Venu Vasudevan

uWave: Accelerometer-based personalized gesture recognition and its applications

The proliferation of accelerometers on consumer electronics has brought an opportunity for interaction based on gestures or physical manipulation of the devices. We present uWave, an efficient recognition algorithm for such interaction using a single three-axis accelerometer. Unlike statistical methods, uWave requires a single training sample for each gesture pattern and allows users to employ personalized gestures and physical manipulations. We evaluate uWave using a large gesture library with over 4000 samples collected from eight users over an elongated period of time for a gesture vocabulary with eight gesture patterns identified by a Nokia research. It shows that uWave achieves 98.6% accuracy, competitive with statistical methods that require significantly more training samples. Our evaluation data set is the largest and most extensive in published studies, to the best of our knowledge. We also present applications of uWave in gesture-based user authentication and interaction with three-dimensional mobile user interfaces using user created gestures.

Hitting the distributed computing sweet spot with TSpaces

Abstract Our world is becoming increasingly heterogeneous, decentralized and distributed, but the software that is supposed to work in this world, usually, is not. TSpaces is a communication package whose purpose is to alleviate the problems of hooking together disparate distributed systems. TSpaces is a global communication middleware component that incorporates database features, such as transactions, persistent data, flexible queries and XML support. TSpaces is an excellent tool for building distributed applications, since it provides an asynchronous and anonymous link between multiple clients or services. The communication link provided by TSpaces gives application builders the advantage of ignoring some of the harder aspects of multi-client synchronization, such as tracking names (and addresses) of all active clients, communication line status, and conversation status. For many different types of applications, the loose synchronization provided by TSpaces works extremely well. This paper relates our experiences in building distributed systems with TSpaces as the central communication component.

Universal Manager: seamless management of enterprise mobile and non-mobile devices

Seamless management of resource constrained wireless devices along with enterprise hosts is complex because of the multitude of management protocols and architectures. An atomic and coordinated management action that spans the scale of the enterprise is needed. In this paper we present the architecture and our experiences in building a Universal Manager that manages all mobile and non-mobile devices in the enterprise. We came up with a multi-protocol gateway that blends intermittently connected mobile devices seamlessly with enterprise hosts. Our implementation of SyncML based mobile devices integrated with SNMP based enterprise manager is deployed in the enterprise and performance results are presented.

Query privacy in wireless sensor networks

Existing mechanisms for querying wireless sensor networks leak client interests to the servers performing the queries. The leaks are not only in terms of specific regions but also of client access patterns. In this paper we introduce the problem of preserving the privacy of clients querying a wireless sensor network owned by untrusted organizations. We investigate two architectures and their corresponding trust models. For the first model, consisting of multiple, mutually distrusting servers governing the network, we devise an efficient protocol, SPYC, and show that it provides full query privacy. For the second model, where all queries are performed through a single server, we introduce two metrics for quantifying the privacy achieved by a clients query sequence. We propose a suite of practical algorithms, then analyze the privacy and efficiency levels they provide. Our TOSSIM simulations show that the proposed query mechanisms are communication efficient while significantly improving client query privacy levels.

User evaluation of lightweight user authentication with a single tri-axis accelerometer

We report a series of user studies that evaluate the feasibility and usability of light-weight user authentication with a single tri-axis accelerometer. We base our investigation on uWave, a state-of-the-art recognition system for user-created free-space manipulation, or gestures. Our user studies address two types of user authentication: non-critical authentication (or identification) for a user to retrieve privacy-insensitive data; and critical authentication for protecting privacy-sensitive data. For non-critical authentication, our evaluation shows that uWave achieves high recognition accuracy (98%) and its usability is comparable with text ID-based authentication. Our results also highlight the importance of constraints for users to select their gestures. For critical authentication, the evaluation shows uWave achieves state-of-the-art resilience to attacks with 3% false positives and 3% false negatives, or 3% equal error rate. We also show that the equal error rate increases to 10% if the attackers see the users performing their gestures. This shows the limitation of gesture-based authentication and highlights the need for visual concealment.

MOBY-a mobile peer-to-peer service and data network

This paper describes the design and implementation of MOBY, a network for mobile peer-to-peer exchange of services and data. Constraints on computing power of mobile devices, limited hardware, networking, and software resources, and ad-hoc nature of mobile clients pose considerable challenges from the points of view of supporting performance goals, ease of service integration, and adaptation. These challenges are addressed in MOBY by dynamic service location and client mapping, surrogates for mobile clients, and standardized interfaces built upon off-the-shelf software components.

Interactive visual object search through mutual information maximization

Searching for small objects (e.g., logos) in images is a critical yet challenging problem. It becomes more difficult when target objects differ significantly from the query object due to changes in scale, viewpoint or style, not to mention partial occlusion or cluttered backgrounds. With the goal to retrieve and accurately locate the small object in the images, we formulate the object search as the problem of finding subimages with the largest mutual information toward the query object. Each image is characterized by a collection of local features. Instead of only using the query object for matching, we propose a discriminative matching using both positive and negative queries to obtain the mutual information score. The user can verify the retrieved subimages and improve the search results incrementally. Our experiments on a challenging logo database of 10,000 images highlight the effectiveness of this approach.

Educating the Next Generation of Mobile Game Developers

Mobile gaming is one of the fastest growing segments in the video game industry. Through a partnership between Motorola Laboratories and GamePipe Laboratory at the University of Southern California, we are exploring Linuxs capabilities for mobile gaming and to provide developers with an alternative to what is predominantly a Java-based medium. Moving beyond Java lets game developers fully leverage the hardware advances and software capabilities of high-end smart phones

Predictive Caching for Video on Demand CDNs

Video on Demand (VoD) services provide a wide range of content options and enable subscribers to select, retrieve and locally consume desired content. In this work we propose caching solutions to improve the scalability of the content distribution networks (CDNs) of existing VoD architectures. We first investigate metrics relevant to this caching framework and subsequently define goals that should be satisfied by an efficient solution. We propose novel techniques for predicting future values of metrics of interest. We use our prediction mechanisms to define the cost imposed on the system (network and caches) by items that are not cached. We use this cost to develop novel caching and static placement strategies. We validate our solutions using log data collected from Motorola equipment from several Comcast VoD deployments.

Is this urgent?: exploring time-sensitive information needs in collaborative question answering

As online Collaborative Question Answering (CQA) servicessuch as Yahoo! Answers and Baidu Knows are attracting users, questions, and answers at an explosive rate, the truly urgent and important questions are increasingly getting lost in the crowd. That is, questions that require immediate responses are pushed out of the way by the trivial but more recently arriving questions. Unlike other questions in collaborative question answering (CQA) for which users might be willing to wait until good answers appear, urgent questions are likely to be of interest to the asker only if answered in the next few minutes or hours. For such questions, late responses are either not useful or are simply not applicable. Unfortunately, current collaborative question-answering systems do not distinguish urgent questions from the rest, and could thus be ineffective for urgent information needs. We explore text- and data- mining methods for automatically identifying urgent questions in the CQA setting. Our results indicate that modeling the question context (i.e., the particular forum/category where the question was posted) can increase classification accuracy compared to the text of the question alone.