scholarly journals TAI-SARNET: Deep Transferred Atrous-Inception CNN for Small Samples SAR ATR

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1724
Author(s):  
Zilu Ying ◽  
Chen Xuan ◽  
Yikui Zhai ◽  
Bing Sun ◽  
Jingwen Li ◽  
...  
Keyword(s):  
Transfer Learning ◽  
Network Architecture ◽  
Learning Strategy ◽  
Target Recognition ◽  
Recognition Performance ◽  
Recognition Rate ◽  
Speckle Noise ◽  
Small Sample ◽  
Operating Conditions ◽  
Small Samples

Since Synthetic Aperture Radar (SAR) targets are full of coherent speckle noise, the traditional deep learning models are difficult to effectively extract key features of the targets and share high computational complexity. To solve the problem, an effective lightweight Convolutional Neural Network (CNN) model incorporating transfer learning is proposed for better handling SAR targets recognition tasks. In this work, firstly we propose the Atrous-Inception module, which combines both atrous convolution and inception module to obtain rich global receptive fields, while strictly controlling the parameter amount and realizing lightweight network architecture. Secondly, the transfer learning strategy is used to effectively transfer the prior knowledge of the optical, non-optical, hybrid optical and non-optical domains to the SAR target recognition tasks, thereby improving the model’s recognition performance on small sample SAR target datasets. Finally, the model constructed in this paper is verified to be 97.97% on ten types of MSTAR datasets under standard operating conditions, reaching a mainstream target recognition rate. Meanwhile, the method presented in this paper shows strong robustness and generalization performance on a small number of randomly sampled SAR target datasets.

scholarly journals An Integrated Counterfactual Sample Generation and Filtering Approach for SAR Automatic Target Recognition with a Small Sample Set

2021 ◽  
Vol 13 (19) ◽  
pp. 3864
Author(s):  
Changjie Cao ◽  
Zongyong Cui ◽  
Zongjie Cao ◽  
Liying Wang ◽  
Jianyu Yang
Keyword(s):  
Target Recognition ◽  
Recognition Performance ◽  
Recognition Rate ◽  
Automatic Target Recognition ◽  
Small Sample ◽  
Generative Adversarial Networks ◽  
Training Set ◽  
Stationary Target ◽  
Sample Set ◽  
Filtering Approach

Although automatic target recognition (ATR) models based on data-driven algorithms have achieved excellent performance in recent years, the synthetic aperture radar (SAR) ATR model often suffered from performance degradation when it encountered a small sample set. In this paper, an integrated counterfactual sample generation and filtering approach is proposed to alleviate the negative influence of a small sample set. The proposed method consists of a generation component and a filtering component. First, the proposed generation component utilizes the overfitting characteristics of generative adversarial networks (GANs), which ensures the generation of counterfactual target samples. Second, the proposed filtering component is built by learning different recognition functions. In the proposed filtering component, multiple SVMs trained by different SAR target sample sets provide pseudo-labels to the other SVMs to improve the recognition rate. Then, the proposed approach improves the performance of the recognition model dynamically while it continuously generates counterfactual target samples. At the same time, counterfactual target samples that are beneficial to the ATR model are also filtered. Moreover, ablation experiments demonstrate the effectiveness of the various components of the proposed method. Experimental results based on the Moving and Stationary Target Acquisition and Recognition (MSTAR) and OpenSARship dataset also show the advantages of the proposed approach. Even though the size of the constructed training set was 14.5% of the original training set, the recognition performance of the ATR model reached 91.27% with the proposed approach.

scholarly journals Target Recognition in SAR Images Based on Multiresolution Representations with 2D Canonical Correlation Analysis

2020 ◽  
Vol 2020 ◽  
pp. 1-9 ◽  
Author(s):  
Xiaojing Tan ◽  
Ming Zou ◽  
Xiqin He
Keyword(s):  
Correlation Analysis ◽  
Canonical Correlation Analysis ◽  
Canonical Correlation ◽  
Target Recognition ◽  
Recognition Performance ◽  
Recognition Rate ◽  
Operating Conditions ◽  
Data Set ◽  
Stationary Target ◽  
Sar Target Recognition

This study proposes a synthetic aperture radar (SAR) target-recognition method based on the fused features from the multiresolution representations by 2D canonical correlation analysis (2DCCA). The multiresolution representations were demonstrated to be more discriminative than the solely original image. So, the joint classification of the multiresolution representations is beneficial to the enhancement of SAR target recognition performance. 2DCCA is capable of exploiting the inner correlations of the multiresolution representations while significantly reducing the redundancy. Therefore, the fused features can effectively convey the discrimination capability of the multiresolution representations while relieving the storage and computational burdens caused by the original high dimension. In the classification stage, the sparse representation-based classification (SRC) is employed to classify the fused features. SRC is an effective and robust classifier, which has been extensively validated in the previous works. The moving and stationary target acquisition and recognition (MSTAR) data set is employed to evaluate the proposed method. According to the experimental results, the proposed method could achieve a high recognition rate of 97.63% for the 10 classes of targets under the standard operating condition (SOC). Under the extended operating conditions (EOC) like configuration variance, depression angle variance, and the robustness of the proposed method are also quantitively validated. In comparison with some other SAR target recognition methods, the superiority of the proposed method can be effectively demonstrated.

scholarly journals Voiceprint Identification for Limited Dataset Using the Deep Migration Hybrid Model Based on Transfer Learning

Sensors ◽  
2018 ◽  
Vol 18 (7) ◽  
pp. 2399 ◽  
Author(s):  
Cunwei Sun ◽  
Yuxin Yang ◽  
Chang Wen ◽  
Kai Xie ◽  
Fangqing Wen
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Hybrid Model ◽  
Data Augmentation ◽  
Small Sample ◽  
Restricted Boltzmann Machine ◽  
Small Samples ◽  
Boltzmann Machine ◽  
Training Time

The convolutional neural network (CNN) has made great strides in the area of voiceprint recognition; but it needs a huge number of data samples to train a deep neural network. In practice, it is too difficult to get a large number of training samples, and it cannot achieve a better convergence state due to the limited dataset. In order to solve this question, a new method using a deep migration hybrid model is put forward, which makes it easier to realize voiceprint recognition for small samples. Firstly, it uses Transfer Learning to transfer the trained network from the big sample voiceprint dataset to our limited voiceprint dataset for the further training. Fully-connected layers of a pre-training model are replaced by restricted Boltzmann machine layers. Secondly, the approach of Data Augmentation is adopted to increase the number of voiceprint datasets. Finally, we introduce fast batch normalization algorithms to improve the speed of the network convergence and shorten the training time. Our new voiceprint recognition approach uses the TLCNN-RBM (convolutional neural network mixed restricted Boltzmann machine based on transfer learning) model, which is the deep migration hybrid model that is used to achieve an average accuracy of over 97%, which is higher than that when using either CNN or the TL-CNN network (convolutional neural network based on transfer learning). Thus, an effective method for a small sample of voiceprint recognition has been provided.

scholarly journals Medically-managed Hospital in the Home: 7 year study of mortality and unplanned interruption

2010 ◽  
Vol 34 (3) ◽  
pp. 269 ◽  
Author(s):  
Michael Montalto ◽  
Benjamin Lui ◽  
Ann Mullins ◽  
Katherine Woodmason
Keyword(s):  
Hospital Care ◽  
Nursing Home Residents ◽  
Low Frequency ◽  
Small Sample ◽  
Acute Hospital ◽  
Operating Conditions ◽  
Small Samples ◽  
Hospital Services ◽  
Acute Hospital Care ◽  
The Impact

Background.Hospital in the Home (HIH) research is characterised by small samples in new programs. We sought to examine a large number of consecutive HIH admissions over many years in an established, medically-managed HIH service in to determine whether: (1) HIH is a safe and effective method of delivering acute hospital care, under usual operating conditions in an established unit; and (2) what patient, condition and treatment variables contribute to a greater risk of failure. Method.A survey of all patients admitted to a medically-managed HIH unit from 2000–2007. Results.A total of 3423 admissions to HIH were examined. Of these 2207 (64.5%) were admitted directly into the HIH from Emergency Department or rooms, with the remainder admitted from hospital wards. A total of 26 653 HIH bed days were delivered, with a mean of 9.3 nursing visits and 4.1 medical visits per admission. A total of 143 patients (4.2%) required an interruption via an unplanned return to hospital; 106 (3.1%) did not subsequently return to HIH. The commonest reasons for unplanned returns to hospital were: no clinical improvement; cardiac conditions; fever; breathlessness and pain. Patients over the age of 50, and those receiving intravenous antibiotic therapy, were more likely to require a return to hospital. Two patients died unexpectedly while in HIH, and a further three patients died unexpectedly after their unplanned return to hospital. This is a total unexpected mortality rate of 0.15%. Conclusion.This sample of HIH patients is five times the number of HIH patients ever enrolled in randomised trials studies of this area. Further, outcomes were achieved in ‘ordinary’ working conditions over a long time period. Care was completed without interruption (return to hospital) in 95.8% of all episodes. Interruption was associated with patients referred from inpatient wards, older patients, and patients who were treated with intravenous antibiotics. Patients referred from Emergency Departments experienced fewer interruptions. Nursing home residents were no more likely to require an interruption to their HIH care. What is known about the topic?Hospital in the Home is the delivery of acute hospital services to patients at home. There is no consensus on the best model of HIH. Studies of HIH have small sample sizes, so support for HIH is often qualified. What does this paper add?This paper describes activity and outcomes for 3423 consecutive patients admitted into a medically-managed HIH over 7 years. This represents an extensive long-term survey of HIH patient care outcomes. What are the implications for practitioners?Medically-managed HIH is able to deliver acute hospital care with low rates of unexpected mortality and unplanned returns to hospital. Trials using low frequency events such as mortality and delirium as outcomes will require very large samples, and such large trials are unlikely to occur. The impact of medically-managed HIH on access to acute hospital services for certain diagnostic groups could be significant and deserves further expansion. The concept of hospitalisation can be refined to include HIH.

Two-Dimensional Orthogonal Unsupervised Discriminant Projection

2012 ◽  
Vol 542-543 ◽  
pp. 1343-1346
Author(s):  
Xing Zhu Liang ◽  
Yu E Lin ◽  
Jing Zhao Li
Keyword(s):  
Feature Extraction ◽  
Sample Size ◽  
Recognition Performance ◽  
Small Sample Size ◽  
Recognition Rate ◽  
Small Sample ◽  
Two Dimensional ◽  
Small Sample Size Problem ◽  
Size Problem ◽  
Discriminant Projection

Unsupervised Discriminant Projection (UDP) is one of the most promising feature extraction methods. However, UDP suffers from the small sample size problem and the optimal basis vectors obtained by the UDP are nonorthogonal. In this paper, we present a new method called Two-dimensional Orthogonal Unsupervised Discriminant Projection (2DOUDP), which is not necessary to convert the image matrix into high-dimensional image vector and does not suffer the small sample size problem. To further improve the recognition performance, the orthogonal projection matrix obtained based on Gram–Schmidt orthogonalization is given. Experimental results on ORL database indicate that the proposed 2DOUDP method achieves better recognition rate than the UDP method and some other orthogonal feature extraction algorithms.

Combination of ELM and BEMD for Target Recognition of SAR Images

2021 ◽  
Vol 30 (13) ◽  
Author(s):  
Zhichao Liu ◽  
Baida Qu
Keyword(s):  
Feature Extraction ◽  
Embedded System ◽  
High Efficiency ◽  
Target Recognition ◽  
Recognition Performance ◽  
Recognition Algorithm ◽  
Operating Conditions ◽  
Intrinsic Mode Functions ◽  
Sar Images ◽  
Stationary Target

For the problem of target recognition of synthetic aperture radar (SAR) images, a method based on the combination of bidimensional empirical mode decomposition (BEMD) and extreme learning machine (ELM) is proposed. BEMD performs feature extraction for SAR images, producing multi-layer bidimensional intrinsic mode functions (BIMF). These BIMFs covey the discrimination of the original target while effectively eliminating the noises. ELM conducts the classification of each BIMF with high efficiency and robustness. Finally, the decisions from different BIMFs are fused using a linear weighting strategy to reach a reliable decision on the target label. The proposed method compensates the relatively low adaptivity of ELM to noise corruption by BEMD feature extraction. Moreover, the multi-layer BIMFs provide more discriminative information for correct decision. Hence, the overall recognition performance can be improved. As an efficient recognition algorithm, the proposed method can be used in an embedded system for wide applications. Experiments are designed and implemented on the moving and stationary target acquisition and recognition (MSTAR) dataset. The proposed method is tested under both the standard operating condition (SOC) and extended operating conditions (EOCs). The results reflect its effectiveness and robustness via quantitative comparisons.

scholarly journals The Improvement of DS Evidence Theory and Its Application in IR/MMW Target Recognition

2016 ◽  
Vol 2016 ◽  
pp. 1-15 ◽  
Author(s):  
Yibing Li ◽  
Jie Chen ◽  
Fang Ye ◽  
Dandan Liu
Keyword(s):  
Target Recognition ◽  
Recognition Performance ◽  
Recognition Rate ◽  
Evidence Theory ◽  
Single Mode ◽  
Recognition System ◽  
Battlefield Environment ◽  
Compound Decision ◽  
The Military ◽  
Decision Making Rule

ATR system has a broad application prospect in the military field, especially in the field of modern defense technology. When paradoxes are in existence in ATR system due to adverse battlefield environment, integration cannot be effectively and reliably carried out only by traditional DS evidence theory. In this paper, a modified DS evidence theory is presented and applied in IR/MMW target recognition system. The improvement of DS evidence theory is realized by three parts: the introduction of sensor priority and evidence credibility to realize the discount processing of evidences, the modification of DS combination rule to enhance the accuracy of synthesis results, and the compound decision-making rule. The application of the modified algorithm in IR/MMW system is designed to deal with paradoxes, improve the target recognition rate, and ensure the reliability of target recognition system. Experiments are given to illustrate that the introduction of the modified DS evidence theory in IR/MMW system is better able to realize satisfactory target recognition performance through multisensor information fusion than any single-mode system.

scholarly journals Research on Airport Target Recognition under Low-Visibility Condition Based on Transfer Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Jiajun Li ◽  
Yongzhong Wang ◽  
Yuexin Qian ◽  
Tianyi Xu ◽  
Kaiwen Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Transfer Learning ◽  
Deep Neural Network ◽  
Target Recognition ◽  
Recognition Rate ◽  
Aviation Industry ◽  
Enhancement Effect ◽  
Learning Networks ◽  
Low Visibility ◽  
Bad Weather

Operational safety in the airport is the focus of the aviation industry. Target recognition under low visibility plays an essential role in arranging the circulation of objects in the airport field, identifying unpredictable obstacles in time, and monitoring aviation operation and ensuring its safety and efficiency. From the perspective of transfer learning, this paper will explore the identification of all targets (mainly including aircraft, humans, ground vehicles, hangars, and birds) in the airport field under low-visibility conditions (caused by bad weather such as fog, rain, and snow). First, a variety of deep transfer learning networks are used to identify well-visible airport targets. The experimental results show that GoogLeNet is more effective, with a recognition rate of more than 90.84%. However, the recognition rates of this method are greatly reduced under the condition of low visibility; some are even less than 10%. Therefore, the low-visibility image is processed with 11 different fog removals and vision enhancement algorithms, and then, the GoogLeNet deep neural network algorithm is used to identify the image. Finally, the target recognition rate can be significantly improved to more than 60%. According to the results, the dark channel algorithm has the best image defogging enhancement effect, and the GoogLeNet deep neural network has the highest target recognition rate.

scholarly journals Radar HRRP Target Recognition Based on Dynamic Learning with Limited Training Data

2021 ◽  
Vol 13 (4) ◽  
pp. 750
Author(s):  
Jingjing Wang ◽  
Zheng Liu ◽  
Rong Xie ◽  
Lei Ran
Keyword(s):  
Test Data ◽  
Learning Strategy ◽  
Target Recognition ◽  
Recognition Performance ◽  
Constraint Propagation ◽  
Automatic Target Recognition ◽  
Label Propagation ◽  
Training Data ◽  
Dynamic Learning ◽  
Radar Automatic Target Recognition

For high-resolution range profile (HRRP)-based radar automatic target recognition (RATR), adequate training data are required to characterize a target signature effectively and get good recognition performance. However, collecting enough training data involving HRRP samples from each target orientation is hard. To tackle the HRRP-based RATR task with limited training data, a novel dynamic learning strategy is proposed based on the single-hidden layer feedforward network (SLFN) with an assistant classifier. In the offline training phase, the training data are used for pretraining the SLFN using a reduced kernel extreme learning machine (RKELM). In the online classification phase, the collected test data are first labeled by fusing the recognition results of the current SLFN and assistant classifier. Then the test samples with reliable pseudolabels are used as additional training data to update the parameters of SLFN with the online sequential RKELM (OS-RKELM). Moreover, to improve the accuracy of label estimation for test data, a novel semi-supervised learning method named constraint propagation-based label propagation (CPLP) was developed as an assistant classifier. The proposed method dynamically accumulates knowledge from training and test data through online learning, thereby reinforcing performance of the RATR system with limited training data. Experiments conducted on the simulated HRRP data from 10 civilian vehicles and real HRRP data from three military vehicles demonstrated the effectiveness of the proposed method when the training data are limited.

scholarly journals Novel MOA Fault Detection Technology Based on Small Sample Infrared Image

Electronics ◽  
2021 ◽  
Vol 10 (15) ◽  
pp. 1748
Author(s):  
Baoquan Wei ◽  
Yong Zuo ◽  
Yande Liu ◽  
Wei Luo ◽  
Kaiyun Wen ◽  
...  
Keyword(s):  
Fault Detection ◽  
Recognition Rate ◽  
Infrared Image ◽  
Detection Algorithm ◽  
Small Sample ◽  
Training Data ◽  
Small Samples ◽  
Generative Adversarial Networks ◽  
Extended Model ◽  
Detection Technology

This paper proposes a novel metal oxide arrester (MOA) fault detection technology based on a small sample infrared image. The research is carried out from the detection process and data enhancement. A lightweight MOA identification and location algorithm is designed at the edge, which can not only reduce the amount of data uploaded, but also reduce the search space of cloud algorithm. In order to improve the accuracy and generalization ability of the defect detection model under the condition of small samples, a multi-model fusion detection algorithm is proposed. Different features of the image are extracted by multiple convolutional neural networks, and then multiple classifiers are trained. Finally, the weighted voting strategy is used for fault diagnosis. In addition, the extended model of fault samples is constructed by transfer learning and deep convolutional generative adversarial networks (DCGAN) to solve the problem of unbalanced training data sets. The experimental results show that the proposed method can realize the accurate location of arrester under the condition of small samples, and after the data expansion, the recognition rate of arrester anomalies can be improved from 83% to 85%, showing high effectiveness and reliability.

Sign in / Sign up

Export Citation Format

Share Document