Deep Convolutional Neural Networks: Structure, Feature Extraction and Training

Namatēvs, Ivars

doi:10.1515/itms-2017-0007

Cited by 78 publications

(49 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…After average pooling, the audio is sent to the second and third discriminator. Each discriminator consists of a convolution layer, four downsampling layer and then another convolution layer for feature mapping [ 21 ]. Each layer uses LeakyReLU for activation.…”

Section: Proposed Systemmentioning

confidence: 99%

Speech synthesis using generative adversarial network for improving readability of Hindi words to recuperate from dyslexia

Atkar

Priyadarshini

2021

Neural Comput & Applic

View full text Add to dashboard Cite

Children learn and develop their abilities at their own pace. One of the most basic skills that they acquire is reading. However, some children struggle with reading longer than their friends, and in such a case, it is possible that they have a learning disorder known as dyslexia. The paper aims to use neural networks, namely generative neural networks, for generating raw audio data of two- or three-letter Hindi words. Using the generated data, a system will be built that will pronounce generated words for children recuperating from dyslexia. The system aims to be an effective helping tool for teachers to speed up the recuperation process by making the child repeat the correct pronunciation of the word. The system uses advance Mel-generative adversarial network neural network for working with Mel-spectrograms of the raw audio, by which the system will model its own audio iteratively, until a satisfactory result is achieved. Generated audio sample contains the Hindi words which will be taught to children. Mel-generative adversarial network will be used to generate audio samples since it provides better results compared to other existing models. 300 basic two- or three-letter Hindi words are taken as an input for assisting 5- to 8-year children. Minimum opinion score is calculated for comparison.

show abstract

Section: Proposed Systemmentioning

confidence: 99%

Speech synthesis using generative adversarial network for improving readability of Hindi words to recuperate from dyslexia

Atkar

Priyadarshini

2021

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…The DR detection is performed by Deep CNN, which inputs the segmented blood vessels. CNNs 34 are feed‐forward networks, in which the data flows in only one direction, that is, from inputs to outputs, whereas CNNs are the advanced versions of artificial neural networks (ANNs). CNN architectures are classified into many layers, such as convolutional and pooling layers that are gathered into modules.…”

Section: Optimal Deep Convolutional Neural Network‐based Diabetic Retmentioning

confidence: 99%

Automatic diagnosis of diabetic retinopathy with the aid of adaptive average filtering with optimized deep convolutional neural network

Roshini¹,

Ravi²,

Mathew³

et al. 2020

Int J Imaging Syst Tech

View full text Add to dashboard Cite

The most effective treatment for diabetic retinopathy (DR) is the early detection through regular screening, which is critical for a better prognosis. Automatic screening of the images would assist the physicians in diagnosing the condition of patients easily and accurately. This condition searches out for special importance of image processing technology in the way of processing the retinal fundus images. Accordingly, this article plans to develop an automatic DR detection model with the aid of three main stages like (a) image preprocessing, (b) blood vessel segmentation, and (c) classification. The preprocessing phase includes two steps: conversion of RGB to Lab, and contrast enhancement. The Histogram equalization process is done using the contrast enhancement of an image. To the next of preprocessing, the segmentation phase starts with a valuable procedure. It includes (a), thresholding the contrast‐enhanced and filtered images, (b) thresholding the keypoints of contrast‐enhanced and filtered images, and (c) adding both thresholded binary images. Here, the filtering process is performed by proposed adaptive average filtering, where the filter coefficients are tuned or optimized by an improved meta‐heuristic algorithm called fitness probability‐based CSO (FP‐CSO). Finally, the classification part uses Deep CNN, where the improvement is exploited on the convolutional layer, which is optimized by the same improved FP‐CSO. Since the conventional CSO depends on a fitness probability in the improved algorithm, the proposed algorithm termed as FP‐CSO. Finally, valuable comparative and performance analysis has confirmed the effectiveness of the proposed model.

show abstract

“…They use used tied weights and pooling layers, this allows them to take advantage of the 2D structure of input data. They can be used in both image and speech applications [27].…”

Section: B Crime Mapping Technologiesmentioning

confidence: 99%

Crime Mapping Model based on Cloud and Spatial Data: A Case Study of Zambia Police Service

Phiri¹,

Phiri²,

Charles³

2020

IJACSA

View full text Add to dashboard Cite

Crime mapping is a strategy used to detect and prevent crime in the police service. The technique involves the use of geographical maps to help crime analysts identify and profile crimes committed in different residential areas, as well as determining best methods of responding. The development of geographic information system (GIS) technologies and spatial analysis applications coupled with cloud computing have significantly improved the ability of crime analysts to perform this crime mapping function. The aim of this research is to automate the processes involved in crime mapping using spatial data. A baseline study was conducted to identify the challenges in the current crime mapping system used by the Zambia Police Service. The results show that 85.2% of the stations conduct crime mapping using physical geographical maps and pins placed on the map while 14.8% indicated that they don't use any form of crime mapping technique. In addition, the study revealed that all stations that participated in the study collect and process the crime reports and statistics manually and keep the results in books and papers. The results of the baseline study were used to develop the business processes and a crime mapping model, this was implemented successfully. The proposed model includes a spatial data visualization of crime data based on Google map. The proposed model is based on the Cloud Architecture, Android Mobile Application, Web Application, Google Map API and Java programming language. A prototype was successfully developed and the test results of the proposed system show improved data visualization and reporting of crime data with reduced dependency on manual transactions. It also proved to be more effective than the current system.

show abstract

Deep Convolutional Neural Networks: Structure, Feature Extraction and Training

Cited by 78 publications

References 35 publications

Speech synthesis using generative adversarial network for improving readability of Hindi words to recuperate from dyslexia

Speech synthesis using generative adversarial network for improving readability of Hindi words to recuperate from dyslexia

Automatic diagnosis of diabetic retinopathy with the aid of adaptive average filtering with optimized deep convolutional neural network

Crime Mapping Model based on Cloud and Spatial Data: A Case Study of Zambia Police Service

Contact Info

Product

Resources

About