Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Author: search.filters.author.Ravi, A.

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    A parallel fuzzy C means algorithm for brain tumor segmentation on multiple MRI images
    (Springer Verlag service@springer.de, 2013) Ravi, A.; Suvarna, A.; D'Souza, A.; Guddeti, G.; Megha
    The Fuzzy C Means (FCM) algorithm has been extensively used in medical image segmentation. But for large data sets the convergence of the FCM algorithm is time consuming and also requires considerable amount of memory. In some real time applications, like Content Based Medical Image Retrieval (CBIR) systems, there is a need to segment a large volume of brain MRI images offline. In this paper, we present an efficient method to cluster data points of all the images at once. The gray level histogram is used in the FCM algorithm to minimize the time for segmentation and the space required. A parallel approach is then applied to further reduce the computation time. The proposed method is found to be almost twice as fast as conventional FCM. © 2013 Springer.
  • No Thumbnail Available
    Item
    A software architecture for a fully decentralized peer to peer system
    (Institute of Electrical and Electronics Engineers Inc., 2015) Ravi, A.; Meghana, I.S.; Chandrasekaran, K.
    In a peer to peer system, each entity needs some services from other entities in the network, and is capable of providing services to other entities in the network. For the system to work each entity has to contribute at least as much as it is receiving. But for this to happen, since the services requested and offered are different across entities, the relative values of each service have to be determined. The relative value of a resource must depend on how much of it is demanded and how much of it is available on the network. A separation of concerns approach in such systems will have to be devised keeping in mind the fact that any concern that the node sets apart as the service providing node's will have to be handled by it when it is acting as the service provider. Furthermore, the distribution of work is also to be handled. All this has to be done without compromising on the quality of service. This paper defines a software architecture for a pure peer to peer system, which uses network science to optimize the overlay network, thereby improving quality of service as well as fault tolerance. © 2015 IEEE.
  • No Thumbnail Available
    Item
    Collision Resolution of VANET Nodes for TDMA MAC Protocol
    (Institute of Electrical and Electronics Engineers Inc., 2023) Gubbi, A.V.; Ravi, A.; Reddy, P.H.; Chandavarkar, B.R.
    TDMA is a channelisation MAC protocol that is advantageous in Vehicular Ad hoc Networks(VANETs) to schedule and control the access to shared communication channels, so that multiple vehicles or nodes can transmit and receive data without interfering with each other. However, when multiple nodes transmit data at the same time slot, a collision can occur, and may result in loss of data or data corruption. This paper aims to investigate and propose an improved collision resolution mechanism that improves the network's throughput and reduces packet loss. The goal is to ensure efficient and reliable communication among nodes in VANETs, which find various applications in emerging technologies. © 2023 IEEE.