Pub Date : 2023-01-01DOI: 10.32604/cmes.2023.044709
Wangchen Yan, Jinbao Yang, Xin Luo
Transfer learning could reduce the time and resources required for the training of new models and be therefore important in generalized applications of the trained machine learning algorithms. In this study, a transfer learning-enhanced convolutional neural network (CNN) was proposed to identify the gross weight and the axle weight of moving vehicles on the bridge. The proposed transfer learning-enhanced CNN model was expected to weigh different bridges based on a small amount of training datasets and provide high identification accuracy. First of all, a CNN algorithm for bridge weigh-in-motion (B-WIM) technology was proposed to identify the axle weight and the gross weight of the typical two-axle, three-axle, and five-axle vehicles as they crossed the bridge with different loading routes and speeds. Then, the pre-trained CNN model was transferred by fine-tuning to weigh the moving vehicles on another bridge. Finally, the identification accuracy and the amount of training data required were compared between the two CNN models. Results showed that the pre-trained CNN model using transfer learning for B-WIM technology could be successfully used for the identification of the axle weight and the gross weight for moving vehicles on another bridge while reducing the training data by 63%. Moreover, the recognition accuracy of the pre-trained CNN model using transfer learning was comparable to that of the original model, showing its promising potentials in the actual applications.
{"title":"Quick Weighing of Passing Vehicles Using the Transfer-Learning-Enhanced Convolutional Neural Network","authors":"Wangchen Yan, Jinbao Yang, Xin Luo","doi":"10.32604/cmes.2023.044709","DOIUrl":"https://doi.org/10.32604/cmes.2023.044709","url":null,"abstract":"Transfer learning could reduce the time and resources required for the training of new models and be therefore important in generalized applications of the trained machine learning algorithms. In this study, a transfer learning-enhanced convolutional neural network (CNN) was proposed to identify the gross weight and the axle weight of moving vehicles on the bridge. The proposed transfer learning-enhanced CNN model was expected to weigh different bridges based on a small amount of training datasets and provide high identification accuracy. First of all, a CNN algorithm for bridge weigh-in-motion (B-WIM) technology was proposed to identify the axle weight and the gross weight of the typical two-axle, three-axle, and five-axle vehicles as they crossed the bridge with different loading routes and speeds. Then, the pre-trained CNN model was transferred by fine-tuning to weigh the moving vehicles on another bridge. Finally, the identification accuracy and the amount of training data required were compared between the two CNN models. Results showed that the pre-trained CNN model using transfer learning for B-WIM technology could be successfully used for the identification of the axle weight and the gross weight for moving vehicles on another bridge while reducing the training data by 63%. Moreover, the recognition accuracy of the pre-trained CNN model using transfer learning was comparable to that of the original model, showing its promising potentials in the actual applications.","PeriodicalId":10451,"journal":{"name":"Cmes-computer Modeling in Engineering & Sciences","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135839612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.32604/cmes.2022.018130
Bei Liu, Xian Zhang
During high-intensity focused ultrasound (HIFU) treatment, the accurate identification of denatured biological tissue is an important practical problem. In this paper, a novel method based on the improved variational mode decomposition (IVMD) and autoregressive (AR) model was proposed, which identified denatured biological tissue according to the characteristics of ultrasonic scattered echo signals during HIFU treatment. Firstly, the IVMD method was proposed to solve the problem that the VMD reconstruction signal still has noise due to the limited number of intrinsic mode functions (IMF). The ultrasonic scattered echo signals were reconstructed by the IVMD to achieve denoising. Then, the AR model was introduced to improve the recognition rate of denatured biological tissues. The AR model order parameter was determined by the Akaike information criterion (AIC) and the characteristics of the AR coefficients were extracted. Finally, the optimal characteristics of the AR coefficients were selected according to the results of receiver operating characteristic (ROC). The experiments showed that the signal-to-noise ratio (SNR) and root mean square error (RMSE) of the reconstructed signal obtained by IVMD was better than those obtained by variational mode decomposition (VMD). The IVMD-AR method was applied to the actual ultrasonic scattered echo signals during HIFU treatment, and the support vector machine (SVM) was used to identify the denatured biological tissue. The results show that compared with sample entropy, information entropy, and energy methods, the proposed IVMD-AR method can more effectively identify denatured biological tissue. The recognition rate of denatured biological tissue was higher, up to 93.0%.
在高强度聚焦超声(HIFU)治疗中，变性生物组织的准确识别是一个重要的现实问题。本文提出了一种基于改进变分模态分解(IVMD)和自回归(AR)模型的方法，根据HIFU治疗过程中超声散射回波信号的特征识别变性生物组织。首先，针对固有模态函数(IMF)数量有限导致VMD重构信号仍然存在噪声的问题，提出了IVMD方法;利用IVMD对超声散射回波信号进行重构，实现去噪。然后，引入AR模型，提高变性生物组织的识别率。利用赤池信息准则(Akaike information criterion, AIC)确定AR模型阶数参数，提取AR系数的特征。最后，根据受试者工作特征(ROC)结果选择最佳的AR系数特征。实验表明，IVMD得到的重构信号信噪比(SNR)和均方根误差(RMSE)优于变分模态分解(VMD)得到的重构信号。将IVMD-AR方法应用于HIFU治疗过程中的实际超声散射回波信号，并利用支持向量机(SVM)识别变性生物组织。结果表明，与样本熵、信息熵和能量方法相比，所提出的IVMD-AR方法能更有效地识别变性生物组织。对变性生物组织的识别率较高，达93.0%。
{"title":"Identification of Denatured Biological Tissues Based on Improved Variational Mode Decomposition and Autoregressive Model during HIFU Treatment","authors":"Bei Liu, Xian Zhang","doi":"10.32604/cmes.2022.018130","DOIUrl":"https://doi.org/10.32604/cmes.2022.018130","url":null,"abstract":"During high-intensity focused ultrasound (HIFU) treatment, the accurate identification of denatured biological tissue is an important practical problem. In this paper, a novel method based on the improved variational mode decomposition (IVMD) and autoregressive (AR) model was proposed, which identified denatured biological tissue according to the characteristics of ultrasonic scattered echo signals during HIFU treatment. Firstly, the IVMD method was proposed to solve the problem that the VMD reconstruction signal still has noise due to the limited number of intrinsic mode functions (IMF). The ultrasonic scattered echo signals were reconstructed by the IVMD to achieve denoising. Then, the AR model was introduced to improve the recognition rate of denatured biological tissues. The AR model order parameter was determined by the Akaike information criterion (AIC) and the characteristics of the AR coefficients were extracted. Finally, the optimal characteristics of the AR coefficients were selected according to the results of receiver operating characteristic (ROC). The experiments showed that the signal-to-noise ratio (SNR) and root mean square error (RMSE) of the reconstructed signal obtained by IVMD was better than those obtained by variational mode decomposition (VMD). The IVMD-AR method was applied to the actual ultrasonic scattered echo signals during HIFU treatment, and the support vector machine (SVM) was used to identify the denatured biological tissue. The results show that compared with sample entropy, information entropy, and energy methods, the proposed IVMD-AR method can more effectively identify denatured biological tissue. The recognition rate of denatured biological tissue was higher, up to 93.0%.","PeriodicalId":10451,"journal":{"name":"Cmes-computer Modeling in Engineering & Sciences","volume":"17 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81381301","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.32604/cmes.2022.018134
K. Liu, Yanqiao Wang
{"title":"Influence of Soil Heterogeneity on the Behavior of Frozen Soil Slope under Freeze-Thaw Cycles","authors":"K. Liu, Yanqiao Wang","doi":"10.32604/cmes.2022.018134","DOIUrl":"https://doi.org/10.32604/cmes.2022.018134","url":null,"abstract":"","PeriodicalId":10451,"journal":{"name":"Cmes-computer Modeling in Engineering & Sciences","volume":"96 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72525296","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.32604/cmes.2022.018123
Debiao Meng, Hongtao Wang, S. Yang, Zhiyuan Lv, Z. Hu, Zihao Wang
{"title":"Fault Analysis of Wind Power Rolling Bearing Based on EMD Feature Extraction","authors":"Debiao Meng, Hongtao Wang, S. Yang, Zhiyuan Lv, Z. Hu, Zihao Wang","doi":"10.32604/cmes.2022.018123","DOIUrl":"https://doi.org/10.32604/cmes.2022.018123","url":null,"abstract":"","PeriodicalId":10451,"journal":{"name":"Cmes-computer Modeling in Engineering & Sciences","volume":"28 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72803478","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.32604/cmes.2022.018201
Jong-In Choi, Sookyun Kim, Shinjin Kang
{"title":"Image Translation Method for Game Character Sprite Drawing","authors":"Jong-In Choi, Sookyun Kim, Shinjin Kang","doi":"10.32604/cmes.2022.018201","DOIUrl":"https://doi.org/10.32604/cmes.2022.018201","url":null,"abstract":"","PeriodicalId":10451,"journal":{"name":"Cmes-computer Modeling in Engineering & Sciences","volume":"31 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80293199","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.32604/cmes.2022.017650
Rizwan Taj, Feng Tao, S. Khurram, Ateeq ur Rehman, Syed Kamran Haider, Akber Abid Gardezi, S. Kanwal
{"title":"Reversible Watermarking Method with Low Distortion for the Secure Transmission of Medical Images","authors":"Rizwan Taj, Feng Tao, S. Khurram, Ateeq ur Rehman, Syed Kamran Haider, Akber Abid Gardezi, S. Kanwal","doi":"10.32604/cmes.2022.017650","DOIUrl":"https://doi.org/10.32604/cmes.2022.017650","url":null,"abstract":"","PeriodicalId":10451,"journal":{"name":"Cmes-computer Modeling in Engineering & Sciences","volume":"10 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87009292","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.32604/cmes.2022.018518
Arif Mehmood, M. Aslam, Muhammad Imran Khan, Humera Qureshi, Choonkill Park, Jung Rye Lee
{"title":"A New Attempt to Neutrosophic Soft Bi-Topological Spaces","authors":"Arif Mehmood, M. Aslam, Muhammad Imran Khan, Humera Qureshi, Choonkill Park, Jung Rye Lee","doi":"10.32604/cmes.2022.018518","DOIUrl":"https://doi.org/10.32604/cmes.2022.018518","url":null,"abstract":"","PeriodicalId":10451,"journal":{"name":"Cmes-computer Modeling in Engineering & Sciences","volume":"136 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84972669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.32604/cmes.2022.019188
Kailei Wang, Mingjing Li, P. Yan, Leiting Dong
{"title":"An Experimental and Numerical Study on the Ballistic Performance of Multi-Layered Moderately-Thick Metallic Targets against 12.7-mm Projectiles","authors":"Kailei Wang, Mingjing Li, P. Yan, Leiting Dong","doi":"10.32604/cmes.2022.019188","DOIUrl":"https://doi.org/10.32604/cmes.2022.019188","url":null,"abstract":"","PeriodicalId":10451,"journal":{"name":"Cmes-computer Modeling in Engineering & Sciences","volume":"33 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84506062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-01-01DOI: 10.32604/cmes.2022.018113
Yuhang Jin, E. Guo, Houli Wu, P. Yan
{"title":"Dynamic-Response Analysis of the Branch System of a Utility Tunnel Subjected to Near-Fault and Far-Field Ground Motions in Different Input Mechanisms","authors":"Yuhang Jin, E. Guo, Houli Wu, P. Yan","doi":"10.32604/cmes.2022.018113","DOIUrl":"https://doi.org/10.32604/cmes.2022.018113","url":null,"abstract":"","PeriodicalId":10451,"journal":{"name":"Cmes-computer Modeling in Engineering & Sciences","volume":"29 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81979084","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：