检索结果-南通市图书馆

Acta Mechanica Solida Sinica 2024年第3期37卷 498-518页

作者： Zihan Jin Jiqiao Zhang Qianpeng He Silang Zhu Tianlong Ouyang Gongfa Chen School of Civil and Transportation Engineering Guangdong University of TechnologyGuangzhou510006China Guangdong Tianxin Electric Power Engineering Testing Co. LtdGuangzhou510663China

Structural damage detection(SDD)remains highly challenging,due to the difficulty in selecting the optimal damage features from a vast amount of *** this study,a tree model-based method using decision tree and random forest was employed for feature selection of vibration response signals in *** datasets were obtained by numerical experiments and vibration experiments,*** features extracted using this method were input into a convolutional neural network to determine the location of structural *** indicated a 5%to 10%improvement in detection accuracy compared to using original datasets without feature selection,demonstrating the feasibility of this *** proposed method,based on tree model and classification,addresses the issue of extracting effective information from numerous vibration response signals in structural health monitoring.

关键词： Feature selection Structural damage detection Decision tree Random forest convolutional neural network

Automated identification of steel weld defects,a convolutional neural network improved machine learning approach

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Structural and Civil Engineering 2024年第2期18卷 294-308页

作者： Zhan SHU Ao WU Yuning SI Hanlin DONG Dejiang WANG Yifan LI School of Mechanics and Engineering Science Shanghai UniversityShanghai 200444China School of Civil Engineering Shanghai Normal UniversityShanghai 201418China Shanghai PinlanData Technology Co. Ltd.Shanghai 200072China

This paper proposes a machine-learning-based methodology to automatically classify different types of steel weld defects,including lack of the fusion,porosity,slag inclusion,and the qualified(no defects)*** methodology solves the shortcomings of existing detection methods,such as expensive equipment,complicated operation and inability to detect internal *** study first collected percussed data from welded steel members with or without weld ***,three methods,the Mel frequency cepstral coefficients,short-time Fourier transform(STFT),and continuous wavelet transform were implemented and compared to explore the most appropriate features for classification of weld *** and convolutional neural network-enhanced algorithms were used to classify,the extracted ***,experiments were designed and performed to validate the proposed *** showed that STFT achieved higher accuracies(up to 96.63%on average)in the weld status *** convolutional neural network-enhanced support vector machine(SVM)outperformed six other algorithms with an average accuracy of 95.8%.In addition,random forest and SVM were efficient approaches with a balanced trade-off between the accuracies and the computational efforts.

关键词： steel weld machine learning convolutional neural network weld defect detection classification task percussion

Expression Recognition Method Based on convolutional neural network and Capsule 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 2024年第4期79卷 1659-1677页

作者： Zhanfeng Wang Lisha Yao School of Computer Science and Artificial Intelligence Chaohu UniversityHefei238000China School of Big Data and Artificial Intelligence Anhui Xinhua UniversityHefei230088China

convolutional neural networks struggle to accurately handle changes in angles and twists in the direction of images,which affects their ability to recognize patterns based on internal feature levels. In contrast, CapsNet overcomesthese limitations by vectorizing information through increased directionality and magnitude, ensuring that spatialinformation is not overlooked. Therefore, this study proposes a novel expression recognition technique calledCAPSULE-VGG, which combines the strengths of CapsNet and convolutional neural networks. By refining andintegrating features extracted by a convolutional neural network before introducing theminto CapsNet, ourmodelenhances facial recognition capabilities. Compared to traditional neural network models, our approach offersfaster training pace, improved convergence speed, and higher accuracy rates approaching stability. Experimentalresults demonstrate that our method achieves recognition rates of 74.14% for the FER2013 expression dataset and99.85% for the CK+ expression dataset. By contrasting these findings with those obtained using conventionalexpression recognition techniques and incorporating CapsNet’s advantages, we effectively address issues associatedwith convolutional neural networks while increasing expression identification accuracy.

关键词： Expression recognition capsule neural network convolutional neural network

Customized convolutional neural network for Accurate Detection of Deep Fake Images in Video Collections

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5期79卷 1995-2014页

作者： Dmitry Gura Bo Dong Duaa Mehiar Nidal Al Said Department of Cadastre and Geoengineering Kuban State Technological UniversityKrasnodar350072Russian Federation Department of Geodesy Kuban State Agrarian UniversityKrasnodar350072Russian Federation School of Innovation and Entrepreneurship Liaoning UniversityLiaoning110031China Department of IT Middle East UniversityAmman11831Jordan College of Mass Communication Ajman UniversityP.O Box 346AjmanUnited Arab Emirates

The motivation for this study is that the quality of deep fakes is constantly improving,which leads to the need to develop new methods for their *** proposed Customized convolutional neural network method involves extracting structured data from video frames using facial landmark detection,which is then used as input to the *** customized convolutional neural network method is the date augmented-based CNN model to generate‘fake data’or‘fake images’.This study was carried out using Python and its *** used 242 films from the dataset gathered by the Deep Fake Detection Challenge,of which 199 were made up and the remaining 53 were *** seconds were allotted for each *** were 318 videos used in all,199 of which were fake and 119 of which were *** proposedmethod achieved a testing accuracy of 91.47%,loss of 0.342,and AUC score of 0.92,outperforming two alternative approaches,CNN and ***,our method succeeded in greater accuracy than contemporary models such as XceptionNet,Meso-4,EfficientNet-BO,MesoInception-4,VGG-16,and *** novelty of this investigation is the development of a new convolutional neural network(CNN)learning model that can accurately detect deep fake face photos.

关键词： Deep fake detection video analysis convolutional neural network machine learning video dataset collection facial landmark prediction accuracy models

High-resolution recognition of FOAM modes via an improved EfficientNet V2 based 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

Frontiers of physics 2024年第3期19卷 175-183页

作者： Youzhi Shi Zuhai Ma Hongyu Chen Yougang Ke Yu Chen Xinxing Zhou International Collaborative Laboratory of 2D Materials for Optoelectronics Science and Technology Institute of Microscale OptoelectronicsShenzhen UniversityShenzhen 518060China Key Laboratory of Low-Dimensional Quantum Structures and Quantum Control of Ministry of Education Synergetic Innovation Center for Quantum Effects and ApplicationsSchool of Physics and ElectronicsHunan Normal UniversityChangsha 410081China Key Laboratory of Hunan Province on Information Photonics and Freespace Optical Communications School of Information Science and EngineeringHunan Institute of Science and TechnologyYueyang 414006China

Vortex beam with fractional orbital angular momentum (FOAM) is the excellent candidate for improving the capacity of free-space optical (FSO) communication system due to its infinite modes. Therefore, the recognition of FOAM modes with higher resolution is always of great concern. In this work, through an improved EfficientNetV2 based convolutional neural network (CNN), we experimentally achieve the implementation of the recognition of FOAM modes with a resolution as high as 0.001. To the best of our knowledge, it is the first time this high resolution has been achieved. Under the strong atmospheric turbulence (AT) (C_(n)^(2)=10^(-15)m^(-2/3)), the recognition accuracy of FOAM modes at 0.1 and 0.01 resolution with our model is up to 99.12% and 92.24% for a long transmission distance of 2000 m. Even for the resolution at 0.001, the recognition accuracy can still remain at 78.77%. This work provides an effective method for the recognition of FOAM modes, which may largely improve the channel capacity of the free-space optical communication.

关键词： OAM free-space optical communication deep learning convolutional neural network

Deep learning methods for noisy sperm image classification from convolutional neural network to visual transformer:a comprehensive comparative study

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent Medicine 2024年第2期4卷 114-127页

作者： Ao Chen Chen Li Md Mamunur Rahaman Yudong Yao Haoyuan Chen Hechen Yang Peng Zhao Weiming Hu Wanli Liu Shuojia Zou Ning Xu Marcin Grzegorzek Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information EngineeringNortheastern UniversityShenyangLiaoning 110169China Department of Electrical and Computer Engineering Stevens Institute of TechnologyHobokenNJ 07030USA School of Arts and Design Liaoning Petrochemical UniversityFushunLiaoning 113001China Institute of Medical Informatics University of LübeckLüebeckGermany

Background With the gradual increase of infertility in the world,among which male sperm problems are the main factor for infertility,more and more couples are using computer-assisted sperm analysis(CASA)to assist in the analysis and treatment of ***,the rapid development of deep learning(DL)has led to strong results in image classification ***,the classification of sperm images has not been well studied in current deep learning methods,and the sperm images are often affected by noise in practical CASA *** purpose of this article is to investigate the anti-noise robustness of deep learning classification methods applied on sperm *** The SVIA dataset is a publicly available large-scale sperm dataset containing three *** this work,we used subset-C,which provides more than 125,000 independent images of sperms and impurities,including 121,401 sperm images and 4,479 impurity *** investigate the anti-noise robustness of deep learning classification methods applied on sperm images,we conducted a comprehensive comparative study of sperm images using many convolutional neural network(CNN)and visual transformer(VT)deep learning methods to find the deep learning model with the most stable anti-noise *** This study proved that VT had strong robustness for the classification of tiny object(sperm and impurity)image datasets under some types of conventional noise and some adversarial *** particular,under the influence of Poisson noise,accuracy changed from 91.45%to 91.08%,impurity precison changed from 92.7%to 91.3%,impurity recall changed from 88.8%to 89.5%,and impurity F1-score changed 90.7%to 90.4%.Meanwhile,sperm precision changed from 90.9%to 90.5%,sperm recall changed from 92.5%to 93.8%,and sperm F1-score changed from 92.1%to 90.4%.Conclusion Sperm image classification may be strongly affected by noise in current deep learning methods;the robustness with regard to noise of VT methods based

关键词： Computer-assisted sperm analysis Anti-noise Robustness Deep learning .Image classification Sperm image Conventional noise Adversarial attacks convolutional neural network Visual transformer

Quick Weighing of Passing Vehicles Using the Transfer-Learning-Enhanced 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

Computer Modeling in Engineering & Sciences 2024年第6期139卷 2507-2524页

作者： Wangchen Yan Jinbao Yang Xin Luo College of Civil Engineering Xiangtan UniversityXiangtan411105China Energy&Environmental Engineering Department China CEC Engineering CorporationChangsha410114China

Transfer learning could reduce the time and resources required by the training of new models and be therefore important for generalized applications of the trainedmachine learning *** this study,a transfer learningenhanced convolutional neural network(CNN)was proposed to identify the gross weight and the axle weight of moving vehicles on 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 *** 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 ***,the pre-trained CNN model was transferred by fine-tuning to weigh themoving vehicle on another ***,the identification accuracy and the amount of training data required were compared between the two CNN *** 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.

关键词： Bridge weigh-in-motion transfer learning convolutional neural network

A convolutional neural network to detect possible hidden data in spatial domain images

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Cybersecurity 2024年第1期7卷 37-52页

作者： Jean De La Croix Ntivuguruzwa Tohari Ahmad Department of Informatics Institut Teknologi Sepuluh Nopember(ITS)Kampus ITS Keputih SukoliloSurabaya60111Indonesia African Center of Excellence in the Internet of Things College of Science and TechnologyUniversity of Rwanda3900KigaliRwanda

Hiding secret data in digital multimedia has been essential to protect the ***,attackers with a steganalysis technique may break *** steganalysis methods have good results with conventional Machine Learning(ML)techniques;however,the introduction of convolutional neural network(CNN),a deep learning paradigm,achieved better performance over the previously proposed ML-based *** the existing CNN-based approaches yield good results,they present performance issues in classification accuracy and stability in the network training *** research proposes a new method with a CNN architecture to improve the hidden data detection accuracy and the training phase stability in spatial domain *** proposed method comprises three phases:pre-processing,feature extraction,and ***,in the pre-processing phase,we use spatial rich model filters to enhance the noise within images altered by data hiding;secondly,in the feature extraction phase,we use two-dimensional depthwise separable convolutions to improve the signal-to-noise and regular convolutions to model local features;and finally,in the classification,we use multi-scale average pooling for local features aggregation and representability enhancement regardless of the input size variation,followed by three fully connected layers to form the final feature maps that we transform into class probabilities using the softmax *** results identify an improvement in the accuracy of the considered recent scheme ranging between 4.6 and 10.2%with reduced training time up to 30.81%.

关键词： Information security Spatial domain steganalysis Deep learning convolutional neural network Infrastructure

Damage Diagnosis of Bleacher Based on an Enhanced convolutional neural network with Training Interference

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Structural Durability & Health Monitoring 2024年第3期18卷 321-339页

作者： Chaozhi Cai Xiaoyu Guo Yingfang Xue Jianhua Ren School of Mechanical and Equipment Engineering Hebei University of EngineeringHandan056038China

Bleachers play a crucial role in practical engineering applications, and any damage incurred during their operationposes a significant threat to the safety of both life and property. Consequently, it becomes imperative to conductdamage diagnosis and health monitoring of bleachers. The intricate structure of bleachers, the varied types ofpotential damage, and the presence of similar vibration data in adjacent locations make it challenging to achievesatisfactory diagnosis accuracy through traditional time-frequency analysis methods. Furthermore, field environmentalnoise can adversely impact the accuracy of bleacher damage diagnosis. To enhance the accuracy and antinoisecapabilities of bleacher damage diagnosis, this paper proposes improvements to the existing convolutionalneural network with Training Interference (TICNN). The result is an advanced convolutional neural networkmodel with superior accuracy and robust anti-noise capabilities, referred to as Enhanced TICNN (ETICNN).ETICNN autonomously extracts optimal damage-sensitive features from the original vibration data. To validatethe superiority of the proposed ETICNN, experiments are conducted using the bleacher model from Qatar Universityas the subject. Comparative studies under identical experimental conditions involve TICNN, Deep convolutionalneural networks with wide first-layer kernels (WDCNN), and One-Dimensional convolutionalneural network (1DCNN). The experimental findings demonstrate that the ETICNN model achieves the highestaccuracy, approximately 99%, and exhibits robust classification abilities in both Phases I and II of the damagediagnosis experiments. Simultaneously, the ETICNN model demonstrates strong anti-noise capabilities, outperformingTICNN by 3% to 4% and surpassing other models in performance.

关键词： Bleacher vibration signal damage diagnosis convolutional neural network anti-noise ability

Improved convolutional neural network for Traffic Scene Segmentation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第3期138卷 2691-2708页

作者： Fuliang Xu Yong Luo Chuanlong Sun Hong Zhao College of Mechanical and Electrical Engineering Qingdao UniversityQingdao266071China

In actual traffic scenarios,precise recognition of traffic participants,such as vehicles and pedestrians,is crucial for intelligent *** study proposes an improved algorithm built on Mask-RCNN to enhance the ability of autonomous driving systems to recognize traffic *** algorithmincorporates long and shortterm memory networks and the fused attention module(GSAM,GCT,and Spatial Attention Module)to enhance the algorithm’s capability to process both global and local ***,to increase the network’s initial operation stability,the original network activation function was replaced with Gaussian error linear *** were conducted using the publicly available Cityscapes *** the test results,it was observed that the revised algorithmoutperformed the original algorithmin terms of AP_(50),AP_(75),and othermetrics by 8.7%and 9.6%for target detection and 12.5%and 13.3%for segmentation.

关键词： Instance segmentation deep learning convolutional neural network attention mechanism