scholarly journals Convolutional Neural Networks Using Skip Connections with Layer Groups for Super-Resolution Image Reconstruction Based on Deep Learning

2020 ◽  
Vol 10 (6) ◽  
pp. 1959
Author(s):  
Hyeongyeom Ahn ◽  
Changhoon Yim
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Image Reconstruction ◽  
Convolutional Neural Networks ◽  
Input Data ◽  
Signal To Noise Ratio ◽  
Super Resolution ◽  
Resolution Image ◽  
Hidden Layer ◽  
Layer Groups

In this paper, we propose a deep learning method with convolutional neural networks (CNNs) using skip connections with layer groups for super-resolution image reconstruction. In the proposed method, entire CNN layers for residual data processing are divided into several layer groups, and skip connections with different multiplication factors are applied from input data to these layer groups. With the proposed method, the processed data in hidden layer units tend to be distributed in a wider range. Consequently, the feature information from input data is transmitted to the output more robustly. Experimental results show that the proposed method yields a higher peak signal-to-noise ratio and better subjective quality than existing methods for super-resolution image reconstruction.

Efficient downscaling of satellite oceanographic data with convolutional neural networks

2021 ◽  
Vol 12 (3) ◽  
pp. 46-47
Author(s):  
Nikita Saxena
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Super Resolution ◽  
Sea Surface ◽  
Clear Sky ◽  
Oceanographic Data ◽  
Computationally Expensive ◽  
Sky Conditions ◽  
Data Inference

Space-borne satellite radiometers measure Sea Surface Temperature (SST), which is pivotal to studies of air-sea interactions and ocean features. Under clear sky conditions, high resolution measurements are obtainable. But under cloudy conditions, data analysis is constrained to the available low resolution measurements. We assess the efficiency of Deep Learning (DL) architectures, particularly Convolutional Neural Networks (CNN) to downscale oceanographic data from low spatial resolution (SR) to high SR. With a focus on SST Fields of Bay of Bengal, this study proves that Very Deep Super Resolution CNN can successfully reconstruct SST observations from 15 km SR to 5km SR, and 5km SR to 1km SR. This outcome calls attention to the significance of DL models explicitly trained for the reconstruction of high SR SST fields by using low SR data. Inference on DL models can act as a substitute to the existing computationally expensive downscaling technique: Dynamical Downsampling. The complete code is available on this Github Repository.

Deep Learning in the Healthcare Industry

2020 ◽  
pp. 220-245 ◽  
Author(s):  
Zahra A. Shirazi ◽  
Camila P. E. de Souza ◽  
Rasha Kashef ◽  
Felipe F. Rodrigues
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Input Data ◽  
Time Series Data ◽  
Short Term Memory ◽  
Healthcare Industry ◽  
Neural Network Models ◽  
Input Layer ◽  
Hidden Layer

Artificial Neural networks (ANN) are composed of nodes that are joint to each other through weighted connections. Deep learning, as an extension of ANN, is a neural network model, but composed of different categories of layers: input layer, hidden layers, and output layers. Input data is fed into the first (input) layer. But the main process of the neural network models is done within the hidden layers, ranging from a single hidden layer to multiple ones. Depending on the type of model, the structure of the hidden layers is different. Depending on the type of input data, different models are applied. For example, for image data, convolutional neural networks are the most appropriate. On the other hand, for text or sequential and time series data, recurrent neural networks or long short-term memory models are the better choices. This chapter summarizes the state-of-the-art deep learning methods applied to the healthcare industry.

scholarly journals Predict Forex Trend via Convolutional Neural Networks

2018 ◽  
Vol 29 (1) ◽  
pp. 941-958 ◽  
Author(s):  
Yun-Cheng Tsai ◽  
Jun-Hao Chen ◽  
Jun-Jie Wang
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Quantitative Data ◽  
Input Data ◽  
Trading Strategies ◽  
Financial Asset ◽  
Time Series Modeling ◽  
Trading Model

Abstract Deep learning is an effective approach to solving image recognition problems. People draw intuitive conclusions from trading charts. This study uses the characteristics of deep learning to train computers in imitating this kind of intuition in the context of trading charts. The main goal of our approach is combining the time-series modeling and convolutional neural networks (CNNs) to build a trading model. We propose three steps to build the trading model. First, we preprocess the input data from quantitative data to images. Second, we use a CNN, which is a type of deep learning, to train our trading model. Third, we evaluate the model’s performance in terms of the accuracy of classification. The experimental results show that if the strategy is clear enough to make the images obviously distinguishable the CNN model can predict the prices of a financial asset. Hence, our approach can help devise trading strategies and help clients automatically obtain personalized trading strategies.

scholarly journals Handwriting Recognition using Deep Learning based Convolutional Neural Network

2019 ◽  
Vol 8 (4) ◽  
pp. 4826-4828
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Convolutional Neural Networks ◽  
Input Data ◽  
Recognition Accuracy ◽  
Handwriting Recognition ◽  
Indian Language ◽  
Character Set

Handwriting is a learned skill that had been an excellent means of communication and documentation for thousands of years. The simple way to communicate with the computers is through either speech or handwriting. Speech has some limitation; hence input through handwriting is recommended. It is difficult to input data for computers for Indian language scripts because of their com-plex character set. This paper focuses on exploring convolutional neural networks (CNN) which is deep learning based for the recognition of handwritten script. The proposed method has shown 99% for handwritten English numerals and promising recognition accuracy for Kannada numerals.

Sign in / Sign up

Export Citation Format

Share Document