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
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
Attributed graphs have an additional sign vector for each node.Typically,edge signs represent like or dislike relationship between the node pairs.This has applications in domains,such as recommender systems,personalis...Attributed graphs have an additional sign vector for each node.Typically,edge signs represent like or dislike relationship between the node pairs.This has applications in domains,such as recommender systems,personalised search,etc.However,limited availability of edge sign information in attributed networks requires inferring the underlying graph embeddings to fill-in the knowledge gap.Such inference is performed by way of node classification which aims to deduce the node characteristics based on the topological structure of the graph and signed interactions between the nodes.The study of attributed networks is challenging due to noise,sparsity,and class imbalance issues.In this work,we consider node centrality in conjunction with edge signs to contemplate the node classification problem in attributed networks.We propose Semi-supervised Node Classification in Attributed graphs(SNCA).SNCA is robust to underlying network noise,and has in-built class imbalance handling capabilities.We perform an extensive experimental study on real-world datasets to showcase the efficiency,scalability,robustness,and pertinence of the solution.The performance results demonstrate the suitability of the solution for large attributed graphs in real-world settings.展开更多
Background:Metastasis to the infraclavicular and supraclavicular lymph nodes(ISLNs)is an important factor that predicts poor survival in patients with breast cancer;however,pathological nodal staging does not traditio...Background:Metastasis to the infraclavicular and supraclavicular lymph nodes(ISLNs)is an important factor that predicts poor survival in patients with breast cancer;however,pathological nodal staging does not traditionally include ISLNs because of their non-routine surgical dissection.This study aimed to evaluate the prognostic impact of ISLN metastasis and propose a refined nodal staging system tailored for patients undergoing neoadjuvant chemotherapy(NAC).Methods:We retrospectively reviewed 1,072 patients with breast cancer with or without ISLN metastasis who received NAC at two institutions(Fujian cohort and Hebei cohort)from 2010 to 2022.We conducted detailed survival analysis to evaluate the diagnostic consistency and prognostic significance of ISLNs.Results:There were no survival differences among patients with ISLN involvement across different assay method-ologies and patient cohorts.Among 887 patients in the Fujian cohort,238 patients(26.8%)with positive ISLNs had significantly inferior 3-year progression-free survival(PFS,75.9%vs.90.4%,P<0.001)and overall survival(OS,90.6%vs.95.9%,P<0.001).After adjusting for potential confounders,ISLN involvement persisted as an independent predictor of both PFS and OS.We propose a refined axillary classification that combines pathologi-cal axillary staging post-NAC with ISLN involvement,revealing 3-year PFS rates of 95.3%,87.6%,73.4%,and 64.5%for the respective four groups defined by this refined classification combining axillary stage and ISLN status.Conclusions:Involvement of the ISLNs was associated with a worse prognosis,underscoring their prognostic value.This finding highlights the potential of ISLN status to influence decisions regarding adjuvant treatment in patients with breast cancer.展开更多
Deep learning significantly improves the accuracy of remote sensing image scene classification,benefiting from the large-scale datasets.However,annotating the remote sensing images is time-consuming and even tough for...Deep learning significantly improves the accuracy of remote sensing image scene classification,benefiting from the large-scale datasets.However,annotating the remote sensing images is time-consuming and even tough for experts.Deep neural networks trained using a few labeled samples usually generalize less to new unseen images.In this paper,we propose a semi-supervised approach for remote sensing image scene classification based on the prototype-based consistency,by exploring massive unlabeled images.To this end,we,first,propose a feature enhancement module to extract discriminative features.This is achieved by focusing the model on the foreground areas.Then,the prototype-based classifier is introduced to the framework,which is used to acquire consistent feature representations.We conduct a series of experiments on NWPU-RESISC45 and Aerial Image Dataset(AID).Our method improves the State-Of-The-Art(SOTA)method on NWPU-RESISC45 from 92.03%to 93.08%and on AID from 94.25%to 95.24%in terms of accuracy.展开更多
With the successive application of deep learning(DL)in classification tasks,the DL-based modulation classification method has become the preference for its state-of-the-art performance.Nevertheless,once the DL recogni...With the successive application of deep learning(DL)in classification tasks,the DL-based modulation classification method has become the preference for its state-of-the-art performance.Nevertheless,once the DL recognition model is pre-trained with fixed classes,the pre-trained model tends to predict incorrect results when identifying incremental classes.Moreover,the incremental classes are usually emergent without label information or only a few labeled samples of incremental classes can be obtained.In this context,we propose a graphbased semi-supervised approach to address the fewshot classes-incremental(FSCI)modulation classification problem.Our proposed method is a twostage learning method,specifically,a warm-up model is trained for classifying old classes and incremental classes,where the unlabeled samples of incremental classes are uniformly labeled with the same label to alleviate the damage of the class imbalance problem.Then the warm-up model is regarded as a feature extractor for constructing a similar graph to connect labeled samples and unlabeled samples,and the label propagation algorithm is adopted to propagate the label information from labeled nodes to unlabeled nodes in the graph to achieve the purpose of incremental classes recognition.Simulation results prove that the proposed method is superior to other finetuning methods and retrain methods.展开更多
The escalating complexity and heterogeneity of modern energy systems—particularly in smart grid and distributed energy infrastructures—has intensified the need for intelligent and scalable security vulnerability cla...The escalating complexity and heterogeneity of modern energy systems—particularly in smart grid and distributed energy infrastructures—has intensified the need for intelligent and scalable security vulnerability classification.To address this challenge,we propose Vulnerability2Vec,a graph-embedding-based framework designed to enhance the automated classification of security vulnerabilities that threaten energy system resilience.Vulnerability2Vec converts Common Vulnerabilities and Exposures(CVE)text explanations to semantic graphs,where nodes represent CVE IDs and key terms(nouns,verbs,and adjectives),and edges capture co-occurrence relationships.Then,it embeds the semantic graphs to a low-dimensional vector space with random-walk sampling and skip-gram with negative sampling.It is possible to identify the latent relationships and structural patterns that traditional sparse vector methods fail to capture.Experimental results demonstrate a classification accuracy of up to 80%,significantly outperforming baseline methods.This approach offers a theoretical basis for classifying vulnerability types as structured semantic patterns in complex software systems.The proposed method models the semantic structure of vulnerabilities,providing a theoretical foundation for their classification.展开更多
Graphs are used as a data structure to describe complex relationships between things.The node classification method based on graph network plays an important role in practical applications.None of the existing graph n...Graphs are used as a data structure to describe complex relationships between things.The node classification method based on graph network plays an important role in practical applications.None of the existing graph node classification methods consider the uneven distribution of node labels.In this paper,a graph convolution algorithm on a directed graph is designed for the distribution of unbalanced graph nodes to realize node classification based on multi-scale fusion graph convolution network.This method designs different propagation depths for each class according to the unbalance ratio on the data set,and different aggregation functions are designed at each layer of the graph convolutional network based on the class propagation depth and the graph adjacency matrix.The scope of information dissemination of positive samples is expanded relatively,thereby improving the accuracy of classification of unbalanced graph nodes.Finally,the effectiveness of the algorithm is verified through experiments on the public text classification datasets.展开更多
Node of network has lots of information, such as topology, text and label information. Therefore, node classification is an open issue. Recently, one vector of node is directly connected at the end of another vector. ...Node of network has lots of information, such as topology, text and label information. Therefore, node classification is an open issue. Recently, one vector of node is directly connected at the end of another vector. However, this method actually obtains the performance by extending dimensions and considering that the text and structural information are one-to-one, which is obviously unreasonable. Regarding this issue, a method by weighting vectors is proposed in this paper. Three methods, negative logarithm, modulus and sigmoid function are used to weight-trained vectors, then recombine the weighted vectors and put them into the SVM classifier for evaluation output. By comparing three different weighting methods, the results showed that using negative logarithm weighting achieved better results than the other two using modulus and sigmoid function weighting, and was superior to directly concatenating vectors in the same dimension.展开更多
Deep Learning(DL)is such a powerful tool that we have seen tremendous success in areas such as Computer Vision,Speech Recognition,and Natural Language Processing.Since Automated Modulation Classification(AMC)is an imp...Deep Learning(DL)is such a powerful tool that we have seen tremendous success in areas such as Computer Vision,Speech Recognition,and Natural Language Processing.Since Automated Modulation Classification(AMC)is an important part in Cognitive Radio Networks,we try to explore its potential in solving signal modulation recognition problem.It cannot be overlooked that DL model is a complex model,thus making them prone to over-fitting.DL model requires many training data to combat with over-fitting,but adding high quality labels to training data manually is not always cheap and accessible,especially in real-time system,which may counter unprecedented data in dataset.Semi-supervised Learning is a way to exploit unlabeled data effectively to reduce over-fitting in DL.In this paper,we extend Generative Adversarial Networks(GANs)to the semi-supervised learning will show it is a method can be used to create a more dataefficient classifier.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
A semi-supervised vector machine is a relatively new learning method using both labeled and unlabeled data in classifi- cation. Since the objective function of the model for an unstrained semi-supervised vector machin...A semi-supervised vector machine is a relatively new learning method using both labeled and unlabeled data in classifi- cation. Since the objective function of the model for an unstrained semi-supervised vector machine is not smooth, many fast opti- mization algorithms cannot be applied to solve the model. In order to overcome the difficulty of dealing with non-smooth objective functions, new methods that can solve the semi-supervised vector machine with desired classification accuracy are in great demand. A quintic spline function with three-times differentiability at the ori- gin is constructed by a general three-moment method, which can be used to approximate the symmetric hinge loss function. The approximate accuracy of the quintic spiine function is estimated. Moreover, a quintic spline smooth semi-support vector machine is obtained and the convergence accuracy of the smooth model to the non-smooth one is analyzed. Three experiments are performed to test the efficiency of the model. The experimental results show that the new model outperforms other smooth models, in terms of classification performance. Furthermore, the new model is not sensitive to the increasing number of the labeled samples, which means that the new model is more efficient.展开更多
Non-collaborative radio transmitter recognition is a significant but challenging issue, since it is hard or costly to obtain labeled training data samples. In order to make effective use of the unlabeled samples which...Non-collaborative radio transmitter recognition is a significant but challenging issue, since it is hard or costly to obtain labeled training data samples. In order to make effective use of the unlabeled samples which can be obtained much easier, a novel semi-supervised classification method named Elastic Sparsity Regularized Support Vector Machine (ESRSVM) is proposed for radio transmitter classification. ESRSVM first constructs an elastic-net graph over data samples to capture the robust and natural discriminating information and then incorporate the information into the manifold learning framework by an elastic sparsity regularization term. Experimental results on 10 GMSK modulated Automatic Identification System radios and 15 FM walkie-talkie radios show that ESRSVM achieves obviously better performance than KNN and SVM, which use only labeled samples for classification, and also outperforms semi-supervised classifier LapSVM based on manifold regularization.展开更多
Objective To explore the semi-supervised learning(SSL) algorithm for long-tail endoscopic image classification with limited annotations.Method We explored semi-supervised long-tail endoscopic image classification in H...Objective To explore the semi-supervised learning(SSL) algorithm for long-tail endoscopic image classification with limited annotations.Method We explored semi-supervised long-tail endoscopic image classification in HyperKvasir,the largest gastrointestinal public dataset with 23 diverse classes.Semi-supervised learning algorithm FixMatch was applied based on consistency regularization and pseudo-labeling.After splitting the training dataset and the test dataset at a ratio of 4:1,we sampled 20%,50%,and 100% labeled training data to test the classification with limited annotations.Results The classification performance was evaluated by micro-average and macro-average evaluation metrics,with the Mathews correlation coefficient(MCC) as the overall evaluation.SSL algorithm improved the classification performance,with MCC increasing from 0.8761 to 0.8850,from 0.8983 to 0.8994,and from 0.9075 to 0.9095 with 20%,50%,and 100% ratio of labeled training data,respectively.With a 20% ratio of labeled training data,SSL improved both the micro-average and macro-average classification performance;while for the ratio of 50% and 100%,SSL improved the micro-average performance but hurt macro-average performance.Through analyzing the confusion matrix and labeling bias in each class,we found that the pseudo-based SSL algorithm exacerbated the classifier’ s preference for the head class,resulting in improved performance in the head class and degenerated performance in the tail class.Conclusion SSL can improve the classification performance for semi-supervised long-tail endoscopic image classification,especially when the labeled data is extremely limited,which may benefit the building of assisted diagnosis systems for low-volume hospitals.However,the pseudo-labeling strategy may amplify the effect of class imbalance,which hurts the classification performance for the tail class.展开更多
Sentiment classification is a useful tool to classify reviews about sentiments and attitudes towards a product or service.Existing studies heavily rely on sentiment classification methods that require fully annotated ...Sentiment classification is a useful tool to classify reviews about sentiments and attitudes towards a product or service.Existing studies heavily rely on sentiment classification methods that require fully annotated inputs.However,there is limited labelled text available,making the acquirement process of the fully annotated input costly and labour-intensive.Lately,semi-supervised methods emerge as they require only partially labelled input but perform comparably to supervised methods.Nevertheless,some works reported that the performance of the semi-supervised model degraded after adding unlabelled instances into training.Literature also shows that not all unlabelled instances are equally useful;thus identifying the informative unlabelled instances is beneficial in training a semi-supervised model.To achieve this,an informative score is proposed and incorporated into semisupervised sentiment classification.The evaluation is performed on a semisupervised method without an informative score and with an informative score.By using the informative score in the instance selection strategy to identify informative unlabelled instances,semi-supervised models perform better compared to models that do not incorporate informative scores into their training.Although the performance of semi-supervised models incorporated with an informative score is not able to surpass the supervised models,the results are still found promising as the differences in performance are subtle with a small difference of 2%to 5%,but the number of labelled instances used is greatly reduced from100%to 40%.The best finding of the proposed instance selection strategy is achieved when incorporating an informative score with a baseline confidence score at a 0.5:0.5 ratio using only 40%labelled data.展开更多
These problems of nonlinearity, fuzziness and few labeled data were rarely considered in traditional remote sensing image classification. A semi-supervised kernel fuzzy C-means （SSKFCM） algorithm is proposed to over...These problems of nonlinearity, fuzziness and few labeled data were rarely considered in traditional remote sensing image classification. A semi-supervised kernel fuzzy C-means （SSKFCM） algorithm is proposed to overcome these disadvantages of remote sensing image classification in this paper. The SSKFCM algorithm is achieved by introducing a kernel method and semi-supervised learning technique into the standard fuzzy C-means （FCM） algorithm. A set of Beijing-1 micro-satellite＇s multispectral images are adopted to be classified by several algorithms, such as FCM, kernel FCM （KFCM）, semi-supervised FCM （SSFCM） and SSKFCM. The classification results are estimated by corresponding indexes. The results indicate that the SSKFCM algorithm significantly improves the classification accuracy of remote sensing images compared with the others.展开更多
Accurate classification of encrypted traffic plays an important role in network management.However,current methods confronts several problems:inability to characterize traffic that exhibits great dispersion,inability ...Accurate classification of encrypted traffic plays an important role in network management.However,current methods confronts several problems:inability to characterize traffic that exhibits great dispersion,inability to classify traffic with multi-level features,and degradation due to limited training traffic size.To address these problems,this paper proposes a traffic granularity-based cryptographic traffic classification method,called Granular Classifier(GC).In this paper,a novel Cardinality-based Constrained Fuzzy C-Means(CCFCM)clustering algorithm is proposed to address the problem caused by limited training traffic,considering the ratio of cardinality that must be linked between flows to achieve good traffic partitioning.Then,an original representation format of traffic is presented based on granular computing,named Traffic Granules(TG),to accurately describe traffic structure by catching the dispersion of different traffic features.Each granule is a compact set of similar data with a refined boundary by excluding outliers.Based on TG,GC is constructed to perform traffic classification based on multi-level features.The performance of the GC is evaluated based on real-world encrypted network traffic data.Experimental results show that the GC achieves outstanding performance for encrypted traffic classification with limited size of training traffic and keeps accurate classification in dynamic network conditions.展开更多
AIM To establish an appropriate N classification system for early gastric cancer(EGC).METHODS Data from 10714 patients who underwent radical gastrectomy between 1988 and2011 were retrieved from the National Cancer Ins...AIM To establish an appropriate N classification system for early gastric cancer(EGC).METHODS Data from 10714 patients who underwent radical gastrectomy between 1988 and2011 were retrieved from the National Cancer Institute's Surveillance,Epidemiology, and End Result database. The overall survival(OS) based on the eighth edition and new tumor lymph node metastasis(TNM) staging systems were compared, and the analysis was repeated in an external validation set from the Fujian Medical University Union Hospital database.RESULTS There were no significant differences in OS between N1 and N2 cancers or between N3a and N3b cancers in cases of EGC. The X-tile program identified that the new staging system for EGC consisted of T1N0, T1N1' [1-6 metastatic lymph nodes(LNs)], and T1N2'( ≥ 7 metastatic LNs). Compared with the eighth edition of the TNM staging system, the OS of patients in T1N1' stage was similar to that of patients with stage IIA disease, whereas the OS of patients in T1N2' stage was similar to that of patients with stage IIB disease. The new TNM staging system exhibited a slightly lower Akaike Information Criterion value and higher χ~2 and c-statistic compared with the eighth edition of the TNM classification system.Similar results were found in the external validation dataset from the external validation set.CONCLUSION We have developed an optional new TNM staging system with a better predictive ability that can be used to accurately predict the 5-year OS of patients with EGC.展开更多
The existing graph convolution methods usually suffer high computational burdens,large memory requirements,and intractable batch-processing.In this paper,we propose a high-efficient variational gridded graph convoluti...The existing graph convolution methods usually suffer high computational burdens,large memory requirements,and intractable batch-processing.In this paper,we propose a high-efficient variational gridded graph convolution network(VG-GCN)to encode non-regular graph data,which overcomes all these aforementioned problems.To capture graph topology structures efficiently,in the proposed framework,we propose a hierarchically-coarsened random walk(hcr-walk)by taking advantage of the classic random walk and node/edge encapsulation.The hcr-walk greatly mitigates the problem of exponentially explosive sampling times which occur in the classic version,while preserving graph structures well.To efficiently encode local hcr-walk around one reference node,we project hcrwalk into an ordered space to form image-like grid data,which favors those conventional convolution networks.Instead of the direct 2-D convolution filtering,a variational convolution block(VCB)is designed to model the distribution of the randomsampling hcr-walk inspired by the well-formulated variational inference.We experimentally validate the efficiency and effectiveness of our proposed VG-GCN,which has high computation speed,and the comparable or even better performance when compared with baseline GCNs.展开更多
An improved on-demand multicast routing protocol(ODMRP), node classification on-demand multicast routing protocol(NC-ODMRP), which is based on node classification in mobile ad hoc networks was proposed. NC-ODMRP class...An improved on-demand multicast routing protocol(ODMRP), node classification on-demand multicast routing protocol(NC-ODMRP), which is based on node classification in mobile ad hoc networks was proposed. NC-ODMRP classifies nodes into such three categories as ordinary node, forwarding group(FG) node, neighbor node of FG node according to their history forwarding information. The categories are distinguished with different weights by a weight table in the nodes. NC-ODMRP chooses the node with the highest weight as an FG node during the setup of forwarding group, which reduces a lot of redundant FG nodes by sharing more FG nodes between different sender and receiver pairs. The simulation results show that NC-ODMRP can reduce more than 20% FG number of ODMRP, thus enhances nearly 14% data forwarding efficiency and 12% energy consumption efficiency when the number of multicast senders is more than 5.展开更多
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 Key Research and Development Program of China(No.2020YFA0909100).
文摘Attributed graphs have an additional sign vector for each node.Typically,edge signs represent like or dislike relationship between the node pairs.This has applications in domains,such as recommender systems,personalised search,etc.However,limited availability of edge sign information in attributed networks requires inferring the underlying graph embeddings to fill-in the knowledge gap.Such inference is performed by way of node classification which aims to deduce the node characteristics based on the topological structure of the graph and signed interactions between the nodes.The study of attributed networks is challenging due to noise,sparsity,and class imbalance issues.In this work,we consider node centrality in conjunction with edge signs to contemplate the node classification problem in attributed networks.We propose Semi-supervised Node Classification in Attributed graphs(SNCA).SNCA is robust to underlying network noise,and has in-built class imbalance handling capabilities.We perform an extensive experimental study on real-world datasets to showcase the efficiency,scalability,robustness,and pertinence of the solution.The performance results demonstrate the suitability of the solution for large attributed graphs in real-world settings.
基金supported by the Fujian Key Laboratory of Intelligent Imaging and Precision Radiotherapy for Tumors(Fujian Medical University)and Clinical Research Center for Radiology and Radiotherapy of Fujian Province(Digestive,Hematological and Breast Malignancies).
文摘Background:Metastasis to the infraclavicular and supraclavicular lymph nodes(ISLNs)is an important factor that predicts poor survival in patients with breast cancer;however,pathological nodal staging does not traditionally include ISLNs because of their non-routine surgical dissection.This study aimed to evaluate the prognostic impact of ISLN metastasis and propose a refined nodal staging system tailored for patients undergoing neoadjuvant chemotherapy(NAC).Methods:We retrospectively reviewed 1,072 patients with breast cancer with or without ISLN metastasis who received NAC at two institutions(Fujian cohort and Hebei cohort)from 2010 to 2022.We conducted detailed survival analysis to evaluate the diagnostic consistency and prognostic significance of ISLNs.Results:There were no survival differences among patients with ISLN involvement across different assay method-ologies and patient cohorts.Among 887 patients in the Fujian cohort,238 patients(26.8%)with positive ISLNs had significantly inferior 3-year progression-free survival(PFS,75.9%vs.90.4%,P<0.001)and overall survival(OS,90.6%vs.95.9%,P<0.001).After adjusting for potential confounders,ISLN involvement persisted as an independent predictor of both PFS and OS.We propose a refined axillary classification that combines pathologi-cal axillary staging post-NAC with ISLN involvement,revealing 3-year PFS rates of 95.3%,87.6%,73.4%,and 64.5%for the respective four groups defined by this refined classification combining axillary stage and ISLN status.Conclusions:Involvement of the ISLNs was associated with a worse prognosis,underscoring their prognostic value.This finding highlights the potential of ISLN status to influence decisions regarding adjuvant treatment in patients with breast cancer.
基金supported in part by the National Natural Science Foundation of China(No.12302252)。
文摘Deep learning significantly improves the accuracy of remote sensing image scene classification,benefiting from the large-scale datasets.However,annotating the remote sensing images is time-consuming and even tough for experts.Deep neural networks trained using a few labeled samples usually generalize less to new unseen images.In this paper,we propose a semi-supervised approach for remote sensing image scene classification based on the prototype-based consistency,by exploring massive unlabeled images.To this end,we,first,propose a feature enhancement module to extract discriminative features.This is achieved by focusing the model on the foreground areas.Then,the prototype-based classifier is introduced to the framework,which is used to acquire consistent feature representations.We conduct a series of experiments on NWPU-RESISC45 and Aerial Image Dataset(AID).Our method improves the State-Of-The-Art(SOTA)method on NWPU-RESISC45 from 92.03%to 93.08%and on AID from 94.25%to 95.24%in terms of accuracy.
基金supported in part by the National Natural Science Foundation of China under Grant No.62171334,No.11973077 and No.12003061。
文摘With the successive application of deep learning(DL)in classification tasks,the DL-based modulation classification method has become the preference for its state-of-the-art performance.Nevertheless,once the DL recognition model is pre-trained with fixed classes,the pre-trained model tends to predict incorrect results when identifying incremental classes.Moreover,the incremental classes are usually emergent without label information or only a few labeled samples of incremental classes can be obtained.In this context,we propose a graphbased semi-supervised approach to address the fewshot classes-incremental(FSCI)modulation classification problem.Our proposed method is a twostage learning method,specifically,a warm-up model is trained for classifying old classes and incremental classes,where the unlabeled samples of incremental classes are uniformly labeled with the same label to alleviate the damage of the class imbalance problem.Then the warm-up model is regarded as a feature extractor for constructing a similar graph to connect labeled samples and unlabeled samples,and the label propagation algorithm is adopted to propagate the label information from labeled nodes to unlabeled nodes in the graph to achieve the purpose of incremental classes recognition.Simulation results prove that the proposed method is superior to other finetuning methods and retrain methods.
基金supported by the MSIT(Ministry of Science and ICT),Republic of Korea,under the Convergence Security Core Talent Training Business Support Program(IITP-2025-RS-2023-00266605,50%)in part by the Institute of Information&Communications Technology Planning&Evaluation(lITP)grant funded by the Korea government(MSIT)(RS-2025-02305436,Development of Digital Innovative Element Technologies for Rapid Prediction of Potential Complex Disasters and Continuous Disaster Prevention,30%)supported by the Chung-Ang University Graduate Research Scholar-ship in 2023(20%).
文摘The escalating complexity and heterogeneity of modern energy systems—particularly in smart grid and distributed energy infrastructures—has intensified the need for intelligent and scalable security vulnerability classification.To address this challenge,we propose Vulnerability2Vec,a graph-embedding-based framework designed to enhance the automated classification of security vulnerabilities that threaten energy system resilience.Vulnerability2Vec converts Common Vulnerabilities and Exposures(CVE)text explanations to semantic graphs,where nodes represent CVE IDs and key terms(nouns,verbs,and adjectives),and edges capture co-occurrence relationships.Then,it embeds the semantic graphs to a low-dimensional vector space with random-walk sampling and skip-gram with negative sampling.It is possible to identify the latent relationships and structural patterns that traditional sparse vector methods fail to capture.Experimental results demonstrate a classification accuracy of up to 80%,significantly outperforming baseline methods.This approach offers a theoretical basis for classifying vulnerability types as structured semantic patterns in complex software systems.The proposed method models the semantic structure of vulnerabilities,providing a theoretical foundation for their classification.
基金the National Natural Science Foundation of China (No.61673265)the National Key Research and Development Program (No.2020YFC1512203)+1 种基金the Special Research Projects for Civil Aircraft (No.MJ-2017-S-38)the Project of CEMEE (No.2019K0302A)。
文摘Graphs are used as a data structure to describe complex relationships between things.The node classification method based on graph network plays an important role in practical applications.None of the existing graph node classification methods consider the uneven distribution of node labels.In this paper,a graph convolution algorithm on a directed graph is designed for the distribution of unbalanced graph nodes to realize node classification based on multi-scale fusion graph convolution network.This method designs different propagation depths for each class according to the unbalance ratio on the data set,and different aggregation functions are designed at each layer of the graph convolutional network based on the class propagation depth and the graph adjacency matrix.The scope of information dissemination of positive samples is expanded relatively,thereby improving the accuracy of classification of unbalanced graph nodes.Finally,the effectiveness of the algorithm is verified through experiments on the public text classification datasets.
文摘Node of network has lots of information, such as topology, text and label information. Therefore, node classification is an open issue. Recently, one vector of node is directly connected at the end of another vector. However, this method actually obtains the performance by extending dimensions and considering that the text and structural information are one-to-one, which is obviously unreasonable. Regarding this issue, a method by weighting vectors is proposed in this paper. Three methods, negative logarithm, modulus and sigmoid function are used to weight-trained vectors, then recombine the weighted vectors and put them into the SVM classifier for evaluation output. By comparing three different weighting methods, the results showed that using negative logarithm weighting achieved better results than the other two using modulus and sigmoid function weighting, and was superior to directly concatenating vectors in the same dimension.
基金This work is supported by the National Natural Science Foundation of China(Nos.61771154,61603239,61772454,6171101570).
文摘Deep Learning(DL)is such a powerful tool that we have seen tremendous success in areas such as Computer Vision,Speech Recognition,and Natural Language Processing.Since Automated Modulation Classification(AMC)is an important part in Cognitive Radio Networks,we try to explore its potential in solving signal modulation recognition problem.It cannot be overlooked that DL model is a complex model,thus making them prone to over-fitting.DL model requires many training data to combat with over-fitting,but adding high quality labels to training data manually is not always cheap and accessible,especially in real-time system,which may counter unprecedented data in dataset.Semi-supervised Learning is a way to exploit unlabeled data effectively to reduce over-fitting in DL.In this paper,we extend Generative Adversarial Networks(GANs)to the semi-supervised learning will show it is a method can be used to create a more dataefficient classifier.
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supported by the Fundamental Research Funds for University of Science and Technology Beijing(FRF-BR-12-021)
文摘A semi-supervised vector machine is a relatively new learning method using both labeled and unlabeled data in classifi- cation. Since the objective function of the model for an unstrained semi-supervised vector machine is not smooth, many fast opti- mization algorithms cannot be applied to solve the model. In order to overcome the difficulty of dealing with non-smooth objective functions, new methods that can solve the semi-supervised vector machine with desired classification accuracy are in great demand. A quintic spline function with three-times differentiability at the ori- gin is constructed by a general three-moment method, which can be used to approximate the symmetric hinge loss function. The approximate accuracy of the quintic spiine function is estimated. Moreover, a quintic spline smooth semi-support vector machine is obtained and the convergence accuracy of the smooth model to the non-smooth one is analyzed. Three experiments are performed to test the efficiency of the model. The experimental results show that the new model outperforms other smooth models, in terms of classification performance. Furthermore, the new model is not sensitive to the increasing number of the labeled samples, which means that the new model is more efficient.
基金Supported by the Hi-Tech Research and Development Program of China (No. 2009AAJ130)
文摘Non-collaborative radio transmitter recognition is a significant but challenging issue, since it is hard or costly to obtain labeled training data samples. In order to make effective use of the unlabeled samples which can be obtained much easier, a novel semi-supervised classification method named Elastic Sparsity Regularized Support Vector Machine (ESRSVM) is proposed for radio transmitter classification. ESRSVM first constructs an elastic-net graph over data samples to capture the robust and natural discriminating information and then incorporate the information into the manifold learning framework by an elastic sparsity regularization term. Experimental results on 10 GMSK modulated Automatic Identification System radios and 15 FM walkie-talkie radios show that ESRSVM achieves obviously better performance than KNN and SVM, which use only labeled samples for classification, and also outperforms semi-supervised classifier LapSVM based on manifold regularization.
文摘Objective To explore the semi-supervised learning(SSL) algorithm for long-tail endoscopic image classification with limited annotations.Method We explored semi-supervised long-tail endoscopic image classification in HyperKvasir,the largest gastrointestinal public dataset with 23 diverse classes.Semi-supervised learning algorithm FixMatch was applied based on consistency regularization and pseudo-labeling.After splitting the training dataset and the test dataset at a ratio of 4:1,we sampled 20%,50%,and 100% labeled training data to test the classification with limited annotations.Results The classification performance was evaluated by micro-average and macro-average evaluation metrics,with the Mathews correlation coefficient(MCC) as the overall evaluation.SSL algorithm improved the classification performance,with MCC increasing from 0.8761 to 0.8850,from 0.8983 to 0.8994,and from 0.9075 to 0.9095 with 20%,50%,and 100% ratio of labeled training data,respectively.With a 20% ratio of labeled training data,SSL improved both the micro-average and macro-average classification performance;while for the ratio of 50% and 100%,SSL improved the micro-average performance but hurt macro-average performance.Through analyzing the confusion matrix and labeling bias in each class,we found that the pseudo-based SSL algorithm exacerbated the classifier’ s preference for the head class,resulting in improved performance in the head class and degenerated performance in the tail class.Conclusion SSL can improve the classification performance for semi-supervised long-tail endoscopic image classification,especially when the labeled data is extremely limited,which may benefit the building of assisted diagnosis systems for low-volume hospitals.However,the pseudo-labeling strategy may amplify the effect of class imbalance,which hurts the classification performance for the tail class.
基金This research is supported by Fundamental Research Grant Scheme(FRGS),Ministry of Education Malaysia(MOE)under the project code,FRGS/1/2018/ICT02/USM/02/9 titled,Automated Big Data Annotation for Training Semi-Supervised Deep Learning Model in Sentiment Classification.
文摘Sentiment classification is a useful tool to classify reviews about sentiments and attitudes towards a product or service.Existing studies heavily rely on sentiment classification methods that require fully annotated inputs.However,there is limited labelled text available,making the acquirement process of the fully annotated input costly and labour-intensive.Lately,semi-supervised methods emerge as they require only partially labelled input but perform comparably to supervised methods.Nevertheless,some works reported that the performance of the semi-supervised model degraded after adding unlabelled instances into training.Literature also shows that not all unlabelled instances are equally useful;thus identifying the informative unlabelled instances is beneficial in training a semi-supervised model.To achieve this,an informative score is proposed and incorporated into semisupervised sentiment classification.The evaluation is performed on a semisupervised method without an informative score and with an informative score.By using the informative score in the instance selection strategy to identify informative unlabelled instances,semi-supervised models perform better compared to models that do not incorporate informative scores into their training.Although the performance of semi-supervised models incorporated with an informative score is not able to surpass the supervised models,the results are still found promising as the differences in performance are subtle with a small difference of 2%to 5%,but the number of labelled instances used is greatly reduced from100%to 40%.The best finding of the proposed instance selection strategy is achieved when incorporating an informative score with a baseline confidence score at a 0.5:0.5 ratio using only 40%labelled data.
基金Supported by the National High Technology Research and Development Programme （No.2007AA12Z227） and the National Natural Science Foundation of China （No.40701146）.
文摘These problems of nonlinearity, fuzziness and few labeled data were rarely considered in traditional remote sensing image classification. A semi-supervised kernel fuzzy C-means （SSKFCM） algorithm is proposed to overcome these disadvantages of remote sensing image classification in this paper. The SSKFCM algorithm is achieved by introducing a kernel method and semi-supervised learning technique into the standard fuzzy C-means （FCM） algorithm. A set of Beijing-1 micro-satellite＇s multispectral images are adopted to be classified by several algorithms, such as FCM, kernel FCM （KFCM）, semi-supervised FCM （SSFCM） and SSKFCM. The classification results are estimated by corresponding indexes. The results indicate that the SSKFCM algorithm significantly improves the classification accuracy of remote sensing images compared with the others.
基金supported in part by the Shandong Provincial Natural Science Foundation under Grant ZR2021QF008the National Natural Science Foundation of China under Grant 62072351+1 种基金in part by the open research project of ZheJiang Lab under grant 2021PD0AB01in part by the 111 Project under Grant B16037。
文摘Accurate classification of encrypted traffic plays an important role in network management.However,current methods confronts several problems:inability to characterize traffic that exhibits great dispersion,inability to classify traffic with multi-level features,and degradation due to limited training traffic size.To address these problems,this paper proposes a traffic granularity-based cryptographic traffic classification method,called Granular Classifier(GC).In this paper,a novel Cardinality-based Constrained Fuzzy C-Means(CCFCM)clustering algorithm is proposed to address the problem caused by limited training traffic,considering the ratio of cardinality that must be linked between flows to achieve good traffic partitioning.Then,an original representation format of traffic is presented based on granular computing,named Traffic Granules(TG),to accurately describe traffic structure by catching the dispersion of different traffic features.Each granule is a compact set of similar data with a refined boundary by excluding outliers.Based on TG,GC is constructed to perform traffic classification based on multi-level features.The performance of the GC is evaluated based on real-world encrypted network traffic data.Experimental results show that the GC achieves outstanding performance for encrypted traffic classification with limited size of training traffic and keeps accurate classification in dynamic network conditions.
基金Supported by Scientific and Technological Innovation Joint Capital Projects of Fujian Province,China,No.2016Y9031Construction Project of Fujian Province Minimally Invasive Medical Center,No.[2017]171
文摘AIM To establish an appropriate N classification system for early gastric cancer(EGC).METHODS Data from 10714 patients who underwent radical gastrectomy between 1988 and2011 were retrieved from the National Cancer Institute's Surveillance,Epidemiology, and End Result database. The overall survival(OS) based on the eighth edition and new tumor lymph node metastasis(TNM) staging systems were compared, and the analysis was repeated in an external validation set from the Fujian Medical University Union Hospital database.RESULTS There were no significant differences in OS between N1 and N2 cancers or between N3a and N3b cancers in cases of EGC. The X-tile program identified that the new staging system for EGC consisted of T1N0, T1N1' [1-6 metastatic lymph nodes(LNs)], and T1N2'( ≥ 7 metastatic LNs). Compared with the eighth edition of the TNM staging system, the OS of patients in T1N1' stage was similar to that of patients with stage IIA disease, whereas the OS of patients in T1N2' stage was similar to that of patients with stage IIB disease. The new TNM staging system exhibited a slightly lower Akaike Information Criterion value and higher χ~2 and c-statistic compared with the eighth edition of the TNM classification system.Similar results were found in the external validation dataset from the external validation set.CONCLUSION We have developed an optional new TNM staging system with a better predictive ability that can be used to accurately predict the 5-year OS of patients with EGC.
基金supported by the Natural Science Foundation of Jiangsu Province(BK20190019,BK20190452)the National Natural Science Foundation of China(62072244,61906094)the Natural Science Foundation of Shandong Province(ZR2020LZH008)。
文摘The existing graph convolution methods usually suffer high computational burdens,large memory requirements,and intractable batch-processing.In this paper,we propose a high-efficient variational gridded graph convolution network(VG-GCN)to encode non-regular graph data,which overcomes all these aforementioned problems.To capture graph topology structures efficiently,in the proposed framework,we propose a hierarchically-coarsened random walk(hcr-walk)by taking advantage of the classic random walk and node/edge encapsulation.The hcr-walk greatly mitigates the problem of exponentially explosive sampling times which occur in the classic version,while preserving graph structures well.To efficiently encode local hcr-walk around one reference node,we project hcrwalk into an ordered space to form image-like grid data,which favors those conventional convolution networks.Instead of the direct 2-D convolution filtering,a variational convolution block(VCB)is designed to model the distribution of the randomsampling hcr-walk inspired by the well-formulated variational inference.We experimentally validate the efficiency and effectiveness of our proposed VG-GCN,which has high computation speed,and the comparable or even better performance when compared with baseline GCNs.
基金Project(90304010) supported by the National Natural Science Foundation of China project supported by the NewCentury Excellent Talents in University
文摘An improved on-demand multicast routing protocol(ODMRP), node classification on-demand multicast routing protocol(NC-ODMRP), which is based on node classification in mobile ad hoc networks was proposed. NC-ODMRP classifies nodes into such three categories as ordinary node, forwarding group(FG) node, neighbor node of FG node according to their history forwarding information. The categories are distinguished with different weights by a weight table in the nodes. NC-ODMRP chooses the node with the highest weight as an FG node during the setup of forwarding group, which reduces a lot of redundant FG nodes by sharing more FG nodes between different sender and receiver pairs. The simulation results show that NC-ODMRP can reduce more than 20% FG number of ODMRP, thus enhances nearly 14% data forwarding efficiency and 12% energy consumption efficiency when the number of multicast senders is more than 5.
