scholarly journals Neural Architectures for Correlated Noise Removal in Image Processing

2016 ◽  
Vol 2016 ◽  
pp. 1-14 ◽  
Author(s):  
Cătălina Cocianu ◽  
Alexandru Stan
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Supervised Learning ◽  
Learning Process ◽  
Noise Removal ◽  
Correlated Noise ◽  
Initial Image ◽  
Neural Architecture ◽  
The Mean ◽  
Index Value

The paper proposes a new method that combines the decorrelation and shrinkage techniques to neural network-based approaches for noise removal purposes. The images are represented as sequences of equal sized blocks, each block being distorted by a stationary statistical correlated noise. Some significant amount of the induced noise in the blocks is removed in a preprocessing step, using a decorrelation method combined with a standard shrinkage-based technique. The preprocessing step provides for each initial image a sequence of blocks that are further compressed at a certain rate, each component of the resulting sequence being supplied as inputs to a feed-forward neural architectureFX→FH→FY. The local memories of the neurons of the layersFHandFYare generated through a supervised learning process based on the compressed versions of blocks of the same index value supplied as inputs and the compressed versions of them resulting as the mean of their preprocessed versions. Finally, using the standard decompression technique, the sequence of the decompressed blocks is the cleaned representation of the initial image. The performance of the proposed method is evaluated by a long series of tests, the results being very encouraging as compared to similar developments for noise removal purposes.

scholarly journals Multi-Scale Aggregation Graph Neural Networks Based on Feature Similarity for Semi-Supervised Learning

Entropy ◽  
2021 ◽  
Vol 23 (4) ◽  
pp. 403
Author(s):  
Xun Zhang ◽  
Lanyan Yang ◽  
Bin Zhang ◽  
Ying Liu ◽  
Dong Jiang ◽  
...  
Keyword(s):  
Neural Network ◽  
Supervised Learning ◽  
Structured Data ◽  
Similarity Matrix ◽  
Scale Feature ◽  
Multi Scale ◽  
Adjacent Node ◽  
Feature Similarity ◽  
The Mean ◽  
Graph Neural Networks

The problem of extracting meaningful data through graph analysis spans a range of different fields, such as social networks, knowledge graphs, citation networks, the World Wide Web, and so on. As increasingly structured data become available, the importance of being able to effectively mine and learn from such data continues to grow. In this paper, we propose the multi-scale aggregation graph neural network based on feature similarity (MAGN), a novel graph neural network defined in the vertex domain. Our model provides a simple and general semi-supervised learning method for graph-structured data, in which only a very small part of the data is labeled as the training set. We first construct a similarity matrix by calculating the similarity of original features between all adjacent node pairs, and then generate a set of feature extractors utilizing the similarity matrix to perform multi-scale feature propagation on graphs. The output of multi-scale feature propagation is finally aggregated by using the mean-pooling operation. Our method aims to improve the model representation ability via multi-scale neighborhood aggregation based on feature similarity. Extensive experimental evaluation on various open benchmarks shows the competitive performance of our method compared to a variety of popular architectures.

scholarly journals A Functionally Separate Autoencoder

2020 ◽  
Author(s):  
Jinxin Wei
Keyword(s):  
Neural Network ◽  
Supervised Learning ◽  
Negative Feedback ◽  
Learning Process ◽  
Inverse Function ◽  
Convolution Neural Network ◽  
Training Process ◽  
New Knowledge

<p><b>According to kids’ learning process, an auto</b><b>-</b><b>encoder</b><b> is designed</b><b> which can be split into two parts. The two parts can work well separately.The top half is an abstract network which is trained by supervised learning and can be used to classify and regress. The bottom half is a concrete network which is accomplished by inverse function and trained by self-supervised learning. It can generate the input of abstract network from concept or label. The network can achieve its intended functionality through testing by mnist dataset and convolution neural network.</b><b> R</b><b>ound function</b><b> is added between the abstract network and concrete network in order</b><b> to get the the representative generation of class.</b><b> T</b><b>he generation ability </b><b> can be increased </b><b>by adding jump connection and negative feedback. At last, the characteristics of </b><b>the</b><b> network</b><b> is discussed</b><b>. </b><b>T</b><b>he input can </b><b>be </b><b>change</b><b>d </b><b>to any form by encoder and then change it back by decoder through inverse function. The concrete network can be seen as the memory stored by the parameters.</b><b> </b><b>Lethe is that when new knowledge input,</b><b> </b><b>the training process make</b><b>s</b><b> the parameter</b><b>s</b><b> change.</b><b></b></p>

scholarly journals A Functionally Separate Autoencoder

2021 ◽  
Author(s):  
Jinxin Wei
Keyword(s):  
Neural Network ◽  
Supervised Learning ◽  
Negative Feedback ◽  
Learning Process ◽  
Inverse Function ◽  
Convolution Neural Network ◽  
Training Process ◽  
New Knowledge

<p><b>According to kids’ learning process, an auto</b><b>-</b><b>encoder</b><b> is designed</b><b> which can be split into two parts. The two parts can work well separately.The top half is an abstract network which is trained by supervised learning and can be used to classify and regress. The bottom half is a concrete network which is accomplished by inverse function and trained by self-supervised learning. It can generate the input of abstract network from concept or label. The network can achieve its intended functionality through testing by mnist dataset and convolution neural network.</b><b> R</b><b>ound function</b><b> is added between the abstract network and concrete network in order</b><b> to get the the representative generation of class.</b><b> T</b><b>he generation ability </b><b> can be increased </b><b>by adding jump connection and negative feedback. At last, the characteristics of </b><b>the</b><b> network</b><b> is discussed</b><b>. </b><b>T</b><b>he input can </b><b>be </b><b>change</b><b>d </b><b>to any form by encoder and then change it back by decoder through inverse function. The concrete network can be seen as the memory stored by the parameters.</b><b> </b><b>Lethe is that when new knowledge input,</b><b> </b><b>the training process make</b><b>s</b><b> the parameter</b><b>s</b><b> change.</b><b></b></p>

Application of Improved BP Neural Network in Threshold Selection for Image Processing

2013 ◽  
Vol 860-863 ◽  
pp. 2872-2875
Author(s):  
Yang Ming He ◽  
Jian Qiang Du
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Adaptive Learning ◽  
Bp Neural Network ◽  
Mean Value ◽  
Good Effect ◽  
Threshold Selection ◽  
The Mean ◽  
Selection For ◽  
The Relationship

There are a lot of methods to select threshold in image processing. Because BP neural network can adapt to fixed environment, it is applied in this area in this paper. Firstly, according to the feature of image, BP neural network is constructed. The input items of network are the features of image. The mean value and variance of gray in the image is the important features of image, so two input items can be chosen. The output items are the values of threshold. If one threshold is chosen, one output item can be chosen. In some condition, two thresholds should be set, then two output items would be chosen. In order to overcome the shortcomings of BP neural network, it should be improved by certain momentum which is used to avoid local minimums. In order to speed the training of the network, adaptive learning rate should be used, too. The BP neural network establishes the relationship between the features of image and the threshold. After training, the network can select suitable threshold for images in fixed environment. Some practical images are used to prove its good effect.

scholarly journals A Functionally Separate Autoencoder

2020 ◽  
Author(s):  
Jinxin Wei
Keyword(s):  
Neural Network ◽  
Supervised Learning ◽  
Negative Feedback ◽  
Learning Process ◽  
Inverse Function ◽  
Convolution Neural Network ◽  
Training Process ◽  
New Knowledge

<p><b>According to kids’ learning process, an auto</b><b>-</b><b>encoder</b><b> is designed</b><b> which can be split into two parts. The two parts can work well separately.The top half is an abstract network which is trained by supervised learning and can be used to classify and regress. The bottom half is a concrete network which is accomplished by inverse function and trained by self-supervised learning. It can generate the input of abstract network from concept or label. The network can achieve its intended functionality through testing by mnist dataset and convolution neural network.</b><b> R</b><b>ound function</b><b> is added between the abstract network and concrete network in order</b><b> to get the the representative generation of class.</b><b> T</b><b>he generation ability </b><b> can be increased </b><b>by adding jump connection and negative feedback. At last, the characteristics of </b><b>the</b><b> network</b><b> is discussed</b><b>. </b><b>T</b><b>he input can </b><b>be </b><b>change</b><b>d </b><b>to any form by encoder and then change it back by decoder through inverse function. The concrete network can be seen as the memory stored by the parameters.</b><b> </b><b>Lethe is that when new knowledge input,</b><b> </b><b>the training process make</b><b>s</b><b> the parameter</b><b>s</b><b> change.</b><b></b></p>

scholarly journals Image Processing and Restriction of Video Downloads Using Cloud

2018 ◽  
Vol 7 (2.32) ◽  
pp. 327 ◽  
Author(s):  
Yaram Hari Krishna ◽  
Kanagala Bharath Kumar ◽  
Dasari Maharshi ◽  
J Amudhavel
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Image Processing ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
Supervised Learning ◽  
Video Processing ◽  
Learning Algorithms ◽  
Machine Learning Algorithms

Flower image classification using deep learning and convolutional neural network (CNN) based on machine learning in Tensor flow. Tensor flow IDE is used to implement machine learning algorithms. Flower image processing is based on supervised learning which detects the parameters of image. Parameters of the image were compared by decision algorithms. These images are classified by neurons in convolutional neural network. Video processing based on machine learning is used in restriction of downloading the videos by preventing the second response from the server and enabling the debugging of the video by removing the request from the user.   

scholarly journals A Functionally Separate Autoencoder

2021 ◽  
Author(s):  
Jinxin Wei
Keyword(s):  
Neural Network ◽  
Supervised Learning ◽  
Negative Feedback ◽  
Learning Process ◽  
Inverse Function ◽  
Convolution Neural Network ◽  
Training Process ◽  
New Knowledge

<p><b>According to kids’ learning process, an auto</b><b>-</b><b>encoder</b><b> is designed</b><b> which can be split into two parts. The two parts can work well separately.The top half is an abstract network which is trained by supervised learning and can be used to classify and regress. The bottom half is a concrete network which is accomplished by inverse function and trained by self-supervised learning. It can generate the input of abstract network from concept or label. The network can achieve its intended functionality through testing by mnist dataset and convolution neural network.</b><b> R</b><b>ound function</b><b> is added between the abstract network and concrete network in order</b><b> to get the the representative generation of class.</b><b> T</b><b>he generation ability </b><b> can be increased </b><b>by adding jump connection and negative feedback. At last, the characteristics of </b><b>the</b><b> network</b><b> is discussed</b><b>. </b><b>T</b><b>he input can </b><b>be </b><b>change</b><b>d </b><b>to any form by encoder and then change it back by decoder through inverse function. The concrete network can be seen as the memory stored by the parameters.</b><b> </b><b>Lethe is that when new knowledge input,</b><b> </b><b>the training process make</b><b>s</b><b> the parameter</b><b>s</b><b> change.</b><b></b></p>

Applying Circle Game to Enhance Students’ Speaking Skill

2020 ◽  
Vol 7 (2) ◽  
pp. 119
Author(s):  
Putri Denaya Side Ayu ◽  
Heri Hidayatullah ◽  
Sri Ariani
Keyword(s):  
Action Research ◽  
Learning Process ◽  
Active Involvement ◽  
Post Test ◽  
Speaking Skill ◽  
The Subject ◽  
The Mean ◽  
Classroom Action Research ◽  
Speaking Skills

This Collaborative Classroom Action Research aimed at enhancing students’ speaking skill through the application of Circle Game. It was conducted in one cycle consisting of two meetings. The subject was the seventh of C class of SMPN 2 Alas Barat consisting of 22 students. The types of data were qualitative (acquiring observation during the learning process) and quantitative (speaking tests). The results qualitatively showed that the implementation of Circle Game enhanced the students’ speaking skills. Such improvement could be seen from their enthusiasm, their interesting feeling in various materials presented by the teacher, their active involvement. In the quantitative findings, the result also showed a higher value of the mean score of the post-test (77.34) rather than the pre-test (75.75). In conclusion, the use of Circle Game can improve students’ speaking skill.

Optimizing Error Rate in Intrusion Detection System Using Artificial Neural Network Algorithm

2018 ◽  
Vol 6 (9) ◽  
pp. 152
Author(s):  
S. Vijaya Rani ◽  
G. N. K. Suresh Babu
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Intrusion Detection ◽  
Error Rate ◽  
Learning Process ◽  
Nearest Neighbor ◽  
Detection System ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Artificial Neural

The illegal hackers  penetrate the servers and networks of corporate and financial institutions to gain money and extract vital information. The hacking varies from one computing system to many system. They gain access by sending malicious packets in the network through virus, worms, Trojan horses etc. The hackers scan a network through various tools and collect information of network and host. Hence it is very much essential to detect the attacks as they enter into a network. The methods  available for intrusion detection are Naive Bayes, Decision tree, Support Vector Machine, K-Nearest Neighbor, Artificial Neural Networks. A neural network consists of processing units in complex manner and able to store information and make it functional for use. It acts like human brain and takes knowledge from the environment through training and learning process. Many algorithms are available for learning process This work carry out research on analysis of malicious packets and predicting the error rate in detection of injured packets through artificial neural network algorithms.

IMPROVING THE STUDENTS’ READING COMPREHENSION ACHIEVEMENT IN DESCRIPTIVE TEXT THROUGH TEAM GAMES TOURNAMENT

2014 ◽  
Vol 3 (3) ◽  
Author(s):  
DesiYusnanda Sari And Sri MindaMurni
Keyword(s):  
Reading Comprehension ◽  
Learning Process ◽  
Quantitative Data ◽  
Qualitative Data ◽  
Reading Scores ◽  
Team Games ◽  
The Subject ◽  
The Mean ◽  
Teaching Learning ◽  
Data Reading

This study attempted to improve the students’ reading comprehension achievement in descriptive text through Team Games Tournament (TGT) method. This study was conducted by using classroom action research. The subject of the research was class IX SMP PAB 10 Medan Estate which consisted of 25 students. The research was conducted in two cycles and the first cycle consisted of four meetings the second cycle consisted of two meetings. The instruments for collecting the data were quantitative data (reading evaluation) and qualitative data (diary note, observation sheet and interview sheet). Based on reading scores, students’ score kept improving in every evaluation. In the test I the mean was 65,33, in the test II the mean was 71,72 and the test III the mean was 84,54.Based on diary note, observation sheet and interview sheet, it was found that teaching-learning process ran well. Students were active, enthusiastic, and interested in reading. The result of the research showed that Team Games Tournament (TGT) method significantly improved students’ achievement in reading comprehension especially in reading descriptive text.

Sign in / Sign up

Export Citation Format

Share Document