Raghupathy Sivakumar is the Wayne J. Holman Chair Professor in the School of Electrical and Computer Engineering at Georgia Tech. He leads the Georgia Tech Networking and Mobile Computing (GNAN) Research Group, where he and his students do research in the areas of wireless networking and mobile computing. He is the Founding Director of CREATE-X, a Georgia Tech initiative to instill entrepreneurial confidence in its students. Previously, he served as the Co-Founder and CTO for StarMobile, Inc. (now PowWow Mobile) between 2012 and 2016, as a Technologist for EMC Corporation between 2011 and 2012, as the Founder and CTO of Asankya, Inc. (now EMC), between 2004 and 2011, and as a Technologist for EG Technology, Inc. (now Arris), between 2001 and 2004.
Professor Sivakumar received his Ph.D. and M.S. degrees in Computer Science from University of Illinois at Urbana-Champaign in 2000 and 1998 respectively, and his B.E. degree in Computer Science from Anna University (Chennai) in 1996. He is a Fellow of the IEEE and the recipient of the School of Electrical and Computer Engineering’s Distinguished Faculty Achievement Award (2016), the Georgia Tech Research Innovation Award (2015), the Class of 1934 Teaching Effectiveness Award (2014), the Georgia Tech Sigma Xi Best Thesis Advisor awards (2006 (Ph.D.), 2004 (M.S.)), the IEEE/CreateNet Broadnets Internet Symposium Best Paper Award (2007), the IEEE ICNP Best Paper Award (Co-author, 2005), the IEEE SECON Best Paper Award (Co-author, 2005), the Outstanding Young Faculty Award at the School of Electrical and Computer Engineering, Georgia Tech (2004), and the ACM MobiCom Best Student Paper Award (Co-author, 2003). He is also the recipient of several awards at the University of Illinois, Urbana-Champaign including the David J. Kuck Best Doctoral Dissertation Award from the Department of Computer Science (2001), the Poppelbaum Award for Excellence in Creative Research and Academic Merit from the Department of Computer Science (2000), the Mavis Memorial Award Scholarship for Excellence in Teaching and Research from the College of Engineering (1999), and the David J. Kuck Best Masters Thesis Award from the Department of Computer Science (1998). He received the University Gold Medal from Anna University in 1996.
Areas of Expertise (6)
Network Quality of Service
University of Illinois at Urbana-Champaign: Ph.D., Computer Science 2000
University of Illinois at Urbana-Champaign: M.S., Computer Science 1998
Anna University: B.E., Computer Science and Engineering 1996
Selected Media Appearances (2)
Atlanta Investor Greg Foster Joins CREATE-X
Georgia Tech News Center online
“Greg brings energy, passion and a wealth of business knowledge to the CREATE-X program,” said Raghupathy Sivakumar, founding director of CREATE-X and Wayne J. Holman Chair Professor in the School of Electrical and Computer Engineering. “I am confident his experience building successful companies from the ground up will serve our students well. With Greg on board, we hope to elevate CREATE-X to the most competitive startup program in the country.”
Georgia Tech Gets $2 Million to Help Churn Out Tech Startups
Center for Digital Education online
Universities that began as teaching institutions and later became centers of research are on the verge of building a third pillar tied to entrepreneurship, Sivakumar said. "Students come in these days wanting to change the world."
Belt conveyance device and image forming apparatus
A belt conveyance device has a configuration where one end of a rotation shaft of an inclinable steering roller that can move an endless belt in the width direction is supported by a first support member that is pivotable on a first pivot axis extending in a first axial line direction intersecting the rotation axis of the steering roller, and the other end of the rotation shaft of the steering roller is supported by a second support member that is pivotable on a second pivot axis that is generally parallel with the rotation axis of another suspending roller and also extends in a direction generally orthogonal to the first axial line.
Scheduled WiFi in single collision domain
In a method for clients to transmit data via a shared medium network, a schedule assigns time slots to individual clients. A collision avoidance scheme determines an offset time to begin transmitting data, which upon expiration, a client senses if any of the clients is transmitting. If a second client is transmitting, then each client sets a first time slot assigned to the second client on the transmission schedule as a starting time slot. The clients track the schedule and transmit to the access point during the next time slot assigned to each client. If no other client is transmitting, then a client transmits data to the access point, sets the first time slot assigned to it as the starting time slot. The schedule is tracked by the clients and they transmit data to the access point during each successive time slot assigned to them.
View virtualization and transformations for mobile applications
Application mobilization has assumed importance given has assumed importance given the proliferation of smartphones amongst the enterprise workforce, and other users. Existing techniques to mobilize applications incur high overheads in terms of time, cost, and effort. Remote computing is a promising basis for application mobilization that has the advantages of zero code rewriting, full functionality applications, and seamless IT manageability. However, it has the major disadvantage of presenting a cumbersome PC application view on the smartphone. In this context the present invention, referred to as* Mobile, is described to perform dynamic transformation of application views for smartphones. Significant performance gains may be achieved by using this system and methodology.
Selected Articles (5)
Mohit Agarwal, Raghupathy Sivakumar
In this work, we consider the problem of detection and interpretation of user preferences using their brainwaves. The specific goal in this context is to determine the preference ranking for a set of objects by solely relying on the brain activity of a user who is wearing an EEG headset wearable. We first establish the feasibility of object ranking (based on an EEG wearable) by a trial and error based analysis of the EEG signals. We then present a machine learning algorithm Cerebro, which can learn the specific nuances of the user's brainwaves for preferences to accurately rank the objects. We measure the accuracy of the algorithm in terms of the Normalized Discounted Cumulative Gain (NDCG), and show that it performs well when trained on 7 objects, and evaluated on 3 objects for the 14 users.
Uma Parthavi Moravapalle, Raghupathy Sivakumar
Mobilizing enterprise applications enable employees to perform their job functions on their smartphones, even when away from a Desktop. Among the different strategies used to mobilize web enterprise applications, application refactoring based services are gaining popularity due to their ease of deployment. Refactoring involves hosting the application as-is on the enterprise cloud and allowing a user to interact with it through a smartphone-optimized UI. These services require APIs provided by the applications to accurately map the smartphone UI to the web application UI.
Of the strategies available to APIfy applications, a front-end only approach based on intelligent screen scraping is particularly attractive as it can APIfy a host of applications without any support from the applications themselves. Front-end strategies, however, rely on being able to accurately and reliably identify UI elements within the application. In this paper, we show that simple approaches which rely on graphical coordinates or the position of an element with respect to a fixed anchor in the application layout are not robust enough for APIfication. In this context, we present Trackr, an algorithm that relies on the notion of quorum fingerprinting to track elements. We then discuss several optimizations to this baseline version. We show through analysis of changes to real-world web-applications that Trackr has considerable benefits. We demonstrate the usage of Trackr through a Dashboard smartphone app that monitors values across different websites within one mobile app.
Yubing Jian, Shruti Lall, Raghupathy Sivakumar
The position of an access point (AP) in a WiFi network has considerable influence on the performance of the network. In this work, we consider the problem of a WiFi AP self-positioning itself adaptively based on the network conditions to deliver improved network performance. Through extensive experimental evaluation, we show that there are indeed significant performance benefits to be attained by allowing the AP to move intelligently. We also rely on theoretical analysis, simulations, and experimental studies to show that the AP optimal location search problem can be split into two parts: a macro-search problem to minimize average path loss between AP and clients, and a micro-search problem to tackle real-time multipath fading effects. We then present Hermes, a self-positioning WiFi AP system that relies on a suite of algorithms to compute and then move to an optimal location within the network. Using a prototype implementation, we show that Hermes can perform up to 117% better than WiFi with no AP mobility, and up to 73% better than related work that allows for AP mobility.
Bhuvana Krishnaswamy, Raghupathy Sivakumar
In this work, we consider the problem of forward error correction in a multiple access molecular communication network with bacteria as transceivers. A number of forward error correction techniques have been developed to maximize throughput and achieve the lower bound on the bit error rate performance. All existing codes were developed for traditional networks and hence the constraints on computational complexity do not match that of bio-circuits. Designing reliable and accurate bio-circuits for operations like polynomial multiplication that are basic to FEC is extremely challenging.
Uma Parthavi Moravapalle, Raghupathy Sivakumar
In this paper, we consider the problem of mobilizing Spot Tasks, a special category of workflows within web-based enterprise applications. Spot tasks are simple workflows that can be finished by interacting with only one page of the application. We present Taskr, a do-it-yourself mobilization solution that users, regardless of their skills, can rely on to mobilize their spot tasks in a robust fashion. Taskr uses remote computing with application refactoring to achieve code-less mobilization and allows for flexible mobile delivery wherein users can execute their spot tasks through Twitter, Email or a native mobile app. We implement a prototype of Taskr and show through user studies that it has the potential to reduce task burden significantly.