scholarly journals A Multiple Comprehensive Analysis of scATAC-seq Based on Auto-Encoder and Matrix Decomposition

Symmetry ◽  
2021 ◽  
Vol 13 (8) ◽  
pp. 1467
Author(s):  
Yuyao Huang ◽  
Yizhou Li ◽  
Yuan Liu ◽  
Runyu Jing ◽  
Menglong Li
Keyword(s):  
Neural Network ◽  
Matrix Factorization ◽  
Network Architecture ◽  
Matrix Decomposition ◽  
Open Chromatin ◽  
Data Set ◽  
Standard Data ◽  
Latent Features ◽  
Novel Method ◽  
Factorization Methods

Single-cell ATAC-seq (scATAC-seq), as the updating of ATAC-seq, provides a novel method for probing open chromatin sites. Currently, research of scATAC-seq is faced with the problem of high dimensionality and the inherent sparsity of the generated data. Recently, several works proposed the use of an autoencoder–decoder, a symmetry neural network architecture, and non-negative matrix factorization methods to characterize the high-dimensional data. To evaluate the performance of multiple methods, in this work, we performed a multiple comparison for characterizing scATAC-seq based on four kinds of auto-encoders known as a symmetry neural network, and two kinds of matrix factorization methods. Different sizes of latent features were used to generate the UMAP plots and for further K-means clustering. Using a gold-standard data set, we practically explored the performance among the methods and the number of latent features in a comprehensive way. Finally, we briefly discuss the underlying difficulties and future directions for scATAC-seq characterizing. As a result, the method designed for handling the sparsity outperforms other tools in the generated dataset.

scholarly journals Arabic Hand Written Character Recognition Based on Contour Matching and Neural Network

2019 ◽  
Vol 12 (2) ◽  
pp. 126
Author(s):  
Marwan Abo Zanona ◽  
Anmar Abuhamdah ◽  
Bassam Mohammed El-Zaghmouri
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Character Recognition ◽  
Computer Algorithms ◽  
Contour Analysis ◽  
Feed Forward Neural Network ◽  
Data Set ◽  
Standard Data ◽  
Contour Matching ◽  
Handwritten Recognition

Complexity of Arabic writing language makes its handwritten recognition very complex in terms of computer algorithms. The Arabic handwritten recognition has high importance in modern applications. The contour analysis of word image can extract special contour features that discriminate one character from another by the mean of vector features. This paper implements a set of pre-processing functions over a handwritten Arabic characters, with contour analysis, to enter the contour vector to neural network to recognize it. The selection of this set of pre-processing algorithms was completed after hundreds of tests and validation. The feed forward neural network architecture was trained using many patterns regardless of the Arabic font style building a rigid recognition model. Because of the shortcomings in Arabic written databases or datasets, the testing was done by non-standard data set. The presented algorithm structure got recognition ratio about 97%.

scholarly journals The Prediction of Buckling Load of Laminated Composite Hat-Stiffened Panels Under Compressive Loading by Using of Neural Networks

2018 ◽  
Vol 12 (1) ◽  
pp. 468-480 ◽  
Author(s):  
Shashi Kumar ◽  
Rajesh Kumar ◽  
Sasankasekhar Mandal ◽  
Atul K. Rahul
Keyword(s):  
Neural Network ◽  
Finite Element ◽  
Network Architecture ◽  
Laminated Composite ◽  
Buckling Load ◽  
Stiffened Panel ◽  
Stiffness Ratio ◽  
Data Set ◽  
Stiffened Panels ◽  
Structural Problems

Background:Stiffened panels are being used as a lightweight structure in aerospace, marine engineering and retrofitting of building and bridge structure. In this paper, two efficient analytical computational tools, namely, Finite Element Analysis (FEA) and Artificial Neural Network (ANN) are used to analyze and compare the results of the laminated composite 750-hat-stiffened panels.Objective:Finite Element (FE) is an efficient and versatile method for the analysis of a complex problem. FE models have been used to generate data set of four different parameters. The four parameters are extensional stiffness ratio of skin in the longitudinal direction to the transverse direction, orthotropy ratio of the panel, the ratio of twisting stiffness to transverse flexural stiffness and smeared extensional stiffness ratio of stiffeners to that of the plate.Results and Conclusion:For training of ANN, multilayer feedforward back-propagation has been used as a network function with two-hidden layers in the neural network. The good network architecture is achieved after several iterations to predict the buckling load of the stiffened panel. ANN prediction for unknown new data set is in good agreement with FEA results of different cases, which show that ANN tool can be used for the design of complex structural problems in civil engineering and optimization of the laminated composite stiffened panel.

scholarly journals A Novel Convolutional Neural Network Architecture for SAR Target Recognition

2019 ◽  
Vol 2019 ◽  
pp. 1-9 ◽  
Author(s):  
Yinjie Xie ◽  
Wenxin Dai ◽  
Zhenxin Hu ◽  
Yijing Liu ◽  
Chuan Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Target Recognition ◽  
Automatic Target Recognition ◽  
Neural Network Architecture ◽  
Data Set ◽  
Stationary Target ◽  
Optical Images

Among many improved convolutional neural network (CNN) architectures in the optical image classification, only a few were applied in synthetic aperture radar (SAR) automatic target recognition (ATR). One main reason is that direct transfer of these advanced architectures for the optical images to the SAR images easily yields overfitting due to its limited data set and less features relative to the optical images. Thus, based on the characteristics of the SAR image, we proposed a novel deep convolutional neural network architecture named umbrella. Its framework consists of two alternate CNN-layer blocks. One block is a fusion of six 3-layer paths, which is used to extract diverse level features from different convolution layers. The other block is composed of convolution layers and pooling layers are mainly utilized to reduce dimensions and extract hierarchical feature information. The combination of the two blocks could extract rich features from different spatial scale and simultaneously alleviate overfitting. The performance of the umbrella model was validated by the Moving and Stationary Target Acquisition and Recognition (MSTAR) benchmark data set. This architecture could achieve higher than 99% accuracy for the classification of 10-class targets and higher than 96% accuracy for the classification of 8 variants of the T72 tank, even in the case of diverse positions located by targets. The accuracy of our umbrella is superior to the current networks applied in the classification of MSTAR. The result shows that the umbrella architecture possesses a very robust generalization capability and will be potential for SAR-ART.

scholarly journals Memristor Based Binary Convolutional Neural Network Architecture With Configurable Neurons

2021 ◽  
Vol 15 ◽  
Author(s):  
Lixing Huang ◽  
Jietao Diao ◽  
Hongshan Nie ◽  
Wei Wang ◽  
Zhiwei Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
High Precision ◽  
Network Architecture ◽  
Large Scale ◽  
Network Performance ◽  
Recognition Accuracy ◽  
Activation Function ◽  
Data Set ◽  
Neuron Activation

The memristor-based convolutional neural network (CNN) gives full play to the advantages of memristive devices, such as low power consumption, high integration density, and strong network recognition capability. Consequently, it is very suitable for building a wearable embedded application system and has broad application prospects in image classification, speech recognition, and other fields. However, limited by the manufacturing process of memristive devices, high-precision weight devices are currently difficult to be applied in large-scale. In the same time, high-precision neuron activation function also further increases the complexity of network hardware implementation. In response to this, this paper proposes a configurable full-binary convolutional neural network (CFB-CNN) architecture, whose inputs, weights, and neurons are all binary values. The neurons are proportionally configured to two modes for different non-ideal situations. The architecture performance is verified based on the MNIST data set, and the influence of device yield and resistance fluctuations under different neuron configurations on network performance is also analyzed. The results show that the recognition accuracy of the 2-layer network is about 98.2%. When the yield rate is about 64% and the hidden neuron mode is configured as −1 and +1, namely ±1 MD, the CFB-CNN architecture achieves about 91.28% recognition accuracy. Whereas the resistance variation is about 26% and the hidden neuron mode configuration is 0 and 1, namely 01 MD, the CFB-CNN architecture gains about 93.43% recognition accuracy. Furthermore, memristors have been demonstrated as one of the most promising devices in neuromorphic computing for its synaptic plasticity. Therefore, the CFB-CNN architecture based on memristor is SNN-compatible, which is verified using the number of pulses to encode pixel values in this paper.

scholarly journals Construction of a far-ultraviolet all-sky map from an incomplete survey: application of a deep learning algorithm

2021 ◽  
Vol 502 (3) ◽  
pp. 3200-3209
Author(s):  
Young-Soo Jo ◽  
Yeon-Ju Choi ◽  
Min-Gi Kim ◽  
Chang-Ho Woo ◽  
Kyoung-Wook Min ◽  
...  
Keyword(s):  
Neural Network ◽  
Galaxy Evolution ◽  
Network Architecture ◽  
Learning Algorithm ◽  
Activation Function ◽  
Dense Layer ◽  
Optical Parameters ◽  
Data Set ◽  
Deep Learning Algorithm ◽  
Far Ultraviolet

ABSTRACT We constructed a far-ultraviolet (FUV) all-sky map based on observations from the Far Ultraviolet Imaging Spectrograph (FIMS) aboard the Korean microsatellite Science and Technology SATellite-1. For the ${\sim}20{{\ \rm per\ cent}}$ of the sky not covered by FIMS observations, predictions from a deep artificial neural network were used. Seven data sets were chosen for input parameters, including five all-sky maps of H α, E(B − V), N(H i), and two X-ray bands, with Galactic longitudes and latitudes. 70 ${{\ \rm per\ cent}}$ of the pixels of the observed FIMS data set were randomly selected for training as target parameters and the remaining 30 ${{\ \rm per\ cent}}$ were used for validation. A simple four-layer neural network architecture, which consisted of three convolution layers and a dense layer at the end, was adopted, with an individual activation function for each convolution layer; each convolution layer was followed by a dropout layer. The predicted FUV intensities exhibited good agreement with Galaxy Evolution Explorer observations made in a similar FUV wavelength band for high Galactic latitudes. As a sample application of the constructed map, a dust scattering simulation was conducted with model optical parameters and a Galactic dust model for a region that included observed and predicted pixels. Overall, FUV intensities in the observed and predicted regions were reproduced well.

scholarly journals Neural Network Analysis of Dynamic Fracture in a Layered Material

MRS Advances ◽  
2019 ◽  
Vol 4 (19) ◽  
pp. 1109-1117 ◽  
Author(s):  
Pankaj Rajak ◽  
Rajiv K. Kalia ◽  
Aiichiro Nakano ◽  
Priya Vashishta
Keyword(s):  
Neural Network ◽  
Dynamic Fracture ◽  
Network Architecture ◽  
Md Simulation ◽  
Structural Phase ◽  
Feature Learning ◽  
Training Data ◽  
Model Complexity ◽  
Feed Forward Neural Network ◽  
Data Set

AbstractDynamic fracture of a two-dimensional MoWSe2 membrane is studied with molecular dynamics (MD) simulation. The system consists of a random distribution of WSe2 patches in a pre-cracked matrix of MoSe2. Under strain, the system shows toughening due to crack branching, crack closure and strain-induced structural phase transformation from 2H to 1T crystal structures. Different structures generated during MD simulation are analyzed using a three-layer, feed-forward neural network (NN) model. A training data set of 36,000 atoms is created where each atom is represented by a 50-dimension feature vector consisting of radial and angular symmetry functions. Hyper parameters of the symmetry functions and network architecture are tuned to minimize model complexity with high predictive power using feature learning, which shows an increase in model accuracy from 67% to 95%. The NN model classifies each atom in one of the six phases which are either as transition metal or chalcogen atoms in 2H phase, 1T phase and defects. Further t-SNE analyses of learned representation of these phases in the hidden layers of the NN model show that separation of all phases become clearer in the third layer than in layers 1 and 2.

scholarly journals Variable Structure Neural Networks for Adaptive Robust Control Using Evolutionary Artificial Potential Fields

2013 ◽  
Vol 64 (1) ◽  
pp. 3-11 ◽  
Author(s):  
Hassen Mekki ◽  
Mohamed Chtourou
Keyword(s):  
Neural Network ◽  
Network Architecture ◽  
Variable Structure ◽  
Adaptive Robust Control ◽  
Potential Fields ◽  
Design Strategies ◽  
Data Set ◽  
Artificial Potential Fields ◽  
The Stability ◽  
Adaptation Law

A novel neural network architecture, is proposed and shown to be useful in approximating the unknown nonlinearities of dynamical systems. In the variable structure neural network, the number of basis functions can be either increased or decreased with time according to specified design strategies so that the network will not overfit or underfit the data set. Based on the Gaussian radial basis function (GRBF) variable neural network, an adaptive state feedback controller is presented. The location of the centers of the GRBFs is analyzed using a new method inspired from evolutionary artificial potential fields method combined with a pruning algorithm. Using this method we can guarantee a minimal number of neuron. It is in noted, that both the recruitment and the pruning is made by a single neuron. Consequently, the recruitment phase does not perturb the network and the pruning does not provoke an oscillation of the output response. The weights of neural network are adapted using a Lyapunov approach. Moreover, the stability of the system can be analyzed and guaranteed by introducing the supervisory controller and modified adaptation law with projection.

scholarly journals A Cascade Graph Convolutional Network for Predicting Protein–Ligand Binding Affinity

2021 ◽  
Vol 22 (8) ◽  
pp. 4023
Author(s):  
Huimin Shen ◽  
Youzhi Zhang ◽  
Chunhou Zheng ◽  
Bing Wang ◽  
Peng Chen
Keyword(s):  
Neural Network ◽  
Ligand Binding ◽  
Convolutional Neural Network ◽  
Binding Affinity ◽  
Network Architecture ◽  
Original Data ◽  
Ligand Complex ◽  
Convolutional Network ◽  
Data Set ◽  
Irregular Data

Accurate prediction of binding affinity between protein and ligand is a very important step in the field of drug discovery. Although there are many methods based on different assumptions and rules do exist, prediction performance of protein–ligand binding affinity is not satisfactory so far. This paper proposes a new cascade graph-based convolutional neural network architecture by dealing with non-Euclidean irregular data. We represent the molecule as a graph, and use a simple linear transformation to deal with the sparsity problem of the one-hot encoding of original data. The first stage adopts ARMA graph convolutional neural network to learn the characteristics of atomic space in the protein–ligand complex. In the second stage, one variant of the MPNN graph convolutional neural network is introduced with chemical bond information and interactive atomic features. Finally, the architecture passes through the global add pool and the fully connected layer, and outputs a constant value as the predicted binding affinity. Experiments on the PDBbind v2016 data set showed that our method is better than most of the current methods. Our method is also comparable to the state-of-the-art method on the data set, and is more intuitive and simple.

scholarly journals A Novel Method for L Band SAR Image Segmentation Based on Pulse Coupled Neural Network

2021 ◽  
Vol 4 (2) ◽  
pp. 117
Author(s):  
Harwikarya Harwikarya ◽  
Sabar Rudiarto ◽  
Glorin Sebastian
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Network Architecture ◽  
Third Generation ◽  
Sar Image ◽  
Neural Network Architecture ◽  
Pulse Coupled Neural Network ◽  
Sar Image Segmentation ◽  
Novel Method ◽  
L Band

Pulse Coupled Neural Network (PCNN) is claimed as a third generation neural network. PCNN has wide purpose in image processing  such as segmentation, feature extraction, sharpening etc.  Not like another neural network architecture, PCNN do not need training. The only weaknes point  of PCNN is parameter tune due to  seven parameters in its five equations. In this research we proposed a novel method for segmentation based on modified PCNN.  In order to evaluate the proposed method, we processed L Band Multipolarisation  Synthetic Apperture Radar Image. The Results showed all area extracted both by using PCNN and ICM-PCNN from the SAR image are match to the groundtruth. There fore the proposed method is work properly.Copyright © 2017  International Journal of  Artificial Intelegence Research.All rights reserved.

Underwater Image Segmentation Using Human Psycho Visual Phenomenon

2018 ◽  
pp. 130-146 ◽  
Author(s):  
Soumyadip Dhar ◽  
Hiranmoy Roy
Keyword(s):  
Image Segmentation ◽  
Wavelet Packet ◽  
Data Set ◽  
Standard Data ◽  
Underwater Image ◽  
Large Numbers ◽  
Visual Technique ◽  
Visual Phenomenon ◽  
Novel Method ◽  
Adaptive Basis Selection

In this chapter, a novel method is proposed for underwater image segmentation based on human psycho visual phenomenon (HVS). In the proposed method the texture property of an image is captured by decomposing it into frequency sub-bands using M-band wavelet packet transform. The sub-bands represent the image in different scales and orientations. The large numbers of sub-bands are pruned by an adaptive basis selection. The proper sub-bands for segmentation are selected depending on the HVS. The HVS imitates the original visual technique of a human being and it is used to divide each sub-band in Weber, De-Vries Rose, and saturation regions. A wavelet packet sub-band is selected for segmentation depending on those three regions. The performance of the proposed method is found to be superior to that of the state-of-the-art methods for underwater image segmentation on standard data set.

Sign in / Sign up

Export Citation Format

Share Document