Qualification: 
Ph.D, M.Tech, B-Tech
subhasrid@am.amrita.edu

Dr. Subhari Duttagupta has received her M. Tech. degree in 1993 in the area of Parallel Computing and received the doctoral degree in 2010 in the area of sensor networks, both from Indian Institute of Technology at Mumbai. Between 1994-2002, she worked in various organizations such as IBM, Micron and HP in USA. Before joining Amrita, she was working as a senior scientist in TCS Research Labs, Mumbai in the area of performance engineering. 

Areas of interest: Performance Evaluation And Modelling Of Systems And Networks, Distributed Systems, Real-Life Applications Using Sensor Networks And Analysing Iot Applications, Internet of Things, Performance Engineering, Modelling and Simulation

Qualification

Year Affiliation
2010 Ph.D, Computer Science and Engineering Indian Institute of Technology, Bombay
1993 M. Tech, Computer Science and Engineering Indian Institute of Technology, Bombay
1991 B. Tech, Computer Science and Engineering Indian Institute of Technology, Bombay

Awards and Achievements

  • 2 USA and 1 EU patents granted, 6 USA patents filed

Research Collaborations

  • IIT Bombay on "Resiliency of Smart Grid"

Publications

Publication Type: Patent

Year of Publication Title

2018

S. Duttagupta, Kumar, M., and Nambiar, M. Karunakara, “Systems and Methods for Predicting Performance of Applications on an Internet of Things (IoT) Platform”, U.S. Patent US15/410,1782018.[Abstract]


Performance prediction systems and method of an Internet of Things (IoT) platform and applications includes obtaining input(s) comprising one of (i) user requests and (ii) sensor observations from sensor(s); invoking Application Programming Interface (APIs) of the platform based on input(s); identifying open flow (OF) and closed flow (CF) requests of system(s) connected to the platform; identifying workload characteristics of the OF and CF requests to obtain segregated OF and segregated CF requests, and a combination of open and closed flow requests; executing performance tests with the APIs based on the workload characteristics; measuring resource utilization of the system(s) and computing service demands of resource(s) from measured utilization, and user requests processed by the platform per unit time; executing the performance tests with the invoked APIs based on volume of workload characteristics pertaining to the application(s); and predicting, using queuing network, performance of the application(s) for the volume of workload characteristics.

More »»

2018

D. Chahal, Duttagupta, S., and Nambiar, M. Karunakara, “Predicting performance of a software application over a target system”, U.S. Patent US14/682,3062018.[Abstract]


System and method for predicting performance of a software application over a target system is disclosed. The method comprises generating a benchmark suite such that benchmark indicates a combination of workloads applied over a set of standard software applications running on a source system. The method further comprises identifying a benchmark of the benchmark suite, wherein the benchmark has performance characteristics same as that of the software application. The method further enables remotely executing the set of standard software applications associated with the benchmark on the target system with the combination of workload as specified by the benchmark. The method further enables recording a performance of the set of standard software applications on the target system. Based on the performance of the standard software applications on the target system the performance of the software application is predicted.

More »»

2017

S. Duttagupta, Kumar, M., Shah, D., and Nambiar, M. Karunakara, “Systems and methods for benchmark based cross platform service demand prediction”, U.S. Patent US15/227,5422017.[Abstract]


Systems and methods for benchmark based cross platform service demand prediction includes generation of performance mimicking benchmarks that require only application level profiling and provide a representative value of service demand of an application under consideration on a production platform, thereby eliminating need for actually deploying the application under consideration on a production platform. The PMBs require only a representative estimate of service demand of the application under test and can be reused to represent multiple applications. The PMBs are generated based on a skeletal benchmark corresponding to the technology stack used by the application under test and an input file generated based on application profiling that provides pre-defined lower level method calls, data flow sequences between multi-tiers of the application under test and send and receive network calls made by the application under consideration.

More »»

2016

S. Duttagupta, Virk, R. Singh, and Nambiar, M. Karunakara, “System and method facilitating performance prediction of multi-threaded application in presence of resource bottlenecks”, U.S. Patent US14/183,4612016.[Abstract]


The present disclosure generally relates to a system and method for predicting performance of a multi-threaded application, and particularly, to a system and method for predicting performance of the multi-threaded application in the presence of resource bottlenecks. In one embodiment, a system for predicting performance of a multi-threaded software application is disclosed. The system may include one or more processors and a memory storing processor-executable instructions for configuring a processor to: represent one or more queuing networks corresponding to resources, the resources being employed to run the multi-threaded application; detect, based on the one or more queuing networks, a concurrency level associated with encountering of a first resource bottleneck; determine, based on the concurrency level, performance metrics associated with the multi-threaded application; and predict the performance of the multi-threaded application based on the performance metrics.

More »»

Publication Type: Conference Proceedings

Year of Publication Title

2017

D. Raj, Dr. Maneesha V. Ramesh, and Duttagupta, S., “Delay Tolerant Routing Protocol For Heterogeneous Marine Vehicular Mobile Ad-Hoc Network”, IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops). IEEE, Kona, HI, USA, pp. 461-466, 2017.[Abstract]


Delay tolerant networks (DTN) are characterized by lack of end-to-end communications and stable infrastructures. This paper deals with DTN networks consisting of a number of heterogeneous mobile fishing vessels where some nodes, referred to as adaptive nodes, are capable of communicating through long-range Wi-Fi whereas other nodes are having simple Wi-Fi access network. The nodes form different clusters consisting of adaptive nodes and access nodes. Message routing in this heterogeneous network happens through adaptive nodes if the source and destination nodes belong to different clusters. Real data from field study reflects that mobile nodes in this network follow Gaussian-Markov mobility model and may have high inter-meeting arrival time based on deployment and node density. Our proposed DTN routing protocol incorporates simple encounter-based message forwarding and achieves lower latency and high delivery probability in the range of 90-98% for most of the scenarios. The proposed protocol is verified through a realistic mobile ad-hoc wireless simulator.

More »»

2016

S. Duttagupta, Kumar, M., and Apte, V., “Performance Mimicking Benchmarks for Multi-tier Applications”, Companion Publication for ACM/SPEC on International Conference on Performance Engineering. ACM, New York, NY, USA, pp. 45-50 , 2016.[Abstract]


Predicting performance of multi-tier enterprise applications for a target platform is of significant importance to IT industries especially when target environment is unavailable for deployment. Performance modeling techniques depend on accurate estimation of resource demands for a specific application. This paper proposes a methodology for deriving Performance Mimicking Benchmarks (PMBs) that can predict resource demand of application server of multi-tier on-line transaction processing applications on a target environment. PMBs do not require the actual application to be deployed on the target itself. These benchmarks invoke similar method calls as the application at different layers in the technology stack that contribute significantly to CPU utilization. Further, they mimic all send and receive interactions with external servers (e.g., database server) and web clients. Ability of PMBs for service demand prediction is validated with a number of sample multi-tier applications including SPECjEnterprise2010 on disparate hardware configurations. These service demands when used in a modified version of Mean Value Analysis algorithm, can predict throughput and response time with accuracy close to 90%.

More »»

2016

S. Duttagupta, Kumar, M., Ranjan, R., and Nambiar, M., “Performance Prediction of IoT Application: An Experimental Analysis”, IoT'16 Proceedings of the 6th International Conference on the Internet of Things. ACM, New York, NY, USA, pp. 43-51, 2016.[Abstract]


The ubiquitous deployment of mobile and sensor devices is creating a new environment, known as the Internet of Things (IoT). In this new realm, wireless sensor nodes, smart devices along with information and communication systems together constitute the elements of new computing environment. For wide acceptance of IoT applications, guaranteeing their performance is important. However, performance analysis of IoT applications encounters a lot of challenges such as interaction among a number of different technologies, various usage patterns of smart devices, numerous possible transactions, unavailability of suitable testing platforms and so on. In this paper, we deal with performance analysis of a scalable IoT platform that attempts to take a holistic approach for enterprise level data management in the IoT domain as well as development of IoT applications. We predict the performance of specific APIs offered by the platform using queuing network modeling and also validate them through experimental analysis on two deployment platforms. Additionally, we are able to predict performance of a real-life energy monitoring application deployed on this platform in a production environment. Our analysis is done mostly based on data extracted from production environment and requires only limited performance tests.

More »»

2016

S. Duttagupta, Kumar, M., and Nambiar, M., “Performance Prediction And Analysis Of Internet Of Things Applications”, Proceedings of the 6th International Conference on the Internet of Things. ACM, New York, USA, pp. 43-51, 2016.[Abstract]


The ubiquitous deployment of mobile and sensor devices is creating a new environment, known as the Internet of Things (IoT). In this new realm, wireless sensor nodes, smart devices along with information and communication systems together constitute the elements of new computing environment. For wide acceptance of IoT applications, guaranteeing their performance is important. However, performance analysis of IoT applications encounters a lot of challenges such as interaction among a number of different technologies, various usage patterns of smart devices, numerous possible transactions, unavailability of suitable testing platforms and so on. In this paper, we deal with performance analysis of a scalable IoT platform that attempts to take a holistic approach for enterprise level data management in the IoT domain as well as development of IoT applications. We predict the performance of specific APIs offered by the platform using queuing network modeling and also validate them through experimental analysis on two deployment platforms. Additionally, we are able to predict performance of a real-life energy monitoring application deployed on this platform in a production environment. Our analysis is done mostly based on data extracted from production environment and requires only limited performance tests

More »»

2015

S. Duttagupta, Virk, R., and Nambiar, M., “Software Bottleneck Analysis During Performance Testing”, International Conference and Workshop on Computing and Communication (IEMCON). IEEE, Vancouver, BC, Canada, pp. 1-7, 2015.[Abstract]


Scalability of a multi-tier enterprise system is limited resources that becomes a bottleneck, by the presence of software and hardware resource bottlenecks. These bottlenecks typically occur at larger number of users. From an IT industry point of view, deployment process of enterprise applications becomes simpler if these bottlenecks are known apriori during the performance testing itself. This paper uses an analytical model based technique for analyzing performance of such a system where the model consists of two layers of queuing networks for software resources and hardware resources. Proposed solution strategy involves identifying all the software resources in the application, estimating their service demands along with service demands of hardware resources, incorporating these parameters into the model and finally solving it. The paper describes a methodology that uses these steps to identify software and hardware bottlenecks for a given enterprise application. The paper further presents two case studies dealing with real-life multi-tier enterprise applications that encounter software resource bottlenecks. The case studies show that the model is able to predict throughput and utilization of servers with accuracy close to 90%.

More »»

2014

R. Mansharamani, Duttagupta, S., and Nehete, A., “Automatically Determining Load Test Duration Using Confidence Intervals”, CMG India Proceedings. pp. 58-68, 2014.[Abstract]


Load testing has become the de facto standard to evaluate performance of applications in the IT industry, thanks to the growing popularity of automated load testing tools. These tools report performance metrics such as average response time and throughput, which are sensitive to the test duration specified by the tester. Too short a duration can lead to inaccurate estimates of performance and too long a duration leads to reduced number of cycles of load testing. Currently, no scientific methodology is followed by load testers to specify run duration. In this paper, we present a simple methodology, using confidence intervals, such that a load test can automatically determine when to converge. We demonstrate the methodology using five lab applications and three real world applications.

More »»

2014

S. Duttagupta, Virk, R., and Nambiar, M., “Predicting Performance In The Presence Of Software And Hardware Resource Bottlenecks”, Symposium on Performance Evaluation of Computer and Telecommunication Systems (SPECTS). IEEE, Monterey, CA, USA, pp. 542-549, 2014.[Abstract]


Scalability of a multi-tier enterprise system is limited by the presence of software and hardware resource bottlenecks. These bottlenecks typically occur at larger number of users. It would help enterprise applications significantly if these bottlenecks are known a-priori during the performance testing itself. This paper deals with predicting the performance of such systems and models an application in terms of a two layer queuing network consisting of software resources and hardware resources. The software modules which require exclusive access by a thread are modeled as a queuing resource and other modules are treated as delay resources in the software queuing network. This network in turn uses a hardware queuing network consisting of resources such as CPU, disk and network. The proposed solution is augmented with additional constraints to ensure that the solution converges at a large number of users. Further, the proposed solution is capable of modeling multi-class requests with critical section and pooling of resources e.g., connection pool or thread pool. We validate the proposed solution with actual experimental results using sample programs and observe that the model is able to predict throughput and resource utilization with close to 90% accuracy.

More »»

2013

S. Duttagupta, Virk, R. S., and Khanapurkar, A., “Performance Extrapolation across Servers”, International CMG Conference 2013. Computer Measurement group, pp. 1-24, 2013.[Abstract]


Page 1. 1 Performance Extrapolation across Servers Subhasri Duttagupta
Page 2. 2 Why do performance extrapolation across servers? What are the techniques for extrapolation? – SPEC-Rates of servers – Single user service-demand based technique What information is required for extrapolation? How the strategies perform for real applications?
Page 3. 3 Why use Performance Extrapolation?
Predict Performance of an application from Test to Production platform
Predict performance for a large number of users – Not enough virtual user licenses Page

More »»

2012

S. Duttagupta and Nambiar, M., “Maximum throughput computation of an application in a multi-tier environment”, 2012 International Symposium on Performance Evaluation of Computer Telecommunication Systems (SPECTS). IEEE, Genoa, Italy, pp. 1-7, 2012.[Abstract]


Performance projection of an application for large number of users involves predicting the maximum throughput that the application can achieve and the maximum number of users it can support. Factors affecting the maximum throughput can include both hardware and software resources of each of the servers associated with the application. In a multi-tier environment, the number of resources affecting the application performance can be quite large. Whenever any of these resources is bottlenecked, i.e., the resource utilization reaches close to 100%, the rate of increase of throughput drops. Further increase in the number of users beyond a certain point may result in reduction in throughput. For any enterprise application that intends to cater to a large number of users, it is desirable to know the maximum throughput it can achieve. This paper proposes a systematic technique for analyzing maximum throughput of any application that can be used irrespective of the test environment or production environment. Our technique computes maximum throughput with more than 95% accuracy in most scenarios. This technique can be useful in reducing the load testing effort and time.

More »»

2012

S. Duttagupta and Virk, R. S., “PerfExt: Performance Extrapolation Tool”, 2012 Fourth International Conference on Computational Intelligence, Modelling and Simulation. IEEE, Kuantan, Malaysia, pp. 369-374, 2012.[Abstract]


Load testing of IT applications is fraught with the challenges of time to market, quality of results, high cost of commercial tools, and accurately representing production like scenarios. It would help IT projects to be able to test with a small number of users and extrapolate to scenarios with much larger number of users. This in turn will cut down cycle times and costs and allow for a variety of extrapolations closer to production. We present Perf Ext, a performance extrapolation tool that uses a statistical empirical modeling technique to extrapolate application performance for a large number of users. The tool provides more than 90% accuracy for a range of applications running across a number of hardware servers. The tool allows performance extrapolation of applications with multiple transactions and its performance is compared with that of MVA.

More »»

2012

S. Duttagupta and Nambiar, M., “Performance Extrapolation Using Load Testing Results”, International Journal of Simulation, Systems, Science and Technology, vol. 13. IEEE, Madrid, Spain, pp. 424-429, 2012.[Abstract]


Load testing of IT applications faces the challenge of providing high quality test results that would represent the performance in production like scenarios, without incurring high cost of commercial load testing tools. It would help IT projects to be able to test with a small number of users and extrapolate to scenarios with much larger number of users. Such an extrapolation strategy when applied to mixture of application workloads running on a shared server environment must take into consideration application characteristics (CPU/IO intensive, memory bound) as well the server capabilities. The goal is to predict the performance of mixture workload, the maximum throughput offered by the application mix and the maximum number of users supported by the system before the throughput starts degrading. In this paper, we propose an extrapolation strategy that analyses a system workload mix based on its service demand on various resources and extrapolates its performance using simple empirical modeling techniques. Moreover, its ability to extrapolate throughput of an application mixture even if there is a change in the mixture, can help in capacity planning of the system.

More »»

2011

S. Duttagupta and Nambiar, M., “Performance Extrapolation for Load Testing Results of Mixture of Applications”, 2011 UKSim 5th European Symposium on Computer Modeling and Simulation. IEEE, Madrid, Spain, pp. 424-429, 2011.[Abstract]


Load testing of IT applications faces the challenge of providing high quality test results that would represent the performance in production like scenarios, without incurring high cost of commercial load testing tools. It would help IT projects to be able to test with a small number of users and extrapolate to scenarios with much larger number of users. Such an extrapolation strategy when applied to mixture of application workloads running on a shared server environment must take into consideration application characteristics (CPU/IO intensive, memory bound) as well the server capabilities. The goal is to predict the performance of mixture workload, the maximum throughput offered by the application mix and the maximum number of users supported by the system before the throughput starts degrading. In this paper, we propose an extrapolation strategy that analyses a system workload mix based on its service demand on various resources and extrapolates its performance using simple empirical modeling techniques. Moreover, its ability to extrapolate throughput of an application mixture even if there is a change in the mixture, can help in capacity planning of the system.

More »»

2011

S. Duttagupta and Mansharamani, R., “Extrapolation Tool For Load Testing Results”, International Symposium on Performance Evaluation of Computer & Telecommunication Systems (SPECTS). IEEE, The Hague, Netherlands, pp. 69-76, 2011.[Abstract]


Load testing of IT applications is fraught with the challenges of time to market, quality of results, high cost of commercial tools, and accurately representing production like scenarios. It would help IT projects to be able to test with a small number of users and extrapolate to scenarios with much larger number of users. This in turn will cut down cycle times and costs and allow for a variety of extrapolations closer to production. We present a simple extrapolation technique based on statistical empirical modeling, which we have found to be more than 90% accurate across a range of applications running across a number of hardware servers. The technique has currently been validated for scenarios where the hardware is the bottleneck and is extensible to a wider range of scenarios as well.

More »»

2011

S. Duttagupta, Ramamritham, K., and Kulkarni, P., “Tracking Dynamic Boundary Fronts Using Sensor Networks”, IEEE Transactions on Parallel and Distributed Systems, vol. 22. IEEE, pp. 1766-1774, 2011.

2009

S. Duttagupta, Ramamritham, K., and Kulkarni, P., “Tracking Dynamic Fronts using Sensor Network”. 2009.[Abstract]


We examine the problem of tracking dynamic boundaries occurring in natural phenomena using a network of range sensors. Two main challenges of the boundary tracking problem are accurate boundary estimation from noisy observations and continuous tracking of the boundary. We propose Dynamic Boundary Tacking (DBTR), an algorithm that combines the spatial estimation and temporal estimation techniques to effectively track a dynamic boundary. The regression-based spatial estimation technique determines discrete points on the boundary and estimates a confidence band around the entire boundary. In addition, a Kalman Filter-based temporal estimation technique tracks changes in the boundary and aperiodically updates the spatial estimation to meet accuracy requirements. DBTR, provides a low communication overhead solution to track boundaries without requiring prior knowledge about the dynamics. Experimental results demonstrate the effectiveness of our algorithm; estimated confidence bands indicate a loss of coverage of less than 2 − 5% for a variety of boundaries with different spatial characteristics.

More »»

2008

S. Duttagupta, Ramamritham, K., and Kulkarni, P., “Tracking Dynamic Boundary Fronts Using Range Sensors”, The fifth European Conference on Wireless Sensor Networks. Springer Berlin/Heidelberg, Bologna, Italy, pp. 125-140, 2008.[Abstract]


We examine the problem of tracking dynamic boundaries occurring in natural phenomena using sensor networks. Remotely
placed sensor nodes produce noisy measurements of various points on the boundary using range-sensing. Two main challenges
of the boundary tracking problem are energy-efficient boundary estimations from noisy observations and continuous tracking of
the boundary. We propose a novel approach which uses discrete estimations of points on the boundary using a regression-based
spatial estimation technique and a smoothing interpolation scheme to estimate a confidence band around the entire boundary. In
addition, a Kalman Filter-based temporal estimation is used to help selectively refresh the estimated boundary at a point only
if the boundary is predicted to move out of the previous estimated intervals at that point. An algorithm for dynamic boundary
tracking (DBTR), the combination of temporal estimation with an aperiodically updated spatial estimation, allows us to provide
a low overhead solution to track dynamic boundaries that does not require prior knowledge about the nature of the dynamics.
Experimental results demonstrate the effectiveness of our algorithm and estimated confidence bands achieve loss of coverage of
less than 2% for smooth boundaries.

More »»

2006

K. Ramamritham, Bahuman, A., Duttagupta, S., Bahuman, C., and Balasundaram, S., “Innovative ICT Tools for Information Provision in Agricultural Extension (December 2005)”, 2006 International Conference on Information and Communication Technologies and Development. IEEE, Berkeley, CA, USA, pp. 34-38, 2006.[Abstract]


aAQUA is an online multilingual, multimedia agricultural portal for disseminating information from and to the grassroots of the Indian agricultural community. aAQUA simultaneously addresses two major challenges in farmer outreach programs - geographic reach and customized delivery. It answers farmers queries based on the location, season, crop and other information provided by farmers. aAQUA makes use of novel database systems and information retrieval techniques like intelligent caching, offline access with intermittent synchronization, semantic-based search, etc. Agricultural content repositories (digital library), Agri-price information (Bhav Puchiye), farmer schemes and various operations support databases (aAQUA-QoS) have also emerged from the experience of aAQUA deployments. aAQUA's large scale deployment provides avenues for researchers to contribute in the areas of knowledge management, cross-lingual information retrieval, and providing accessible content for rural populations. Apart from agriculture, aAQUA can be configured and customized for expert advice over mobile networks and the Internet in education, Healthcare and other domains of interest to a developing population. This paper will showcase the utility of various component databases built into aAQUA to enhance the QoS delivered to rural populations

More »»

2006

S. Duttagupta, Ramamritham, K., and Ramanathan, P., “Distributed Boundary Estimation using Sensor Networks”, 2006 IEEE International Conference on Mobile Ad Hoc and Sensor Systems. IEEE, Vancouver, BC, Canada, pp. 316-325, 2006.[Abstract]


We examine the problem of determining boundaries occurring in natural phenomena using sensor networks. Sensor nodes remotely collect data about various points on the boundary. From this data, we estimate the boundary along with the confidence intervals using a regression relationship among sensor locations and the distances to the boundary. The confidence intervals are guaranteed to be narrower than a specified maximum width. Our distributed boundary estimation strategy uses a hierarchical structure of clusters of sensor nodes and requires 20-50% less messages as compared to a centralized scheme. The computed intervals show desired coverage of the true boundary points. Further, motivated by the practical need to estimate the boundary with a minimum number of sensors, we develop an adaptive approach for turning sensors on and off. The number of ON sensors in this scheme is only about 15% more than what a practical Oracle needs, to evaluate the boundary and confidence intervals around it. Our algorithms are also evaluated using data from real sensors on a testbed

More »»

2006

S. Duttagupta, Ramamritham, K., and B, A., “aAQUA: A Database-Backended Multilingual, Multimedia Community Forum”, Proceedings of the 2006 ACM SIGMOD international conference on Management of data. ACM, New York, USA, pp. 784-786, 2006.[Abstract]


aAQUA is an online multilingual, multimedia Agricultural portal for disseminating information from and to rural communities. It answers farmers’ queries based on the location, season, crop and other information provided by farmers. aAQUA makes use of novel database systems and information retrieval techniques like intelligent caching, offline access with intermittent synchronization, semantic-based search, etc. aAQUA’s large scale deployment provides avenues for researchers to contribute in the areas of knowledge management, cross-lingual information retrieval, and providing accessible content for rural populations. Apart from agriculture, aAQUA can be configured and customized for expert advice in education, healthcare and other domains of interest to a developing population. This demonstration showcases the utility of various component DB/IR technologies built into aAQUA to enhance the QoS delivered to rural populations.

More »»

2006

S. Duttagupta, Ramamritham, K., and Ramanathan, P., “Distributed Boundary Tracking Using Sensor Networks”, The 3rd IEEE International Conference on Mobile Adhoc and Sensor Systems (MASS). IEEE, Vancouver, Canada, pp. 316-325, 2006.[Abstract]


We examine the problem of determining boundaries occurring in natural phenomena using sensor networks. Sensor nodes remotely collect data about various points on the boundary. From this data, we estimate the boundary along with the confidence intervals using a regression relationship among sensor locations and the distances to the boundary. The confidence intervals are guaranteed to be narrower than a specified maximum width. Our distributed boundary estimation strategy uses a hierarchical structure of clusters of sensor nodes and requires 20-50% less messages as compared to a centralized scheme. The computed intervals show desired coverage of the true boundary points. Further, motivated by the practical need to estimate the boundary with a minimum number of sensors, we develop an adaptive approach for turning sensors on and off. The number of ON sensors in this scheme is only about 15% more than what a practical Oracle needs, to evaluate the boundary and confidence intervals around it. Our algorithms are also evaluated using data from real sensors on a testbed

More »»

Publication Type: Journal Article

Year of Publication Title

2016

M. Nambiar, Kattepur, A., Bhaskaran, G., Singhal, R., and Duttagupta, S., “Model Driven Software Performance Engineering: Current Challenges and Way Ahead”, SIGMETRICS Performance Evaluation Review, vol. 43, pp. 53–62, 2016.[Abstract]


Performance model solvers and simulation engines have been around for more than two decades. Yet, performance modeling has not received wide acceptance in the software industry, unlike pervasion of modeling and simulation tools in other industries. This paper explores underlying causes and looks at challenges that need to be overcome to increase utility of performance modeling, in order to make critical decisions on software based products and services. Multiple real-world case studies and examples are included to highlight our viewpoints on performance engineering. Finally, we conclude with some possible directions the performance modeling community could take, for better predictive capabilities required for industrial use.

More »»

2011

S. Duttagupta, Ramamritham, K., and Kulkarni, P., “Tracking Dynamic Boundaries Using Sensor Network”, IEEE Transactions on Parallel and Distributed Systems, vol. 22, pp. 1766-1774, 2011.[Abstract]


We examine the problem of tracking dynamic boundaries occurring in natural phenomena using a network of range sensors. Two main challenges of the boundary tracking problem are accurate boundary estimation from noisy observations and continuous tracking of the boundary. We propose Dynamic Boundary Tracking (DBTR), an algorithm that combines the spatial estimation and temporal estimation techniques. The regression-based spatial estimation technique determines discrete points on the boundary and estimates a confidence band around the entire boundary. In addition, a Kalman Filter-based temporal estimation technique tracks changes in the boundary and aperiodically updates the spatial estimate to meet accuracy requirements. DBTR provides a low energy solution compared to similar periodic update techniques to track boundaries without requiring prior knowledge about the dynamics. Experimental results demonstrate the effectiveness of our algorithm; estimated confidence bands indicate a loss of coverage of less than 2 to 5 percent for a variety of boundaries with different spatial characteristics.

More »»

2007

A. Bahuman, Bahuman, C., Baru, M., Duttagupta, S., and Ramamritham, K., “Developmental Informatics at IIT Bombay”, SIGMOD Rec., vol. 36, pp. 47–53, 2007.[Abstract]


IIT Bombay's Developmental Informatics Lab is a cross disciplinary group consisting of 6 faculty, 30 research staff and several students. The lab is working towards increasing access to information -- through the use of internet and communication technologies -- to communities in the developing world especially rural and small town India. The lab is supported by Indian Government funding sources as well as corporate and multi-lateral agencies to solve technical problems in local communities in sustainable ways. This paper focuses on two mature projects of the lab -- one caters to Indian farmers while another helps with the education of tribal populations.

More »»

2004

K. Ramamritham, Bahuman, A., Kumar, R., Chand, A., Duttagupta, S., Kumar, G. V. Raja, and Rao, C., “aAQUA: A Multilingual, Multimedia Forum for the Community”, IEEE International Conference on Multimedia and Expo, vol. 3, 2004.[Abstract]


aAQUA is an online multilingual, multimedia Question and Answer based community forum for disseminating information from and to the grassroots of the Indian Community. Arising out of this forum is development of content in one’s local language. Additionally, the content is more participative and, therefore, more localized in terms of needs and requirements, issues and solutions.

More »»

Publication Type: Book Chapter

Year of Publication Title

2003

K. Ramamritham, Duttagupta, S., Joshi, A., Mathur, G., and Vilankar, T., “An Interface-Driven Approach to Information Provision for Wired and Wireless Customers”, in Mobile Computing, Hrushikesha Mohanty and Ratan K. Ghosh (ed.), Allied Publishers, 2003, pp. 102-109.