ON THE COMPARISON OF NN-BASED ARCHITECTURES FOR DIABETIC DAMAGE DETECTION IN RETINAL IMAGES

The automatic screening of retinal images for an early detection of diabetic symptoms and an early prevention of diabetic retinopathies has been a prime focus in recent times. In this paper a contribution to improve diabetic damage detection in retinal images via neural networks is proposed by comparing two neural strategies. By considering the first architecture, fundus oculi symptomatic pale regions are firstly highlighted by enhancing image contrast with a neurofuzzy subnet, which is synthesized using a Sparsely-Connected Neural Network. Then, obtained contrast-enhanced images with bimodal histograms are globally segmented, after an optimal thresholding performed by a neural subsystem. In output binary images, suspect diabetic areas are finally isolated. By considering the second architecture, an EBP MLP neural net is synthesized, where a suitable training set of suspect patterns is developed by (5 × 5) windows centered on damaged pixels in gold standard images provided by clinicians. Performances are evaluated by percentage measures of exactness in the detection of suspect damaged areas via a comparison with gold standard images provided by clinicians. Results of both strategies are discussed and compared with other researchers' ones.

Download Full-text

Detection for Corn/Weed Images Using Moment Invariants by BPNN Classifier

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.605-607.2183 ◽

2012 ◽

Vol 605-607 ◽

pp. 2183-2186

Author(s):

Lan Lan Wu ◽

Jie Wu ◽

You Xian Wen ◽

Hui Peng ◽

Zhi Hui Zhu

Keyword(s):

Neural Network ◽

Image Processing ◽

Imaging System ◽

Back Propagation ◽

Back Propagation Neural Network ◽

Detection Accuracy ◽

Training Set ◽

Shape Model ◽

Binary Images ◽

Invariant Moments

This study was conducted to discriminate the weed from the corn in a field combined neural network classifier with image processing technology. The corn and weed images were scanned using a colour imaging system. In the first step, an approximate location of the object of interest was determined by minimum enclosing rectangle, in which image processing was done to obtain the binary image. In the second step, the seven invariant moments were extracted from binary images and used as input to the back propagation neural network (BPNN) classifier. The training set was used to construct shape model representing the objects. The detection accuracy was enhanced by adjusting the number of neurons in the network. Experimental results showed that the BPNN classifier achieved overall detection accuracy of 94.52% with 7-28-1.

Download Full-text

Barley Diseases Discrimination Based on Neural Network

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.687-691.3914 ◽

2014 ◽

Vol 687-691 ◽

pp. 3914-3916

Author(s):

Lin Ming Wang

Keyword(s):

Neural Network ◽

Image Recognition ◽

New Technology ◽

Texture Features ◽

Experimental Results ◽

Neural Net ◽

Training Set ◽

The Neural Network ◽

Test Sets ◽

Spot Color

First disease spot color and texture features were extracted from barley field images in Gansu, and the feature vectors were used as input vector to establish barley diseases classifier model. Then the neural network was applied to rain classified model with collected images as training set. Finally, two groups of random selected images as test sets were used to perform classified verification experiments. The experimental results show that the overall accuracy of barley dis-eases recognition model is above 86.7%. Therefore, Barley disease image recognition based on neural net-work provides a new technology for the classified treatment of barley diseases.

Download Full-text

Compare the Segmentation Accuracy of Heart Substructure on Contrast Enhanced CT by Deep Convolutional Neural Network with Different Loss Functions

10.21203/rs.3.rs-83236/v1 ◽

2020 ◽

Author(s):

Danju Huang ◽

Han Bai ◽

Li Wang ◽

Yu Hou ◽

Lan Li ◽

...

Keyword(s):

Neural Network ◽

Left Ventricle ◽

Right Ventricle ◽

Right Atrium ◽

Gold Standard ◽

Loss Functions ◽

Contrast Enhanced Ct ◽

Contrast Enhanced ◽

Enhanced Ct ◽

Segmentation Accuracy

Abstract Background: We aimed to compare the segmentation accuracy of heart substructure on contrast enhanced CT by deep neural network combined with different loss functions.Methods: We collected 35 thoracic tumor patients admitted to the Department of Radiation Oncology of Yunnan Cancer Hospital. Organ-at-risks (OARs) were defined as 10 organs of cardiac substructures (pericardium, heart, left atrium, left ventricle, right atrium, right ventricle, left main stem, left anterior descending Branch, left circumflex branch, right coronary artery), and use the OARs manually outlined by radiation oncologists on enhanced localization CT as the gold standard. The automatic segmentation results of GDL U-Net, WCEGDL U-Net, ELL U-Net, and GDL V-Net are compared with the gold standard. DSC, JC, HD, VD are used as quantitative evaluation indicators. Results: The segmentation DSC of the pericardium, heart, atrium, and ventricle of the DCNN with different loss functions all reached above 0.87. WCEGDL U-Net segmented the pericardium with DSC of 0.961 and 95% HD of 3.449mm; The segmentation DSC of the heart by ELL U-Net reached 0.965, and the 95% HD was 3.477mm; GDL U-Net segmentation of left atrium and right ventricle is better, DSC is 0.896 (95% HD: 3.429mm), 0.912 (95% HD: 4.242mm);GDL V-Net has better segmentation performance for right atrium and left ventricle, with DSC of 0.881 (95% HD: 3.904mm) and 0.940 (95% HD: 2.821mm). Conclusions: The DCNN proposed in this study have achieved better segmentation effects on the pericardium, heart and four chambers in cardiac substructure segmentation.

Download Full-text

Dynamic learning rate neural network training and composite structural damage detection

AIAA Journal ◽

10.2514/3.13701 ◽

1997 ◽

Vol 35 ◽

pp. 1522-1527

Author(s):

H. Luo ◽

S. Hanagud

Keyword(s):

Neural Network ◽

Damage Detection ◽

Structural Damage ◽

Learning Rate ◽

Neural Network Training ◽

Structural Damage Detection ◽

Dynamic Learning ◽

Network Training

Download Full-text

Using artificial neural network condensation to facilitate adaption of machine learning in medical settings by reducing computational burden (Preprint)

10.2196/preprints.20767 ◽

2020 ◽

Author(s):

Dianbo Liu

Keyword(s):

Neural Network ◽

Machine Learning ◽

Third World ◽

Mortality Prediction ◽

Neural Net ◽

Medical Settings ◽

Hidden Layer ◽

Applications Of Machine Learning ◽

Computational Resources ◽

Developed Nations

BACKGROUND Applications of machine learning (ML) on health care can have a great impact on people’s lives. At the same time, medical data is usually big, requiring a significant amount of computational resources. Although it might not be a problem for wide-adoption of ML tools in developed nations, availability of computational resource can very well be limited in third-world nations and on mobile devices. This can prevent many people from benefiting of the advancement in ML applications for healthcare. OBJECTIVE In this paper we explored three methods to increase computational efficiency of either recurrent neural net-work(RNN) or feedforward (deep) neural network (DNN) while not compromising its accuracy. We used in-patient mortality prediction as our case analysis upon intensive care dataset. METHODS We reduced the size of RNN and DNN by applying pruning of “unused” neurons. Additionally, we modified the RNN structure by adding a hidden-layer to the RNN cell but reduce the total number of recurrent layers to accomplish a reduction of total parameters in the network. Finally, we implemented quantization on DNN—forcing the weights to be 8-bits instead of 32-bits. RESULTS We found that all methods increased implementation efficiency–including training speed, memory size and inference speed–without reducing the accuracy of mortality prediction. CONCLUSIONS This improvements allow the implementation of sophisticated NN algorithms on devices with lower computational resources.

Download Full-text

Geometric property-based convolutional neural network for indoor object detection

International Journal of Advanced Robotic Systems ◽

10.1177/1729881421993323 ◽

2021 ◽

Vol 18 (1) ◽

pp. 172988142199332

Author(s):

Xintao Ding ◽

Boquan Li ◽

Jinbao Wang

Keyword(s):

Neural Network ◽

Object Detection ◽

Convolutional Neural Network ◽

Geometric Property ◽

Ground Truth ◽

Geometric Constraints ◽

Depth Information ◽

Training Set ◽

Object Knowledge ◽

The Mean

Indoor object detection is a very demanding and important task for robot applications. Object knowledge, such as two-dimensional (2D) shape and depth information, may be helpful for detection. In this article, we focus on region-based convolutional neural network (CNN) detector and propose a geometric property-based Faster R-CNN method (GP-Faster) for indoor object detection. GP-Faster incorporates geometric property in Faster R-CNN to improve the detection performance. In detail, we first use mesh grids that are the intersections of direct and inverse proportion functions to generate appropriate anchors for indoor objects. After the anchors are regressed to the regions of interest produced by a region proposal network (RPN-RoIs), we then use 2D geometric constraints to refine the RPN-RoIs, in which the 2D constraint of every classification is a convex hull region enclosing the width and height coordinates of the ground-truth boxes on the training set. Comparison experiments are implemented on two indoor datasets SUN2012 and NYUv2. Since the depth information is available in NYUv2, we involve depth constraints in GP-Faster and propose 3D geometric property-based Faster R-CNN (DGP-Faster) on NYUv2. The experimental results show that both GP-Faster and DGP-Faster increase the performance of the mean average precision.

Download Full-text

Super multi-step wind speed forecasting system with training set extension and horizontal–vertical integration neural network

Applied Energy ◽

10.1016/j.apenergy.2021.116908 ◽

2021 ◽

Vol 292 ◽

pp. 116908

Author(s):

Ling Liu ◽

Jujie Wang

Keyword(s):

Neural Network ◽

Wind Speed ◽

Vertical Integration ◽

Training Set ◽

Wind Speed Forecasting ◽

Forecasting System

Download Full-text

Deep learning for denoising

Geophysics ◽

10.1190/geo2018-0668.1 ◽

2019 ◽

Vol 84 (6) ◽

pp. V333-V350 ◽

Cited By ~ 15

Author(s):

Siwei Yu ◽

Jianwei Ma ◽

Wenlong Wang

Keyword(s):

Neural Network ◽

Deep Learning ◽

Graphics Processing Unit ◽

Random Noise ◽

Stochastic Gradient Descent ◽

Processing Unit ◽

Noise Attenuation ◽

Optimal Parameters ◽

Training Set ◽

Unknown Variance

Compared with traditional seismic noise attenuation algorithms that depend on signal models and their corresponding prior assumptions, removing noise with a deep neural network is trained based on a large training set in which the inputs are the raw data sets and the corresponding outputs are the desired clean data. After the completion of training, the deep-learning (DL) method achieves adaptive denoising with no requirements of (1) accurate modelings of the signal and noise or (2) optimal parameters tuning. We call this intelligent denoising. We have used a convolutional neural network (CNN) as the basic tool for DL. In random and linear noise attenuation, the training set is generated with artificially added noise. In the multiple attenuation step, the training set is generated with the acoustic wave equation. The stochastic gradient descent is used to solve the optimal parameters for the CNN. The runtime of DL on a graphics processing unit for denoising has the same order as the [Formula: see text]-[Formula: see text] deconvolution method. Synthetic and field results indicate the potential applications of DL in automatic attenuation of random noise (with unknown variance), linear noise, and multiples.

Download Full-text