检索结果-南通市图书馆

Image segmentation of exfoliated two-dimensional materials by generative adversarial network-based data augmentation

在线全文

学校读者我要写书评

暂无评论

Chinese Physics B 2024年第3期33卷 112-117页

作者：程晓昱解晨雪刘宇伦白瑞雪肖南海任琰博张喜林马惠蒋崇云 College of Electronic Information and Optical Engineering Nankai UniversityTianjin 300350China School of Physical Science and Technology Tiangong UniversityTianjin 300387China

Mechanically cleaved two-dimensional materials are random in size and thickness.Recognizing atomically thin flakes by human experts is inefficient and unsuitable for scalable production.Deep learning algorithms have been adopted as an alternative,nevertheless a major challenge is a lack of sufficient actual training images.Here we report the generation of synthetic two-dimensional materials images using StyleGAN3 to complement the dataset.DeepLabv3Plus network is trained with the synthetic images which reduces overfitting and improves recognition accuracy to over 90%.A semi-supervisory technique for labeling images is introduced to reduce manual efforts.The sharper edges recognized by this method facilitate material stacking with precise edge alignment,which benefits exploring novel properties of layered-material devices that crucially depend on the interlayer twist-angle.This feasible and efficient method allows for the rapid and high-quality manufacturing of atomically thin materials and devices.

关键词： two-dimensional materials deep learning data augmentation generating adversarial networks

Perpendicular-Cutdepth:Perpendicular Direction Depth Cutting data augmentation Method

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第4期79卷 927-941页

作者： Le Zou Linsong Hu Yifan Wang Zhize Wu Xiaofeng Wang Anhui Provincial Engineering Laboratory of Big data Technology Application forUrban Infrastructure School ofArtificial Intelligence and Big DataHefei UniversityHefei230601China Institute of Applied Optimization School of Artificial Intelligence and Big DataHefei UniversityHefei230601China

Depth estimation is an important task in computer vision.Collecting data at scale for monocular depth estimation is challenging,as this task requires simultaneously capturing RGB images and depth information.Therefore,data augmentation is crucial for this task.Existing data augmentationmethods often employ pixel-wise transformations,whichmay inadvertently disrupt edge features.In this paper,we propose a data augmentationmethod formonocular depth estimation,which we refer to as the Perpendicular-Cutdepth method.This method involves cutting realworld depth maps along perpendicular directions and pasting them onto input images,thereby diversifying the data without compromising edge features.To validate the effectiveness of the algorithm,we compared it with existing convolutional neural network(CNN)against the current mainstream data augmentation algorithms.Additionally,to verify the algorithm’s applicability to Transformer networks,we designed an encoder-decoder network structure based on Transformer to assess the generalization of our proposed algorithm.Experimental results demonstrate that,in the field of monocular depth estimation,our proposed method,Perpendicular-Cutdepth,outperforms traditional data augmentationmethods.On the indoor dataset NYU,our method increases accuracy from0.900 to 0.907 and reduces the error rate from0.357 to 0.351.On the outdoor dataset KITTI,our method improves accuracy from 0.9638 to 0.9642 and decreases the error rate from 0.060 to 0.0598.

关键词： Perpendicular depth estimation data augmentation

Defect Detection Model Using Time Series data augmentation and Transformation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第2期78卷 1713-1730页

作者： Gyu-Il Kim Hyun Yoo Han-Jin Cho Kyungyong Chung Department of Computer Science Kyonggi UniversitySuwon-si16227Korea Contents Convergence Software Research Institue Kyonggi UniversitySuwon-si16227Korea Department of Energy IT Engineering Far East UniversityEumsung-gun27601Korea Division of AI Computer Science and Engineering Kyonggi UniversitySuwon-si16227Korea

Time-series data provide important information in many fields,and their processing and analysis have been the focus of much research.However,detecting anomalies is very difficult due to data imbalance,temporal dependence,and noise.Therefore,methodologies for data augmentation and conversion of time series data into images for analysis have been studied.This paper proposes a fault detection model that uses time series data augmentation and transformation to address the problems of data imbalance,temporal dependence,and robustness to noise.The method of data augmentation is set as the addition of noise.It involves adding Gaussian noise,with the noise level set to 0.002,to maximize the generalization performance of the model.In addition,we use the Markov Transition Field(MTF)method to effectively visualize the dynamic transitions of the data while converting the time series data into images.It enables the identification of patterns in time series data and assists in capturing the sequential dependencies of the data.For anomaly detection,the PatchCore model is applied to show excellent performance,and the detected anomaly areas are represented as heat maps.It allows for the detection of anomalies,and by applying an anomaly map to the original image,it is possible to capture the areas where anomalies occur.The performance evaluation shows that both F1-score and Accuracy are high when time series data is converted to images.Additionally,when processed as images rather than as time series data,there was a significant reduction in both the size of the data and the training time.The proposed method can provide an important springboard for research in the field of anomaly detection using time series data.Besides,it helps solve problems such as analyzing complex patterns in data lightweight.

关键词： Defect detection time series deep learning data augmentation data transformation

data augmentation and Random Multi-Model Deep Learning for data Classification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第3期74卷 5191-5207页

作者： Fatma Harby Adel Thaljaoui Durre Nayab Suliman Aladhadh Salim EL Khediri Rehan Ullah Khan Computer Science Department Future Academy-Higher Future Institute for Specialized Technological StudiesEgypt Department of Computer Systems Engineering Faculty of Electrical and Computer EngineeringUniversity of Engineering and TechnologyPeshawar25120Pakistan Department of Information Technology College of ComputerQassim UniversityBuraydahSaudi Arabia Department of Computer Sciences Faculty of Sciences of GafsaUniversity of GafsaGafsaTunisia

In the machine learning(ML)paradigm,data augmentation serves as a regularization approach for creating ML models.The increase in the diversification of training samples increases the generalization capabilities,which enhances the prediction performance of classifiers when tested on unseen examples.Deep learning(DL)models have a lot of parameters,and they frequently overfit.Effectively,to avoid overfitting,data plays a major role to augment the latest improvements in DL.Nevertheless,reliable data collection is a major limiting factor.Frequently,this problem is undertaken by combining augmentation of data,transfer learning,dropout,and methods of normalization in batches.In this paper,we introduce the application of data augmentation in the field of image classification using Random Multi-model Deep Learning(RMDL)which uses the association approaches of multi-DL to yield random models for classification.We present a methodology for using Generative Adversarial Networks(GANs)to generate images for data augmenting.Through experiments,we discover that samples generated by GANs when fed into RMDL improve both accuracy and model efficiency.Experimenting across both MNIST and CIAFAR-10 datasets show that,error rate with proposed approach has been decreased with different random models.

关键词： data augmentation generative adversarial networks classification machine learning random multi-model deep learning

data augmentation Using Contour Image for Convolutional Neural Network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第6期75卷 4669-4680页

作者： Seung-Yeon Hwang Jeong-Joon Kim Department of Computer Engineering Anyang UniversityAnyang-si14058Korea Department of ICT Convergence Engineering Anyang UniversityAnyang-si14058Korea

With the development of artificial intelligence-related technologies such as deep learning,various organizations,including the government,are making various efforts to generate and manage big data for use in artificial intelligence.However,it is difficult to acquire big data due to various social problems and restrictions such as personal information leakage.There are many problems in introducing technology in fields that do not have enough training data necessary to apply deep learning technology.Therefore,this study proposes a mixed contour data augmentation technique,which is a data augmentation technique using contour images,to solve a problem caused by a lack of ***,a famous convolutional neural network(CNN)architecture,and CIFAR-10,a benchmark data set,are used for experimental performance evaluation to prove the superiority of the proposed method.And to prove that high performance improvement can be achieved even with a small training dataset,the ratio of the training dataset was divided into 70%,50%,and 30%for comparative analysis.As a result of applying the mixed contour data augmentation technique,it was possible to achieve a classification accuracy improvement of up to 4.64%and high accuracy even with a small amount of data set.In addition,it is expected that the mixed contour data augmentation technique can be applied in various fields by proving the excellence of the proposed data augmentation technique using benchmark datasets.

关键词： data augmentation image classification deep learning convolutional neural network mixed contour image benchmark dataset

data-driven glass-forming ability criterion for bulk amorphous metals with data augmentation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Materials Science & Technology 2022年第26期121卷 99-104页

作者： Jie Xiong Tong-Yi Zhang School of Materials Science and Engineering Harbin Institute of TechnologyShenzhen 518000China Hong Kong University of Science and Technology(Guangzhou) Guangzhou 511400China Material Genome Institute Shanghai UniversityShanghai 200444China

A data augmentation technique is employed in the current work on a training dataset of 610 bulk metallic glasses(BMGs),which are randomly selected from 762 collected data.An ensemble machine learning(ML)model is developed on augmented training dataset and tested by the rest 152 data.The result shows that ML model has the ability to predict the maximal diameter Dmaxof BMGs more accurate than all reported ML models.In addition,the novel ML model gives the glass forming ability(GFA)rules:average atomic radius ranging from 140 pm to 165 pm,the value of TT/(T-T)(T-T)being higher than 2.5,the entropy of mixing being higher than 10 J/K/mol,and the enthalpy of mixing ranging from-32 k J/mol to-26 k J/mol.ML model is interpretative,thereby deepening the understanding of GFA.

关键词： Materials informatics Glass-forming ability data augmentation Model interpretation Meta-ensemble model

A novel deep generative modeling-based data augmentation strategy for improving short-term building energy predictions

在线全文

学校读者我要写书评

暂无评论

Building Simulation 2022年第2期15卷 197-211页

作者： Cheng Fan Meiling Chen Rui Tang Jiayuan Wang Key Laboratory for Resilient Infrastructures of Coastal Cities(Shenzhen University) Ministry of EducationChina Sino-Australia Joint Research Center in BIM and Smart Construction Shenzhen UniversityShenzhenChina Building Technology&Urban Systems Division Lawrence Berkeley National LaboratoryUSA

Short-term building energy predictions serve as one of the fundamental tasks in building operation management.While large numbers of studies have explored the value of various supervised machine learning techniques in energy predictions,few studies have addressed the potential data shortage problem in developing data-driven models.One promising solution is data augmentation,which aims to enrich existing building data resources for reliable predictive modeling.This study proposes a deep generative modeling-based data augmentation strategy for improving short-term building energy predictions.Two types of conditional variational autoencoders have been designed for synthetic energy data generation using fully connected and one-dimensional convolutional layers respectively.data experiments have been designed to evaluate the value of data augmentation using actual measurements from 52 buildings.The results indicate that conditional variational autoencoders are capable of generating high-quality synthetic data samples,which in turns helps to enhance the accuracy in short-term building energy predictions.The average performance enhancement ratios in terms of CV-RMSE range between 12%and 18%.Practical guidelines have been obtained to ensure the validity and quality of synthetic building energy data.The research outcomes are valuable for enhancing the robustness and reliability of data-driven models for smart building operation management.

关键词： building energy predictions data augmentation data-driven models generative modeling variational autoencoders

Rolling bearing fault diagnostics based on improved data augmentation and ConvNet

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2023年第4期34卷 1074-1084页

作者： KULEVOME Delanyo Kwame Bensah WANG Hong WANG Xuegang School of Information and Communication Engineering University of Electronic Science and Technology of ChinaChengdu 611731China Yangtze Delta Region Institute(Huzhou) University of Electronic Science and Technology of ChinaHuzhou 313001China

Convolutional neural networks(CNNs)are well suited to bearing fault classification due to their ability to learn discriminative spectro-temporal patterns.However,gathering sufficient cases of faulty conditions in real-world engineering scenarios to train an intelligent diagnosis system is challenging.This paper proposes a fault diagnosis method combining several augmentation schemes to alleviate the problem of limited fault data.We begin by identifying relevant parameters that influence the construction of a spectrogram.We leverage the uncertainty principle in processing time-frequency domain signals,making it impossible to simultaneously achieve good time and frequency resolutions.A key determinant of this phenomenon is the window function's choice and length used in implementing the shorttime Fourier transform.The Gaussian,Kaiser,and rectangular windows are selected in the experimentation due to their diverse characteristics.The overlap parameter's size also influences the outcome and resolution of the spectrogram.A 50%overlap is used in the original data transformation,and±25%is used in implementing an effective augmentation policy to which two-stage regular CNN can be applied to achieve improved performance.The best model reaches an accuracy of 99.98%and a cross-domain accuracy of 92.54%.When combined with data augmentation,the proposed model yields cutting-edge results.

关键词： bearing failure short-time Fourier transform prognostics and health management data augmentation fault diagnosis

data augmentation via joint multi-scale CNN and multi-channel attention for bumblebee image generation

在线全文

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2023年第3期30卷 32-40,98页

作者： Du Rong Chen Shudong Li Weiwei Zhang Xueting Wang Xianhui Ge Jin Intelligent Manufacturing Electronics Research and Development Center Institute of Microelectronics of the Chinese Academy of SciencesBeijing 100029China School of Integrated Circuits University of Chinese Academy of SciencesBeijing 100049China Institute of Zoology Chinese Academy of SciencesBeijing 100080China Center for Excellence in Biotic Interactions University of Chinese Academy of SciencesBeijing 100049China

The difficulty of bumblebee data collecting and the laborious nature of bumblebee data annotation sometimes result in a lack of training data,which impairs the effectiveness of deep learning based counting methods.Given that it is challenging to produce the detailed background information in the generated bumblebee images using current data augmentation methods,in this paper,a joint multi-scale convolutional neural network and multi-channel attention based generative adversarial network(MMGAN)is proposed.MMGAN generates the bumblebee image in accordance with the corresponding density map marking the bumblebee positions.Specifically,the multi-scale convolutional neural network(CNN)module utilizes multiple convolution kernels to completely extract features of different scales from the input bumblebee image and density map.To generate various targets in the generated image,the multi-channel attention module builds numerous intermediate generation layers and attention maps.These targets are then stacked to produce a bumblebee image with a specific number of bumblebees.The proposed model obtains the greatest performance in bumblebee image generating tasks,and such generated bumblebee images considerably improve the efficiency of deep learning based counting methods in bumblebee counting applications.

关键词： data augmentation image generation attention mechanism