Conference Papers

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

Browse

Subject: search.filters.subject.fuzzy logic

Search Results

Now showing 1 - 4 of 4
  • No Thumbnail Available
    Item
    An approach for character segmentation of handwritten Bangla and devanagari script
    (Institute of Electrical and Electronics Engineers Inc., 2015) Bhattad, A.J.; Chaudhuri, B.B.
    In this paper a scheme for segmentation of unconstrained handwritten Devanagari and Bangla words into characters and its sub-parts is proposed. Firstly, the region above headline is identified by counting the number of white to black transitions in each row, which followed by its separation. Then the characters are segmented using fuzzy logic. For each column, the inputs to the fuzzy system are the location of first white pixel, thickness of the first black stroke, count of white pixels, and the run length count of white pixels. © 2015 IEEE.
  • No Thumbnail Available
    Item
    Cloud performance evaluation using fuzzy logic
    (Institute of Electrical and Electronics Engineers Inc., 2015) Saxena, G.; Nanath, K.
    Cloud computing is the latest form of evolution of distributed computing which eradicates the need to own the expensive hardware resources, as the resources can be easily obtained on cloud in pay-per-usage manner. This proves to be very cost efficient to users as they no longer need to depend on the hardware resources to satisfy their needs. For measuring cloud performance there exist a few approaches, yet there is scope for experimenting and developing new approaches for evaluating cloud efficiency. This paper attempts to measure cloud performance by using fuzzy logic by taking into consideration different performance parameters of the cloud. A metric for analyzing the performance of the cloud is derived upon, by considering various performance parameters and proves to be helpful in comparing various cloud services. The method proposed in this paper is very flexible and easy to understand. The results provide useful information and directions for further research in this new emerging field. © 2015 IEEE.
  • No Thumbnail Available
    Item
    Dynamic Resource Allocation Using Fuzzy Prediction System
    (Institute of Electrical and Electronics Engineers Inc., 2018) Raghunath, B.R.; Annappa, B.
    Virtualization is the main technology in the large scale data centers with which resources are shared among different application running on different VMs. Virtualization through virtual machine monitor (VMM) like Xen only provides resource isolation among co-located VMs. However, it has been shown that resource isolation does not imply performance isolation between VMs. Hence it necessitates on-demand allocation of the physical shared resources to individual VM as per their dynamic requirements to satisfy the SLA between customer and cloud provider. To do this efficiently future resource utilization is predicted using fuzzy logic based prediction. To avoid underestimation prediction errors due to spikes in the workload, the predicted values are padded with proper value and immediately resource caps are raised. The resource conflict is resolved locally if resources are available otherwise migration is triggered. This scheme allocates resources efficiently and reduces the response time as compared to static allocation. The resource saving with proposed method is around 30-40% and around 10-20% performance improvement in terms of response time of an application. © 2018 IEEE.
  • No Thumbnail Available
    Item
    Intelligent Rush Hour Management in Metro Station
    (Institute of Electrical and Electronics Engineers Inc., 2024) Anandu, V.P.; Vinatha Urundady, U.; Bharath, Y.K.; Neethu, V.S.
    Addressing the issue of high crowd density in metro stations during rush hours is indeed a significant challenge, but innovative solutions can help enhance passenger experience and streamline the boarding process. The goal is to implement a Smart Crowd Management System that provides real-time information about congestion levels in metro stations and estimates the time required for passengers to board trains during peak hours. The implementation of a Smart Crowd Management System can significantly improve the passenger experience in metro stations, making the commute more efficient and less stressful during rush hours. This proposal outlines a holistic approach combining sensor technology, machine learning, digital communication, and mobile applications to address the challenges of crowd density in metropolitan cities like Delhi. In this work, an intelligent system is developed with MATLAB/Simulink interface having fuzzy logic and neural network classifier to indicate expected time of departure and degree of congestion in the station. The outputs are displayed in TFT screen, LEDs and ThingSpeak-IoT platform. © 2024 IEEE.