Sujata Banerjee
Research Subjects
Sujata Banerjee has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Ashutosh Saxena
Computer Science Department Cornell University
1 shared publication - Brighten Godfrey
UIUC and Broadcom
1 shared publication - Joon-Myung Kang
Hewlett Packard Labs, Palo Alto, CA, USA
1 shared publication - Mario Alfredo Hernández Sánchez
Universidad Autónoma del Estado de Tlaxcala
1 shared publication - Radhika Niranjan Mysore
VMWare Research, Palo Alto, CA, United States of America
1 shared publication - Rauf Izmailov
Applied Communication Sciences
1 shared publication
Latest Publications
- 11 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 18, 1002-1007
An Integrated Approach to Enhance the Prediction of Liver Disease Prognosis
Clustering, a fundamental data analysis technique, involves grouping similar data elements. In the realm of data mining, clustering analysis is a widely employed method, and its effectiveness depends on the choice of clustering algorithm. This study explores various algorithms, including the well-known K-Means, comparing their merits and drawbacks. Emphasis is placed on addressing concerns related to clustering algorithms, such as time complexity and accuracy, with the goal of enhancing performance across diverse contexts, particularly in handling large datasets. The study’s findings, primarily focused on efficiency, are framed in the context of large datasets. Notably, the research delves into three prominent clustering methods—K-Means, FCM, and hierarchical clustering—evaluating their applicability using the Indian Liver Patient dataset. Through rigorous experimentation, our proposed novel approach demonstrates significant enhancements over the traditional K-Means clustering algorithm, underscoring its efficacy and potential. Ultimately, this work contributes to the advancement of healthcare analytics and underscores the vital role of data-driven techniques in advancing global public health through early disease detection.
- 11 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 18, 1002-1007
An Integrated Approach to Enhance the Prediction of Liver Disease Prognosis
Clustering, a fundamental data analysis technique, involves grouping similar data elements. In the realm of data mining, clustering analysis is a widely employed method, and its effectiveness depends on the choice of clustering algorithm. This study explores various algorithms, including the well-known K-Means, comparing their merits and drawbacks. Emphasis is placed on addressing concerns related to clustering algorithms, such as time complexity and accuracy, with the goal of enhancing performance across diverse contexts, particularly in handling large datasets. The study’s findings, primarily focused on efficiency, are framed in the context of large datasets. Notably, the research delves into three prominent clustering methods—K-Means, FCM, and hierarchical clustering—evaluating their applicability using the Indian Liver Patient dataset. Through rigorous experimentation, our proposed novel approach demonstrates significant enhancements over the traditional K-Means clustering algorithm, underscoring its efficacy and potential. Ultimately, this work contributes to the advancement of healthcare analytics and underscores the vital role of data-driven techniques in advancing global public health through early disease detection.
- Open Access
- 10 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 438-451
Murphy: Performance Diagnosis of Distributed Cloud Applications
- 10 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 438-451
Open AccessMurphy: Performance Diagnosis of Distributed Cloud Applications
- 1 March 2020
- Published by Springer Nature in CSI Transactions on ICT
- Vol. 8 (1) , 61-64
Smart programmable networks
- 1 March 2020
- Published by Springer Nature in CSI Transactions on ICT
- Vol. 8 (1) , 61-64
Smart programmable networks
- 1 May 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-9
SLA-verifier: Stateful and quantitative verification for service chaining
Network verification has been recently proposed to detect network misconfigurations. Existing work focuses on the reachability. This paper proposes a framework that verifies the Service Level Agreement (SLA) compliance of the network using static verification. This work proposes a quantitative model and a set of algorithms for verifying performance properties of a network with switches and middleboxes, i.e., service chains. We develop SLA-Verifier and evaluate its efficiency using simulation on real-world data and testbed experiments. To improve the SLA violation detection accuracy, our system uses verification results to optimize online monitoring.
- 1 May 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-9
SLA-verifier: Stateful and quantitative verification for service chaining
Network verification has been recently proposed to detect network misconfigurations. Existing work focuses on the reachability. This paper proposes a framework that verifies the Service Level Agreement (SLA) compliance of the network using static verification. This work proposes a quantitative model and a set of algorithms for verifying performance properties of a network with switches and middleboxes, i.e., service chains. We develop SLA-Verifier and evaluate its efficiency using simulation on real-world data and testbed experiments. To improve the SLA violation detection accuracy, our system uses verification results to optimize online monitoring.
- 1 January 2017
- Published by Optica Publishing Group
- p. W4J.2
Efficient and Verifiable Service Function Chaining in NFV: Current Solutions and Emerging Challenges
The ability to deploy Service Function Chains (SFC) efficiently and correctly is important in Network Functions Virtualization (NFV) infrastructures. This talk discusses the challenges and emerging solutions for scalable instantiation and verification of SFCs.
- 1 January 2017
- Published by Optica Publishing Group
- p. W4J.2
Efficient and Verifiable Service Function Chaining in NFV: Current Solutions and Emerging Challenges
The ability to deploy Service Function Chains (SFC) efficiently and correctly is important in Network Functions Virtualization (NFV) infrastructures. This talk discusses the challenges and emerging solutions for scalable instantiation and verification of SFCs.
- Open Access
- 1 January 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 0743166X,p. 1-13
A Fast Content-Based Data Distribution Infrastructure
We present Sieve - an infrastructure for fast content-based data distribution to interested users. The ability of Sieve to filter and forward high-bandwidth data streams stems from its distributed pipelined architecture. The complex message filtering task is broken-up into a sequence of light-weight filtering components resulting in high end-to-end throughput. Furthermore, since each component is assigned to a node based on its resource constraints, the queue buildup inside the nodes is minimal resulting in low end-to-end latency. Our experimental results based on real system implementation show that Sieve can sustain a throughput of more than 5000 messages per second for 100000 subscriptions with predicates of 10 attributes.
- 1 January 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 0743166X,p. 1-13
Open AccessA Fast Content-Based Data Distribution Infrastructure
We present Sieve - an infrastructure for fast content-based data distribution to interested users. The ability of Sieve to filter and forward high-bandwidth data streams stems from its distributed pipelined architecture. The complex message filtering task is broken-up into a sequence of light-weight filtering components resulting in high end-to-end throughput. Furthermore, since each component is assigned to a node based on its resource constraints, the queue buildup inside the nodes is minimal resulting in low end-to-end latency. Our experimental results based on real system implementation show that Sieve can sustain a throughput of more than 5000 messages per second for 100000 subscriptions with predicates of 10 attributes.