episodes in the semi-controlled lab study, and achieved an accuracy of 90.1% and an F1-score of 90.9% in detecting chewing instances. In the unconstrained, outside-the-lab evaluation, EarBit obtained an accuracy of 93% and an F1-score of 80.1% in detecting chewing instances. It also accurately recognized all but one recorded eating episodes. These episodes ranged from a 2 minute snack to a 30 minute meal.

SkinWire

Current wearable form factors often house electronics using an enclosure that is attached to the body. This form factor, while wearable, tends to protrude from the body and therefore can limit wearability. While emerging research in on-skin interfaces from the HCI and wearable communities have generated form factors with lower profiles, they often still require support by conventional electronics and associated form factors for the microprocessor, wireless communication, and battery units. In this work, we introduce SkinWire, a fabrication approach that extends the early work in on-skin interfaces to shift wearable devices from their traditional box-like forms to a fully self-contained on-skin form factor.

Detecting Mastication

This paper presents an approach for automatically detecting eating activities by measuring deformations in the ear canal walls due to mastication activity. These deformations are measured with three infrared proximity sensors encapsulated in an off-the-shelf earpiece. To evaluate our method, we conducted a user study in a lab setting where 20 participants were asked to perform eating and non-eating activities. A user dependent analysis demonstrated that eating could be detected with 95.3% accuracy. This result indicates that proximity sensing offers an alternative to acoustic and inertial sensing in eating detection while providing benefits in terms of privacy and robustness to noise.

TapSkin

The touchscreen has been the dominant input surface for smartphones and smartwatches. However, its small size compared to a phone limits the richness of the input gestures that can be supported. We present TapSkin, an interaction technique that recognizes up to 11 distinct tap gestures on the skin around the watch using only the inertial sensors and microphone on a commodity smartwatch. An evaluation with 12 participants shows our system can provide classification accuracies from 90.69% to 97.32% in three gesture families--number pad, d-pad, and corner taps. We discuss the opportunities and remaining challenges for widespread use of this technique to increase input richness on a smartwatch without requiring further on-body instrumentation.

Silent Speech

We address the problem of performing silent speech recognition where vocalized audio is not available (e.g. due to a user’s medical condition) or is highly noisy (e.g. during firefighting or combat). We describe our wearable system to capture tongue and jaw movements during silent speech. The system has two components: the Tongue Magnet Interface (TMI), which utilizes the 3-axis magnetometer aboard Google Glass to measure the movement of a small magnet glued to the user’s tongue, and the Outer Ear Interface (OEI), which measures the deformation in the ear canal caused by jaw movements using proximity sensors embedded in a set of earmolds. We collected a data set of 1901 utterances of 11 distinct phrases silently mouthed by six able-bodied participants. Recognition relies on using hidden Markov modelbased techniques to select one of the 11 phrases. We present encouraging results for user dependent recognition.

Sign Language Recognition

In Automatic Sign Language Recognition (ASLR), robust hand tracking and detection is key to good recognition accuracy. We introduce a new dataset of depth data from continuously signed American Sign Language (ASL) sentences. We present analysis showing numerous errors of the Microsoft Kinect Skeleton Tracker (MKST) in cases where hands are close to the body, close to each other, or when the arms cross. We also propose a method based on domain-driven random forest regression, which predicts real world 3D hand locations using features generated from depth images. We show that our hand detector (DDRFR) has >20% improvement over the MKST within a margin of error of 5 cm from the ground truth.

Enhancing haptic representation for 2D objects

This paper considers two dimensional object tracking and recognition using combined texture and pressure cues. Tactile object recognition plays a major role in several HCI applications especially scientific visualization for the visually impaired. A tactile display based on a pantograph mechanism and 2Γ—2 vibrotactile unit array was used to represent haptic virtual objects. Two experiments were carried out to evaluate the efficiency and reliability of this novel method. The first experiment studied how the combined texture and pressure cues improves the haptic interaction compared to using pressure cues only. The second experiment examined users' capability to track and recognize objects with two dimensional shapes using this method. Results obtained indicate an improvement in boundary recognition and tracking accuracy by the combined stimulation over the sole pressure stimulation. Results also demonstrate the capability of users to readily define shapes for most of the virtually represented objects.