检索结果-内蒙古大学图书馆

data-Enhanced Low-Cycle Fatigue Life Prediction Model Based on Nickel-Based Superalloys

ACTA MECHANICA SOLIDA SINICA 2024年 1-12页

作者： Xu, Luopeng Xiong, Lei Zhang, Rulun Zheng, Jiajun Zou, Huawei Li, Zhixin Wang, Xiaopeng Wang, Qingyuan Civil Aviat Flight Univ China Sch Sci Guanghan 618307 Peoples R China Civil Aviat Flight Univ China Aviat Engn Inst Guanghan 618307 Peoples R China Civil Aviat Flight Univ China Sichuan Prov Engn Technol Res Ctr Gen Aircraft Mai Guanghan 618307 Peoples R China Sichuan Univ Polymer Res Inst State Key Lab Polymer Mat Engn Chengdu 610065 Peoples R China China Three Gorges Univ Hubei Key Lab Hydropower Machinery Equipment Desig Yichang 443002 Peoples R China Chengdu Univ Sch Mech Engn Chengdu 610106 Peoples R China

To overcome the challenges of limited experimental data and improve the accuracy of empirical formulas, we propose a low-cycle fatigue (LCF) life prediction model for nickel-based superalloys using a data augmentation method. This method utilizes a variational autoencoder (VAE) to generate low-cycle fatigue data and form an augmented dataset. The Pearson correlation coefficient (PCC) is employed to verify the similarity of feature distributions between the original and augmented datasets. Six machine learning models, namely random forest (RF), artificial neural network (ANN), support vector machine (SVM), gradient-boosted decision tree (GBDT), eXtreme Gradient Boosting (XGBoost), and Categorical Boosting (CatBoost), are utilized to predict the LCF life of nickel-based superalloys. Results indicate that the proposed data augmentation method based on VAE can effectively expand the dataset, and the mean absolute error (MAE), root mean square error (RMSE), and R-squared (R2) values achieved using the CatBoost model, with respective values of 0.0242, 0.0391, and 0.9538, are superior to those of the other models. The proposed method reduces the cost and time associated with LCF experiments and accurately establishes the relationship between fatigue characteristics and LCF life of nickel-based superalloys.

关键词： Nickel-based superalloy Low-cycle fatigue (LCF) Fatigue life prediction data augmentation method Machine learning model Variational autoencoder (VAE)

来源：评论

学校读者我要写书评

暂无评论

ENHANCED ASR FOR STUTTERING SPEECH: COMBINING ADVERSARIAL AND SIGNAL-BASED data augmentation

ENHANCED ASR FOR STUTTERING SPEECH: COMBINING ADVERSARIAL AN...

引用

2024 Spoken Language Technology Workshop

作者： Huang, Shangkun Zhang, Dejun Deng, Jing Zheng, Rong Beijing Fosafer Informat Technol Co Ltd Beijing Peoples R China

ISBN: (纸本)9798350392265;9798350392258

This paper presents our submission to the SLT2024 StutteringSpeech Challenge, focusing on augmenting stuttering data using straightforward and effective techniques. We combined adversarial and signal-based data augmentation methods, including modifying speech rate and rhythm, inserting silence segments, repeating speech segments, and applying Generative Adversarial Network-based (GAN-based) perturbation. These techniques enabled us to generate stuttering speech from fluent speech, which we used to train our automatic speech recognition (ASR) model, enhancing its robustness for individuals with stuttering. Our system achieved a character error rate (CER) of 12.30% in the StutteringSpeech Challenge Track 2, demonstrating a relative improvement of 35.87% over the official baseline and securing first place in the competition.

关键词： Stuttered speech automatic speech recognition GAN data augmentation method

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based substation remote construction management and AI automatic violation detection system

引用

IET GENERATION TRANSMISSION & DISTRIBUTION 2022年第9期16卷 1714-1726页

作者： Yan, Kai Li, Quanjing Li, Hao Wang, Haifeng Fang, Yuping Xing, Lin Yang, Yang Bai, Haicheng Zhou, Chengjiang Yunnan Normal Univ Sch Informat Sci & Technol Kunming 650500 Yunnan Peoples R China Yunnan Normal Univ Lab Pattern Recognit & Artificial Intelligence Kunming 650500 Yunnan Peoples R China Yunnan Normal Univ Sch Phys & Elect Informat Kunming 650500 Yunnan Peoples R China Yunnan Normal Univ Sch Vocat & Tech Educ Kunming 650500 Yunnan Peoples R China

Workplace video surveillance and timely response to operational violations are critical to avoid operator injuries at power construction sites. Here, a system that combines remote substation construction management and artificial intelligence object detection techniques to intellectualize the power construction management process and identify violations during construction in real time is proposed. To improve the detection accuracy, a data augmentation method, including three operations: (1) object segmentation and background fusion;(2) partial erasing;and (3) other basic transformations, is also proposed. Six variants of the You Only Look Once (YOLO) model are trained as detectors for comparative experiments on a dataset collected at the practical construction site. The experimental results show that the detection precision and recall of the YOLOv5-s model are 0.852 and 0.922, with high accuracy and low miss rate, which meet the requirements of robustness and accuracy in detecting realistic power construction violations.

关键词： object detection image segmentation data augmentation power construction sites artificial intelligence object detection techniques video surveillance detection accuracy operator injuries substations realistic power construction violations timely response workplace video surveillance power construction management process remote substation construction management data augmentation method operational violations AI automatic violation detection system background fusion deep learning-based substation remote construction management deep learning (artificial intelligence) practical construction site detection precision artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis method Based on Xgboost and LR Fusion Model under data Imbalance

引用

Journal of Beijing Institute of Technology 2022年第4期31卷 401-412页

作者： Liling Ma Tianyi Wang Xiaoran Liu Junzheng Wang Wei Shen School of Automation Beijing Institute of TechnologyBeijing 100081China

Diagnosis methods based on machine learning and deep learning are widely used in the field of motor fault ***,due to the fact that the data imbalance caused by the high cost of obtaining fault data will lead to insufficient generalization performance of the diagnosis *** response to this problem,a motor fault monitoring system is proposed,which includes a fault diagnosis method(Xgb_LR)based on the optimized gradient boosting decision tree(Xgboost)and logistic regression(LR)fusion model and a data augmentation method named data simulation neighborhood interpolation(DSNI).The Xgb_LR method combines the advantages of the two models and has positive adaptability to imbalanced ***,the DSNI method can be used as an auxiliary method of the diagnosis method to reduce the impact of data imbalance by expanding the original data(signal).Simulation experiments verify the effectiveness of the proposed methods.

关键词： imbalanced data fault diagnosis data augmentation method

来源：评论

学校读者我要写书评

暂无评论

Expression retargeting from images to three-dimensional face models represented in texture space

引用

JOURNAL OF THE SOCIETY FOR INFORMATION DISPLAY 2022年第10期30卷 775-788页

作者： Tu, Ziqi Weng, Dongdong Liang, Bin Luo, Le Beijing Inst Technol Sch Opt & Photon Beijing Engn Res Ctr Mixed Real & Adv Display Beijing 100081 Peoples R China

Facial expressions play a very important role in creating a vivid and realistic virtual character. This paper proposes a convolutional neural network-based facial expression retargeting framework named EXPUV-Net, which can extract expression information from an image and transfer it to a specified 3D face. With the help of the nonlinear generator, the proposed framework can generate rich facial expressions and does not rely on the blendshape model. A data augmentation approach is adopted in this paper, which can improve the adaptability of the proposed framework. The framework can realize expression retargeting for face models with different topologies. This paper also demonstrates the effectiveness of the proposed framework through some experiments and compares it with some linear face model-based methods for facial component extraction and face reconstruction. The results show that the proposed framework has better performance than the linear methods. The proposed framework is very helpful for facial expression generation for virtual characters.

关键词： data augmentation method expression information extraction expression retargeting mixed reality virtual character

来源：评论

学校读者我要写书评

暂无评论

Road defect detection from on-board cameras with scarce and cross-domain data

引用

AUTOMATION IN CONSTRUCTION 2022年 144卷

作者： Zhou, Wei Zhan, Yunfei Zhang, Hancheng Zhao, Lei Wang, Chen Southeast Univ Sch Transportat Southeast Univ Rd Nanjing 211189 Jiangsu Peoples R China Purple Mt Labs Mozhou East Rd Nanjing 210008 Jiangsu Peoples R China

Deep learning methods have attained promising performance on road defect detection from on-board cameras. However, they oftentimes rely heavily on well-annotated datasets with sufficient samples, limiting the practical applications when only few labeled samples are available. To fill this gap, this paper proposes a framework based on Faster Region-Convolutional Neural Network (Faster R-CNN) for road defect detection with scarce and cross-domain data. First, a defect weighting branch is developed to enable Faster R-CNN to quickly learn to detect road defects with few annotated data, then a data augmentation method is proposed to enlarge the abundance of annotated data and alleviate the cross-domain issue. Experimental results demonstrate that the proposed framework has attained better performance compared to a state-of-the-art few-shot detector, in terms of an improved mean average precision of 1.83% when only limited samples (i.e., 30 images per category) are provided for training. In the future, the proposed framework could also be extended to other detection tasks with limited data (e.g., construction vehicle detection), allowing humans to reduce their efforts and time required for arduous data collection and annotation.

关键词： Road defect detection Computer vision Few-shot object detection data augmentation method

来源：评论

学校读者我要写书评

暂无评论

UCT-GAN: underwater image colour transfer generative adversarial network

引用

IET IMAGE PROCESSING 2020年第14期14卷 3613-3622页

作者： Deng, Junjie Luo, Gege Zhao, Caidan Xiamen Univ Sch Informat Xiamen 361005 Peoples R China Xiamen Univ Sch Elect Sci & Engn Xiamen 361005 Peoples R China

Underwater image enhancement algorithms improve image quality and indirectly enhance underwater visibility. Although many underwater image enhancement neural networks have been proposed, they require large amounts of data. To reduce the amount of data required while providing better image enhancement, this study proposes an underwater image colour transfer generative adversarial network (UCT-GAN). The authors first design a non-linear mapping function to generate colour cast images according to original images. Then, the authors utilise these image pairs (i.e. colour cast images and corresponding original images) to guide the UCT-GAN in learning the inverse function of the designed non-linear mapping function. Finally, colour cast images are restored via the inverse function. A data augmentation method based on Poisson fusion and block combination is also proposed to overcome the problem of requiring a large amount of training data. Moreover, the authors extend UCT-GAN into a multi-class colour transfer network to achieve an array of underwater image enhancements. Experimental results indicate that the proposed UCT-GAN can more effectively resolve underwater image colour cast compared to existing algorithms.

关键词： image enhancement image colour analysis neural nets image fusion geophysical image processing image restoration image enhancement algorithms image quality underwater visibility enhancement underwater image enhancement neural networks underwater image colour transfer generative adversarial network UCT-GAN nonlinear mapping function image pairs inverse function multiclass colour transfer network colour cast image restoration Poisson fusion block combination training data data augmentation method

来源：评论

学校读者我要写书评

暂无评论

BitMix: data augmentation for image steganalysis

引用

ELECTRONICS LETTERS 2020年第24期56卷 1311-1314页

作者： Yu, I. -J. Ahn, W. Nam, S. -H. Lee, H. -K. Korea Adv Inst Sci & Technol Sch Comp Daejeon South Korea

Convolutional neural networks for image steganalysis demonstrate better performances with employing concepts from high-level vision tasks. The major employed concept is to use data augmentation to avoid overfitting due to limited data. To augment data without damaging the message embedding, only rotating multiples of 90 degrees or horizontally flipping are used in steganalysis, which generates eight fixed results from one sample. To overcome this limitation, the authors propose BitMix, a data augmentation method for spatial image steganalysis. BitMix mixes a cover and stego image pair by swapping the random patch and generates an embedding adaptive label with the ratio of the number of pixels modified in the swapped patch to those in the cover-stego pair. The authors explore optimal hyperparameters, the ratio of applying BitMix in the mini-batch, and the size of the bounding box for swapping patch. The results reveal that using BitMix improves the performance of spatial image steganalysis and better than other data augmentation methods.

关键词： Bayes methods steganography learning (artificial intelligence) computer vision convolutional neural nets image resolution swapping patch BitMix spatial image steganalysis convolutional neural networks high-level vision tasks employed concept message embedding data augmentation method image pair embedding adaptive label swapped patch cover-stego pair

来源：评论

学校读者我要写书评

暂无评论

Breast mass detection in digital mammography based on anchor-free architecture

引用

COMPUTER methodS AND PROGRAMS IN BIOMEDICINE 2021年 205卷 106033-106033页

作者： Cao, Haichao Pu, Shiliang Tan, Wenming Tong, Junyan Hikvis Digital Technol Co Ltd Hangzhou 310051 Peoples R China

Background and objective: Accurate detection of breast masses in mammography images is critical to di-agnose early breast cancer, which can greatly improve the patients' survival rate. However, it is still a big challenge due to the heterogeneity of breast masses and the complexity of their surrounding environ-ment. Therefore, how to develop a robust breast mass detection framework in clinical practical applica-tions to improve patient survival is a topic that researchers need to continue to explore. methods: To address these problems, we propose a one-stage object detection architecture, called Breast Mass Detection Network (BMassDNet), based on anchor-free and feature pyramid which makes the de-tection of breast masses of different sizes well adapted. We introduce a truncation normalization method combine it with adaptive histogram equalization to enhance the contrast between the breast mass the surrounding environment. Meanwhile, to solve the overfitting problem caused by small data size, propose a natural deformation data augmentation method and mend the train data dynamic updat-method based on the data complexity to effectively utilize the limited data. Finally, we use transfer learning to assist the training process and to improve the robustness of the model ulteriorly. Results: On the INbreast dataset, each image has an average of 0.495 false positives whilst the recall rate 0.930;On the DDSM dataset, when each image has 0.599 false positives, the recall rate reaches 0.943. Conclusions: The experimental results on datasets INbreast and DDSM show that the proposed BMassD-can obtain competitive detection performance over the current top ranked methods. (c) 2021 Published by Elsevier B.V.

关键词： Breast mass detection Anchor-free architecture Image enhancement method data augmentation method Training method

来源：评论

学校读者我要写书评

暂无评论

SAR ATR with full-angle data augmentation and feature polymerisation

引用

JOURNAL OF ENGINEERING-JOE 2019年第19期2019卷 6226-6230页

作者： Zhai, Yikui Ma, Hui Liu, Jian Deng, Wenbo Shang, Lijuan Sun, Bing Jiang, Ziyi Guan, Huixin Zhi, Yihang Wu, Xi Zhou, Jihua Wuyi Univ Sch Informat Engn Jiangmen Peoples R China Beihang Univ Scool Elect & Informat Engn Beijing Peoples R China Wuyi Univ Sch Comp Jiangmen Peoples R China

Utilising neural networks to learn and extract valuable features has achieved satisfactory performance for synthetic aperture radar automatic target recognition (SAR ATR). However, such target recognition capability could be seriously limited by severe image rotation. To greatly improve the performance of convolutional neural networks-based SAR ATR, a data augmentation method combining region of interest (ROI) extraction and full-angle rotation method is firstly proposed in this study. Then, an inception-SAR NET is presented to polymerise multi-branch feature maps. The superior performance of inception-SAR NET structures is obtained by comprehensive experiments. Finally, the results based on MSTAR dataset demonstrate that authors' methods could achieve the most advanced performance.

关键词： radar imaging synthetic aperture radar image recognition radar target recognition feature extraction object recognition convolutional neural nets radar computing feature polymerisation synthetic aperture radar automatic target recognition target recognition capability convolutional neural networks-based SAR ATR full-angle rotation method multibranch feature maps inception-SAR NET structures image rotation data augmentation method

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：