Le T. Nguyen

ACComplice: Location inference using accelerometers on smartphones

The security and privacy risks posed by smartphone sensors such as microphones and cameras have been well documented. However, the importance of accelerometers have been largely ignored. We show that accelerometer readings can be used to infer the trajectory and starting point of an individual who is driving. This raises concerns for two main reasons. First, unauthorized access to an individuals location is a serious invasion of privacy and security. Second, current smartphone operating systems allow any application to observe accelerometer readings without requiring special privileges. We demonstrate that accelerometers can be used to locate a device owner to within a 200 meter radius of the true location. Our results are comparable to the typical accuracy for handheld global positioning systems.

Recognizing new activities with limited training data

Activity recognition (AR) systems are typically built to recognize a predefined set of common activities. However, these systems need to be able to learn new activities to adapt to a users needs. Learning new activities is especially challenging in practical scenarios when a user provides only a few annotations for training an AR model. In this work, we study the problem of recognizing new activities with a limited amount of labeled training data. Due to the shortage of labeled data, small variations of the new activity will not be detected resulting in a significant degradation of the systems recall. We propose the FE-AT (Feature-based and Attribute-based learning) approach, which leverages the relationship between existing and new activities to compensate for the shortage of the labeled data. We evaluate FE-AT on three public datasets and demonstrate that it outperforms traditional AR approaches in recognizing new activities, especially when only a few training instances are available.

Wi-Fi fingerprinting through active learning using smartphones

Indoor positioning is one of the key components enabling retail-related services such as location-based product recommendations or in-store navigation. In the recent years, active research has shown that indoor positioning systems based on Wi-Fi fingerprints can achieve a high positioning accuracy. However, the main barrier of broad adoption is the labor-intensive process of collecting labeled fingerprints. In this work, we propose an approach for reducing the amount of labeled data instances required for training a Wi-Fi fingerprint model. The reduction of the labeling effort is achieved by leveraging dead reckoning and an active learning-based approach for selecting data instances for labeling. We demonstrate through experiments that we can construct a Wi-Fi fingerprint database with significantly less labels while achieving a high positioning accuracy.

SuperAD: supervised activity discovery

Activity recognition (AR) has become an essential component of many applications present in our everyday lives such as life-logging, fitness tracking, health and wellbeing monitoring. To build an AR system, one needs to first identify a set of activities of interest and collect labeled training data for these activities. However, activities of interest are not often known in advance. For example, a system designed to monitor a users life style for potential diabetes risk needs to recognize all physical activities a user performs in her daily life. Given the large number of possible human activities, many of them cannot be foreseen during the model training time. In this work, we study the problem of discovering these unknown activities after the system is deployed by asking users to provide additional labels. Our goal is to discover all the unknown activities (i.e., obtain at least one label per class) while minimizing the amount of labels a user needs to provide. We propose SuperAD (Supervised Activity Discovery) approach, which combines active learning, semi-supervised learning and generative modeling to discover new unknown activities. We show that the proposed approach is especially effective when discovering activities with imbalance class distribution.

IdentityLink: user-device linking through visual and RF-signal cues

Mobile devices have become peoples indispensable companion, since they allow each individual to be constantly connected with the outside world. In order to keep connected, the devices periodically send out data, which reveal some information about the device owner. Data sent by these devices can be captured by any external observer. Since the observer can observe only the wireless data, the actual person using the device is unknown. In this work, we propose IdentityLink, an approach leveraging the captured wireless data and computer vision to infer the user-device links, i.e., inferring which device is carried by which user. Knowing the user-device links opens up new opportunities for applications such as identifying unauthorized personnel in enterprises or finding criminals by law enforcement. By conducting experiments in a realistic scenario, we demonstrate how IdentityLink can be effectively applied to real practice.

Wait time prediction: how to avoid waiting in lines?

One of the challenges of organizations providing services to the public is the effective resource allocation. Many service providers such as hospitals, city halls or department of motor vehicles suffer from a service demand, which is unevenly distributed over the day. In this work, we evaluate techniques for predicting the service demand. We use the wait time dataset collected from the websites of California Department of Motor Vehicles (DMV). We extract patterns of the service demand in form of wait time during each hour of a day and each day of a week. This information is used to train multiple machine learning models in order to predict the future wait time at DMV offices.