scholarly journals A Pipeline Abnormal Signal Detection Method Based on 1D-Faster R-CNN

2020 ◽  
Author(s):  
Zhen Zhang ◽  
Weiguo Lin
Keyword(s):  
Target Detection ◽  
Small Sample ◽  
Experimental Results ◽  
New Method ◽  
False Alarms ◽  
Original Sample ◽  
Abnormal Signal ◽  
Location Method ◽  
Training Samples ◽  
Recognition Errors

Aimed at the detection difficulty of local abnormal signals during pipeline operation, this paper takes the local abnormal signals as the detected targets, and proposes a new method based on target detection to extract abnormal signals with different amplitude and shape; and for the case where there are few actual leak samples, combined with the characteristics that the training samples of each module of the model itself are derivative samples of the original sample, so as to realize the small sample training of the model. Finally, a new pipeline leak detection and location method is proposed by combining the 1D-faster R-CNN with the cross-correlation location method based on signal matching. The experimental results show that the proposed method effectively extracts local abnormal signals, accurately alarms leak signals, and eliminates the false alarms caused by the recognition errors of normal signals.

A New Method for Forecasting of Non-Point Source Pollutant Load

2014 ◽  
Vol 955-959 ◽  
pp. 1167-1171
Author(s):  
Guang Qing Zeng ◽  
Wei Zhao ◽  
Biao Han ◽  
Xiu Qin Bu ◽  
Guo Shao Su
Keyword(s):  
Point Source ◽  
Influencing Factors ◽  
Small Sample ◽  
New Method ◽  
Monitoring Data ◽  
Support Vector ◽  
Pollutant Load ◽  
Training Samples ◽  
Highly Nonlinear ◽  
Gp Model

Gaussian process (GP) is a newly developed machine learning technology based on statistical theoretical fundamentals, which has successful application in the field of solving for highly nonlinear problems. Conventional methods for forecasting of non-point source pollutant load often meet great difficulty since relationship between pollutant load and its influencing factors is highly complicated nonlinear. A new method based on GP is proposed for forecasting of non-point source pollutant load. The monitoring data of a certain river since 1976 to 1990 are preformed to obtain the training samples and test samples. Nonlinear mapping relationship between non-point source pollutant load and its influencing factors can be constructed by GP learning with the training samples. The monitoring data of a certain river since 1991 to 1993 are preformed to testify the effects of the method above. The results of case studies show that the method is feasible, effective and simple to implement for forecasting of non-point source pollutant load. It has merits of self-adaptive parameters determination and better capacity for solving nonlinear small sample problems comparing with the artificial neural networks method and Support Vector Machine method. The good performance of GP model makes it very attractive for a wide range of application in environmental engineering.

scholarly journals SAR Target Detection Based on Improved SSD with Saliency Map and Residual Network

2022 ◽  
Vol 14 (1) ◽  
pp. 180
Author(s):  
Fang Zhou ◽  
Fengjie He ◽  
Changchun Gui ◽  
Zhangyu Dong ◽  
Mengdao Xing
Keyword(s):  
Target Detection ◽  
Structure Optimization ◽  
Saliency Map ◽  
Small Sample ◽  
Detection Methods ◽  
Single Shot ◽  
Model Structure ◽  
Aspect Ratios ◽  
Training Samples ◽  
Image Dataset

A target detection method based on an improved single shot multibox detector (SSD) is proposed to solve insufficient training samples for synthetic aperture radar (SAR) target detection. We propose two strategies to improve the SSD: model structure optimization and small sample augmentation. For model structure optimization, the first approach is to extract deep features of the target with residual networks instead of with VGGNet. Then, the aspect ratios of the default boxes are redesigned to match the different targets’ sizes. For small sample augmentation, besides the routine image processing methods, such as rotating, translating, and mirroring, enough training samples are obtained based on the saliency map theory in machine vision. Lastly, a simulated SAR image dataset called Geometric Objects (GO) is constructed, which contains dihedral angles, surface plates and cylinders. The experimental results on the GO-simulated image dataset and the MSTAR real image dataset demonstrate that the proposed method has better performance in SAR target detection than other detection methods.

Picture Recognition Errors in the Differential Diagnosis of Alzheimer’s Disease

2019 ◽  
Vol 30 (3) ◽  
pp. 157-168
Author(s):  
Helmut Hildebrandt ◽  
Jana Schill ◽  
Jana Bördgen ◽  
Andreas Kastrup ◽  
Paul Eling
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Differential Diagnosis ◽  
Clinical Diagnosis ◽  
Response Bias ◽  
Recognition Task ◽  
Discriminatory Power ◽  
False Alarms ◽  
Picture Recognition ◽  
Recognition Errors

Abstract. This article explores the possibility of differentiating between patients suffering from Alzheimer’s disease (AD) and patients with other kinds of dementia by focusing on false alarms (FAs) on a picture recognition task (PRT). In Study 1, we compared AD and non-AD patients on the PRT and found that FAs discriminate well between these groups. Study 2 served to improve the discriminatory power of the FA score on the picture recognition task by adding associated pairs. Here, too, the FA score differentiated well between AD and non-AD patients, though the discriminatory power did not improve. The findings suggest that AD patients show a liberal response bias. Taken together, these studies suggest that FAs in picture recognition are of major importance for the clinical diagnosis of AD.

ER rule classifier with an optimization operator recommendation

2021 ◽  
pp. 1-13
Author(s):  
Xiaoyan Wang ◽  
Jianbin Sun ◽  
Qingsong Zhao ◽  
Yaqian You ◽  
Jiang Jiang
Keyword(s):  
Classification Accuracy ◽  
Comprehensive Analysis ◽  
Small Sample ◽  
Empirical Knowledge ◽  
Classification Methods ◽  
Turbofan Engine ◽  
Training Samples ◽  
Optimization Operator ◽  
Recommendation Strategy

It is difficult for many classic classification methods to consider expert experience and classify small-sample datasets well. The evidential reasoning rule (ER rule) classifier can solve these problems. The ER rule has strong processing and comprehensive analysis abilities for diversified mixed information and can solve problems with expert experience effectively. Moreover, the initial parameters of the classifier constructed based on the ER rule can be set according to empirical knowledge instead of being trained by a large number of samples, which can help the classifier classify small-sample datasets well. However, the initial parameters of the ER rule classifier need to be optimized, and choosing the best optimization algorithm is still a challenge. Considering these problems, the ER rule classifier with an optimization operator recommendation is proposed in this paper. First, the initial ER rule classifier is constructed based on training samples and expert experience. Second, the adjustable parameters are optimized, in which the optimization operator recommendation strategy is applied to select the best algorithm by partial samples, and then experiments with full samples are carried out. Finally, a case study on a turbofan engine degradation simulation dataset is carried out, and the results indicate that the ER rule classifier has a higher classification accuracy than other classic classifiers, which demonstrates the capability and effectiveness of the proposed ER rule classifier with an optimization operator recommendation.

scholarly journals Realizing Target Detection in SAR Images Based on Multiscale Superpixel Fusion

Sensors ◽  
2021 ◽  
Vol 21 (5) ◽  
pp. 1643
Author(s):  
Ming Liu ◽  
Shichao Chen ◽  
Fugang Lu ◽  
Mengdao Xing ◽  
Jingbiao Wei
Keyword(s):  
Synthetic Aperture Radar ◽  
False Alarm ◽  
False Alarm Rate ◽  
Target Detection ◽  
Synthetic Aperture ◽  
False Alarms ◽  
Sar Image ◽  
Constant False Alarm Rate ◽  
Sar Images ◽  
Complex Scenes

For target detection in complex scenes of synthetic aperture radar (SAR) images, the false alarms in the land areas are hard to eliminate, especially for the ones near the coastline. Focusing on the problem, an algorithm based on the fusion of multiscale superpixel segmentations is proposed in this paper. Firstly, the SAR images are partitioned by using different scales of superpixel segmentation. For the superpixels in each scale, the land-sea segmentation is achieved by judging their statistical properties. Then, the land-sea segmentation results obtained in each scale are combined with the result of the constant false alarm rate (CFAR) detector to eliminate the false alarms located on the land areas of the SAR image. In the end, to enhance the robustness of the proposed algorithm, the detection results obtained in different scales are fused together to realize the final target detection. Experimental results on real SAR images have verified the effectiveness of the proposed algorithm.

scholarly journals Target Detection Network for SAR Images Based on Semi-Supervised Learning and Attention Mechanism

2021 ◽  
Vol 13 (14) ◽  
pp. 2686
Author(s):  
Di Wei ◽  
Yuang Du ◽  
Lan Du ◽  
Lu Li
Keyword(s):  
Feature Extraction ◽  
Supervised Learning ◽  
Target Detection ◽  
Scene Recognition ◽  
Attention Mechanism ◽  
Sar Image ◽  
Target Level ◽  
Sar Images ◽  
Training Samples ◽  
Pass Through

The existing Synthetic Aperture Radar (SAR) image target detection methods based on convolutional neural networks (CNNs) have achieved remarkable performance, but these methods require a large number of target-level labeled training samples to train the network. Moreover, some clutter is very similar to targets in SAR images with complex scenes, making the target detection task very difficult. Therefore, a SAR target detection network based on a semi-supervised learning and attention mechanism is proposed in this paper. Since the image-level label simply marks whether the image contains the target of interest or not, which is easier to be labeled than the target-level label, the proposed method uses a small number of target-level labeled training samples and a large number of image-level labeled training samples to train the network with a semi-supervised learning algorithm. The proposed network consists of a detection branch and a scene recognition branch with a feature extraction module and an attention module shared between these two branches. The feature extraction module can extract the deep features of the input SAR images, and the attention module can guide the network to focus on the target of interest while suppressing the clutter. During the semi-supervised learning process, the target-level labeled training samples will pass through the detection branch, while the image-level labeled training samples will pass through the scene recognition branch. During the test process, considering the help of global scene information in SAR images for detection, a novel coarse-to-fine detection procedure is proposed. After the coarse scene recognition determining whether the input SAR image contains the target of interest or not, the fine target detection is performed on the image that may contain the target. The experimental results based on the measured SAR dataset demonstrate that the proposed method can achieve better performance than the existing methods.

scholarly journals Adaptive target detection in hyperspectral imaging from two sets of training samples with different means

2021 ◽  
Vol 181 ◽  
pp. 107909
Author(s):  
Olivier Besson ◽  
François Vincent ◽  
Stefania Matteoli
Keyword(s):  
Hyperspectral Imaging ◽  
Target Detection ◽  
Training Samples

A new method for monitoring the redox potential of fuel salt based on the deposition of 95Nb on Hastelloy C276

2021 ◽  
Vol 109 (5) ◽  
pp. 357-365
Author(s):  
Zhiqiang Cheng ◽  
Zhongqi Zhao ◽  
Junxia Geng ◽  
Xiaohe Wang ◽  
Jifeng Hu ◽  
...  
Keyword(s):  
Redox Potential ◽  
Molten Salt ◽  
Specific Activity ◽  
Chemical Reduction ◽  
Quantitative Approach ◽  
Experimental Results ◽  
New Method ◽  
Molten Salt Reactor ◽  
Fuel Salt ◽  
Well Correlation

Abstract To develop the application of 95Nb as an indicator of redox potential for fuel salt in molten salt reactor (MSR), the specific activity of 95Nb in FLiBe salt and its deposition of 95Nb on Hastelloy C276 have been studied. Experimental results indicated that the amount of 95Nb deposited on Hastelloy C276 resulted from its chemical reduction exhibited a positive correlation with the decrease of 95Nb activity in FLiBe salt and the relative deposition coefficient of 95Nb to 103Ru appeared a well correlation with 95Nb activity in FLiBe salt. Both correlations implied that the measurement of 95Nb activity deposited on Hastelloy C276 specimen might provide a quantitative approach for monitoring the redox potential of fuel salt in MSR.

Aircraft Cable Fault Location Based on Detection Model

2011 ◽  
Vol 55-57 ◽  
pp. 332-336 ◽  
Author(s):  
Xiao Lin Liu ◽  
Zhi Quan Li
Keyword(s):  
Fault Location ◽  
Reference Signal ◽  
Experimental Results ◽  
Civil Aviation ◽  
Location Method ◽  
Aviation Maintenance ◽  
Location System ◽  
Detection Model ◽  
Experimental Installation

An aircraft cable fault location method based on detection model is proposed to solve the problem of being difficult to inspect the fault for the civil aviation maintenance. In response to the condition of the experimental installation, the reference signal is designed. The fault of the cable can be located according to the reflected waveform. An aircraft cable fault location system is designed and the experimental results show that the method is rational and effective.

scholarly journals Random Forest with Adaptive Local Template for Pedestrian Detection

2015 ◽  
Vol 2015 ◽  
pp. 1-11 ◽  
Author(s):  
Tao Xiang ◽  
Tao Li ◽  
Mao Ye ◽  
Zijian Liu
Keyword(s):  
Computer Vision ◽  
Random Forest ◽  
Classification Accuracy ◽  
Template Matching ◽  
Detection Method ◽  
State Of The Art ◽  
Pedestrian Detection ◽  
Sliding Window ◽  
Experimental Results ◽  
Training Samples

Pedestrian detection with large intraclass variations is still a challenging task in computer vision. In this paper, we propose a novel pedestrian detection method based on Random Forest. Firstly, we generate a few local templates with different sizes and different locations in positive exemplars. Then, the Random Forest is built whose splitting functions are optimized by maximizing class purity of matching the local templates to the training samples, respectively. To improve the classification accuracy, we adopt a boosting-like algorithm to update the weights of the training samples in a layer-wise fashion. During detection, the trained Random Forest will vote the category when a sliding window is input. Our contributions are the splitting functions based on local template matching with adaptive size and location and iteratively weight updating method. We evaluate the proposed method on 2 well-known challenging datasets: TUD pedestrians and INRIA pedestrians. The experimental results demonstrate that our method achieves state-of-the-art or competitive performance.

Sign in / Sign up

Export Citation Format

Share Document