Abdominal organ segmentation is the segregation of a single or multiple abdominal organ(s) into semantic image segments of pixels identified with homogeneous features such as color and texture, and intensity. The abdo...Abdominal organ segmentation is the segregation of a single or multiple abdominal organ(s) into semantic image segments of pixels identified with homogeneous features such as color and texture, and intensity. The abdominal organ(s) condition is mostly connected with greater morbidity and mortality. Most patients often have asymptomatic abdominal conditions and symptoms, which are often recognized late;hence the abdomen has been the third most common cause of damage to the human body. That notwithstanding,there may be improved outcomes where the condition of an abdominal organ is detected earlier. Over the years, supervised and semi-supervised machine learning methods have been used to segment abdominal organ(s) in order to detect the organ(s) condition. The supervised methods perform well when the used training data represents the target data, but the methods require large manually annotated data and have adaptation problems. The semi-supervised methods are fast but record poor performance than the supervised if assumptions about the data fail to hold. Current state-of-the-art methods of supervised segmentation are largely based on deep learning techniques due to their good accuracy and success in real world applications. Though it requires a large amount of training data for automatic feature extraction, deep learning can hardly be used. As regards the semi-supervised methods of segmentation, self-training and graph-based techniques have attracted much research attention. Self-training can be used with any classifier but does not have a mechanism to rectify mistakes early. Graph-based techniques thrive on their convexity, scalability, and effectiveness in application but have an out-of-sample problem. In this review paper, a study has been carried out on supervised and semi-supervised methods of performing abdominal organ segmentation. An observation of the current approaches, connection and gaps are identified, and prospective future research opportunities are enumerated.展开更多
Automated classification of gas flow states in blast furnaces using top-camera imagery typically demands a large volume of labeled data,whose manual annotation is both labor-intensive and cost-prohibitive.To mitigate ...Automated classification of gas flow states in blast furnaces using top-camera imagery typically demands a large volume of labeled data,whose manual annotation is both labor-intensive and cost-prohibitive.To mitigate this challenge,we present an enhanced semi-supervised learning approach based on the Mean Teacher framework,incorporating a novel feature loss module to maximize classification performance with limited labeled samples.The model studies show that the proposed model surpasses both the baseline Mean Teacher model and fully supervised method in accuracy.Specifically,for datasets with 20%,30%,and 40%label ratios,using a single training iteration,the model yields accuracies of 78.61%,82.21%,and 85.2%,respectively,while multiple-cycle training iterations achieves 82.09%,81.97%,and 81.59%,respectively.Furthermore,scenario-specific training schemes are introduced to support diverse deployment need.These findings highlight the potential of the proposed technique in minimizing labeling requirements and advancing intelligent blast furnace diagnostics.展开更多
Predicting blasting quality during tunnel construction holds practical significance.In this study,a new semi-supervised learning method using convolutional variational autoencoder(CVAE)and deep neural network(DNN)is p...Predicting blasting quality during tunnel construction holds practical significance.In this study,a new semi-supervised learning method using convolutional variational autoencoder(CVAE)and deep neural network(DNN)is proposed for the prediction of blasting quality grades.Tunnel blasting quality can be measured by over/under excavation.The occurrence of over/under excavation is influenced by three factors:geological conditions,blasting parameters,and tunnel geometric dimensions.The proposed method reflects the geological conditions through measurements while drilling and utilizes blasting parameters,tunnel geometric dimensions,and tunnel depth as input variables to achieve tunnel blasting quality grades prediction.Furthermore,the model is optimized by considering the influence of surrounding rock mass features on the predicted positions.The results demonstrate that the proposed method outperforms other commonly used machine learning and deep learning algorithms in extracting over/under excavation feature information and achieving blasting quality prediction.展开更多
Modal parameters can accurately characterize the structural dynamic properties and assess the physical state of the structure.Therefore,it is particularly significant to identify the structural modal parameters accordi...Modal parameters can accurately characterize the structural dynamic properties and assess the physical state of the structure.Therefore,it is particularly significant to identify the structural modal parameters according to the monitoring data information in the structural health monitoring(SHM)system,so as to provide a scientific basis for structural damage identification and dynamic model modification.In view of this,this paper reviews methods for identifying structural modal parameters under environmental excitation and briefly describes how to identify structural damages based on the derived modal parameters.The paper primarily introduces data-driven modal parameter recognition methods(e.g.,time-domain,frequency-domain,and time-frequency-domain methods,etc.),briefly describes damage identification methods based on the variations of modal parameters(e.g.,natural frequency,modal shapes,and curvature modal shapes,etc.)and modal validation methods(e.g.,Stability Diagram and Modal Assurance Criterion,etc.).The current status of the application of artificial intelligence(AI)methods in the direction of modal parameter recognition and damage identification is further discussed.Based on the pre-vious analysis,the main development trends of structural modal parameter recognition and damage identification methods are given to provide scientific references for the optimized design and functional upgrading of SHM systems.展开更多
Accurate prediction of the remaining useful life(RUL)is crucial for the design and management of lithium-ion batteries.Although various machine learning models offer promising predictions,one critical but often overlo...Accurate prediction of the remaining useful life(RUL)is crucial for the design and management of lithium-ion batteries.Although various machine learning models offer promising predictions,one critical but often overlooked challenge is their demand for considerable run-to-failure data for training.Collection of such training data leads to prohibitive testing efforts as the run-to-failure tests can last for years.Here,we propose a semi-supervised representation learning method to enhance prediction accuracy by learning from data without RUL labels.Our approach builds on a sophisticated deep neural network that comprises an encoder and three decoder heads to extract time-dependent representation features from short-term battery operating data regardless of the existence of RUL labels.The approach is validated using three datasets collected from 34 batteries operating under various conditions,encompassing over 19,900 charge and discharge cycles.Our method achieves a root mean squared error(RMSE)within 25 cycles,even when only 1/50 of the training dataset is labelled,representing a reduction of 48%compared to the conventional approach.We also demonstrate the method's robustness with varying numbers of labelled data and different weights assigned to the three decoder heads.The projection of extracted features in low space reveals that our method effectively learns degradation features from unlabelled data.Our approach highlights the promise of utilising semi-supervised learning to reduce the data demand for reliability monitoring of energy devices.展开更多
Existing semi-supervisedmedical image segmentation algorithms use copy-paste data augmentation to correct the labeled-unlabeled data distribution mismatch.However,current copy-paste methods have three limitations:(1)t...Existing semi-supervisedmedical image segmentation algorithms use copy-paste data augmentation to correct the labeled-unlabeled data distribution mismatch.However,current copy-paste methods have three limitations:(1)training the model solely with copy-paste mixed pictures from labeled and unlabeled input loses a lot of labeled information;(2)low-quality pseudo-labels can cause confirmation bias in pseudo-supervised learning on unlabeled data;(3)the segmentation performance in low-contrast and local regions is less than optimal.We design a Stochastic Augmentation-Based Dual-Teaching Auxiliary Training Strategy(SADT),which enhances feature diversity and learns high-quality features to overcome these problems.To be more precise,SADT trains the Student Network by using pseudo-label-based training from Teacher Network 1 and supervised learning with labeled data,which prevents the loss of rare labeled data.We introduce a bi-directional copy-pastemask with progressive high-entropy filtering to reduce data distribution disparities and mitigate confirmation bias in pseudo-supervision.For the mixed images,Deep-Shallow Spatial Contrastive Learning(DSSCL)is proposed in the feature spaces of Teacher Network 2 and the Student Network to improve the segmentation capabilities in low-contrast and local areas.In this procedure,the features retrieved by the Student Network are subjected to a random feature perturbation technique.On two openly available datasets,extensive trials show that our proposed SADT performs much better than the state-ofthe-art semi-supervised medical segmentation techniques.Using only 10%of the labeled data for training,SADT was able to acquire a Dice score of 90.10%on the ACDC(Automatic Cardiac Diagnosis Challenge)dataset.展开更多
Intrusion detection involves identifying unauthorized network activity and recognizing whether the data constitute an abnormal network transmission.Recent research has focused on using semi-supervised learning mechani...Intrusion detection involves identifying unauthorized network activity and recognizing whether the data constitute an abnormal network transmission.Recent research has focused on using semi-supervised learning mechanisms to identify abnormal network traffic to deal with labeled and unlabeled data in the industry.However,real-time training and classifying network traffic pose challenges,as they can lead to the degradation of the overall dataset and difficulties preventing attacks.Additionally,existing semi-supervised learning research might need to analyze the experimental results comprehensively.This paper proposes XA-GANomaly,a novel technique for explainable adaptive semi-supervised learning using GANomaly,an image anomalous detection model that dynamically trains small subsets to these issues.First,this research introduces a deep neural network(DNN)-based GANomaly for semi-supervised learning.Second,this paper presents the proposed adaptive algorithm for the DNN-based GANomaly,which is validated with four subsets of the adaptive dataset.Finally,this study demonstrates a monitoring system that incorporates three explainable techniques—Shapley additive explanations,reconstruction error visualization,and t-distributed stochastic neighbor embedding—to respond effectively to attacks on traffic data at each feature engineering stage,semi-supervised learning,and adaptive learning.Compared to other single-class classification techniques,the proposed DNN-based GANomaly achieves higher scores for Network Security Laboratory-Knowledge Discovery in Databases and UNSW-NB15 datasets at 13%and 8%of F1 scores and 4.17%and 11.51%for accuracy,respectively.Furthermore,experiments of the proposed adaptive learning reveal mostly improved results over the initial values.An analysis and monitoring system based on the combination of the three explainable methodologies is also described.Thus,the proposed method has the potential advantages to be applied in practical industry,and future research will explore handling unbalanced real-time datasets in various scenarios.展开更多
The accuracy of laser-induced breakdown spectroscopy(LIBS) quantitative method is greatly dependent on the amount of certified standard samples used for training. However, in practical applications, only limited stand...The accuracy of laser-induced breakdown spectroscopy(LIBS) quantitative method is greatly dependent on the amount of certified standard samples used for training. However, in practical applications, only limited standard samples with labeled certified concentrations are available. A novel semi-supervised LIBS quantitative analysis method is proposed, based on co-training regression model with selection of effective unlabeled samples. The main idea of the proposed method is to obtain better regression performance by adding effective unlabeled samples in semisupervised learning. First, effective unlabeled samples are selected according to the testing samples by Euclidean metric. Two original regression models based on least squares support vector machine with different parameters are trained by the labeled samples separately, and then the effective unlabeled samples predicted by the two models are used to enlarge the training dataset based on labeling confidence estimation. The final predictions of the proposed method on the testing samples will be determined by weighted combinations of the predictions of two updated regression models. Chromium concentration analysis experiments of 23 certified standard high-alloy steel samples were carried out, in which 5 samples with labeled concentrations and 11 unlabeled samples were used to train the regression models and the remaining 7 samples were used for testing. With the numbers of effective unlabeled samples increasing, the root mean square error of the proposed method went down from 1.80% to 0.84% and the relative prediction error was reduced from 9.15% to 4.04%.展开更多
The separation-of-variable(SOV)methods,such as the improved SOV method,the variational SOV method,and the extended SOV method,have been proposed by the present authors and coworkers to obtain the closed-form analytica...The separation-of-variable(SOV)methods,such as the improved SOV method,the variational SOV method,and the extended SOV method,have been proposed by the present authors and coworkers to obtain the closed-form analytical solutions for free vibration and eigenbuckling of rectangular plates and circular cylindrical shells.By taking the free vibration of rectangular thin plates as an example,this work presents the theoretical framework of the SOV methods in an instructive way,and the bisection–based solution procedures for a group of nonlinear eigenvalue equations.Besides,the explicit equations of nodal lines of the SOV methods are presented,and the relations of nodal line patterns and frequency orders are investigated.It is concluded that the highly accurate SOV methods have the same accuracy for all frequencies,the mode shapes about repeated frequencies can also be precisely captured,and the SOV methods do not have the problem of missing roots as well.展开更多
Generative adversarial networks(GANs) have become a competitive method among computer vision tasks. There have been many studies devoted to utilizing generative network to do generative tasks, such as images synthesis...Generative adversarial networks(GANs) have become a competitive method among computer vision tasks. There have been many studies devoted to utilizing generative network to do generative tasks, such as images synthesis. In this paper, a semi-supervised learning scheme is incorporated with generative adversarial network on image classification tasks to improve the image classification accuracy. Two applications of GANs are mainly focused on: semi-supervised learning and generation of images which can be as real as possible. The whole process is divided into two sections. First, only a small part of the dataset is utilized as labeled training data. And then a huge amount of samples generated from the generator is added into the training samples to improve the generalization of the discriminator. Through the semi-supervised learning scheme, full use of the unlabeled data is made which may contain potential information. Thus, the classification accuracy of the discriminator can be improved. Experimental results demonstrate the improvement of the classification accuracy of discriminator among different datasets, such as MNIST, CIFAR-10.展开更多
Soil improvement is one of the most important issues in geotechnical engineering practice.The wide application of traditional improvement techniques(cement/chemical materials)are limited due to damage ecological en-vi...Soil improvement is one of the most important issues in geotechnical engineering practice.The wide application of traditional improvement techniques(cement/chemical materials)are limited due to damage ecological en-vironment and intensify carbon emissions.However,the use of microbially induced calcium carbonate pre-cipitation(MICP)to obtain bio-cement is a novel technique with the potential to induce soil stability,providing a low-carbon,environment-friendly,and sustainable integrated solution for some geotechnical engineering pro-blems in the environment.This paper presents a comprehensive review of the latest progress in soil improvement based on the MICP strategy.It systematically summarizes and overviews the mineralization mechanism,influ-encing factors,improved methods,engineering characteristics,and current field application status of the MICP.Additionally,it also explores the limitations and correspondingly proposes prospective applications via the MICP approach for soil improvement.This review indicates that the utilization of different environmental calcium-based wastes in MICP and combination of materials and MICP are conducive to meeting engineering and market demand.Furthermore,we recommend and encourage global collaborative study and practice with a view to commercializing MICP technique in the future.The current review purports to provide insights for engineers and interdisciplinary researchers,and guidance for future engineering applications.展开更多
Soft sensing has been widely used in chemical industry to build an online monitor of the variables which are unmeasurable online or measurable online but with a high cost. One inherent difficulty is insufficiency of t...Soft sensing has been widely used in chemical industry to build an online monitor of the variables which are unmeasurable online or measurable online but with a high cost. One inherent difficulty is insufficiency of the training samples because the labeled data are limited. Besides, the traditional soft-sensing structure has no online correction mechanism. The forecasting result may be incorrect if the working condition is changed. In this work, a semi-supervised learning(SSL) method is proposed to build the soft-sensing model by use of the unlabeled data. Meanwhile, an online correction mechanism is proposed to establish a soft-sensing approach. The mechanism estimates the input variables at each step by a prediction model and calibrates the output variables by a compensation model. The experimental results show that the proposed method has better prediction accuracy and generalization ability than other approaches.展开更多
For indoor location estimation based on received signal strength( RSS) in wireless local area networks( WLAN),in order to reduce the influence of noise on the positioning accuracy,a large number of RSS should be colle...For indoor location estimation based on received signal strength( RSS) in wireless local area networks( WLAN),in order to reduce the influence of noise on the positioning accuracy,a large number of RSS should be collected in offline phase. Therefore,collecting training data with positioning information is time consuming which becomes the bottleneck of WLAN indoor localization. In this paper,the traditional semisupervised learning method based on k-NN and ε-NN graph for reducing collection workload of offline phase are analyzed,and the result shows that the k-NN or ε-NN graph are sensitive to data noise,which limit the performance of semi-supervised learning WLAN indoor localization system. Aiming at the above problem,it proposes a l1-graph-algorithm-based semi-supervised learning( LG-SSL) indoor localization method in which the graph is built by l1-norm algorithm. In our system,it firstly labels the unlabeled data using LG-SSL and labeled data to build the Radio Map in offline training phase,and then uses LG-SSL to estimate user's location in online phase. Extensive experimental results show that,benefit from the robustness to noise and sparsity ofl1-graph,LG-SSL exhibits superior performance by effectively reducing the collection workload in offline phase and improving localization accuracy in online phase.展开更多
In order to solve the problem of the variable coefficient ordinary differen-tial equation on the bounded domain,the Lagrange interpolation method is used to approximate the exact solution of the equation,and the error...In order to solve the problem of the variable coefficient ordinary differen-tial equation on the bounded domain,the Lagrange interpolation method is used to approximate the exact solution of the equation,and the error between the numerical solution and the exact solution is obtained,and then compared with the error formed by the difference method,it is concluded that the Lagrange interpolation method is more effective in solving the variable coefficient ordinary differential equation.展开更多
Ocean energy has progressively gained considerable interest due to its sufficient potential to meet the world’s energy demand,and the blade is the core component in electricity generation from the ocean current.Howev...Ocean energy has progressively gained considerable interest due to its sufficient potential to meet the world’s energy demand,and the blade is the core component in electricity generation from the ocean current.However,the widened hydraulic excitation frequency may satisfy the blade resonance due to the time variation in the velocity and angle of attack of the ocean current,even resulting in blade fatigue and destructively interfering with grid stability.A key parameter that determines the resonance amplitude of the blade is the hydrodynamic damping ratio(HDR).However,HDR is difficult to obtain due to the complex fluid-structure interaction(FSI).Therefore,a literature review was conducted on the hydrodynamic damping characteristics of blade-like structures.The experimental and simulation methods used to identify and obtain the HDR quantitatively were described,placing emphasis on the experimental processes and simulation setups.Moreover,the accuracy and efficiency of different simulation methods were compared,and the modal work approach was recommended.The effects of key typical parameters,including flow velocity,angle of attack,gap,rotational speed,and cavitation,on the HDR were then summarized,and the suggestions on operating conditions were presented from the perspective of increasing the HDR.Subsequently,considering multiple flow parameters,several theoretical derivations and semi-empirical prediction formulas for HDR were introduced,and the accuracy and application were discussed.Based on the shortcomings of the existing research,the direction of future research was finally determined.The current work offers a clear understanding of the HDR of blade-like structures,which could improve the evaluation accuracy of flow-induced vibration in the design stage.展开更多
The classification of respiratory sounds is crucial in diagnosing and monitoring respiratory diseases.However,auscultation is highly subjective,making it challenging to analyze respiratory sounds accurately.Although d...The classification of respiratory sounds is crucial in diagnosing and monitoring respiratory diseases.However,auscultation is highly subjective,making it challenging to analyze respiratory sounds accurately.Although deep learning has been increasingly applied to this task,most existing approaches have primarily relied on supervised learning.Since supervised learning requires large amounts of labeled data,recent studies have explored self-supervised and semi-supervised methods to overcome this limitation.However,these approaches have largely assumed a closedset setting,where the classes present in the unlabeled data are considered identical to those in the labeled data.In contrast,this study explores an open-set semi-supervised learning setting,where the unlabeled data may contain additional,unknown classes.To address this challenge,a distance-based prototype network is employed to classify respiratory sounds in an open-set setting.In the first stage,the prototype network is trained using labeled and unlabeled data to derive prototype representations of known classes.In the second stage,distances between unlabeled data and known class prototypes are computed,and samples exceeding an adaptive threshold are identified as unknown.A new prototype is then calculated for this unknown class.In the final stage,semi-supervised learning is employed to classify labeled and unlabeled data into known and unknown classes.Compared to conventional closed-set semisupervised learning approaches,the proposed method achieved an average classification accuracy improvement of 2%–5%.Additionally,in cases of data scarcity,utilizing unlabeled data further improved classification performance by 6%–8%.The findings of this study are expected to significantly enhance respiratory sound classification performance in practical clinical settings.展开更多
Unmanned aerial vehicles(UAVs)have become crucial tools in moving target tracking due to their agility and ability to operate in complex,dynamic environments.UAVs must meet several requirements to achieve stable track...Unmanned aerial vehicles(UAVs)have become crucial tools in moving target tracking due to their agility and ability to operate in complex,dynamic environments.UAVs must meet several requirements to achieve stable tracking,including maintaining continuous target visibility amidst occlusions,ensuring flight safety,and achieving smooth trajectory planning.This paper reviews the latest advancements in UAV-based target tracking,highlighting information prediction,tracking strategies,and swarm cooperation.To address challenges including target visibility and occlusion,real-time prediction and tracking in dynamic environments,flight safety and coordination,resource management and energy efficiency,the paper identifies future research directions aimed at improving the performance,reliability,and scalability of UAV tracking system.展开更多
Large amounts of labeled data are usually needed for training deep neural networks in medical image studies,particularly in medical image classification.However,in the field of semi-supervised medical image analysis,l...Large amounts of labeled data are usually needed for training deep neural networks in medical image studies,particularly in medical image classification.However,in the field of semi-supervised medical image analysis,labeled data is very scarce due to patient privacy concerns.For researchers,obtaining high-quality labeled images is exceedingly challenging because it involves manual annotation and clinical understanding.In addition,skin datasets are highly suitable for medical image classification studies due to the inter-class relationships and the inter-class similarities of skin lesions.In this paper,we propose a model called Coalition Sample Relation Consistency(CSRC),a consistency-based method that leverages Canonical Correlation Analysis(CCA)to capture the intrinsic relationships between samples.Considering that traditional consistency-based models only focus on the consistency of prediction,we additionally explore the similarity between features by using CCA.We enforce feature relation consistency based on traditional models,encouraging the model to learn more meaningful information from unlabeled data.Finally,considering that cross-entropy loss is not as suitable as the supervised loss when studying with imbalanced datasets(i.e.,ISIC 2017 and ISIC 2018),we improve the supervised loss to achieve better classification accuracy.Our study shows that this model performs better than many semi-supervised methods.展开更多
In the realm of medical image segmentation,particularly in cardiac magnetic resonance imaging(MRI),achieving robust performance with limited annotated data is a significant challenge.Performance often degrades when fa...In the realm of medical image segmentation,particularly in cardiac magnetic resonance imaging(MRI),achieving robust performance with limited annotated data is a significant challenge.Performance often degrades when faced with testing scenarios from unknown domains.To address this problem,this paper proposes a novel semi-supervised approach for cardiac magnetic resonance image segmentation,aiming to enhance predictive capabilities and domain generalization(DG).This paper establishes an MT-like model utilizing pseudo-labeling and consistency regularization from semi-supervised learning,and integrates uncertainty estimation to improve the accuracy of pseudo-labels.Additionally,to tackle the challenge of domain generalization,a data manipulation strategy is introduced,extracting spatial and content-related information from images across different domains,enriching the dataset with a multi-domain perspective.This papers method is meticulously evaluated on the publicly available cardiac magnetic resonance imaging dataset M&Ms,validating its effectiveness.Comparative analyses against various methods highlight the out-standing performance of this papers approach,demonstrating its capability to segment cardiac magnetic resonance images in previously unseen domains even with limited annotated data.展开更多
The element-free Galerkin(EFG)method,which constructs shape functions via moving least squares(MLS)approximation,represents a fundamental and widely studied meshless method in numerical computation.Although it achieve...The element-free Galerkin(EFG)method,which constructs shape functions via moving least squares(MLS)approximation,represents a fundamental and widely studied meshless method in numerical computation.Although it achieves high computational accuracy,the shape functions are more complex than those in the conventional finite element method(FEM),resulting in great computational requirements.Therefore,improving the computational efficiency of the EFG method represents an important research direction.This paper systematically reviews significant contributions fromdomestic and international scholars in advancing the EFGmethod.Including the improved element-free Galerkin(IEFG)method,various interpolating EFG methods,four distinct complex variable EFG methods,and a series of dimension splitting meshless methods.In the numerical examples,the effectiveness and efficiency of the three methods are validated by analyzing the solutions of the IEFG method for 3D steadystate anisotropic heat conduction,3D elastoplasticity,and large deformation problems,as well as the performance of two-dimensional splitting meshless methods in solving the 3D Helmholtz equation.展开更多
基金supported by National Natural Science Foundation of China(Nos.61772242,61976106 and 61572239)the China Postdoctoral Science Foundation(No.2017M611737)+1 种基金the Six Talent Peaks Project in Jiangsu Province(No.DZXX-122)the Key Special Project of Health and Family Planning Science and Technology in Zhenjiang City(No.SHW2017019)。
文摘Abdominal organ segmentation is the segregation of a single or multiple abdominal organ(s) into semantic image segments of pixels identified with homogeneous features such as color and texture, and intensity. The abdominal organ(s) condition is mostly connected with greater morbidity and mortality. Most patients often have asymptomatic abdominal conditions and symptoms, which are often recognized late;hence the abdomen has been the third most common cause of damage to the human body. That notwithstanding,there may be improved outcomes where the condition of an abdominal organ is detected earlier. Over the years, supervised and semi-supervised machine learning methods have been used to segment abdominal organ(s) in order to detect the organ(s) condition. The supervised methods perform well when the used training data represents the target data, but the methods require large manually annotated data and have adaptation problems. The semi-supervised methods are fast but record poor performance than the supervised if assumptions about the data fail to hold. Current state-of-the-art methods of supervised segmentation are largely based on deep learning techniques due to their good accuracy and success in real world applications. Though it requires a large amount of training data for automatic feature extraction, deep learning can hardly be used. As regards the semi-supervised methods of segmentation, self-training and graph-based techniques have attracted much research attention. Self-training can be used with any classifier but does not have a mechanism to rectify mistakes early. Graph-based techniques thrive on their convexity, scalability, and effectiveness in application but have an out-of-sample problem. In this review paper, a study has been carried out on supervised and semi-supervised methods of performing abdominal organ segmentation. An observation of the current approaches, connection and gaps are identified, and prospective future research opportunities are enumerated.
基金financial support provided by the Natural Science Foundation of Hebei Province,China(No.E2024105036)the Tangshan Talent Funding Project,China(Nos.B202302007 and A2021110015)+1 种基金the National Natural Science Foundation of China(No.52264042)the Australian Research Council(No.IH230100010)。
文摘Automated classification of gas flow states in blast furnaces using top-camera imagery typically demands a large volume of labeled data,whose manual annotation is both labor-intensive and cost-prohibitive.To mitigate this challenge,we present an enhanced semi-supervised learning approach based on the Mean Teacher framework,incorporating a novel feature loss module to maximize classification performance with limited labeled samples.The model studies show that the proposed model surpasses both the baseline Mean Teacher model and fully supervised method in accuracy.Specifically,for datasets with 20%,30%,and 40%label ratios,using a single training iteration,the model yields accuracies of 78.61%,82.21%,and 85.2%,respectively,while multiple-cycle training iterations achieves 82.09%,81.97%,and 81.59%,respectively.Furthermore,scenario-specific training schemes are introduced to support diverse deployment need.These findings highlight the potential of the proposed technique in minimizing labeling requirements and advancing intelligent blast furnace diagnostics.
基金financially supported by the Science and Technology Research and Development Project of China Railway Corporation(Grant No.N2023G079)the National Key R&D Program of China(Grant No.2024YFE0198500).
文摘Predicting blasting quality during tunnel construction holds practical significance.In this study,a new semi-supervised learning method using convolutional variational autoencoder(CVAE)and deep neural network(DNN)is proposed for the prediction of blasting quality grades.Tunnel blasting quality can be measured by over/under excavation.The occurrence of over/under excavation is influenced by three factors:geological conditions,blasting parameters,and tunnel geometric dimensions.The proposed method reflects the geological conditions through measurements while drilling and utilizes blasting parameters,tunnel geometric dimensions,and tunnel depth as input variables to achieve tunnel blasting quality grades prediction.Furthermore,the model is optimized by considering the influence of surrounding rock mass features on the predicted positions.The results demonstrate that the proposed method outperforms other commonly used machine learning and deep learning algorithms in extracting over/under excavation feature information and achieving blasting quality prediction.
基金supported by the Innovation Foundation of Provincial Education Department of Gansu(2024B-005)the Gansu Province National Science Foundation(22YF7GA182)the Fundamental Research Funds for the Central Universities(No.lzujbky2022-kb01)。
文摘Modal parameters can accurately characterize the structural dynamic properties and assess the physical state of the structure.Therefore,it is particularly significant to identify the structural modal parameters according to the monitoring data information in the structural health monitoring(SHM)system,so as to provide a scientific basis for structural damage identification and dynamic model modification.In view of this,this paper reviews methods for identifying structural modal parameters under environmental excitation and briefly describes how to identify structural damages based on the derived modal parameters.The paper primarily introduces data-driven modal parameter recognition methods(e.g.,time-domain,frequency-domain,and time-frequency-domain methods,etc.),briefly describes damage identification methods based on the variations of modal parameters(e.g.,natural frequency,modal shapes,and curvature modal shapes,etc.)and modal validation methods(e.g.,Stability Diagram and Modal Assurance Criterion,etc.).The current status of the application of artificial intelligence(AI)methods in the direction of modal parameter recognition and damage identification is further discussed.Based on the pre-vious analysis,the main development trends of structural modal parameter recognition and damage identification methods are given to provide scientific references for the optimized design and functional upgrading of SHM systems.
基金supported by the National Natural Science Foundation of China(No.52207229)the Key Research and Development Program of Ningxia Hui Autonomous Region of China(No.2024BEE02003)+1 种基金the financial support from the AEGiS Research Grant 2024,University of Wollongong(No.R6254)the financial support from the China Scholarship Council(No.202207550010).
文摘Accurate prediction of the remaining useful life(RUL)is crucial for the design and management of lithium-ion batteries.Although various machine learning models offer promising predictions,one critical but often overlooked challenge is their demand for considerable run-to-failure data for training.Collection of such training data leads to prohibitive testing efforts as the run-to-failure tests can last for years.Here,we propose a semi-supervised representation learning method to enhance prediction accuracy by learning from data without RUL labels.Our approach builds on a sophisticated deep neural network that comprises an encoder and three decoder heads to extract time-dependent representation features from short-term battery operating data regardless of the existence of RUL labels.The approach is validated using three datasets collected from 34 batteries operating under various conditions,encompassing over 19,900 charge and discharge cycles.Our method achieves a root mean squared error(RMSE)within 25 cycles,even when only 1/50 of the training dataset is labelled,representing a reduction of 48%compared to the conventional approach.We also demonstrate the method's robustness with varying numbers of labelled data and different weights assigned to the three decoder heads.The projection of extracted features in low space reveals that our method effectively learns degradation features from unlabelled data.Our approach highlights the promise of utilising semi-supervised learning to reduce the data demand for reliability monitoring of energy devices.
基金supported by the Natural Science Foundation of China(No.41804112,author:Chengyun Song).
文摘Existing semi-supervisedmedical image segmentation algorithms use copy-paste data augmentation to correct the labeled-unlabeled data distribution mismatch.However,current copy-paste methods have three limitations:(1)training the model solely with copy-paste mixed pictures from labeled and unlabeled input loses a lot of labeled information;(2)low-quality pseudo-labels can cause confirmation bias in pseudo-supervised learning on unlabeled data;(3)the segmentation performance in low-contrast and local regions is less than optimal.We design a Stochastic Augmentation-Based Dual-Teaching Auxiliary Training Strategy(SADT),which enhances feature diversity and learns high-quality features to overcome these problems.To be more precise,SADT trains the Student Network by using pseudo-label-based training from Teacher Network 1 and supervised learning with labeled data,which prevents the loss of rare labeled data.We introduce a bi-directional copy-pastemask with progressive high-entropy filtering to reduce data distribution disparities and mitigate confirmation bias in pseudo-supervision.For the mixed images,Deep-Shallow Spatial Contrastive Learning(DSSCL)is proposed in the feature spaces of Teacher Network 2 and the Student Network to improve the segmentation capabilities in low-contrast and local areas.In this procedure,the features retrieved by the Student Network are subjected to a random feature perturbation technique.On two openly available datasets,extensive trials show that our proposed SADT performs much better than the state-ofthe-art semi-supervised medical segmentation techniques.Using only 10%of the labeled data for training,SADT was able to acquire a Dice score of 90.10%on the ACDC(Automatic Cardiac Diagnosis Challenge)dataset.
基金supported by Korea Institute for Advancement of Technology(KIAT)grant funded by theKoreaGovernment(MOTIE)(P0008703,The CompetencyDevelopment Program for Industry Specialist).
文摘Intrusion detection involves identifying unauthorized network activity and recognizing whether the data constitute an abnormal network transmission.Recent research has focused on using semi-supervised learning mechanisms to identify abnormal network traffic to deal with labeled and unlabeled data in the industry.However,real-time training and classifying network traffic pose challenges,as they can lead to the degradation of the overall dataset and difficulties preventing attacks.Additionally,existing semi-supervised learning research might need to analyze the experimental results comprehensively.This paper proposes XA-GANomaly,a novel technique for explainable adaptive semi-supervised learning using GANomaly,an image anomalous detection model that dynamically trains small subsets to these issues.First,this research introduces a deep neural network(DNN)-based GANomaly for semi-supervised learning.Second,this paper presents the proposed adaptive algorithm for the DNN-based GANomaly,which is validated with four subsets of the adaptive dataset.Finally,this study demonstrates a monitoring system that incorporates three explainable techniques—Shapley additive explanations,reconstruction error visualization,and t-distributed stochastic neighbor embedding—to respond effectively to attacks on traffic data at each feature engineering stage,semi-supervised learning,and adaptive learning.Compared to other single-class classification techniques,the proposed DNN-based GANomaly achieves higher scores for Network Security Laboratory-Knowledge Discovery in Databases and UNSW-NB15 datasets at 13%and 8%of F1 scores and 4.17%and 11.51%for accuracy,respectively.Furthermore,experiments of the proposed adaptive learning reveal mostly improved results over the initial values.An analysis and monitoring system based on the combination of the three explainable methodologies is also described.Thus,the proposed method has the potential advantages to be applied in practical industry,and future research will explore handling unbalanced real-time datasets in various scenarios.
基金supported by National Natural Science Foundation of China (No. 51674032)
文摘The accuracy of laser-induced breakdown spectroscopy(LIBS) quantitative method is greatly dependent on the amount of certified standard samples used for training. However, in practical applications, only limited standard samples with labeled certified concentrations are available. A novel semi-supervised LIBS quantitative analysis method is proposed, based on co-training regression model with selection of effective unlabeled samples. The main idea of the proposed method is to obtain better regression performance by adding effective unlabeled samples in semisupervised learning. First, effective unlabeled samples are selected according to the testing samples by Euclidean metric. Two original regression models based on least squares support vector machine with different parameters are trained by the labeled samples separately, and then the effective unlabeled samples predicted by the two models are used to enlarge the training dataset based on labeling confidence estimation. The final predictions of the proposed method on the testing samples will be determined by weighted combinations of the predictions of two updated regression models. Chromium concentration analysis experiments of 23 certified standard high-alloy steel samples were carried out, in which 5 samples with labeled concentrations and 11 unlabeled samples were used to train the regression models and the remaining 7 samples were used for testing. With the numbers of effective unlabeled samples increasing, the root mean square error of the proposed method went down from 1.80% to 0.84% and the relative prediction error was reduced from 9.15% to 4.04%.
基金supported by the National Natural Science Foundation of China(12172023).
文摘The separation-of-variable(SOV)methods,such as the improved SOV method,the variational SOV method,and the extended SOV method,have been proposed by the present authors and coworkers to obtain the closed-form analytical solutions for free vibration and eigenbuckling of rectangular plates and circular cylindrical shells.By taking the free vibration of rectangular thin plates as an example,this work presents the theoretical framework of the SOV methods in an instructive way,and the bisection–based solution procedures for a group of nonlinear eigenvalue equations.Besides,the explicit equations of nodal lines of the SOV methods are presented,and the relations of nodal line patterns and frequency orders are investigated.It is concluded that the highly accurate SOV methods have the same accuracy for all frequencies,the mode shapes about repeated frequencies can also be precisely captured,and the SOV methods do not have the problem of missing roots as well.
基金Supported by the National Natural Science Foundation of China(No.61501457)National Key Technology R&D Program(No.2015BAK21B00)
文摘Generative adversarial networks(GANs) have become a competitive method among computer vision tasks. There have been many studies devoted to utilizing generative network to do generative tasks, such as images synthesis. In this paper, a semi-supervised learning scheme is incorporated with generative adversarial network on image classification tasks to improve the image classification accuracy. Two applications of GANs are mainly focused on: semi-supervised learning and generation of images which can be as real as possible. The whole process is divided into two sections. First, only a small part of the dataset is utilized as labeled training data. And then a huge amount of samples generated from the generator is added into the training samples to improve the generalization of the discriminator. Through the semi-supervised learning scheme, full use of the unlabeled data is made which may contain potential information. Thus, the classification accuracy of the discriminator can be improved. Experimental results demonstrate the improvement of the classification accuracy of discriminator among different datasets, such as MNIST, CIFAR-10.
基金funded by the National Natural Science Foundation of China(No.41962016)the Natural Science Foundation of NingXia(Nos.2023AAC02023,2023A1218,and 2021AAC02006).
文摘Soil improvement is one of the most important issues in geotechnical engineering practice.The wide application of traditional improvement techniques(cement/chemical materials)are limited due to damage ecological en-vironment and intensify carbon emissions.However,the use of microbially induced calcium carbonate pre-cipitation(MICP)to obtain bio-cement is a novel technique with the potential to induce soil stability,providing a low-carbon,environment-friendly,and sustainable integrated solution for some geotechnical engineering pro-blems in the environment.This paper presents a comprehensive review of the latest progress in soil improvement based on the MICP strategy.It systematically summarizes and overviews the mineralization mechanism,influ-encing factors,improved methods,engineering characteristics,and current field application status of the MICP.Additionally,it also explores the limitations and correspondingly proposes prospective applications via the MICP approach for soil improvement.This review indicates that the utilization of different environmental calcium-based wastes in MICP and combination of materials and MICP are conducive to meeting engineering and market demand.Furthermore,we recommend and encourage global collaborative study and practice with a view to commercializing MICP technique in the future.The current review purports to provide insights for engineers and interdisciplinary researchers,and guidance for future engineering applications.
基金the National Natural Science Foundation of China(Nos.61374110 and 61074060)the Specialized Research Fund for the Doctoral Program of Higher Education of China(No.20120073110017)
文摘Soft sensing has been widely used in chemical industry to build an online monitor of the variables which are unmeasurable online or measurable online but with a high cost. One inherent difficulty is insufficiency of the training samples because the labeled data are limited. Besides, the traditional soft-sensing structure has no online correction mechanism. The forecasting result may be incorrect if the working condition is changed. In this work, a semi-supervised learning(SSL) method is proposed to build the soft-sensing model by use of the unlabeled data. Meanwhile, an online correction mechanism is proposed to establish a soft-sensing approach. The mechanism estimates the input variables at each step by a prediction model and calibrates the output variables by a compensation model. The experimental results show that the proposed method has better prediction accuracy and generalization ability than other approaches.
基金Sponsored by the National Natural Science Foundation of China(Grant No.61101122)the National High Technology Research and Development Program of China(Grant No.2012AA120802)the National Science and Technology Major Project of the Ministry of Science and Technology of China(Grant No.2012ZX03004-003)
文摘For indoor location estimation based on received signal strength( RSS) in wireless local area networks( WLAN),in order to reduce the influence of noise on the positioning accuracy,a large number of RSS should be collected in offline phase. Therefore,collecting training data with positioning information is time consuming which becomes the bottleneck of WLAN indoor localization. In this paper,the traditional semisupervised learning method based on k-NN and ε-NN graph for reducing collection workload of offline phase are analyzed,and the result shows that the k-NN or ε-NN graph are sensitive to data noise,which limit the performance of semi-supervised learning WLAN indoor localization system. Aiming at the above problem,it proposes a l1-graph-algorithm-based semi-supervised learning( LG-SSL) indoor localization method in which the graph is built by l1-norm algorithm. In our system,it firstly labels the unlabeled data using LG-SSL and labeled data to build the Radio Map in offline training phase,and then uses LG-SSL to estimate user's location in online phase. Extensive experimental results show that,benefit from the robustness to noise and sparsity ofl1-graph,LG-SSL exhibits superior performance by effectively reducing the collection workload in offline phase and improving localization accuracy in online phase.
文摘In order to solve the problem of the variable coefficient ordinary differen-tial equation on the bounded domain,the Lagrange interpolation method is used to approximate the exact solution of the equation,and the error between the numerical solution and the exact solution is obtained,and then compared with the error formed by the difference method,it is concluded that the Lagrange interpolation method is more effective in solving the variable coefficient ordinary differential equation.
基金Supported by the National Natural Science Foundation of China(Nos.52222904 and 52309117)China Postdoctoral Science Foundation(Nos.2022TQ0168 and 2023M731895).
文摘Ocean energy has progressively gained considerable interest due to its sufficient potential to meet the world’s energy demand,and the blade is the core component in electricity generation from the ocean current.However,the widened hydraulic excitation frequency may satisfy the blade resonance due to the time variation in the velocity and angle of attack of the ocean current,even resulting in blade fatigue and destructively interfering with grid stability.A key parameter that determines the resonance amplitude of the blade is the hydrodynamic damping ratio(HDR).However,HDR is difficult to obtain due to the complex fluid-structure interaction(FSI).Therefore,a literature review was conducted on the hydrodynamic damping characteristics of blade-like structures.The experimental and simulation methods used to identify and obtain the HDR quantitatively were described,placing emphasis on the experimental processes and simulation setups.Moreover,the accuracy and efficiency of different simulation methods were compared,and the modal work approach was recommended.The effects of key typical parameters,including flow velocity,angle of attack,gap,rotational speed,and cavitation,on the HDR were then summarized,and the suggestions on operating conditions were presented from the perspective of increasing the HDR.Subsequently,considering multiple flow parameters,several theoretical derivations and semi-empirical prediction formulas for HDR were introduced,and the accuracy and application were discussed.Based on the shortcomings of the existing research,the direction of future research was finally determined.The current work offers a clear understanding of the HDR of blade-like structures,which could improve the evaluation accuracy of flow-induced vibration in the design stage.
基金supported by Innovative Human Resource Development for Local Intellectualization Programthrough the Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(IITP-2025-RS-2022-00156360).
文摘The classification of respiratory sounds is crucial in diagnosing and monitoring respiratory diseases.However,auscultation is highly subjective,making it challenging to analyze respiratory sounds accurately.Although deep learning has been increasingly applied to this task,most existing approaches have primarily relied on supervised learning.Since supervised learning requires large amounts of labeled data,recent studies have explored self-supervised and semi-supervised methods to overcome this limitation.However,these approaches have largely assumed a closedset setting,where the classes present in the unlabeled data are considered identical to those in the labeled data.In contrast,this study explores an open-set semi-supervised learning setting,where the unlabeled data may contain additional,unknown classes.To address this challenge,a distance-based prototype network is employed to classify respiratory sounds in an open-set setting.In the first stage,the prototype network is trained using labeled and unlabeled data to derive prototype representations of known classes.In the second stage,distances between unlabeled data and known class prototypes are computed,and samples exceeding an adaptive threshold are identified as unknown.A new prototype is then calculated for this unknown class.In the final stage,semi-supervised learning is employed to classify labeled and unlabeled data into known and unknown classes.Compared to conventional closed-set semisupervised learning approaches,the proposed method achieved an average classification accuracy improvement of 2%–5%.Additionally,in cases of data scarcity,utilizing unlabeled data further improved classification performance by 6%–8%.The findings of this study are expected to significantly enhance respiratory sound classification performance in practical clinical settings.
基金financial support provided by the Natural Science Foundation of Hunan Province of China(Grant No.2021JJ10045)the Open Research Subject of State Key Laboratory of Intelligent Game(Grant No.ZBKF-24-01)+1 种基金the Postdoctoral Fellowship Program of CPSF(Grant No.GZB20240989)the China Postdoctoral Science Foundation(Grant No.2024M754304)。
文摘Unmanned aerial vehicles(UAVs)have become crucial tools in moving target tracking due to their agility and ability to operate in complex,dynamic environments.UAVs must meet several requirements to achieve stable tracking,including maintaining continuous target visibility amidst occlusions,ensuring flight safety,and achieving smooth trajectory planning.This paper reviews the latest advancements in UAV-based target tracking,highlighting information prediction,tracking strategies,and swarm cooperation.To address challenges including target visibility and occlusion,real-time prediction and tracking in dynamic environments,flight safety and coordination,resource management and energy efficiency,the paper identifies future research directions aimed at improving the performance,reliability,and scalability of UAV tracking system.
基金sponsored by the National Natural Science Foundation of China Grant No.62271302the Shanghai Municipal Natural Science Foundation Grant 20ZR1423500.
文摘Large amounts of labeled data are usually needed for training deep neural networks in medical image studies,particularly in medical image classification.However,in the field of semi-supervised medical image analysis,labeled data is very scarce due to patient privacy concerns.For researchers,obtaining high-quality labeled images is exceedingly challenging because it involves manual annotation and clinical understanding.In addition,skin datasets are highly suitable for medical image classification studies due to the inter-class relationships and the inter-class similarities of skin lesions.In this paper,we propose a model called Coalition Sample Relation Consistency(CSRC),a consistency-based method that leverages Canonical Correlation Analysis(CCA)to capture the intrinsic relationships between samples.Considering that traditional consistency-based models only focus on the consistency of prediction,we additionally explore the similarity between features by using CCA.We enforce feature relation consistency based on traditional models,encouraging the model to learn more meaningful information from unlabeled data.Finally,considering that cross-entropy loss is not as suitable as the supervised loss when studying with imbalanced datasets(i.e.,ISIC 2017 and ISIC 2018),we improve the supervised loss to achieve better classification accuracy.Our study shows that this model performs better than many semi-supervised methods.
基金Supported by the National Natural Science Foundation of China(No.62001313)the Key Project of Liaoning Provincial Department of Science and Technology(No.2021JH2/10300134,2022JH1/10500004)。
文摘In the realm of medical image segmentation,particularly in cardiac magnetic resonance imaging(MRI),achieving robust performance with limited annotated data is a significant challenge.Performance often degrades when faced with testing scenarios from unknown domains.To address this problem,this paper proposes a novel semi-supervised approach for cardiac magnetic resonance image segmentation,aiming to enhance predictive capabilities and domain generalization(DG).This paper establishes an MT-like model utilizing pseudo-labeling and consistency regularization from semi-supervised learning,and integrates uncertainty estimation to improve the accuracy of pseudo-labels.Additionally,to tackle the challenge of domain generalization,a data manipulation strategy is introduced,extracting spatial and content-related information from images across different domains,enriching the dataset with a multi-domain perspective.This papers method is meticulously evaluated on the publicly available cardiac magnetic resonance imaging dataset M&Ms,validating its effectiveness.Comparative analyses against various methods highlight the out-standing performance of this papers approach,demonstrating its capability to segment cardiac magnetic resonance images in previously unseen domains even with limited annotated data.
基金supported by the National Natural Science Foundation of China(Grant No.12271341).
文摘The element-free Galerkin(EFG)method,which constructs shape functions via moving least squares(MLS)approximation,represents a fundamental and widely studied meshless method in numerical computation.Although it achieves high computational accuracy,the shape functions are more complex than those in the conventional finite element method(FEM),resulting in great computational requirements.Therefore,improving the computational efficiency of the EFG method represents an important research direction.This paper systematically reviews significant contributions fromdomestic and international scholars in advancing the EFGmethod.Including the improved element-free Galerkin(IEFG)method,various interpolating EFG methods,four distinct complex variable EFG methods,and a series of dimension splitting meshless methods.In the numerical examples,the effectiveness and efficiency of the three methods are validated by analyzing the solutions of the IEFG method for 3D steadystate anisotropic heat conduction,3D elastoplasticity,and large deformation problems,as well as the performance of two-dimensional splitting meshless methods in solving the 3D Helmholtz equation.
