Romit Roy Choudhury

Duke University, Durham, North Carolina, United States

Are you Romit Roy Choudhury?

Claim your profile

Publications (103)23.14 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: We present eNav, a smartphone-based vehicular GPS navigation system that has an energy-saving location sensing mode capable of drastically reducing navigation energy needs. Traditional implementations sample the phone GPS at the highest possible rate (usually 1Hz) to ensure constant highest possible localization accuracy. This practice results in excessive phone battery consumption and reduces the attainable length of a navigation session. The seemingly most common solution would be to always use a car-charger and keep the phone plugged-in during navigation at all times. However, according to a comprehensive survey we conducted, only a small percent of people would actually always carry around their phones' car-chargers and cables, as doing so is inconvenient and defeats the true ''wireless'' nature of mobile phones. In addressing this problem, eNav exploits the phone's lower-energy on-board motion sensors for approximate location sensing when the vehicle is sufficiently far from the next navigation waypoint, using actual GPS sampling only when close. Our user study shows that, while remaining virtually transparent to users, eNav can reduce navigation energy consumption by over 80% without compromising navigation quality or user experience.
    Proceedings of the 13th international symposium on Information processing in sensor networks; 04/2014
  • Conference Paper: Injecting life into toys
    Songchun Fan, Hyojeong Shin, Romit Roy Choudhury
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper envisions a future in which smartphones can be inserted into toys, such as a teddy bear, to make them interactive to children. Our idea is to leverage the smartphones' sensors to sense children's gestures, cues, and reactions, and interact back through acoustics, vibration, and when possible, the smartphone display. This paper is an attempt to explore this vision, ponder on applications, and take the first steps towards addressing some of the challenges. Our limited measurements from actual kids indicate that each child is quite unique in his/her "gesture vocabulary", motivating the need for personalized models. To learn these models, we employ signal processing-based approaches that first identify the presence of a gesture in a phone's sensor stream, and then learn its patterns for reliable classification. Our approach does not require manual supervision (i.e., the child is not asked to make any specific gesture); the phone detects and learns through observation and feedback. Our prototype, while far from a complete system, exhibits promise -- we now believe that an unsupervised sensing approach can enable new kinds of child-toy interactions.
    Proceedings of the 15th Workshop on Mobile Computing Systems and Applications; 02/2014
  • Chuan Qin, Xuan Bao, R.R. Choudhury, S. Nelakuditi
    [Show abstract] [Hide abstract]
    ABSTRACT: Mobile phones are becoming the convergent platform for personal sensing, computing, and communication. This paper attempts to exploit this convergence toward the problem of automatic image tagging. We envision TagSense, a mobile phone-based collaborative system that senses the people, activity, and context in a picture, and merges them carefully to create tags on-the-fly. The main challenge pertains to discriminating phone users that are in the picture from those that are not. We deploy a prototype of TagSense on eight Android phones, and demonstrate its effectiveness through 200 pictures, taken in various social settings. While research in face recognition continues to improve image tagging, TagSense is an attempt to embrace additional dimensions of sensing toward this end goal. Performance comparison with Apple iPhoto and Google Picasa shows that such an out-of-band approach is valuable, especially with increasing device density and greater sophistication in sensing and learning algorithms.
    IEEE Transactions on Mobile Computing 01/2014; 13(1):61-74. · 2.40 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: This issue of MC2R features the posters and demonstrations submitted to ACM HotMobile 2013.
    ACM SIGMOBILE Mobile Computing and Communications Review 11/2013; 17(3):19-20.
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper describes a system for automatically rating content - mainly movies and videos - at multiple granularities. Our key observation is that the rich set of sensors available on today's smartphones and tablets could be used to capture a wide spectrum of user reactions while users are watching movies on these devices. Examples range from acoustic signatures of laughter to detect which scenes were funny, to the stillness of the tablet indicating intense drama. Moreover, unlike in most conventional systems, these ratings need not result in just one numeric score, but could be expanded to capture the user's experience. We combine these ideas into an Android based prototype called Pulse, and test it with 11 users each of whom watched 4 to 6 movies on Samsung tablets. Encouraging results show consistent correlation between the user's actual ratings and those generated by the system. With more rigorous testing and optimization, Pulse could be a candidate for real-world adoption.
    Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing; 09/2013
  • Xuan Bao, Yin Lin, Uichin Lee, Ivica Rimac, Romit Roy Choudhury
    [Show abstract] [Hide abstract]
    ABSTRACT: The proliferation of pictures and videos in the Internet is imposing heavy demands on mobile data networks. Though emerging wireless technologies will provide more bandwidth, the increase in demand will easily consume the additional capacity. To alleviate this problem, we explore the possibility of serving user requests from other mobile devices located geographically close to the user. For instance, when Alice reaches areas with high device density – Data Spots – the cellular operator learns Alice’s content request, and guides her device to nearby devices that have the requested content. Importantly, communication between the nearby devices can be mediated by servers, avoiding many of the known problems of pure ad hoc communication. This paper argues this viability through systematic prototyping, measurements, and measurement-driven analysis.
    IEEE INFOCOM 2013; 04/2013
  • Xuan Bao, Mahanth Gowda, Ratul Mahajan, Romit Roy Choudhury
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper envisions a new research direction that we call psychological computing. The key observation is that, even though computing systems are missioned to satisfy human needs, there has been little attempt to bring understandings of human need/psychology into core system design. This paper makes the case that percolating psychological insights deeper into the computing layers is valuable, even essential. Through examples from content caching, vehicular systems, and network scheduling, we argue that psychological awareness can not only offer performance gains to known technological problems, but also spawn new kinds of systems that are difficult to conceive otherwise.
    Proceedings of the 14th Workshop on Mobile Computing Systems and Applications; 02/2013
  • He Wang, Xuan Bao, Romit Roy Choudhury, Srihari Nelakuditi
    [Show abstract] [Hide abstract]
    ABSTRACT: Wearable cameras and displays, such as the Google Glass, are around the corner. This paper explores techniques that jointly leverage camera-enabled glasses and smartphones to recognize individuals in the visual surrounding. While face recognition would be one approach to this problem, we believe that it may not be always possible to see a person's face. Our technique is complementary to face recognition, and exploits the intuition that colors of clothes, decorations, and even human motion patterns, can together make up a "fingerprint". When leveraged systematically, it may be feasible to recognize individuals with reasonable consistency. This paper reports on our attempts, with early results from a prototype built on Android Galaxy phones and PivotHead's camera-enabled glasses. We call our system InSight.
    Proceedings of the 14th Workshop on Mobile Computing Systems and Applications; 02/2013
  • S. Sen, N. Santhapuri, R.R. Choudhury, S. Nelakuditi
    [Show abstract] [Hide abstract]
    ABSTRACT: Successive interference cancellation (SIC) is a PHY capability that allows a receiver to decode packets that arrive simultaneously. While the technique is well known in communications literature, emerging software radio platforms are making practical experimentation feasible. This motivates us to study the extent of throughput gains possible with SIC from a MAC layer perspective and scenarios where such gains are worth pursuing. We find that contrary to our initial expectation, the gains are not high when the bits of interfering signals are not known a priori to the receiver. Moreover, we observe that the scope for SIC gets squeezed by the advances in bitrate adaptation. In particular, our analysis shows that interfering one-to-one transmissions benefit less from SIC than scenarios with many-to-one transmissions (such as when clients upload data to a common access point). In view of this, we develop an SIC-aware scheduling algorithm that employs client pairing and power reduction to extract the most gains from SIC. We believe that our findings will be useful guidelines for moving forward with SIC-aware protocol research.
    IEEE Transactions on Mobile Computing 01/2013; 12(2):346-357. · 2.40 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Today's smartphones provide a variety of sensors, enabling high-resolution measurements of user behavior. We envision that many services can benefit from short-term predictions of complex human behavioral patterns. While enablement of behavior awareness through sensing is a broad research theme, one possibility is in predicting how quickly a person will move through a space. Such a prediction service could have numerous applications. For one example, we imagine shop owners predicting how long a particular customer is likely to browse merchandise, and issue targeted mobile coupons accordingly - customers in a hurry can be encouraged to stay and consider discounts. Within a space of moderate size, WiFi access points are uniquely positioned to track a statistical framework for user length of stay, passively recording metrics such as WiFI signal strength (RSSI) and potentially receiving client-uploaded sensor data. In this work, we attempt to quantity this opportunity, and show that human dwell time can be predicted with reasonable accuracy, even when restricted to passively observed WiFi RSSI.
    INFOCOM, 2013 Proceedings IEEE; 01/2013
  • Source
    Songchun Fan, Mahanth Gowda, Romit Roy Choudhury
    [Show abstract] [Hide abstract]
    ABSTRACT: The Wi-Fi interface is one of the major energy consuming components in smart phones. Wi-Fi scanning process contributes significantly to this. We present a solution based on partial scan, which produces full scan results, by performing only incomplete scan process. Using a decision tree algorithm, we propose such a prediction scheme, with the help of cached scan results.
    Proceedings of the 10th international conference on Mobile systems, applications, and services; 06/2012
  • [Show abstract] [Hide abstract]
    ABSTRACT: Many context aware applications can benefit from using high-level sensing results with semantic meanings (e.g, busy/idle). This paper proposes a platform design that provides high-level "virtual sensor" abstractions and enables new virtual sensors to be bootstrapped from existing ones.
    06/2012;
  • Source
    Souvik Sen, Romit Roy Choudhury, Srihari Nelakuditi
    [Show abstract] [Hide abstract]
    ABSTRACT: The rapid growth of location-based applications has spurred extensive research on localization. Nonetheless, indoor localization remains an elusive problem mostly because the accurate techniques come at the expense of cumbersome war-driving or additional infrastructure. Towards a solution that is easier to adopt, we propose SpinLoc that is free from these requirements. Instead, SpinLoc levies a little bit of the localization burden on the humans, expecting them to rotate around once to estimate their locations. Our main observation is that wireless signals attenuate differently, based on how the human body is blocking the signal. We find that this attenuation can reveal the directions of the APs in indoor environments, ultimately leading to localization. This paper studies the feasibility of SpinLoc in real-world indoor environments using off-the-shelf WiFi hardware. Our preliminary evaluation demonstrates accuracies comparable toschemes that rely on expensive war-driving.
    01/2012;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: A growing number of mobile apps are exploiting smartphone sensors to infer user behavior, activity, or context. For instance, an app may infer from the accelerometer that its user is inside a car; another app may infer if the user is at a dance party from sound, light, and motion information from multiple users. Regardless of what is being inferred, these apps require training (i.e., the raw sensor data need to be initially labeled with the ground truth, such as "driving" or "dance party"). Obtaining labeled data for new mobile sensing apps is proving to be a "chicken and egg" problem. Users who install such apps are usually not willing to help with labeling – they demand immediate service. Without a reasonable amount of labeling, the apps are not able to perform inference, and are not worth installing. This paper aims to address this problem, helping mobile apps to bootstrap with just a few users. Our core intuition is that even though each user may be different, they may exhibit similar patterns on certain sensing dimensions some of the time. For instance, different users may walk and drive at different speeds, but certain speeds will indicate driving for all users. These common patterns could be used as "seeds" to model the new user, and label her data on all other dimensions. We prototype a technique to automatically extract the commonalities to seed models for new users and learn a unique personalized inference model for each user. We evaluate the proposed technique through example apps and real world data.
    01/2012;
  • Source
    Sanjeev Singh, Srihari Nelakuditi, Romit Roy Choudhury, Yang Tong
    [Show abstract] [Hide abstract]
    ABSTRACT: Motor vehicle accidents are one of the leading causes of death. While lane departure warning, blind spot warning, and driver attention monitoring systems for avoiding collisions have been in development for quite sometime, to date mostly luxury cars are only equipped with these safety features. As a cheaper and ubiquitous alternative, we explore how a smartphone can assist an inattentive driver by leveraging its front and back cameras apart from other sensors. The challenge, however, is given the resource constraints of a smartphone, how quickly and accurately can it detect an unintended maneuver and alert the driver. In this paper, we describe our on-going attempt to address this challenge.
    01/2012;
  • Souvik Sen, Božidar Radunovic, Romit Roy Choudhury, Tom Minka
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper explores the viability of precise indoor localization using physical layer information in WiFi systems. We find evidence that channel responses from multiple OFDM subcarriers can be a promising location signature. While these signatures certainly vary over time and environmental mobility, we notice that their core structure preserves certain properties that are amenable to localization. We attempt to harness these opportunities through a functional system called PinLoc, implemented on off-the-shelf Intel 5300 cards. We evaluate the system in a busy engineering building, a crowded student center, a cafeteria, and at the Duke University museum, and demonstrate localization accuracies in the granularity of 1m x 1m boxes, called "spots". Results from 100 spots show that PinLoc is able to localize users to the correct spot with 89% mean accuracy, while incurring less than 6% false positives. We believe this is an important step forward, compared to the best indoor localization schemes of today, such as Horus.
    01/2012;
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose a content distribution strategy over municipal WiFi networks where Access Points (APs) collaboratively cache popular multimedia content, and disseminate them in a manner that each mobile device has the portion of the content just-in-time for playback. If successful, we envision that a child will be able to seamlessly watch a movie in a car, as her tablet downloads different parts of the movie over different WiFi APs at different times.
    ACM SIGCOMM Computer Communication Review 01/2012; 42(4). · 0.91 Impact Factor
  • Justin Gregory Manweiler, Puneet Jain, Romit Roy Choudhury
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper attempts to solve the following problem: can a distant object be localized by looking at it through a smartphone. As an example use-case, while driving on a highway entering New York, we want to look at one of the skyscrapers through the smartphone camera, and compute its GPS location. While the problem would have been far more difficult five years back, the growing number of sensors on smartphones, combined with advances in computer vision, have opened up important opportunities. We harness these opportunities through a system called Object Positioning System (OPS) that achieves reasonable localization accuracy. Our core technique uses computer vision to create an approximate D structure of the object and camera, and applies mobile phone sensors to scale and rotate the structure to its absolute configuration. Then, by solving (nonlinear) optimizations on the residual (scaling and rotation) error, we ultimately estimate the object's GPS position. We have developed OPS on Android NexusS phones and experimented with localizing 50 objects in the Duke University campus. We believe that OPS shows promising results, enabling a variety of applications. Our ongoing work is focused on coping with large GPS errors, which proves to be the prime limitation of the current prototype.
    01/2012;
  • J. Manweiler, R.R. Choudhury
    [Show abstract] [Hide abstract]
    ABSTRACT: WiFi continues to be a prime source of energy consumption in mobile devices. This paper observes that, despite a rich body of research in WiFi energy management, there is room for improvement. Our key finding is that WiFi energy optimizations have conventionally been designed with a single AP in mind. However, network contention among different APs can dramatically increase a client's energy consumption. Each client may have to keep awake for long durations before its own AP gets a chance to send it packets to it. As AP density increases, the waiting time inflates, resulting in a proportional decrease in battery life. We design SleepWell, a system that achieves energy efficiency by evading network contention. The APs regulate the sleeping window of their clients in a way that different APs are active/inactive during nonoverlapping time windows. The solution is analogous to the common wisdom of going late to office and coming back late, thereby avoiding the rush hours. We implement SleepWell on a testbed of eight Laptops and nine Android phones, and evaluate it over a wide variety of scenarios and traffic patterns. Results show a median gain of up to 2x when WiFi links are strong; when links are weak and the network density is high, the gains can be even more.
    IEEE Transactions on Mobile Computing 01/2012; 11(5):739-752. · 2.40 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: We propose UnLoc, an unsupervised indoor localization scheme that bypasses the need for war-driving. Our key observation is that certain locations in an indoor environment present identifiable signatures on one or more sensing dimensions. An elevator, for instance, imposes a distinct pattern on a smartphone's accelerometer; a corridor-corner may overhear a unique set of WiFi access points; a specific spot may experience an unusual magnetic fluctuation. We hypothesize that these kind of signatures naturally exist in the environment, and can be envisioned as internal landmarks of a building. Mobile devices that "sense" these landmarks can recalibrate their locations, while dead-reckoning schemes can track them between landmarks. Results from 3 different indoor settings, including a shopping mall, demonstrate median location errors of 1:69m. War-driving is not necessary, neither are floorplans the system simultaneously computes the locations of users and landmarks, in a manner that they converge reasonably quickly. We believe this is an unconventional approach to indoor localization, holding promise for real-world deployment.
    01/2012;

Publication Stats

2k Citations
23.14 Total Impact Points

Institutions

  • 2008–2013
    • Duke University
      • • Department of Computer Science
      • • Department of Electrical and Computer Engineering (ECE)
      Durham, North Carolina, United States
    • University of South Carolina
      • Department of Computer Science & Engineering
      Columbia, SC, United States
  • 2002–2006
    • University of Illinois, Urbana-Champaign
      • • Department of Computer Science
      • • Coordinated Science Laboratory
      Urbana, IL, United States
  • 2000
    • Haldia Institute of Technology
      Kolkata, Bengal, India