Prabavathy Balasundaram
Research Subjects
Prabavathy Balasundaram has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
Chitra Babu
Anna Univ, Dept Comp Sci & Engn, Chennai, Tamil Nadu, India
3 shared publicationsPradeep Ganesh
Department of Computer Science and Engineering, Sri Sivasubramaniya Nadar College of Engineering, Chennai, Tamil Nadu, India
1 shared publicationPradeep Rengaswamy
IIT Kharagpur, Dept Comp Sci & Engn, Kharagpur, W Bengal, India
1 shared publicationPravinkrishnan K
Department of Computer Science and Engineering, Sri Sivasubramaniya Nadar College of Engineering, Chennai, Tamil Nadu, India
1 shared publicationRahul Kumar Mukesh
Department of Computer Science and Engineering, Sri Sivasubramaniya Nadar College of Engineering, Chennai, Tamil Nadu, India
1 shared publicationSubha Devi M
Department of Computer Science and Engineering, SSN College of Engineering, Kalavakkam, Tamil Nadu 603110, India
1 shared publication
Latest Publications
- Open Access
- 15 June 2024
- Published by EMITTER International Journal of Engineering Technology in EMITTER International Journal of Engineering Technology
- Vol. 12 (1) , 62-89
A Novel Technology Stack for Automated Road Quality Assessment Framework using Deep Learning Techniques
Road infrastructure plays a pivotal role in supporting societal, economic, and cultural progress. The capacity of a road refers to its ability to handle vehicular volume. Inadequate road capacity and the presence of defects like potholes and cracks result in suboptimal travel conditions and pose significant safety risks for drivers, cyclists, and pedestrians. The regular evaluation of these road quality aspects is essential for effective maintenance. However, current methods for assessing road capacity are time-consuming, subjective, and heavily reliant on manual labor. Moreover, existing deep learning-based approaches for detecting road defects often lack accuracy. To overcome these challenges, a fully automated and accurate system for evaluating road quality is imperative. Thus, the objective of this research work is to propose a novel technology stack for a comprehensive Automated Road Quality Assessment (ARQA) framework designed to assess road quality. The experimental findings demonstrate that the suggested vehicle detection and pothole detection methods work effectively and exhibit enhancements of 18% and 6%, respectively, in comparison to existing approaches.
- 15 June 2024
- Published by EMITTER International Journal of Engineering Technology in EMITTER International Journal of Engineering Technology
- Vol. 12 (1) , 62-89
Open AccessA Novel Technology Stack for Automated Road Quality Assessment Framework using Deep Learning Techniques
Road infrastructure plays a pivotal role in supporting societal, economic, and cultural progress. The capacity of a road refers to its ability to handle vehicular volume. Inadequate road capacity and the presence of defects like potholes and cracks result in suboptimal travel conditions and pose significant safety risks for drivers, cyclists, and pedestrians. The regular evaluation of these road quality aspects is essential for effective maintenance. However, current methods for assessing road capacity are time-consuming, subjective, and heavily reliant on manual labor. Moreover, existing deep learning-based approaches for detecting road defects often lack accuracy. To overcome these challenges, a fully automated and accurate system for evaluating road quality is imperative. Thus, the objective of this research work is to propose a novel technology stack for a comprehensive Automated Road Quality Assessment (ARQA) framework designed to assess road quality. The experimental findings demonstrate that the suggested vehicle detection and pothole detection methods work effectively and exhibit enhancements of 18% and 6%, respectively, in comparison to existing approaches.
- 29 June 2023
- Published by ICI Bucharest in Revista Română de Informatică şi Automatică
- Vol. 33 (2) , 23-34
Telepulse: A Novel Scalable Serverless Framework for Vehicle Telematics using Microsoft Azure Cloud Service
- 29 June 2023
- Published by ICI Bucharest in Revista Română de Informatică şi Automatică
- Vol. 33 (2) , 23-34
Telepulse: A Novel Scalable Serverless Framework for Vehicle Telematics using Microsoft Azure Cloud Service
- Open Access
- 18 September 2019
- Published by The Scientific and Technological Research Council of Turkey (TUBITAK-ULAKBIM) - DIGITAL COMMONS JOURNALS in Turkish Journal of Electrical Engineering and Computer Sciences
- Vol. 27 (5) , 3994-4008
A distributed load balancing algorithm for deduplicated storage
- 18 September 2019
- Published by The Scientific and Technological Research Council of Turkey (TUBITAK-ULAKBIM) - DIGITAL COMMONS JOURNALS in Turkish Journal of Electrical Engineering and Computer Sciences
- Vol. 27 (5) , 3994-4008
Open AccessA distributed load balancing algorithm for deduplicated storage
- 18 March 2016
- Published by Oxford University Press (OUP) in The Computer Journal
- Vol. 60 (3) , 444-456
Improving Read Throughput of Deduplicated Cloud Storage using Frequent Pattern-Based Prefetching Technique
In a cloud storage, while deduplication enables optimal storage space utilization, it also incurs a substantial overhead in maintaining the metadata, namely, the Fingerprint Index and the File Recipe. As this metadata is huge, it has to be stored in the disk which causes considerable read-latency in Deduplicated Cloud Storage (DCS). In order to improve this read-latency, it would be highly beneficial to prefetch the relevant fingerprints in a cache. Many existing research solutions have utilized either the spatial locality or the similarity among the files to prefetch the relevant fingerprints. However, the DCS that has been designed and implemented in this paper is intended to cater to non-backup workloads that do not exhibit significant spatial locality or similarity among the files. Hence, this paper proposes a suitable alternative prefetching approach that mines the pattern of client read accesses to find the most frequently accessed files. The proposed prefetching approach has been implemented and incorporated in the DCS. The experimental investigations indicate that the proposed prefetching approach improves the cache hit rates by 140% and increases the read throughput by 88% when compared with the Extreme Binning approach (Bhagwat, D., Eshghi, K. Long, D.D.E. and Lillibridge, M. (2009) Extreme Binning: Scalable, Parallel Deduplication for Chunk-based File Backup. Proc. MASCOTS'09, London, UK, September 21–23, pp. 1–9. IEEE) while incurring only a marginal computational overhead of 1.7 s.
- 18 March 2016
- Published by Oxford University Press (OUP) in The Computer Journal
- Vol. 60 (3) , 444-456
Improving Read Throughput of Deduplicated Cloud Storage using Frequent Pattern-Based Prefetching Technique
In a cloud storage, while deduplication enables optimal storage space utilization, it also incurs a substantial overhead in maintaining the metadata, namely, the Fingerprint Index and the File Recipe. As this metadata is huge, it has to be stored in the disk which causes considerable read-latency in Deduplicated Cloud Storage (DCS). In order to improve this read-latency, it would be highly beneficial to prefetch the relevant fingerprints in a cache. Many existing research solutions have utilized either the spatial locality or the similarity among the files to prefetch the relevant fingerprints. However, the DCS that has been designed and implemented in this paper is intended to cater to non-backup workloads that do not exhibit significant spatial locality or similarity among the files. Hence, this paper proposes a suitable alternative prefetching approach that mines the pattern of client read accesses to find the most frequently accessed files. The proposed prefetching approach has been implemented and incorporated in the DCS. The experimental investigations indicate that the proposed prefetching approach improves the cache hit rates by 140% and increases the read throughput by 88% when compared with the Extreme Binning approach (Bhagwat, D., Eshghi, K. Long, D.D.E. and Lillibridge, M. (2009) Extreme Binning: Scalable, Parallel Deduplication for Chunk-based File Backup. Proc. MASCOTS'09, London, UK, September 21–23, pp. 1–9. IEEE) while incurring only a marginal computational overhead of 1.7 s.