Investigation of severity level of diabetic retinopathy using adaboost classifier algorithm

When acoustic emission detection technology is applied to detect the agglomeration in uidized bed reactors (FBRs), the collected acoustic emission samples are usually non-stationarity and unbalanced, making it di cult to extract stable and separable classi cation features. In this study, the voiceprint features of collected acoustic emission signals were extracted with the Mel Frequency Cepstrum Coe cients (MFCC) and Linear Prediction Cepstrum Coe cients (LPCC). Extracted voiceprint features of LPCC and MFCC were fused with RelieF algorithm to form the stable R-LPMFCC feature, which were then compressed with principal components analysis (PCA) as input data for classi cation. The cost factor and GINI index-based decision-making calculation were introduced to the Adaboost algorithm to signi cantly improve its accuracy and F-score when classifying unbalanced samples. The comparative experimental results in a uidized-bed pilot plant verify the e ectiveness and feasibility of the proposed method.

show abstract

“…e linear prediction coe cient (LPC) α k is obtained by solving the following optimization problem (Washburn et al, 2020) as min…”

Section: Voiceprint Feature Extraction With Lpccmentioning

confidence: 99%

Monitoring of Agglomeration in Fluidized-Bed Reactor Based on Voiceprint Features Recognition with Unbalanced Samples

Zhao

Chen

Pang

2022

J. Chem. Eng. Japan

View full text Add to dashboard Cite

show abstract

“…4. Traditional machine learning algorithms, namely, ABC [8,9], is ensemble classifier that combines weak classifiers and forms a robust classifier. DTC [10,11] is a supervised algorithm used for both regression and classification problems.…”

Section: Classification Phasementioning

confidence: 99%

Classification of Cotton Leaf Diseases Using AlexNet and Machine Learning Models

Borugadda

Lakshmi

Govindu

2021

CJAST

View full text Add to dashboard Cite

Computer vision has been demonstrated as state-of-the-art technology in precision agriculture in recent years. In this paper, an Alex net model was implemented to identify and classify cotton leaf diseases. Cotton Dataset consists of 2275 images, in which 1952 images were used for training and 324 images were used for validation. Five convolutional layers of the AlexNet deep learning technique is applied for features extraction from raw data. They were remaining three fully connected layers of AlexNet and machine learning classification algorithms such as Ada Boost Classifier (ABC), Decision Tree Classifier (DTC), Gradient Boosting Classifier (GBC). K Nearest Neighbor (KNN), Logistic Regression (LR), Random Forest Classifier (RFC), and Support Vector Classifier (SVC) are used for classification. Three fully connected layers of Alex Net provided the best performance model with a 94.92% F1_score at the training time of about 51min.

show abstract

“…Washburn et al [19] describe a technique based on active contours and mathematical morphology for identifying the boundary of OD in the fundus image of the retina. Preprocessing of the images is highly needed for effective boundary detection, which is based on local minima detection and morphologic filtering.…”

Section: Related Workmentioning

confidence: 99%

A Novel Filtered Segmentation-Based Bayesian Deep Neural Network Framework on Large Diabetic Retinopathy Databases

Akbar¹,

Midhunchakkaravarthy²

2020

RIA

View full text Add to dashboard Cite

Image thresholding-based segmentation models play a vital role in the detection of Diabetic retinopathy (DR) on large databases. Most of the conventional segmentation-based classification models are independent of over segmented regions and outliers. Also, these models have less true positive rate and high error rate on different DR feature sets. In order to overcome these problems, a novel filtered based segmentation framework is designed and implemented on the large DR feature space. In this work, a novel image filtering approach, optimal image segmentation approach and hybrid Bayesian deep learning framework are developed on the large DR image databases. Experimental results proved that the proposed filtered segmentation-based Bayesian deep neural network has better accuracy and runtime than the conventional models on different DR variation databases.

show abstract

Investigation of severity level of diabetic retinopathy using adaboost classifier algorithm

Cited by 16 publications

References 13 publications

Monitoring of Agglomeration in Fluidized-Bed Reactor Based on Voiceprint Features Recognition with Unbalanced Samples

Monitoring of Agglomeration in Fluidized-Bed Reactor Based on Voiceprint Features Recognition with Unbalanced Samples

Classification of Cotton Leaf Diseases Using AlexNet and Machine Learning Models

A Novel Filtered Segmentation-Based Bayesian Deep Neural Network Framework on Large Diabetic Retinopathy Databases

Contact Info

Product

Resources

About