Abhinav Parate

RisQ: recognizing smoking gestures with inertial sensors on a wristband

Smoking-induced diseases are known to be the leading cause of death in the United States. In this work, we design RisQ, a mobile solution that leverages a wristband containing a 9-axis inertial measurement unit to capture changes in the orientation of a persons arm, and a machine learning pipeline that processes this data to accurately detect smoking gestures and sessions in real-time. Our key innovations are four-fold: a) an arm trajectory-based method that extracts candidate hand-to-mouth gestures, b) a set of trajectory-based features to distinguish smoking gestures from confounding gestures including eating and drinking, c) a probabilistic model that analyzes sequences of hand-to-mouth gestures and infers which gestures are part of individual smoking sessions, and d) a method that leverages multiple IMUs placed on a persons body together with 3D animation of a persons arm to reduce burden of self-reports for labeled data collection. Our experiments show that our gesture recognition algorithm can detect smoking gestures with high accuracy (95.7%), precision (91%) and recall (81%). We also report a user study that demonstrates that we can accurately detect the number of smoking sessions with very few false positives over the period of a day, and that we can reliably extract the beginning and end of smoking session periods.

Practical prediction and prefetch for faster access to applications on mobile phones

Mobile phones have evolved from communication devices to indispensable accessories with access to real-time content. The increasing reliance on dynamic content comes at the cost of increased latency to pull the content from the Internet before the user can start using it. While prior work has explored parts of this problem, they ignore the bandwidth costs of prefetching, incur significant training overhead, need several sensors to be turned on, and do not consider practical systems issues that arise from the limited background processing capability supported by mobile operating systems. In this paper, we make app prefetch practical on mobile phones. Our contributions are two-fold. First, we design an app prediction algorithm, APPM, that requires no prior training, adapts to usage dynamics, predicts not only which app will be used next but also when it will be used, and provides high accuracy without requiring additional sensor context. Second, we perform parallel prefetch on screen unlock, a mechanism that leverages the benefits of prediction while operating within the constraints of mobile operating systems. Our experiments are conducted on long-term traces, live deployments on the Android Play Market, and user studies, and show that we outperform prior approaches to predicting app usage, while also providing practical ways to prefetch application content on mobile phones.

Leveraging graphical models to improve accuracy and reduce privacy risks of mobile sensing

The proliferation of sensors on mobile phones and wearables has led to a plethora of context classifiers designed to sense the individuals context. We argue that a key missing piece in mobile inference is a layer that fuses the outputs of several classifiers to learn deeper insights into an individuals habitual patterns and associated correlations between contexts, thereby enabling new systems optimizations and opportunities. In this paper, we design CQue, a dynamic bayesian network that operates over classifiers for individual contexts, observes relations across these outputs across time, and identifies opportunities for improving energy-efficiency and accuracy by taking advantage of relations. In addition, such a layer provides insights into privacy leakage that might occur when seemingly innocuous user context revealed to different applications on a phone may be combined to reveal more information than originally intended. In terms of system architecture, our key contribution is a clean separation between the detection layer and the fusion layer, enabling classifiers to solely focus on detecting the context, and leverage temporal smoothing and fusion mechanisms to further boost performance by just connecting to our higher-level inference engine. To applications and users, CQue provides a query interface, allowing a) applications to obtain more accurate context results while remaining agnostic of what classifiers/sensors are used and when, and b) users to specify what contexts they wish to keep private, and only allow information that has low leakage with the private context to be revealed. We implemented CQue in Android, and our results show that CQue can i) improve activity classification accuracy up to 42%, ii) reduce energy consumption in classifying social, location and activity contexts with high accuracy(>90%) by reducing the number of required classifiers by at least 33%, and iii) effectively detect and suppress contexts that reveal private information.

Detecting cocaine use with wearable electrocardiogram sensors

Ubiquitous physiological sensing has the potential to profoundly improve our understanding of human behavior, leading to more targeted treatments for a variety of disorders. The long term goal of this work is development of novel computational tools to support the study of addiction in the context of cocaine use. The current paper takes the first step in this important direction by posing a simple, but crucial question: Can cocaine use be reliably detected using wearable electrocardiogram (ECG) sensors? The main contributions in this paper include the presentation of a novel clinical study of cocaine use, the development of a computational pipeline for inferring morphological features from noisy ECG waveforms, and the evaluation of feature sets for cocaine use detection. Our results show that 32mg/70kg doses of cocaine can be detected with the area under the receiver operating characteristic curve levels above 0.9 both within and between-subjects.

A framework for safely publishing communication traces

A communication trace is a detailed record of the communication between two entities. Communication traces are vital for research in computer networks and study of network protocols in various domains, but their release is severely constrained by privacy and security concerns. In this paper, we propose a framework in which a trace owner can match an anonymizing transformation with the requirements of analysts. The trace owner can release multiple transformed traces, each customized to an analysts needs, or a single transformation satisfying all requirements. The framework enables formal reasoning about anonymization policies, for example to verify that a given trace has utility for the analyst, or to obtain the most secure anonymization for the desired level of utility. Because communication traces are typically very large, we also provide techniques that allow efficient application of transformations using relational database systems.

Detecting Eating and Smoking Behaviors Using Smartwatches

Inertial sensors embedded in commercial smartwatches and fitness bands are among the most informative and valuable on-body sensors for monitoring human behavior. This is because humans perform a variety of daily activities that impacts their health, and many of these activities involve using hands and have some characteristic hand gesture associated with it. For example, activities like eating food or smoking a cigarette require the direct use of hands and have a set of distinct hand gesture characteristics. However, recognizing these behaviors is a challenging task because the hand gestures associated with these activities occur only sporadically over the course of a day, and need to be separated from a large number of irrelevant hand gestures. In this chapter, we will look at approaches designed to detect behaviors involving sporadic hand gestures. These approaches involve two main stages: (1) spotting the relevant hand gestures in a continuous stream of sensor data, and (2) recognizing the high-level activity from the sequence of recognized hand gestures. We will describe and discuss the various categories of approaches used for each of these two stages, and conclude with a discussion about open questions that remain to be addressed.