Deep Learning-Based Quantitative Assessment of Multimodal Features using Lenet Model

Deep learning is used by many applications that are currently the latest technology in evert aspect. Ischemic sensation is a prompt emergency that has necessities to diagnose and treatment it by various deep learning models. For properly detect the stoke must be identifies their feasibility and their risk assessment to make it more early and efficient treatment. Essentially it develops automated methods for identifying and segmented stroke lesions. The MRI images give the good outcomes for early prediction of disease though the various machine learning and deep learning techniques. With the help of MRI images, it provides no ionizing radiation that is used in the imaging method. It develops automated methods which develop and identify the segmented stroke lesions. The various deep learning methods such as the accuracy as in terms of outcome obtained for the brain stroke prediction in the field of IOT and deep learning that improved the performance. In this research the image datasets samples are used to test model by the feature engineering model has been proposed to deploy the MRI images using preprocessing algorithm. The various machine learning algorithms such Dense121, ResNet121, Exception, VGG-16, LeNet etc. These features are trained and validated by pre-trained convolutional neural networks (CNN). The best classification result has been selected by deploying IMV. The proposed work achieved and computed accuracy as in terms such as for Le_Net is 99.4 which is deep learning model.