Top 10 Deemed Universities in Chennai
1800 425 44 38 | From 9 AM to 5.30 PM (IST) | Mon. to Sat
HITSEEE 2021 Important Dates : Last Date for Applying HITSEEE - April 10, 2021
|
Online Entrance Exam Dates - April 28 to May 02, 2021
|
Work as You Study Scheme (WAYS)

SECOND AUSTRALIAN PATENT | Event Date: Wednesday, 20th, January 2021

Dr. K. Sakthidasan Sankaran, Assoc. Prof. ECE; and Dr. N. Vasudevan, Prof., ECE & Dean E & T have attained the 2nd Australian Patent for the invention titled “Intuitionistic Fuzzy Based Deep Learning Model for Visual Interpretation of Low Dose X-Ray Image Charge Controller Using Machine Learning”on 20 Jan. 2021. Interestingly, the duo isalso a part of the team which obtained the First Australian Patent for Innovation titled “Maximum Power Point Trackable and Optimized IOT Based PV Charge Controller Using Machine Learning”.

Description:

“Intuitionistic Fuzzy Based Deep Learning Model for Visual Interpretation of Low Dose X-Ray Image Charge Controller Using Machine Learning” is related to effective detection of all abnormalities structural problems associated for aged women (35 to 55) during mammography screening test by Intuitionistic Fuzzy based deep learning model for visual interpretation of low dose x-ray image. This invention mainly focuses on improvising infection detection capability as well as enlarge abnormalities portion with high visual quality for better understanding about infection depth by introducing a new deep learning model based on Intuitionistic Fuzzy logic sets for effective visual interpretation which provide a promise solution to mammography problem (lesions and lumps) in low-dose X-ray images. It gives effective detection of the breast’s tissue deformity formation on the mammogram. It is achieved by doing low-level feature pixels which are properly adjusted through convolutional neural networks (CNNs) where foreground and background region is separated and then applied to fuzzy plan. It is converted into appropriate linguistic parametric variables and each can be mapped into corresponding fuzzy set rules (Fuzzification). The fuzzifier accepts the fuzzy rules at the input side and then applied to the subsequent carried out by hyperbolic regularization. It involves the membership grade modification by Intuitionistic Fuzzy logic sets.