scholarly journals A Phase Filtering Method with Scale Recurrent Networks for InSAR

2020 ◽  
Vol 12 (20) ◽  
pp. 3453
Author(s):  
Liming Pu ◽  
Xiaoling Zhang ◽  
Zenan Zhou ◽  
Jun Shi ◽  
Shunjun Wei ◽  
...  
Keyword(s):  
Deep Learning ◽  
Structural Phase ◽  
Input Image ◽  
Deformation Monitoring ◽  
Feature Maps ◽  
Data Set ◽  
Real Time Processing ◽  
Practical Applications ◽  
Filtering Method ◽  
Interferometric Phase

Phase filtering is a key issue in interferometric synthetic aperture radar (InSAR) applications, such as deformation monitoring and topographic mapping. The accuracy of the deformation and terrain height is highly dependent on the quality of phase filtering. Researchers are committed to continuously improving the accuracy and efficiency of phase filtering. Inspired by the successful application of neural networks in SAR image denoising, in this paper we propose a phase filtering method that is based on deep learning to efficiently filter out the noise in the interferometric phase. In this method, the real and imaginary parts of the interferometric phase are filtered while using a scale recurrent network, which includes three single scale subnetworks based on the encoder-decoder architecture. The network can utilize the global structural phase information contained in the different-scaled feature maps, because RNN units are used to connect the three different-scaled subnetworks and transmit current state information among different subnetworks. The encoder part is used for extracting the phase features, and the decoder part restores detailed information from the encoded feature maps and makes the size of the output image the same as that of the input image. Experiments on simulated and real InSAR data prove that the proposed method is superior to three widely-used phase filtering methods by qualitative and quantitative comparisons. In addition, on the same simulated data set, the overall performance of the proposed method is better than another deep learning-based method (DeepInSAR). The runtime of the proposed method is only about 0.043s for an image with a size of 1024×1024 pixels, which has the significant advantage of computational efficiency in practical applications that require real-time processing.

scholarly journals Time-ResNeXt for epilepsy recognition based on EEG signals in wireless networks

2020 ◽  
Vol 2020 (1) ◽  
Author(s):  
Shaoqiang Wang ◽  
Shudong Wang ◽  
Song Zhang ◽  
Yifan Wang
Keyword(s):  
Deep Learning ◽  
Network Structure ◽  
Signal Recognition ◽  
Eeg Signals ◽  
Real World Data ◽  
Data Set ◽  
Practical Applications ◽  
Epilepsy Diagnosis ◽  
Single Data ◽  
Electroencephalogram Eeg

Abstract To automatically detect dynamic EEG signals to reduce the time cost of epilepsy diagnosis. In the signal recognition of electroencephalogram (EEG) of epilepsy, traditional machine learning and statistical methods require manual feature labeling engineering in order to show excellent results on a single data set. And the artificially selected features may carry a bias, and cannot guarantee the validity and expansibility in real-world data. In practical applications, deep learning methods can release people from feature engineering to a certain extent. As long as the focus is on the expansion of data quality and quantity, the algorithm model can learn automatically to get better improvements. In addition, the deep learning method can also extract many features that are difficult for humans to perceive, thereby making the algorithm more robust. Based on the design idea of ResNeXt deep neural network, this paper designs a Time-ResNeXt network structure suitable for time series EEG epilepsy detection to identify EEG signals. The accuracy rate of Time-ResNeXt in the detection of EEG epilepsy can reach 91.50%. The Time-ResNeXt network structure produces extremely advanced performance on the benchmark dataset (Berne-Barcelona dataset) and has great potential for improving clinical practice.

scholarly journals SIAMESE NETWORK COMBINED WITH ATTENTION MECHANISM FOR OBJECT TRACKING

2020 ◽  
Vol XLIII-B2-2020 ◽  
pp. 1315-1322
Author(s):  
D. Zhang ◽  
J. Lv ◽  
Z. Cheng ◽  
Y. Bai ◽  
Y. Cao
Keyword(s):  
Deep Learning ◽  
Object Tracking ◽  
Network Model ◽  
Input Image ◽  
Attention Mechanism ◽  
Tracking Algorithm ◽  
Learning Object ◽  
Feature Maps ◽  
Siamese Network ◽  
Network Object

Abstract. After the development of deep learning object tracking methods in recent years, the fully convolutional siamese network object tracking algorithm SiamFC has become a more classic deep learning object tracking algorithm. In view of the problem that the accuracy of the tracking results of SiamFC will be reduced in the case of complex backgrounds, this paper introduces the attention mechanism based on the SiamFC, which performs channel and spatial weighting on the feature maps obtained by convolution of the input image. At the same time, the backbone network model of CNN in the algorithm is adjusted, then the siamese network combined with attention mechanism for object tracking is proposed. It can strengthen the effectiveness of the results of feature extraction and enhance the ability of the network model to discriminate targets. In this paper, the algorithm is tested on the OTB2015, VOT2016 and VOT2017 datasets, and compared with multiple object tracking algorithms. Experimental results show that the algorithm in this paper can better solve the complex background problem in object tracking, and has certain advantages compared with other algorithms.

scholarly journals Comparative Analysis of Deep Neural Networks for the Detection and Decoding of Data Matrix Landmarks in Cluttered Indoor Environments

2021 ◽  
Vol 103 (1) ◽  
Author(s):  
Tiago Almeida ◽  
Vitor Santos ◽  
Oscar Martinez Mozos ◽  
Bernardo Lourenço
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Input Image ◽  
Automated Guided Vehicles ◽  
Data Matrix ◽  
Single Shot ◽  
Indoor Environments ◽  
Data Set ◽  
Valid Solution

AbstractData Matrix patterns imprinted as passive visual landmarks have shown to be a valid solution for the self-localization of Automated Guided Vehicles (AGVs) in shop floors. However, existing Data Matrix decoding applications take a long time to detect and segment the markers in the input image. Therefore, this paper proposes a pipeline where the detector is based on a real-time Deep Learning network and the decoder is a conventional method, i.e. the implementation in libdmtx. To do so, several types of Deep Neural Networks (DNNs) for object detection were studied, trained, compared, and assessed. The architectures range from region proposals (Faster R-CNN) to single-shot methods (SSD and YOLO). This study focused on performance and processing time to select the best Deep Learning (DL) model to carry out the detection of the visual markers. Additionally, a specific data set was created to evaluate those networks. This test set includes demanding situations, such as high illumination gradients in the same scene and Data Matrix markers positioned in skewed planes. The proposed approach outperformed the best known and most used Data Matrix decoder available in libraries like libdmtx.

scholarly journals Attention neural collaboration filtering based on GRU for recommender systems

2021 ◽  
Author(s):  
Hongbin Xia ◽  
Yang Luo ◽  
Yuan Liu
Keyword(s):  
Deep Learning ◽  
Collaborative Filtering ◽  
Recommendation System ◽  
Auxiliary Information ◽  
User Preferences ◽  
Feature Representation ◽  
Long Distance ◽  
Data Set ◽  
Filtering Method ◽  
The Impact

AbstractThe collaborative filtering method is widely used in the traditional recommendation system. The collaborative filtering method based on matrix factorization treats the user’s preference for the item as a linear combination of the user and the item latent vectors, and cannot learn a deeper feature representation. In addition, the cold start and data sparsity remain major problems for collaborative filtering. To tackle these problems, some scholars have proposed to use deep neural network to extract text information, but did not consider the impact of long-distance dependent information and key information on their models. In this paper, we propose a neural collaborative filtering recommender method that integrates user and item auxiliary information. This method fully integrates user-item rating information, user assistance information and item text assistance information for feature extraction. First, Stacked Denoising Auto Encoder is used to extract user features, and Gated Recurrent Unit with auxiliary information is used to extract items’ latent vectors, respectively. The attention mechanism is used to learn key information when extracting text features. Second, the latent vectors learned by deep learning techniques are used in multi-layer nonlinear networks to learn more abstract and deeper feature representations to predict user preferences. According to the verification results on the MovieLens data set, the proposed model outperforms other traditional approaches and deep learning models making it state of the art.

scholarly journals Time-ResNeXt for epilepsy recognition based on EEG signals

2019 ◽  
Author(s):  
shaoqiang Wang ◽  
Yifan Wang ◽  
Shudong Wang
Keyword(s):  
Deep Learning ◽  
Network Structure ◽  
Signal Recognition ◽  
Eeg Signals ◽  
Real World Data ◽  
Data Set ◽  
Practical Applications ◽  
Epilepsy Diagnosis ◽  
Single Data ◽  
Electroencephalogram Eeg

AbstractObjectiveTo automatically detect dynamic EEG signals to reduce the time cost of epilepsy diagnosis. In the signal recognition of electroencephalogram (EEG) of epilepsy, traditional machine learning and statistical methods require manual feature labeling engineering in order to show excellent results on a single data set. And the artificially selected features may carry a bias, and cannot guarantee the validity and expansibility in real-world data. In practical applications, deep learning methods can release people from feature engineering to a certain extent. As long as the focus is on the expansion of data quality and quantity, the algorithm model can learn automatically to get better improvements. In addition, the deep learning method can also extract many features that are difficult for humans to perceive, thereby making the algorithm more robust.MethodBased on the design idea of ResNeXt deep neural network, this paper designs a Time-ResNeXt network structure suitable for time series EEG epilepsy detection to identify EEG signals.ResultsThe accuracy rate of Time-ResNeXt in the detection of EEG epilepsy can reach 90.50%.ConclusionThe Time-ResNeXt network structure produces extremely advanced performance on the benchmark dataset (Berne-Barcelona dataset), and has great potential for improving clinical practice.

MFNet algorithm based on indoor scene segmentation

2021 ◽  
pp. 1-10
Author(s):  
Rui Cao ◽  
Feng Jiang ◽  
Zhao Wu ◽  
Jia Ren
Keyword(s):  
Deep Learning ◽  
Learning Task ◽  
Vital Role ◽  
Scene Segmentation ◽  
Feature Maps ◽  
Real Time Processing ◽  
Multi Scale ◽  
Indoor Scene ◽  
Convolution Kernels ◽  
Hardware Platforms

With the advancement of computer performance, deep learning is playing a vital role on hardware platforms. Indoor scene segmentation is a challenging deep learning task because indoor objects tend to obscure each other, and the dense layout increases the difficulty of segmentation. Still, current networks pursue accuracy improvement, sacrifice speed, and augment memory resource usage. To solve this problem, achieve a compromise between accuracy, speed, and model size. This paper proposes Multichannel Fusion Network (MFNet) for indoor scene segmentation, which mainly consists of Dense Residual Module(DRM) and Multi-scale Feature Extraction Module(MFEM). MFEM uses depthwise separable convolution to cut the number of parameters, matches different sizes of convolution kernels and dilation rates to achieve optimal receptive field; DRM fuses feature maps at several levels of resolution to optimize segmentation details. Experimental results on the NYU V2 dataset show that the proposed method achieves very competitive results compared with other advanced algorithms, with a segmentation speed of 38.47 fps, nearly twice that of Deeplab v3+, but only 1/5 of the number of parameters of Deeplab v3 + . Its segmentation results were close to those of advanced segmentation networks, making it beneficial for the real-time processing of images.

scholarly journals Transforming Retinal Photographs to Entropy Images in Deep Learning to Improve Automated Detection for Diabetic Retinopathy

2018 ◽  
Vol 2018 ◽  
pp. 1-6 ◽  
Author(s):  
Gen-Min Lin ◽  
Mei-Juan Chen ◽  
Chia-Hung Yeh ◽  
Yu-Yang Lin ◽  
Heng-Yu Kuo ◽  
...  
Keyword(s):  
Diabetic Retinopathy ◽  
Deep Learning ◽  
Sensitivity And Specificity ◽  
Block Size ◽  
Detection Accuracy ◽  
Data Sets ◽  
Feature Maps ◽  
Data Set ◽  
Fundus Photographs ◽  
Grade 3

Entropy images, representing the complexity of original fundus photographs, may strengthen the contrast between diabetic retinopathy (DR) lesions and unaffected areas. The aim of this study is to compare the detection performance for severe DR between original fundus photographs and entropy images by deep learning. A sample of 21,123 interpretable fundus photographs obtained from a publicly available data set was expanded to 33,000 images by rotating and flipping. All photographs were transformed into entropy images using block size 9 and downsized to a standard resolution of 100 × 100 pixels. The stages of DR are classified into 5 grades based on the International Clinical Diabetic Retinopathy Disease Severity Scale: Grade 0 (no DR), Grade 1 (mild nonproliferative DR), Grade 2 (moderate nonproliferative DR), Grade 3 (severe nonproliferative DR), and Grade 4 (proliferative DR). Of these 33,000 photographs, 30,000 images were randomly selected as the training set, and the remaining 3,000 images were used as the testing set. Both the original fundus photographs and the entropy images were used as the inputs of convolutional neural network (CNN), and the results of detecting referable DR (Grades 2–4) as the outputs from the two data sets were compared. The detection accuracy, sensitivity, and specificity of using the original fundus photographs data set were 81.80%, 68.36%, 89.87%, respectively, for the entropy images data set, and the figures significantly increased to 86.10%, 73.24%, and 93.81%, respectively (all p values <0.001). The entropy image quantifies the amount of information in the fundus photograph and efficiently accelerates the generating of feature maps in the CNN. The research results draw the conclusion that transformed entropy imaging of fundus photographs can increase the machinery detection accuracy, sensitivity, and specificity of referable DR for the deep learning-based system.

scholarly journals A Dynamic Learning Method for the Classification of the HEp-2 Cell Images

Electronics ◽  
2019 ◽  
Vol 8 (8) ◽  
pp. 850 ◽  
Author(s):  
Caleb Vununu ◽  
Suk-Hwan Lee ◽  
Oh-Jun Kwon ◽  
Ki-Ryong Kwon
Keyword(s):  
Deep Learning ◽  
Input Image ◽  
Complete Analysis ◽  
Discrete Wavelet ◽  
Significant Heterogeneity ◽  
Feature Maps ◽  
Dynamic Learning ◽  
Analysis Of The Images

The complete analysis of the images representing the human epithelial cells of type 2, commonly referred to as HEp-2 cells, is one of the most important tasks in the diagnosis procedure of various autoimmune diseases. The problem of the automatic classification of these images has been widely discussed since the unfolding of deep learning-based methods. Certain datasets of the HEp-2 cell images exhibit an extreme complexity due to their significant heterogeneity. We propose in this work a method that tackles specifically the problem related to this disparity. A dynamic learning process is conducted with different networks taking different input variations in parallel. In order to emphasize the localized changes in intensity, the discrete wavelet transform is used to produce different versions of the input image. The approximation and detail coefficients are fed to four different deep networks in a parallel learning paradigm in order to efficiently homogenize the features extracted from the images that have different intensity levels. The feature maps from these different networks are then concatenated and passed to the classification layers to produce the final type of the cellular image. The proposed method was tested on a public dataset that comprises images from two intensity levels. The significant heterogeneity of this dataset limits the discrimination results of some of the state-of-the-art deep learning-based methods. We have conducted a comparative study with these methods in order to demonstrate how the dynamic learning proposed in this work manages to significantly minimize this heterogeneity related problem, thus boosting the discrimination results.

scholarly journals Addressing Overfitting Problem in Deep Learning-Based Solutions for Next Generation Data-Driven Networks

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Mansheng Xiao ◽  
Yuezhong Wu ◽  
Guocai Zuo ◽  
Shuangnan Fan ◽  
Huijun Yu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Data Driven ◽  
Next Generation Networks ◽  
Next Generation ◽  
Data Set ◽  
Practical Applications ◽  
Maximum Value ◽  
Network Problems ◽  
Overfitting Problem

Next-generation networks are data-driven by design but face uncertainty due to various changing user group patterns and the hybrid nature of infrastructures running these systems. Meanwhile, the amount of data gathered in the computer system is increasing. How to classify and process the massive data to reduce the amount of data transmission in the network is a very worthy problem. Recent research uses deep learning to propose solutions for these and related issues. However, deep learning faces problems like overfitting that may undermine the effectiveness of its applications in solving different network problems. This paper considers the overfitting problem of convolutional neural network (CNN) models in practical applications. An algorithm for maximum pooling dropout and weight attenuation is proposed to avoid overfitting. First, design the maximum value pooling dropout in the pooling layer of the model to sparse the neurons and then introduce the regularization based on weight attenuation to reduce the complexity of the model when the gradient of the loss function is calculated by backpropagation. Theoretical analysis and experiments show that the proposed method can effectively avoid overfitting and can reduce the error rate of data set classification by more than 10% on average than other methods. The proposed method can improve the quality of different deep learning-based solutions designed for data management and processing in next-generation networks.

Internet of things image recognition system based on deep learning

2021 ◽  
pp. 1-9
Author(s):  
Jing Li ◽  
Xinfang Li ◽  
Yuwen Ning
Keyword(s):  
Deep Learning ◽  
Internet Of Things ◽  
Image Recognition ◽  
Image Annotation ◽  
Feature Representation ◽  
Support Vector ◽  
Training Algorithms ◽  
Neural Network Models ◽  
Data Set ◽  
Practical Applications

At present, many exciting results have been achieved in the application of deep learning to image recognition. However, there are still many problems to be overcome before deep learning is used in practical applications such as image retrieval, image annotation, and image-text conversion. This paper studies the structure of deep learning, improves the commonly used training algorithms, and proposes two new neural network models for different application scenarios. This paper uses Support Vector Machine (SVM) as the main classifier for Internet of Things image recognition and uses the database of this paper to train SVM and CNN. At the same time, the effectiveness of the two for image recognition is tested, and the trained classifier is used for image recognition. The result surface: In the labeled data set, the rank-1 accuracy of CNN is 85.77%, which is higher than 90.28% of the SVM method. In the detection data, CNN’s rank-1 accuracy rate is 83.11%, which also exceeds SVM’s 80.22%. SVM+CNN has a rank 1 value of 84.69% for the detection data set. This shows that deep learning can map the feature representation of the image and the feature representation of the word to the same space, making the calculation of the similarity and correlation between the image and the text easier and more straightforward.

Sign in / Sign up

Export Citation Format

Share Document