Conference Papers

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

Browse

Subject: search.filters.subject.Convolution Neural Network

Search Results

Now showing 1 - 4 of 4
  • No Thumbnail Available
    Item
    Image Based Tomato Leaf Disease Detection
    (Institute of Electrical and Electronics Engineers Inc., 2019) Kumar, A.; Vani, M.
    Leaf diseases are the major problem in agricultural sector, which affects crop production as well as economic profit. Early detection of diseases using deep learning could avoid such a disaster. Currently, Convolutional Neural Network (CNN) is a class of deep learning which is widely used for the image classification task. We have performed experiments with the CNN architecture for detecting disease in tomato leaves. We trained a deep convolutional neural network using PlantVillage dataset of 14,903 images of diseased and healthy plant leaves, to identify the type of leaves. The trained model achieves test accuracy of 99.25%. © 2019 IEEE.
  • No Thumbnail Available
    Item
    Acoustic Scene Classification using Deep Learning Architectures
    (Institute of Electrical and Electronics Engineers Inc., 2021) V Spoorthy; Mulimani, M.; Koolagudi, S.G.
    Enabling devices to make sense of sound is known as Acoustic Scene Classification (ASC). The analysis of various scenes by applying computational algorithms is known as computational auditory scene analysis. The main aim of this paper is to classify audio recordings based on the scenes/environment in which they are recorded. Deep learning is amongst the recent trends in most of the applications. In this paper, two deep learning algorithms are used to perform the classification of acoustic scenes, namely Convolution Neural Network (CNN) and Convolution-Recurrent Neural Network (CRNN). The model is evaluated on three activation functions, namely, ReLU, LeakyReLU and ELU. The highest recognition accuracy achieved for ASC task is 90.96% from CRNN model. The model performed well on basic convolution architecture with 10.9% improvement from the baseline system of this task. © 2021 IEEE.
  • No Thumbnail Available
    Item
    Impact of Image Augmentation in COVID-19 Detection Using Chest X-Ray Images
    (Institute of Electrical and Electronics Engineers Inc., 2022) Azade, A.; Anand Kumar, M.
    COVID-19 continues to have a devastating impact on people's lives worldwide. In order to combat this condition, it is critical to test affected people in a timely and cost-effective manner. Radiological examination is one of the most efficient ways to attain this goal, with the most widely available and least expensive alternative being a CXR. The artificial intelligence and data science communities have aided in the global response to COVID-19, a novel coronavirus. Detection and diagnosis techniques have focused on developing rapid diagnostic approaches based on chest X-rays and deep learning. In this paper, we have analyzed the impact of augmentation in COVID-19 CXR images with normal lung opacity and viral pneumonia images and presented a model for the detection of COVID-19. © 2022 IEEE.
  • No Thumbnail Available
    Item
    Diabetic Retinopathy Detection Using Novel Loss Function in Deep Learning
    (Springer Science and Business Media Deutschland GmbH, 2024) Singh, S.; Annappa, B.; Dodia, S.
    Globally, the number of diabetics has significantly increased in recent years. Several age groups are affected. Diabetic Retinopathy (DR) affects those with diabetes for a long time. DR is a side effect of diabetes that affects the retina’s blood vessels and is caused by high blood sugar levels. Therefore, early detection and treatment are preferred. Manual recognition concerns and a lack of technology support for ophthalmologists are the most complex problems. Nowadays, Deep Learning (DL) based approaches are used significantly for creating DR detection systems because of the ongoing development of Artificial Intelligence (AI) techniques. This paper uses the APTOS dataset of retina images to train four deep Convolution Neural Network (CNN) models using a novel loss function. The four DL models used are VGG16, Resnet50, DenseNet121, and DenseNet169 to explain their rich properties and improve the classification for different phases of DR. The experimental results of this study demonstrate that VGG16 produced the lowest accuracy of 73.26% on the APTOS dataset, while DenseNet169-based detection gives the most significant result of 96.68% accuracy among the four approaches. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.