Scribd Logo
Upload

Welcome to Scribd!

  • 24 views

    A Deep Learning Convolutional Neural Network in Health Care Environment

    Uploaded by

    Vasiha Fathima R

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd

    A Deep Learning Convolutional Neural Network in Health Care Environment

    Uploaded by

    Vasiha Fathima R
    24 views17 pages

    Original Title

    Untitled

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    24 views17 pages

    A Deep Learning Convolutional Neural Network in Health Care Environment

    Uploaded by

    Vasiha Fathima R

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    of 17

    ARKA EDUCATIONAL & CULTURAL TRUST ( REGD.

    )
    JAIN INSTITUTE OF TECHNOLOGY, DAVANGERE

    DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING.

    TECHNICAL SEMINAR
    ON

    A DEEP LEARNING CONVOLUTIONAL NEURAL


    NETWORK IN HEALTH CARE ENVIRONMENT

    Presented By: Seminar Guide:


    Vasiha Fathima R (4JD19CS059) H.S Saraswathi
    8th sem , CS & E dept Asst prof
    Jain Institute of Technology Dept of CSE,JIT
    Davanagere Davangere
    CONTENTS

    1. Introduction
    2. Architecture
    3. Convolutional Layers
    4. Applications
    5. Benefits and Limitations
    6. Conclusion
    7. References
    INTRODUCTION
    Most modern Deep Learning models are based on artificial neural networks, specifically CNNs. A convolutional
    neural network is a class of deep neural networks, most commonly applied to analyzing visual imagery. They have
    applications in image and video recognition, recommender systems, image classification, image segmentation,
    medical image analysis, natural language processing, brain-computer interfaces, and financial time series.

    CNN is very useful as it minimises human effort by automatically detecting the features. For example, for apples
    and mangoes, it would automatically detect the distinct features of each class on its own.

    The term ‘Convolution” in CNN denotes the mathematical function of convolution which is a special kind of
    linear operation wherein two functions are multiplied to produce a third function which expresses how the shape
    of one function is modified by the other. In simple terms, two images which can be represented as matrices are
    multiplied to give an output that is used to extract features from the image
    Fig : Representation of a convolutional neural network

    This is a representation of a convolutional neural network, where an image is used as an input and the result is
    category detection. CNN layers process the input and pass its result to the next layer which is similar to the
    response of a neuron in the visual cortex to a specific stimulus.
     
    Examples of CNN in use :
    CNNs can be used in many different applications. To name a few; realistic face generation, super resolution, style
    transfer, and black and white to color pictures. It can also be used within digital solutions to enable greater
    personalisation and prediction features.
    RELATED WORK

    Serial no. Authors Description

    1. Hinton G
    ARCHITECTURE
    There are two main parts to a CNN architecture

    • A convolution tool that separates and identifies the various features of the image for analysis in a process called
    as Feature Extraction.

    • The network of feature extraction consists of many pairs of convolutional or pooling layers.

    • A fully connected layer that utilizes the output from the convolution process and predicts the class of the image
    based on the features extracted in previous stages.

    • This CNN model of feature extraction aims to reduce the number of features present in a dataset. It creates new
    features which summarises the existing features contained in an original set of features. There are many CNN
    layers as shown in the CNN architecture diagram.
    CONVOLUTIONAL LAYERS
    There are three types of layers that make up the CNN which are the convolutional layers, pooling layers, and fully-
    connected (FC) layers. When these layers are stacked, a CNN architecture will be formed. In addition to these three
    layers, there are two more important parameters which are the dropout layer and the activation function which
    are defined below.

    1.Convolutional Layer

    This layer is the first layer that is used to extract the various features from the input images. In this layer, the
    mathematical operation of convolution is performed between the input image and a filter of a particular size MxM.
    By sliding the filter over the input image, the dot product is taken between the filter and the parts of the input image
    with respect to the size of the filter (MxM).
    The output is termed as the Feature map which gives us information about the image such as the corners and edges.
    Later, this feature map is fed to other layers to learn several other features of the input image.
    The convolution layer in CNN passes the result to the next layer once applying the convolution operation in the
    input. Convolutional layers in CNN benefit a lot as they ensure the spatial relationship between the pixels is intact.
    2.Pooling Layer

    In most cases, a Convolutional Layer is followed by a Pooling Layer. The primary aim of this
    layer is to decrease the size of the convolved feature map to reduce the computational costs. This
    is performed by decreasing the connections between layers and independently operates on each
    feature map. Depending upon method used, there are several types of Pooling operations. It
    basically summarises the features generated by a convolution layer.
    This CNN model generalises the features extracted by the convolution layer, and helps the
    networks to recognise the features independently. With the help of this, the computations are also
    reduced in a network.

    3.Fully Connected Layer

    The Fully Connected (FC) layer consists of the weights and biases along with the neurons and is
    used to connect the neurons between two different layers. These layers are usually placed before
    the output layer and form the last few layers of a CNN Architecture.
    In this, the input image from the previous layers are flattened and fed to the FC layer. The
    flattened vector then undergoes few more FC layers where the mathematical functions operations
    usually take place. In this stage, the classification process begins to take place. The reason two
    layers are connected is that two fully connected layers will perform better than a single connected
    layer. These layers in CNN reduce the human supervision
    4.Dropout

    Dropout results in improving the performance of a machine learning model as it


    prevents overfitting by making the network simpler. It drops neurons from the neural
    networks during training.

    5.Activation Functions

    Finally, one of the most important parameters of the CNN model is the activation
    function. They are used to learn and approximate any kind of continuous and
    complex relationship between variables of the network. In simple words, it decides
    which information of the model should fire in the forward direction and which ones
    should not at the end of the network.
    METHODOLOGY
    Convolutional Neural Networks used for :

    Here are some of the common applications of convolutional neural networks:


    Semantic segmentation: Researchers have used convolutional neural networks to improve
    semantic segmentation models by incorporating rich information.
    Object detection: Convolutional neural networks are used in self-driving cars as well as
    facial recognition systems for object detection.
    Image captioning: Convolutional neural networks are used to caption and describe images, making it easier for
    visually impaired people to understand what the images are trying to convey. It is even used heavily by YouTube.
    Voice synthesis: Google Assistant’s voice synthesizer uses Deepmind’s WaveNet ConvNet model.
    Astrophysics: they are used to make sense of radio telescope data and predict the probable visual image to
    represent that data.
    Convolutional neural networks have even found applications to some extent in population genetic inference as
    well as in disease identification. They are also used for the purpose of fraud detection.
    The future of CNNs :
    Ever since the breakthrough of CNN in 2012, the evolution in Deep Learning techniques has accelerated
    exponentially, ranging from image classification models used by self driven vehicles to text generation models
    like GPT-3 that produces human-like texts. For that reason we can expect that Deep Learning tools will continue
    evolving in the next 5 to 10 years to a point this kind technology will be widely democratised and become a
    standard tool for every person, having an ubiquitous presence in our daily lives.
    BENEFITS OF CNN
    The benefits of using CNNs over other traditional neural networks in the computer vision
    environment are listed as follows:
    1.The main reason to consider CNN is the weight sharing feature, which reduces the number of
    trainable network parameters and in turn helps the network to enhance generalization and to avoid
    overfitting.
    2.Concurrently learning the feature extraction layers and the classification layer causes the model
    output to be both highly organized and highly reliant on the extracted features.
    3.Large-scale network implementation is much easier with CNN than with other neural networks.
    4.CNNs do not require human supervision for the task of identifying important features.
    5.CNNs are very accurate at image recognition and classification.
    6.Convolutional neural networks also minimize computation in comparison with a regular neural
    network.
    7.CNNs make use of the same knowledge across all image locations.
    LIMITATIONS OF CNN :

    1.CNNs have a hard time classifying images with different positions.


    2.A lot of training data is needed for the CNN to be effective.
    3.CNNs tend to be much slower because of operations like maxpool.
    4.In case the convolutional neural network is made up of multiple layers, the training process could take a
    particularly long time if the computer does not have a good GPU.
    5.Convolutional neural networks will recognize the image as clusters of pixels which are arranged in
    distinct patterns. They don’t understand them as components present in the image.
    6.They fail to encode the position and orientation of objects.
    7.Difficulty in dealing with variance in data presented.
    CONCLUSION

    In this paper we discuss the important issues that related Convolutional Neural Network (CNN) and explain
    the effect each parameter on performance of network . The most important layer in CNN is convolution
    layer Which takes most of the time within the network. Network performance also depends on the number of
    levels within the network. But in the other hand as the number of levels increases the time required to train
    and test the network. Today the CNN consider as power full tool within machine learning for a lot of
    application such as face detection and image , video recognitions and voice recognition. CNN is the best
    artificial neural network, it is used for modeling image but it is not limited to just modeling of the image but
    out of many of its applications. There are many improvised versions based on CNN architecture like
    AlexNet, VGG, YOLO, and many more
    REFERENCES
    Received: 25 March 2020 / Revised: 5 October 2020 / Accepted: 22 November 2020 /
    Published online: 3 January 2021 © The Author(s), under exclusive licence to Springer-Verlag
    GmbH, DE part of Springer Nature 2021
    THANK
    YOU…!

    You might also like