scholarly journals Swin–UNet++: A Nested Swin Transformer Architecture for Location Identification and Morphology Segmentation of Dimples on 2.25Cr1Mo0.25V Fractured Surface

Materials ◽  
2021 ◽  
Vol 14 (24) ◽  
pp. 7504
Author(s):  
Pan Liu ◽  
Yan Song ◽  
Mengyu Chai ◽  
Zelin Han ◽  
Yu Zhang

The precise identification of micro-features on 2.25Cr1Mo0.25V steel is of great significance for understanding the mechanism of hydrogen embrittlement (HE) and evaluating the alloy’s properties of HE resistance. Presently, the convolution neural network (CNN) of deep learning is widely applied in the micro-features identification of alloy. However, with the development of the transformer in image recognition, the transformer-based neural network performs better on the learning of global and long-range semantic information than CNN and achieves higher prediction accuracy. In this work, a new transformer-based neural network model Swin–UNet++ was proposed. Specifically, the architecture of the decoder was redesigned to more precisely detect and identify the micro-feature with complex morphology (i.e., dimples) of 2.25Cr1Mo0.25V steel fracture surface. Swin–UNet++ and other segmentation models performed state-of-the-art (SOTA) were compared on the dimple dataset constructed in this work, which consists of 830 dimple scanning electron microscopy (SEM) images on 2.25Cr1Mo0.25V steel fracture surface. The segmentation results show Swin–UNet++ not only realizes the accurate identification of dimples but displays a much higher prediction accuracy and stronger robustness than Swin–Unet and UNet. Moreover, efforts from this work will also provide an important reference value to the identification of other micro-features with complex morphologies.

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-13
Author(s):  
Changchang Yin ◽  
Xuezhen Cheng ◽  
Xilu Liu ◽  
Meng Zhao

Accurate identification and classification of atmospheric particulates can provide the basis for their source apportionment. Most current research studies mainly focus on the classification of atmospheric particles based on the energy spectrum of particles, which has the problems of low accuracy and being time-consuming. It is necessary to study the classification method of atmospheric particles with higher accuracy. In this paper, a convolutional neural network (CNN) model with attention mechanism is proposed to identify and classify the scanning electron microscopy (SEM) images of atmospheric particles. First, this work established a database, Qingdao 2016–2018, for atmospheric particles classification research. This database consists of 3469 SEM images of single particulates. Secondly, by analyzing the morphological characteristics of single particle SEM images, it can be divided into four categories: fibrous particles, flocculent particles, spherical particles, and mineral particles. Thirdly, by introducing attention mechanism into convolutional neural network, an Attention-CNN model for the identification and classification of the four types of atmospheric particles based on the SEM images is established. Finally, the Attention-CNN model is trained and tested based on the SEM images database, and the results of identification and classification for four types of particles are obtained. Under the same SEM images database, the classification results from Attention-CNN are compared with those of CNN and SVM. It is found that Attention-CNN has higher classification accuracy and reduces significantly the misclassification number of particles, which shows the focusing effect of attention mechanism.


2019 ◽  
Author(s):  
CHIEN WEI ◽  
Chi Chow Julie ◽  
Chou Willy

UNSTRUCTURED Backgrounds: Dengue fever (DF) is an important public health issue in Asia. However, the disease is extremely hard to detect using traditional dichotomous (i.e., absent vs. present) evaluations of symptoms. Convolution neural network (CNN), a well-established deep learning method, can improve prediction accuracy on account of its usage of a large number of parameters for modeling. Whether the HT person fit statistic can be combined with CNN to increase the prediction accuracy of the model and develop an application (APP) to detect DF in children remains unknown. Objectives: The aim of this study is to build a model for the automatic detection and classification of DF with symptoms to help patients, family members, and clinicians identify the disease at an early stage. Methods: We extracted 19 feature variables of DF-related symptoms from 177 pediatric patients (69 diagnosed with DF) using CNN to predict DF risk. The accuracy of two sets of characteristics (19 symptoms and four other variables, including person mean, standard deviation, and two HT-related statistics matched to DF+ and DF−) for predicting DF, were then compared. Data were separated into training and testing sets, and the former was used to predict the latter. We calculated the sensitivity (Sens), specificity (Spec), and area under the receiver operating characteristic curve (AUC) across studies for comparison. Results: We observed that (1) the 23-item model yields a higher accuracy rate (0.95) and AUC (0.94) than the 19-item model (accuracy = 0.92, AUC = 0.90) based on the 177-case training set; (2) the Sens values are almost higher than the corresponding Spec values (90% in 10 scenarios) for predicting DF; (3) the Sens and Spec values of the 23-item model are consistently higher than those of the 19-item model. An APP was subsequently designed to detect DF in children. Conclusion: The 23-item model yielded higher accuracy rates (0.95) and AUC (0.94) than the 19-item model (accuracy = 0.92, AUC = 0.90). An APP could be developed to help patients, family members, and clinicians discriminate DF from other febrile illnesses at an early stage.


1998 ◽  
Vol 21 (4) ◽  
pp. 468-468
Author(s):  
Philip J. Benson

Failure to take note of distinctive attributes in the distal stimulus leads to an inadequate proximal encoding. Representation of similarities in Chorus suffers in this regard. Distinctive qualities may require additional complex representation (e.g., reference to linguistic terms) in order to facilitate discrimination. Additional semantic information, which configures proximal attributes, permits accurate identification of true veridical stimuli.


2020 ◽  
Vol 2020 ◽  
pp. 1-9
Author(s):  
Jun Zhao ◽  
Xumei Chen

An intelligent evaluation method is presented to analyze the competitiveness of airlines. From the perspective of safety, service, and normality, we establish the competitiveness indexes of traffic rights and the standard sample base. The self-organizing mapping (SOM) neural network is utilized to self-organize and self-learn the samples in the state of no supervision and prior knowledge. The training steps of high convergence speed and high clustering accuracy are determined based on the multistep setting. The typical airlines index data are utilized to verify the effect of the self-organizing mapping neural network on the airline competitiveness analysis. The simulation results show that the self-organizing mapping neural network can accurately and effectively classify and evaluate the competitiveness of airlines, and the results have important reference value for the allocation of traffic rights resources.


Genes ◽  
2021 ◽  
Vol 12 (3) ◽  
pp. 354
Author(s):  
Lu Zhang ◽  
Xinyi Qin ◽  
Min Liu ◽  
Ziwei Xu ◽  
Guangzhong Liu

As a prevalent existing post-transcriptional modification of RNA, N6-methyladenosine (m6A) plays a crucial role in various biological processes. To better radically reveal its regulatory mechanism and provide new insights for drug design, the accurate identification of m6A sites in genome-wide is vital. As the traditional experimental methods are time-consuming and cost-prohibitive, it is necessary to design a more efficient computational method to detect the m6A sites. In this study, we propose a novel cross-species computational method DNN-m6A based on the deep neural network (DNN) to identify m6A sites in multiple tissues of human, mouse and rat. Firstly, binary encoding (BE), tri-nucleotide composition (TNC), enhanced nucleic acid composition (ENAC), K-spaced nucleotide pair frequencies (KSNPFs), nucleotide chemical property (NCP), pseudo dinucleotide composition (PseDNC), position-specific nucleotide propensity (PSNP) and position-specific dinucleotide propensity (PSDP) are employed to extract RNA sequence features which are subsequently fused to construct the initial feature vector set. Secondly, we use elastic net to eliminate redundant features while building the optimal feature subset. Finally, the hyper-parameters of DNN are tuned with Bayesian hyper-parameter optimization based on the selected feature subset. The five-fold cross-validation test on training datasets show that the proposed DNN-m6A method outperformed the state-of-the-art method for predicting m6A sites, with an accuracy (ACC) of 73.58%–83.38% and an area under the curve (AUC) of 81.39%–91.04%. Furthermore, the independent datasets achieved an ACC of 72.95%–83.04% and an AUC of 80.79%–91.09%, which shows an excellent generalization ability of our proposed method.


2021 ◽  
Vol 11 (12) ◽  
pp. 5615
Author(s):  
Łukasz Sobolewski ◽  
Wiesław Miczulski

Ensuring the best possible stability of UTC(k) (local time scale) and its compliance with the UTC scale (Universal Coordinated Time) forces predicting the [UTC-UTC(k)] deviations, the article presents the results of work on two methods of constructing time series (TS) for a neural network (NN), increasing the accuracy of UTC(k) prediction. In the first method, two prepared TSs are based on the deviations determined according to the UTC scale with a 5-day interval. In order to improve the accuracy of predicting the deviations, the PCHIP interpolating function is used in subsequent TSs, obtaining TS elements with a 1-day interval. A limitation in the improvement of prediction accuracy for these TS has been a too large prediction horizon. The introduction in 2012 of the additional UTC Rapid scale by BIPM makes it possible to shorten the prediction horizon, and the building of two TSs has been proposed according to the second method. Each of them consists of two subsets. The first subset is based on deviations determined according to the UTC scale, the second on the UTC Rapid scale. The research of the proposed TS in the field of predicting deviations for the Polish Timescale by means of GMDH-type NN shows that the best accuracy of predicting the deviations has been achieved for TS built according to the second method.


Author(s):  
Yangping Li ◽  
Yangyi Liu ◽  
Sihua Luo ◽  
Zi Wang ◽  
Ke Wang ◽  
...  

Abstract The attractive mechanical properties of nickel-based superalloys primarily arise from an assembly of γ′ precipitates with desirable size, volume fraction, morphology and spatial distribution. In addition, the solutioning cooling rate after super solvus heat treatment is critical for controlling the features of γ′ precipitates. However, the correlation between these multidimensional parameters and mechanical hardness has not been well established to date. Scanning electron microscope (SEM) images with different γ′ precipitates were investigated in this study, and artificial neural network (ANN) method was used to build a microstructure-mechanical property model. The critical step in this work is to extract different microstructural features from hundreds of SEM images. In order to improve the accuracy of prediction, the cooling rate was also considered as the input. In this work, the methodology was proved to be capable of bridging microstructural features and mechanical properties under the inspiration of material genome spirit.


Complexity ◽  
2018 ◽  
Vol 2018 ◽  
pp. 1-9 ◽  
Author(s):  
Jinshuan Peng ◽  
Yiming Shao

Risky driving behavior is a major cause of traffic conflicts, which can develop into road traffic accidents, making the timely and accurate identification of such behavior essential to road safety. A platform was therefore established for analyzing the driving behavior of 20 professional drivers in field tests, in which overclose car following and lane departure were used as typical risky driving behaviors. Characterization parameters for identification were screened and used to determine threshold values and an appropriate time window for identification. A neural network-Bayesian filter identification model was established and data samples were selected to identify risky driving behavior and evaluate the identification efficiency of the model. The results obtained indicated a successful identification rate of 83.6% when the neural network model was solely used to identify risky driving behavior, but this could be increased to 92.46% once corrected by the Bayesian filter. This has important theoretical and practical significance in relation to evaluating the efficiency of existing driver assist systems, as well as the development of future intelligent driving systems.


Sign in / Sign up

Export Citation Format

Share Document