scholarly journals A Method for Image Recognition of Insulator Jacket Defects under Small Sample Conditions

2022 ◽  
Vol 2160 (1) ◽  
pp. 012062
Author(s):  
Xinhai Li ◽  
Lingcheng Zeng ◽  
Yongyin Lu ◽  
Yuede Lin ◽  
Xinxiong Zeng
Keyword(s):  
Image Recognition ◽  
Original Data ◽  
Small Sample ◽  
Small Scale ◽  
Learning Technology ◽  
Accurate Identification ◽  
Data Set ◽  
Meta Learning ◽  
Model Training ◽  
Defect Recognition

Abstract Accurate identification of insulator jacket defect images requires a large number of samples for model training, and the actual defect image datasets available for model training is seriously insufficient. In order to solve the problems of the model cannot be trained, over-fitting and low accuracy caused by too few training samples, this paper proposes a new method for image recognition of insulator jacket defects under small sample conditions, which combines image enhancement technology and meta-learning technology to train the U-Net image segmentation network, and finally obtain the image recognition model of the insulator jacket defect. In this paper, the defect recognition models using meta-learning method and without meta-learning are compared experimentally, and the results show that the proposed method can achieve accurate recognition with a small-scale original data set.

scholarly journals Deep generative models in DataSHIELD

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Stefan Lenz ◽  
Moritz Hess ◽  
Harald Binder
Keyword(s):  
Genetic Variant ◽  
Small Sample Size ◽  
Synthetic Data ◽  
Routine Data ◽  
Original Data ◽  
Generative Models ◽  
Small Sample ◽  
Generative Adversarial Networks ◽  
Artificial Data ◽  
Data Set

Abstract Background The best way to calculate statistics from medical data is to use the data of individual patients. In some settings, this data is difficult to obtain due to privacy restrictions. In Germany, for example, it is not possible to pool routine data from different hospitals for research purposes without the consent of the patients. Methods The DataSHIELD software provides an infrastructure and a set of statistical methods for joint, privacy-preserving analyses of distributed data. The contained algorithms are reformulated to work with aggregated data from the participating sites instead of the individual data. If a desired algorithm is not implemented in DataSHIELD or cannot be reformulated in such a way, using artificial data is an alternative. Generating artificial data is possible using so-called generative models, which are able to capture the distribution of given data. Here, we employ deep Boltzmann machines (DBMs) as generative models. For the implementation, we use the package “BoltzmannMachines” from the Julia programming language and wrap it for use with DataSHIELD, which is based on R. Results We present a methodology together with a software implementation that builds on DataSHIELD to create artificial data that preserve complex patterns from distributed individual patient data. Such data sets of artificial patients, which are not linked to real patients, can then be used for joint analyses. As an exemplary application, we conduct a distributed analysis with DBMs on a synthetic data set, which simulates genetic variant data. Patterns from the original data can be recovered in the artificial data using hierarchical clustering of the virtual patients, demonstrating the feasibility of the approach. Additionally, we compare DBMs, variational autoencoders, generative adversarial networks, and multivariate imputation as generative approaches by assessing the utility and disclosure of synthetic data generated from real genetic variant data in a distributed setting with data of a small sample size. Conclusions Our implementation adds to DataSHIELD the ability to generate artificial data that can be used for various analyses, e.g., for pattern recognition with deep learning. This also demonstrates more generally how DataSHIELD can be flexibly extended with advanced algorithms from languages other than R.

Gender and bias in the International Relations curriculum: Insights from reading lists

2018 ◽  
Vol 25 (2) ◽  
pp. 383-407 ◽  
Author(s):  
Kiran Phull ◽  
Gokhan Ciflikli ◽  
Gustav Meibauer
Keyword(s):  
International Relations ◽  
Gender Bias ◽  
Gender Gap ◽  
Original Data ◽  
Careful Consideration ◽  
Small Sample ◽  
Pedagogical Practices ◽  
London School ◽  
Teaching Materials ◽  
Data Set

Following growing academic interest and activism targeting gender bias in university curricula, we present the first analysis of female exclusion in a complete International Relations curriculum, across degree levels and disciplinary subfields. Previous empirical research on gender bias in the teaching materials of International Relations has been limited in scope, that is, restricted to PhD curricula, non-random sampling, small sample sizes or predominately US-focused. By contrast, this study uses an original data set of 43 recent syllabi comprising the entire International Relations curriculum at the London School of Economics to investigate the gender gap in the discipline’s teaching materials. We find evidence of bias that reproduces patterns of female exclusion: 79.2% of texts on reading lists are authored exclusively by men, reflecting the representation of women neither in the professional discipline nor in the published discipline. We find that level of study, subfield and the gender and seniority of the course convener matter. First, female author inclusion improves as the level of study progresses from undergraduate to PhD. This suggests the rigid persistence of a ‘traditional International Relations canon’ at the earliest disciplinary stage. Second, the International Organisations/Law subfield is more gender-inclusive than Security or Regional Studies, while contributions from Gender/Feminist Studies are dominated by female authorship. These patterns are suggestive of gender stereotyping within subfields. Third, female-authored readings are assigned less frequently by male and/or more senior course conveners. Tackling gender bias in the taught discipline must therefore involve a careful consideration of the linkages between knowledge production and dissemination, institutional hiring and promotion, and pedagogical practices.

Deep Learning for the Detection and Recognition of Rail Defects in Ultrasound B-Scan Images

2021 ◽  
pp. 036119812110215
Author(s):  
Zhengxing Chen ◽  
Qihang Wang ◽  
Kanghua Yang ◽  
Tianle Yu ◽  
Jidong Yao ◽  
...  
Keyword(s):  
Deep Learning ◽  
Image Recognition ◽  
Defect Detection ◽  
High Performance ◽  
Image Data ◽  
Small Scale ◽  
Detection Accuracy ◽  
Data Set ◽  
Detection Rates ◽  
B Scan Images

Rail defect detection is crucial to rail operations safety. Addressing the problem of high false alarm rates and missed detection rates in rail defect detection, this paper proposes a deep learning method using B-scan image recognition of rail defects with an improved YOLO (you only look once) V3 algorithm. Specifically, the developed model can automatically position a box in B-scan images and recognize EFBWs (electric flash butt welds), normal bolt holes, BHBs (bolt hole breaks), and SSCs (shells, spalling, or corrugation). First, the network structure of the YOLO V3 model is modified to enlarge the receptive field of the model, thus improving the detection accuracy of the model for small-scale objects. Second, B-scan image data are analyzed and standardized. Third, the initial training parameters of the improved YOLO V3 model are adjusted. Finally, the experiments are performed on 453 B-scan images as the test data set. Results show that the B-scan image recognition model based on the improved YOLO V3 algorithm reached high performance in its precision. Additionally, the detection accuracy and efficiency are improved compared with the original model and the final mean average precision can reach 87.41%.

scholarly journals Few Samples of SAR Automatic Target Recognition Based on Enhanced-Shape CNN

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Mengmeng Huang ◽  
Fang Liu ◽  
Xianfa Meng
Keyword(s):  
Target Recognition ◽  
Recognition Rate ◽  
Automatic Target Recognition ◽  
Small Sample ◽  
Training Data ◽  
Small Scale ◽  
Data Set ◽  
Shape Information ◽  
Target Shape ◽  
The One

Synthetic Aperture Radar (SAR), as one of the important and significant methods for obtaining target characteristics in the field of remote sensing, has been applied to many fields including intelligence search, topographic surveying, mapping, and geological survey. In SAR field, the SAR automatic target recognition (SAR ATR) is a significant issue. However, on the other hand, it also has high application value. The development of deep learning has enabled it to be applied to SAR ATR. Some researchers point out that existing convolutional neural network (CNN) paid more attention to texture information, which is often not as good as shape information. Wherefore, this study designs the enhanced-shape CNN, which enhances the target shape at the input. Further, it uses an improved attention module, so that the network can highlight target shape in SAR images. Aiming at the problem of the small scale of the existing SAR data set, a small sample experiment is conducted. Enhanced-shape CNN achieved a recognition rate of 99.29% when trained on the full training set, while it is 89.93% on the one-eighth training data set.

Estimation of technical efficiency and output growth decomposition for small-scale rice farmers in Eastern India

2020 ◽  
Vol 10 (2) ◽  
pp. 139-156 ◽  
Author(s):  
Wei Wu
Keyword(s):  
Technical Efficiency ◽  
Decomposition Analysis ◽  
Output Growth ◽  
Small Sample ◽  
Small Scale ◽  
Rice Farming ◽  
Eastern India ◽  
Data Set ◽  
Content Type ◽  
Production Growth

Purpose The purpose of this paper is to estimate the degree of technical efficiency, determinants of technical inefficiencies and driving forces behind the production growth for a panel data set collected during the 1998/1999 and 2004/2006 Kharif cropping season, from 452 small-scale rice farming households in the Giridih and Purulia districts of Eastern India. Design/methodology/approach The estimations of technical efficiency utilize stochastic frontier production function with a sub-model of inefficiency effects at both aggregated farm level and disaggregated plot level where traditional varieties (TVs) and high-yielding varieties (HYVs) are differentiated. The output growth decomposition analysis identifies the main contributor to the total rice production growth. Findings The results indicate that the sampled farms are operated at moderate levels of technical efficiency. The production of HYV rice is associated with higher technical efficiency compared to TV rice. Farming experience, education attainment, landholding size, the share of non-agricultural income and the share of land in the lower terraces account for the differences in technical inefficiencies across the sampled farms. The decomposition analysis suggests that as technical efficiency decreased, technical change is the main source of production growth during the survey period. Research limitations/implications The small sample size applied in the analysis will result in an insufficient representativeness of the study area. Originality/value This paper fills the literature gap as estimations of technical efficiency that account for subtle differences in adopted rice varieties are still rare in India.

A method for low-frequency noise suppression based on mathematical morphology in microseismic monitoring

Geophysics ◽  
2016 ◽  
Vol 81 (3) ◽  
pp. V159-V167 ◽  
Author(s):  
Huijian Li ◽  
Runqiu Wang ◽  
Siyuan Cao ◽  
Yangkang Chen ◽  
Weilin Huang
Keyword(s):  
Mathematical Morphology ◽  
Large Scale ◽  
Noise Suppression ◽  
Low Frequency ◽  
Original Data ◽  
Small Scale ◽  
Frequency Noise ◽  
Low Frequency Noise ◽  
Data Set ◽  
Microseismic Data

The frequency of microseismic data is higher than that of conventional seismic data. The range of effective frequency is usually from 100 to 500 Hz, and low-frequency noise is a common disturbance in downhole monitoring. Conventional signal analysis techniques, such as band-pass filters, have their limitation in microseismic data processing when the useful signals and noise share the same frequency band. We have developed a novel method to suppress low-frequency noise in microseismic data based on mathematical morphology theory that aims at distinguishing useful signals and noise according to their tiny differences of waveform. By choosing suitable structure elements, we have extracted low-frequency noise from a original data set. We first developed the fundamental principle of mathematical morphology and the formulation of our approach. Then, we used a synthetic data example that was composed of a Ricker wavelet and low-frequency noise to test the feasibility and performance of the proposed approach. Our results from the synthetic example indicate that the proposed approach can effectively suppress large-scale low-frequency noise while slightly decreasing the small-scale signals. Finally, we have applied the proposed approach to field microseismic data and obtained very encouraging results.

scholarly journals Demonstrating an approach for evaluating synthetic geospatial and temporal epidemiologic data utility: Results from analyzing >1.8 million SARS-CoV-2 tests in the United States National COVID Cohort Collaborative (N3C)

2021 ◽  
Author(s):  
Jason A Thomas ◽  
Randi E Foraker ◽  
Noa Zamstein ◽  
Philip RO Payne ◽  
Adam B Wilcox ◽  
...  
Keyword(s):  
Synthetic Data ◽  
Patient Characteristics ◽  
Original Data ◽  
The United States ◽  
Small Sample ◽  
Sample Sizes ◽  
Data Set ◽  
Data Utility ◽  
Small Sample Sizes ◽  
Zip Code

Objective: To evaluate whether synthetic data derived from a national COVID-19 data set could be used for geospatial and temporal epidemic analyses. Materials and Methods: Using an original data set (n = 1,854,968 SARS-CoV-2 tests) and its synthetic derivative, we compared key indicators of COVID-19 community spread through analysis of aggregate and zip-code level epidemic curves, patient characteristics and outcomes, distribution of tests by zip code, and indicator counts stratified by month and zip code. Similarity between the data was statistically and qualitatively evaluated. Results: In general, synthetic data closely matched original data for epidemic curves, patient characteristics, and outcomes. Synthetic data suppressed labels of zip codes with few total tests (mean = 2.9 ± 2.4; max = 16 tests; 66% reduction of unique zip codes). Epidemic curves and monthly indicator counts were similar between synthetic and original data in a random sample of the most tested (top 1%; n = 171) and for all unsuppressed zip codes (n = 5,819), respectively. In small sample sizes, synthetic data utility was notably decreased. Discussion: Analyses on the population-level and of densely-tested zip codes (which contained most of the data) were similar between original and synthetically-derived data sets. Analyses of sparsely-tested populations were less similar and had more data suppression. Conclusion: In general, synthetic data were successfully used to analyze geospatial and temporal trends. Analyses using small sample sizes or populations were limited, in part due to purposeful data label suppression - an attribute disclosure countermeasure. Users should consider data fitness for use in these cases.

scholarly journals Machine Learning in Action: Stroke Diagnosis and Outcome Prediction

2021 ◽  
Vol 12 ◽  
Author(s):  
Shraddha Mainali ◽  
Marin E. Darsie ◽  
Keaton S. Smetana
Keyword(s):  
Machine Learning ◽  
Outcome Prediction ◽  
Clinical Decision Making ◽  
Small Sample ◽  
Machine Learning Algorithms ◽  
Patient Specific ◽  
Learning Technology ◽  
Learning Tools ◽  
Data Set ◽  
Stroke Diagnosis

The application of machine learning has rapidly evolved in medicine over the past decade. In stroke, commercially available machine learning algorithms have already been incorporated into clinical application for rapid diagnosis. The creation and advancement of deep learning techniques have greatly improved clinical utilization of machine learning tools and new algorithms continue to emerge with improved accuracy in stroke diagnosis and outcome prediction. Although imaging-based feature recognition and segmentation have significantly facilitated rapid stroke diagnosis and triaging, stroke prognostication is dependent on a multitude of patient specific as well as clinical factors and hence accurate outcome prediction remains challenging. Despite its vital role in stroke diagnosis and prognostication, it is important to recognize that machine learning output is only as good as the input data and the appropriateness of algorithm applied to any specific data set. Additionally, many studies on machine learning tend to be limited by small sample size and hence concerted efforts to collate data could improve evaluation of future machine learning tools in stroke. In the present state, machine learning technology serves as a helpful and efficient tool for rapid clinical decision making while oversight from clinical experts is still required to address specific aspects not accounted for in an automated algorithm. This article provides an overview of machine learning technology and a tabulated review of pertinent machine learning studies related to stroke diagnosis and outcome prediction.

Rotational Characteristics of the Green Solar Corona: 1947-1991

1994 ◽  
Vol 144 ◽  
pp. 139-141 ◽  
Author(s):  
J. Rybák ◽  
V. Rušin ◽  
M. Rybanský
Keyword(s):  
Solar Corona ◽  
World Wide ◽  
Rotation Period ◽  
Original Data ◽  
Coronal Emission ◽  
Time Intervals ◽  
Data Set ◽  
The World ◽  
Coronal Emission Line ◽  
Homogeneous Data

AbstractFe XIV 530.3 nm coronal emission line observations have been used for the estimation of the green solar corona rotation. A homogeneous data set, created from measurements of the world-wide coronagraphic network, has been examined with a help of correlation analysis to reveal the averaged synodic rotation period as a function of latitude and time over the epoch from 1947 to 1991.The values of the synodic rotation period obtained for this epoch for the whole range of latitudes and a latitude band ±30° are 27.52±0.12 days and 26.95±0.21 days, resp. A differential rotation of green solar corona, with local period maxima around ±60° and minimum of the rotation period at the equator, was confirmed. No clear cyclic variation of the rotation has been found for examinated epoch but some monotonic trends for some time intervals are presented.A detailed investigation of the original data and their correlation functions has shown that an existence of sufficiently reliable tracers is not evident for the whole set of examinated data. This should be taken into account in future more precise estimations of the green corona rotation period.

Smart teaching mode based on particle swarm image recognition and human-computer interaction deep learning

2020 ◽  
Vol 39 (4) ◽  
pp. 5699-5711
Author(s):  
Shirong Long ◽  
Xuekong Zhao
Keyword(s):  
Feature Extraction ◽  
Particle Swarm Optimization ◽  
Deep Learning ◽  
Real Time ◽  
Image Recognition ◽  
Particle Swarm ◽  
Learning Technology ◽  
Search Performance ◽  
Swarm Optimization ◽  
Teaching Mode

The smart teaching mode overcomes the shortcomings of traditional teaching online and offline, but there are certain deficiencies in the real-time feature extraction of teachers and students. In view of this, this study uses the particle swarm image recognition and deep learning technology to process the intelligent classroom video teaching image and extracts the classroom task features in real time and sends them to the teacher. In order to overcome the shortcomings of the premature convergence of the standard particle swarm optimization algorithm, an improved strategy for multiple particle swarm optimization algorithms is proposed. In order to improve the premature problem in the search performance algorithm of PSO algorithm, this paper combines the algorithm with the useful attributes of other algorithms to improve the particle diversity in the algorithm, enhance the global search ability of the particle, and achieve effective feature extraction. The research indicates that the method proposed in this paper has certain practical effects and can provide theoretical reference for subsequent related research.

Sign in / Sign up

Export Citation Format

Share Document