scholarly journals Design an Early Detection and Classification for Diabetic Retinopathy by Deep Feature Extraction based Convolution Neural Network

2021 ◽  
Vol 3 (2) ◽  
pp. 81-94
Author(s):  
Akey Sungheetha ◽  
Rajesh Sharma R
Keyword(s):  
Early Detection ◽  
Early Identification ◽  
Confusion Matrix ◽  
Research Work ◽  
Fundus Images ◽  
Detection Algorithms ◽  
Deep Feature ◽  
Deep Networks ◽  
Difficult Challenge ◽  
Deep Feature Extraction

Early identification of diabetics using retinopathy images is still a difficult challenge. Many illness diagnosis techniques are accomplished by using the blood vessels present in fundus images. Many conventional methods fail to detect Hard Executes (HE) present in retinopathy images, which are used to determine the severity of diabetes disease. To overcome this challenge, the proposed research work extracts the features by incorporating deep networks through convolution neural networks (CNN). The micro aneurysm may be seen in the early stages of the transformation from normal to sick condition on the images for mild DR. The level of severity of the diabetes condition may be classified by using the confusion matrix detection results. The early detection of the diabetic condition has been achieved through the HE spotted in the blood vessel of an eye by using the proposed CNN framework. The proposed framework is also used to detect a person’s diabetic condition. This article consisting of proof for the accuracy of the proposed framework is higher than other traditional detection algorithms.

Towards Robust Localization Deep Feature Extraction by CNN

2020 ◽  
Author(s):  
Erik Carlbaum ◽  
Sina Sharif Mansouri ◽  
Christoforos Kanellakis ◽  
Anton Koval ◽  
George Nikolakopoulos
Keyword(s):  
Feature Extraction ◽  
Deep Feature ◽  
Robust Localization ◽  
Deep Feature Extraction

Smart paddy field monitoring system using deep learning and IoT

2021 ◽  
pp. 1063293X2198894
Author(s):  
Prabira Kumar Sethy ◽  
Santi Kumari Behera ◽  
Nithiyakanthan Kannan ◽  
Sridevi Narayanan ◽  
Chanki Pandey
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Transfer Learning ◽  
Paddy Field ◽  
New Technology ◽  
Support Vector ◽  
Nitrogen Status ◽  
Deep Feature ◽  
Per Capita ◽  
Deep Feature Extraction

Paddy is an essential nutrient worldwide. Rice gives 21% of worldwide human per capita energy and 15% of per capita protein. Asia represented 60% of the worldwide populace, about 92% of the world’s rice creation, and 90% of worldwide rice utilization. With the increase in population, the demand for rice is increased. So, the productivity of farming is needed to be enhanced by introducing new technology. Deep learning and IoT are hot topics for research in various fields. This paper suggested a setup comprising deep learning and IoT for monitoring of paddy field remotely. The vgg16 pre-trained network is considered for the identification of paddy leaf diseases and nitrogen status estimation. Here, two strategies are carried out to identify images: transfer learning and deep feature extraction. The deep feature extraction approach is combined with a support vector machine (SVM) to classify images. The transfer learning approach of vgg16 for identifying four types of leaf diseases and prediction of nitrogen status results in 79.86% and 84.88% accuracy. Again, the deep features of Vgg16 and SVM results for identifying four types of leaf diseases and prediction of nitrogen status have achieved an accuracy of 97.31% and 99.02%, respectively. Besides, a framework is suggested for monitoring of paddy field remotely based on IoT and deep learning. The suggested prototype’s superiority is that it controls temperature and humidity like the state-of-the-art and can monitor the additional two aspects, such as detecting nitrogen status and diseases.

Early Detection of Ototoxicity Using 1/6th-Octave Steps

2003 ◽  
Vol 14 (08) ◽  
pp. 444-450 ◽  
Author(s):  
Stephen A. Fausti ◽  
Wendy J. Helt ◽  
David S. Phillips ◽  
Jane S. Gordon ◽  
Gene W. Bratt ◽  
...  
Keyword(s):  
Early Detection ◽  
Early Identification ◽  
High Frequency ◽  
Detection Rate ◽  
Frequency Range ◽  
Test Protocol ◽  
Hearing Results ◽  
Testing Protocol ◽  
Initial Work ◽  
Auditory Research

The National Center for Rehabilitative Auditory Research has developed a protocol to provide early identification of ototoxicity for patients receiving ototoxic medications. The initial work involved patients with relatively good high-frequency hearing and resulted in the use of an individualized, sensitive frequency range separated by 1/16th-octave intervals. This protocol tested puretone frequencies at 1/6th-octave steps above 9 kHz, but only conventional audiometric frequencies were tested below 9 kHz. More recently, the testing protocol was expanded to include 1/6th-octave testing below 9 kHz. The primary question of interest was to determine whether adding 1/16th-octave test frequencies below 9 kHz would increase the ototoxicity detection rate for patients with poorer hearing. Results indicated 76 of the 210 (36.2%) ears that demonstrated initial ototoxic hearing change would have been missed or detected later if only conventional frequency testing was conducted. Therefore, for individuals with poorer hearing, expanding the use of the 1/16th-octave test protocol provides earlier identification of ototoxicity.

scholarly journals ANN and SVM to recognize Texture features for spontaneous Detection and Rating of Diabetic Retinopathy

2019 ◽  
Vol 9 (1) ◽  
pp. 5590-5595
Keyword(s):  
Diabetic Retinopathy ◽  
Research Work ◽  
Texture Features ◽  
Support Vector ◽  
Fundus Images ◽  
Small Vessels ◽  
The Neural Network ◽  
Major Loss ◽  
Occurrence Matrix ◽  
Fluid Leak

The higher levels of blood glucose most often causes a metabolic disorder commonly called as Diabetes, scientifically as Diabetes Mellitus. A consequence of this is a major loss of vision and in long terms may eventually cause complete blindness. It initiates with swelling on blood vessels, formation of microaneurysms at the end of narrow capillaries. Haemorrhages due to rupture of small vessels and fluid leak causes exudates. The specialist examines it to diagnose and gives proper treatment. Fundus images are the fundamental tool for proper diagnosis of patients by medical experts. In this research work the fundus images are taken for processing, the neural network and support vector machine are trained for the proposed model. The features are extracted from the diabetic retinopathy image by using texture based algorithms such as Gabor, Local binary pattern and Gray level co-occurrence matrix for rating the level of diabetic retinopathy. The performance of all methods is calculated based on accuracy, precision, Recall and f-measure.

Sign in / Sign up

Export Citation Format

Share Document