Domain adaptation aims to reduce the distribution gap between the training data(source domain)and the target data.This enables effective predictions even for domains not seen during training.However,most conventional ...Domain adaptation aims to reduce the distribution gap between the training data(source domain)and the target data.This enables effective predictions even for domains not seen during training.However,most conventional domain adaptation methods assume a single source domain,making them less suitable for modern deep learning settings that rely on diverse and large-scale datasets.To address this limitation,recent research has focused on Multi-Source Domain Adaptation(MSDA),which aims to learn effectively from multiple source domains.In this paper,we propose Efficient Domain Transition for Multi-source(EDTM),a novel and efficient framework designed to tackle two major challenges in existing MSDA approaches:(1)integrating knowledge across different source domains and(2)aligning label distributions between source and target domains.EDTM leverages an ensemble-based classifier expert mechanism to enhance the contribution of source domains that are more similar to the target domain.To further stabilize the learning process and improve performance,we incorporate imitation learning into the training of the target model.In addition,Maximum Classifier Discrepancy(MCD)is employed to align class-wise label distributions between the source and target domains.Experiments were conducted using Digits-Five,one of the most representative benchmark datasets for MSDA.The results show that EDTM consistently outperforms existing methods in terms of average classification accuracy.Notably,EDTM achieved significantly higher performance on target domains such as Modified National Institute of Standards and Technolog with blended background images(MNIST-M)and Street View House Numbers(SVHN)datasets,demonstrating enhanced generalization compared to baseline approaches.Furthermore,an ablation study analyzing the contribution of each loss component validated the effectiveness of the framework,highlighting the importance of each module in achieving optimal performance.展开更多
Recently,COVID-19 has posed a challenging threat to researchers,scientists,healthcare professionals,and administrations over the globe,from its diagnosis to its treatment.The researchers are making persistent efforts ...Recently,COVID-19 has posed a challenging threat to researchers,scientists,healthcare professionals,and administrations over the globe,from its diagnosis to its treatment.The researchers are making persistent efforts to derive probable solutions formanaging the pandemic in their areas.One of the widespread and effective ways to detect COVID-19 is to utilize radiological images comprising X-rays and computed tomography(CT)scans.At the same time,the recent advances in machine learning(ML)and deep learning(DL)models show promising results in medical imaging.Particularly,the convolutional neural network(CNN)model can be applied to identifying abnormalities on chest radiographs.While the epidemic of COVID-19,much research is led on processing the data compared with DL techniques,particularly CNN.This study develops an improved fruit fly optimization with a deep learning-enabled fusion(IFFO-DLEF)model for COVID-19 detection and classification.The major intention of the IFFO-DLEF model is to investigate the presence or absence of COVID-19.To do so,the presented IFFODLEF model applies image pre-processing at the initial stage.In addition,the ensemble of three DL models such as DenseNet169,EfficientNet,and ResNet50,are used for feature extraction.Moreover,the IFFO algorithm with a multilayer perceptron(MLP)classification model is utilized to identify and classify COVID-19.The parameter optimization of the MLP approach utilizing the IFFO technique helps in accomplishing enhanced classification performance.The experimental result analysis of the IFFO-DLEF model carried out on the CXR image database portrayed the better performance of the presented IFFO-DLEF model over recent approaches.展开更多
Statistics are most crucial than ever due to the accessibility of huge counts of data from several domains such as finance,medicine,science,engineering,and so on.Statistical data mining(SDM)is an interdisciplinary dom...Statistics are most crucial than ever due to the accessibility of huge counts of data from several domains such as finance,medicine,science,engineering,and so on.Statistical data mining(SDM)is an interdisciplinary domain that examines huge existing databases to discover patterns and connections from the data.It varies in classical statistics on the size of datasets and on the detail that the data could not primarily be gathered based on some experimental strategy but conversely for other resolves.Thus,this paper introduces an effective statistical Data Mining for Intelligent Rainfall Prediction using Slime Mould Optimization with Deep Learning(SDMIRPSMODL)model.In the presented SDMIRP-SMODL model,the feature subset selection process is performed by the SMO algorithm,which in turn minimizes the computation complexity.For rainfall prediction.Convolution neural network with long short-term memory(CNN-LSTM)technique is exploited.At last,this study involves the pelican optimization algorithm(POA)as a hyperparameter optimizer.The experimental evaluation of the SDMIRP-SMODL approach is tested utilizing a rainfall dataset comprising 23682 samples in the negative class and 1865 samples in the positive class.The comparative outcomes reported the supremacy of the SDMIRP-SMODL model compared to existing techniques.展开更多
A generalization of supervised single-label learning based on the assumption that each sample in a dataset may belong to more than one class simultaneously is called multi-label learning.The main objective of this wor...A generalization of supervised single-label learning based on the assumption that each sample in a dataset may belong to more than one class simultaneously is called multi-label learning.The main objective of this work is to create a novel framework for learning and classifying imbalancedmulti-label data.This work proposes a framework of two phases.The imbalanced distribution of themulti-label dataset is addressed through the proposed Borderline MLSMOTE resampling method in phase 1.Later,an adaptive weighted l21 norm regularized(Elastic-net)multilabel logistic regression is used to predict unseen samples in phase 2.The proposed Borderline MLSMOTE resampling method focuses on samples with concurrent high labels in contrast to conventional MLSMOTE.The minority labels in these samples are called difficult minority labels and are more prone to penalize classification performance.The concurrentmeasure is considered borderline,and labels associated with samples are regarded as borderline labels in the decision boundary.In phase II,a novel adaptive l21 norm regularized weighted multi-label logistic regression is used to handle balanced data with different weighted synthetic samples.Experimentation on various benchmark datasets shows the outperformance of the proposed method and its powerful predictive performances over existing conventional state-of-the-art multi-label methods.展开更多
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.RS-2024-00406320)the Institute of Information&Communica-tions Technology Planning&Evaluation(IITP)-Innovative Human Resource Development for Local Intellectualization Program Grant funded by the Korea government(MSIT)(IITP-2026-RS-2023-00259678).
文摘Domain adaptation aims to reduce the distribution gap between the training data(source domain)and the target data.This enables effective predictions even for domains not seen during training.However,most conventional domain adaptation methods assume a single source domain,making them less suitable for modern deep learning settings that rely on diverse and large-scale datasets.To address this limitation,recent research has focused on Multi-Source Domain Adaptation(MSDA),which aims to learn effectively from multiple source domains.In this paper,we propose Efficient Domain Transition for Multi-source(EDTM),a novel and efficient framework designed to tackle two major challenges in existing MSDA approaches:(1)integrating knowledge across different source domains and(2)aligning label distributions between source and target domains.EDTM leverages an ensemble-based classifier expert mechanism to enhance the contribution of source domains that are more similar to the target domain.To further stabilize the learning process and improve performance,we incorporate imitation learning into the training of the target model.In addition,Maximum Classifier Discrepancy(MCD)is employed to align class-wise label distributions between the source and target domains.Experiments were conducted using Digits-Five,one of the most representative benchmark datasets for MSDA.The results show that EDTM consistently outperforms existing methods in terms of average classification accuracy.Notably,EDTM achieved significantly higher performance on target domains such as Modified National Institute of Standards and Technolog with blended background images(MNIST-M)and Street View House Numbers(SVHN)datasets,demonstrating enhanced generalization compared to baseline approaches.Furthermore,an ablation study analyzing the contribution of each loss component validated the effectiveness of the framework,highlighting the importance of each module in achieving optimal performance.
基金This research was partly supported by the Technology Development Program of MSS[No.S3033853]by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(No.2020R1I1A3069700).
文摘Recently,COVID-19 has posed a challenging threat to researchers,scientists,healthcare professionals,and administrations over the globe,from its diagnosis to its treatment.The researchers are making persistent efforts to derive probable solutions formanaging the pandemic in their areas.One of the widespread and effective ways to detect COVID-19 is to utilize radiological images comprising X-rays and computed tomography(CT)scans.At the same time,the recent advances in machine learning(ML)and deep learning(DL)models show promising results in medical imaging.Particularly,the convolutional neural network(CNN)model can be applied to identifying abnormalities on chest radiographs.While the epidemic of COVID-19,much research is led on processing the data compared with DL techniques,particularly CNN.This study develops an improved fruit fly optimization with a deep learning-enabled fusion(IFFO-DLEF)model for COVID-19 detection and classification.The major intention of the IFFO-DLEF model is to investigate the presence or absence of COVID-19.To do so,the presented IFFODLEF model applies image pre-processing at the initial stage.In addition,the ensemble of three DL models such as DenseNet169,EfficientNet,and ResNet50,are used for feature extraction.Moreover,the IFFO algorithm with a multilayer perceptron(MLP)classification model is utilized to identify and classify COVID-19.The parameter optimization of the MLP approach utilizing the IFFO technique helps in accomplishing enhanced classification performance.The experimental result analysis of the IFFO-DLEF model carried out on the CXR image database portrayed the better performance of the presented IFFO-DLEF model over recent approaches.
基金This research was partly supported by the Technology Development Program of MSS[No.S3033853]by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.2021R1A4A1031509).
文摘Statistics are most crucial than ever due to the accessibility of huge counts of data from several domains such as finance,medicine,science,engineering,and so on.Statistical data mining(SDM)is an interdisciplinary domain that examines huge existing databases to discover patterns and connections from the data.It varies in classical statistics on the size of datasets and on the detail that the data could not primarily be gathered based on some experimental strategy but conversely for other resolves.Thus,this paper introduces an effective statistical Data Mining for Intelligent Rainfall Prediction using Slime Mould Optimization with Deep Learning(SDMIRPSMODL)model.In the presented SDMIRP-SMODL model,the feature subset selection process is performed by the SMO algorithm,which in turn minimizes the computation complexity.For rainfall prediction.Convolution neural network with long short-term memory(CNN-LSTM)technique is exploited.At last,this study involves the pelican optimization algorithm(POA)as a hyperparameter optimizer.The experimental evaluation of the SDMIRP-SMODL approach is tested utilizing a rainfall dataset comprising 23682 samples in the negative class and 1865 samples in the positive class.The comparative outcomes reported the supremacy of the SDMIRP-SMODL model compared to existing techniques.
基金partly supported by the Technology Development Program of MSS(No.S3033853)by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.2021R1A4A1031509).
文摘A generalization of supervised single-label learning based on the assumption that each sample in a dataset may belong to more than one class simultaneously is called multi-label learning.The main objective of this work is to create a novel framework for learning and classifying imbalancedmulti-label data.This work proposes a framework of two phases.The imbalanced distribution of themulti-label dataset is addressed through the proposed Borderline MLSMOTE resampling method in phase 1.Later,an adaptive weighted l21 norm regularized(Elastic-net)multilabel logistic regression is used to predict unseen samples in phase 2.The proposed Borderline MLSMOTE resampling method focuses on samples with concurrent high labels in contrast to conventional MLSMOTE.The minority labels in these samples are called difficult minority labels and are more prone to penalize classification performance.The concurrentmeasure is considered borderline,and labels associated with samples are regarded as borderline labels in the decision boundary.In phase II,a novel adaptive l21 norm regularized weighted multi-label logistic regression is used to handle balanced data with different weighted synthetic samples.Experimentation on various benchmark datasets shows the outperformance of the proposed method and its powerful predictive performances over existing conventional state-of-the-art multi-label methods.
