T. Gnanasekaran
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
T. Gnanasekaran has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- T. D. Subash
Department of Electrical and Electronics Engineering, Mangalam College of Engineering, Kerala, India
4 shared publications - Priya Baldoss
Anna Univ, Informat & Commun Engn Dept, Chennai, Tamil Nadu, India
3 shared publications - T. D. Subash
School of Marine Engineering Equipment, Zhejiang Ocean University, Zhoushan, Zhejiang, China
3 shared publications - B. V. Santhosh Krishna
New Horizon College of Engineering
2 shared publications C. Divya
Centre for IT & Eng, Manonmaniam Sundaranar University, 627012, India
2 shared publications- J. Ajayan
SR University
2 shared publications
Latest Publications
- 12 April 2024
- Published by IGI Global Scientific Publishing
- p. 19-34
Technical Challenges Faced in Designing Frameworks for AI-Based Earth Monitoring Systems
In an era defined by unprecedented advancements in technology, AI-based Earth monitoring systems have emerged as transformative tools for understanding and safeguarding our planet. This chapter navigates through the intricacies of AI-based Earth monitoring systems, from the critical technical challenges of data integration, quality, and availability to the crucial interdisciplinary collaborations that hold the key to their success. Improving an AI-based Earth tracking system affords quite a number of particular technical demanding situations. Data integration stands out as a pivotal technical challenge. Addressing data integration, quality, and availability, as well as communication gaps, is critical for their success. When it comes to implementing this device inside the actual world, the scalability of the device and capability protection dangers ought to be addressed. Therefore, designing a framework for an AI-based earth-tracking system requires successfully resolving a diffusion of technically demanding situations. Request access from your librarian to read this chapter's full text.
- 12 April 2024
- Published by IGI Global Scientific Publishing
- p. 19-34
Technical Challenges Faced in Designing Frameworks for AI-Based Earth Monitoring Systems
In an era defined by unprecedented advancements in technology, AI-based Earth monitoring systems have emerged as transformative tools for understanding and safeguarding our planet. This chapter navigates through the intricacies of AI-based Earth monitoring systems, from the critical technical challenges of data integration, quality, and availability to the crucial interdisciplinary collaborations that hold the key to their success. Improving an AI-based Earth tracking system affords quite a number of particular technical demanding situations. Data integration stands out as a pivotal technical challenge. Addressing data integration, quality, and availability, as well as communication gaps, is critical for their success. When it comes to implementing this device inside the actual world, the scalability of the device and capability protection dangers ought to be addressed. Therefore, designing a framework for an AI-based earth-tracking system requires successfully resolving a diffusion of technically demanding situations. Request access from your librarian to read this chapter's full text.
- 12 April 2024
- Published by IGI Global Scientific Publishing
- p. 165-185
An Early Warning System for Predicting Earthquakes
Earthquakes have long pose a vast danger to human existence and infrastructure. Over time, sizeable studies have been performed in the field of earthquake prediction, mainly on the improvement of an early warning machine. This essay aims to discover the background of earthquake prediction, the want for an early warning system, and the advancements made in this vicinity to mitigate the impact of seismic occasions. This chapter offers the development of a complicated and reliable early warning machine that utilizes a combination of seismic information analysis and device learning techniques. The goals of an early warning system for predicting earthquakes are to offer timely statistics to permit suitable actions, reduce the lack of existence and assets, and foster resilience in affected groups. The advancements in era and studies have provided us with the gear and expertise essential to construct a robust and reliable system that can save limitless lives and limit harm to infrastructure.
- 12 April 2024
- Published by IGI Global Scientific Publishing
- p. 165-185
An Early Warning System for Predicting Earthquakes
Earthquakes have long pose a vast danger to human existence and infrastructure. Over time, sizeable studies have been performed in the field of earthquake prediction, mainly on the improvement of an early warning machine. This essay aims to discover the background of earthquake prediction, the want for an early warning system, and the advancements made in this vicinity to mitigate the impact of seismic occasions. This chapter offers the development of a complicated and reliable early warning machine that utilizes a combination of seismic information analysis and device learning techniques. The goals of an early warning system for predicting earthquakes are to offer timely statistics to permit suitable actions, reduce the lack of existence and assets, and foster resilience in affected groups. The advancements in era and studies have provided us with the gear and expertise essential to construct a robust and reliable system that can save limitless lives and limit harm to infrastructure.
- 29 July 2019
- Published by Springer Nature in Peer-to-Peer Networking and Applications
- Vol. 13 (2) , 717-728
To optimize load of hybrid P2P cloud data-center using efficient load optimization and resource minimization algorithm
- 29 July 2019
- Published by Springer Nature in Peer-to-Peer Networking and Applications
- Vol. 13 (2) , 717-728
To optimize load of hybrid P2P cloud data-center using efficient load optimization and resource minimization algorithm
- 1 June 2019
- Published by American Scientific Publishers in Journal of Medical Imaging and Health Informatics
- Vol. 9 (5) , 1000-1010
Unsupervised Automated Retinal Vessel Extraction Framework Using Enhanced Filtering and Hessian Based Method with Hysteresis Thresholding
The retinal blood vessels act as a diagnostic indicator of several severe pathologies like Diabetes, Hypertension, and Stroke. Fundus photograph is the most common modality for examination of eyes. Medical experts use fundus examination during eye diagnosis. However, the quality as well as resolution of fundus images are rapidly increasing, resulting in many challenges. In this paper, an unsupervised automated framework for the extraction of retinal vessels by using enhanced filtering and hessian-based method with hysteresis thresholding is presented. In this framework, we have considered two publicly available datasets, DRIVE and DR-HAGIS consisting of more pathological high-resolution images for experimentation. In this framework, there are four major phases: (i) Pre-processing phase for the extraction of green channel and contrast enhancement; (ii) Vessel enhancement phase for enhancement of wide and thin vessels; (iii) Vessel detection phase for the extraction of vessels; (iv) Post-processing phase for filling the holes and to remove isolated pixels. Our method achieves 0.9601 accuracy on DRIVE dataset and 0.9484, 0.9496, 0.9487, 0.9480 on DR-HAGIS with Glaucoma, Hypertension, Diabetic Retinopathy, Age-Related Macular Degeneration (AMD) images respectively. Our results manifest that the proposed framework performs fine at extracting blood vessels from pathological images in addition to healthy retinal images and is comparable with existing methods.
- 1 June 2019
- Published by American Scientific Publishers in Journal of Medical Imaging and Health Informatics
- Vol. 9 (5) , 1000-1010
Unsupervised Automated Retinal Vessel Extraction Framework Using Enhanced Filtering and Hessian Based Method with Hysteresis Thresholding
The retinal blood vessels act as a diagnostic indicator of several severe pathologies like Diabetes, Hypertension, and Stroke. Fundus photograph is the most common modality for examination of eyes. Medical experts use fundus examination during eye diagnosis. However, the quality as well as resolution of fundus images are rapidly increasing, resulting in many challenges. In this paper, an unsupervised automated framework for the extraction of retinal vessels by using enhanced filtering and hessian-based method with hysteresis thresholding is presented. In this framework, we have considered two publicly available datasets, DRIVE and DR-HAGIS consisting of more pathological high-resolution images for experimentation. In this framework, there are four major phases: (i) Pre-processing phase for the extraction of green channel and contrast enhancement; (ii) Vessel enhancement phase for enhancement of wide and thin vessels; (iii) Vessel detection phase for the extraction of vessels; (iv) Post-processing phase for filling the holes and to remove isolated pixels. Our method achieves 0.9601 accuracy on DRIVE dataset and 0.9484, 0.9496, 0.9487, 0.9480 on DR-HAGIS with Glaucoma, Hypertension, Diabetic Retinopathy, Age-Related Macular Degeneration (AMD) images respectively. Our results manifest that the proposed framework performs fine at extracting blood vessels from pathological images in addition to healthy retinal images and is comparable with existing methods.
- 1 February 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 311-315
An Assessment Survey of Cloud Simulators for Fault Identification
Cloud computing is a large set of logical computational resources accessible via internet. Cloud computing offers services to obtain coherence, scalability, economy subscale with maximum efficiency and resource optimization. Fault tolerance is the characteristic that enables the system to stay operating and adhere SLA even when the in the system faults and failures. For a system to be fault tolerant the interval of fault identification and removal must be minimum to follow the QoS requirements. virtualization in the Data center can assist in fault prediction that makes the system fault tolerant. A cloud simluator is an extensible tool to analyse, evaluate and measure the system performance of the cloud cloud applications to satisfy the QoS provisions. This paper deals with the survey of the various cloud simulators with emphasis on using CloudSim
- 1 February 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 311-315
An Assessment Survey of Cloud Simulators for Fault Identification
Cloud computing is a large set of logical computational resources accessible via internet. Cloud computing offers services to obtain coherence, scalability, economy subscale with maximum efficiency and resource optimization. Fault tolerance is the characteristic that enables the system to stay operating and adhere SLA even when the in the system faults and failures. For a system to be fault tolerant the interval of fault identification and removal must be minimum to follow the QoS requirements. virtualization in the Data center can assist in fault prediction that makes the system fault tolerant. A cloud simluator is an extensible tool to analyse, evaluate and measure the system performance of the cloud cloud applications to satisfy the QoS provisions. This paper deals with the survey of the various cloud simulators with emphasis on using CloudSim
- 1 February 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 307-310
Optimization of Cloud Data Center using CloudSim – A methodology
Cloud computing can be termed as provisioning of computing power, storage, Infrastructure and other resources over the internet as an on-demand pay service. Recent developments in the technological advancement are in the cloud storage, security, fault tolerances, load balancing and optimization. Cloud simulator is a tool that assists in modelling different cloud applications. Cloudism offers a simulation framework for modelling and simulation that emphasis more on exploring design issues without factoring cloud infrastructure and services. Load balancing in cloud is a method of allocation of workload across multiple nodes to obtain resource optimization with minimum response time. In this paper the state of the art of the cloud simulations along with an approach implemented using CloudSim3.0 is illustrated.
- 1 February 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 307-310
Optimization of Cloud Data Center using CloudSim – A methodology
Cloud computing can be termed as provisioning of computing power, storage, Infrastructure and other resources over the internet as an on-demand pay service. Recent developments in the technological advancement are in the cloud storage, security, fault tolerances, load balancing and optimization. Cloud simulator is a tool that assists in modelling different cloud applications. Cloudism offers a simulation framework for modelling and simulation that emphasis more on exploring design issues without factoring cloud infrastructure and services. Load balancing in cloud is a method of allocation of workload across multiple nodes to obtain resource optimization with minimum response time. In this paper the state of the art of the cloud simulations along with an approach implemented using CloudSim3.0 is illustrated.
- Open Access
- 8 June 2018
- Published by Science Publishing Corporation in International Journal of Engineering & Technology
- Vol. 7 (2.33) , 67-70
Review on failure forecast in cloud for a fault tolerant system
Cloud Computing is an increasingly popular computer paradigm constituting a large infrastructure involving storage, memory, servers and applications accessible via computer network. The cloud system design aims to provide on-demand services with scalability on diverse resources to ensure efficient resource utilization in addition to effectiveness. As cloud is a service-oriented infrastructure, it is critically imperative that the system is highly reliable to meet the Service Level Agreement (SLA). To achieve reliability, cloud requires a very efficient fault tolerance mechanism. Serviceability and reliability is impacted by any failure in the system. Prior prediction of faults in the system helps in overcoming failures. The Fault Tolerance in cloud involves ascertaining the resource fitness to execute scheduled task. The process involves prior screening of resources against various tasks as part of scheduling process. The scheduling process relies significantly on the virtualization of resources to maintain high efficiency.
- 8 June 2018
- Published by Science Publishing Corporation in International Journal of Engineering & Technology
- Vol. 7 (2.33) , 67-70
Open AccessReview on failure forecast in cloud for a fault tolerant system
Cloud Computing is an increasingly popular computer paradigm constituting a large infrastructure involving storage, memory, servers and applications accessible via computer network. The cloud system design aims to provide on-demand services with scalability on diverse resources to ensure efficient resource utilization in addition to effectiveness. As cloud is a service-oriented infrastructure, it is critically imperative that the system is highly reliable to meet the Service Level Agreement (SLA). To achieve reliability, cloud requires a very efficient fault tolerance mechanism. Serviceability and reliability is impacted by any failure in the system. Prior prediction of faults in the system helps in overcoming failures. The Fault Tolerance in cloud involves ascertaining the resource fitness to execute scheduled task. The process involves prior screening of resources against various tasks as part of scheduling process. The scheduling process relies significantly on the virtualization of resources to maintain high efficiency.
- Open Access
- 8 June 2018
- Published by Science Publishing Corporation in International Journal of Engineering & Technology
- Vol. 7 (3.3) , 56-58
State of the art - optimization techniques in cloud environment
A Cloud is a network of a shared pool of configurable and computing resources providing efficient, on-demand pay-as-per-use access. Its main objectives being: Scalability, High availability of resources and to reduce the overhead incurred. Scheduling is the method of determining the order by which the jobs have to be executed. It determines the various tasks that are to be executed in parallel and the efficient resource to carry out the tasks. Load balancing is the method of balancing the load across various resources by fixing a threshold and migrating the tasks to the under loaded resources based on the threshold. Optimization techniques are used to find a finite solution for scheduling of tasks although not optimal. Various optimization techniques are employed based on Cost, CPU utilization and to balance the load. This paper deals with the importance of optimization, the various metrics and constraints associated. A literature survey on the various optimization techniques is also analyzed based on the attributes of the tasks.
- 8 June 2018
- Published by Science Publishing Corporation in International Journal of Engineering & Technology
- Vol. 7 (3.3) , 56-58
Open AccessState of the art - optimization techniques in cloud environment
A Cloud is a network of a shared pool of configurable and computing resources providing efficient, on-demand pay-as-per-use access. Its main objectives being: Scalability, High availability of resources and to reduce the overhead incurred. Scheduling is the method of determining the order by which the jobs have to be executed. It determines the various tasks that are to be executed in parallel and the efficient resource to carry out the tasks. Load balancing is the method of balancing the load across various resources by fixing a threshold and migrating the tasks to the under loaded resources based on the threshold. Optimization techniques are used to find a finite solution for scheduling of tasks although not optimal. Various optimization techniques are employed based on Cost, CPU utilization and to balance the load. This paper deals with the importance of optimization, the various metrics and constraints associated. A literature survey on the various optimization techniques is also analyzed based on the attributes of the tasks.
- 11 April 2018
- Published by Springer Nature
- p. 743-752
Unsupervised Morphological Approach for Retinal Vessel Segmentation
- 11 April 2018
- Published by Springer Nature
- p. 743-752
Unsupervised Morphological Approach for Retinal Vessel Segmentation