Image set classification using candidate sets selection and improved reverse training

Ren, Zhenwen; Wu, Bin; Zhang, Xiaoqian; Sun, Quansen

doi:10.1016/j.neucom.2019.03.010

Cited by 17 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, there are some other similar designs published in literatures. Ren et al [34] used the two-stage cascaded model to select the most promising candidate sets to achieve the image set classification task. Nam et al [35] removed noise signal in the first stage and realize target signal classification in the second stage.…”

Section: Methodsmentioning

confidence: 99%

Automated lung ultrasound scoring for evaluation of coronavirus disease 2019 pneumonia using two-stage cascaded deep learning model

Xing

et al. 2022

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

Coronavirus disease 2019 (COVID-19) pneumonia has erupted worldwide, causing massive population deaths and huge economic losses. In clinic, lung ultrasound (LUS) plays an important role in the auxiliary diagnosis of COVID-19 pneumonia. However, the lack of medical resources leads to the low using efficiency of the LUS, to address this problem, a novel automated LUS scoring system for evaluating COVID-19 pneumonia based on the two-stage cascaded deep learning model was proposed in this paper. 18,330 LUS images collected from 26 COVID-19 pneumonia patients were successfully assigned scores by two experienced doctors according to the designed four-level scoring standard for training the model. At the first stage, we made a secondary selection of these scored images through five ResNet-50 models and five-fold cross validation to obtain the available 12,949 LUS images which were highly relevant to the initial scoring results. At the second stage, three deep learning models including ResNet-50, Vgg-19, and GoogLeNet were formed the cascaded scored model and trained using the new dataset, whose predictive result was obtained by the voting mechanism. In addition, 1000 LUS images collected another 5 COVID-19 pneumonia patients were employed to test the model. Experiments results showed that the automated LUS scoring model was evaluated in terms of accuracy, sensitivity, specificity, and F1-score, being 96.1%, 96.3%, 98.8%, and 96.1%, respectively. They proved the proposed two-stage cascaded deep learning model could automatically score an LUS image, which has great potential for application to the clinics on various occasions.

show abstract

Section: Methodsmentioning

confidence: 99%

Automated lung ultrasound scoring for evaluation of coronavirus disease 2019 pneumonia using two-stage cascaded deep learning model

Xing

et al. 2022

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

show abstract

“…For a data set D with k clusters and similar member labels (p), KNN can be obtained for test sample 𝑇𝑆 ℎ within a test set (𝑇𝑆). For this purpose, the distance of the sample test 𝑇𝑆 ℎ , denoted as 𝑑 𝑗𝑖 between cluster members 𝑥 𝑗𝑖 is calculated using Equation (6). Then, 𝑑 𝑗𝑖 is sorted in ascending order to form 𝑑𝑠 𝑗𝑖 as Equation ( 7) and the average of K members from 𝑑𝑠 𝑗𝑖 is calculated as 𝑎𝑣𝑒 𝑖 to yield the best K as modeled in Equation (8).…”

Section: K-nearest Neighbors Regressionmentioning

confidence: 99%

“…Generally, classification should lead to a more accurate prediction and occasionally a reduced execution time [2][3][4][5]. TSS is also a common tool in image processing and image recognition where large data sets may be available for classification [6,7]. Outlier data with unacceptable distance with other consistently dispersed data may at times exist.…”

Section: Introductionmentioning

confidence: 99%

Outlier Detection in Test Samples using Standard Deviation and Unsupervised Training Set Selection

Mohseni¹,

Nematzadeh²,

Akbarib³

et al. 2023

IJE

View full text Add to dashboard Cite

Outlier detection is a technique to identify and remove significantly different data from the more correct and consistent data in a data set. Outlier data can have negative impact on classification and clustering performance; that should be identified and removed to improve the classification efficiency. Regardless of whether a classifying technique classifies an outlier correctly, the very notion of identifying a data as outlier is of great significance. In this paper, a new approach is proposed for outlier data detection within a test data set along with unsupervised training set selection. The selected training set is used for two-step classification. After unsupervised clustering the training set, the closest cluster to a test sample is selected using the Euclidean distance measure. Then, the outlier in the test sample is identified with the concepts of standard deviation and mean value. The results showed by evaluating the distance of each sample of the test set with the new selected data set. the accuracy of the classifiers is enhanced after detection and elimination of outlier data.

show abstract

“…Signal Dictionary Sparse Vector Unlike single-image classification algorithms, effective image-set methods [7,83] need to exploit the hidden structure among image sets additionally, e.g., the interand intra-set data variations. Furthermore, popular deep features tend to be generic and incorporate very little prior knowledge by learning from large-scale, high-quality, and fully annotated training datasets.…”

Section: Introductionmentioning

confidence: 99%

Image classification with limited data information

Cheng

View full text Add to dashboard Cite

and all the other members in LIV group and Rose lab for their accompanying. I enjoy the time spent with them, sharing knowledge and expertise, and offering encouragement during challenging times. They provide different perspectives and insights, enriching the overall work experience.Lastly, I would like to express my heartfelt gratitude to my beloved family and friends. I am deeply thankful to my parents and grandparents for their unwavering support and boundless love throughout my life.

show abstract

Image set classification using candidate sets selection and improved reverse training

Cited by 17 publications

References 21 publications

Automated lung ultrasound scoring for evaluation of coronavirus disease 2019 pneumonia using two-stage cascaded deep learning model

Automated lung ultrasound scoring for evaluation of coronavirus disease 2019 pneumonia using two-stage cascaded deep learning model

Outlier Detection in Test Samples using Standard Deviation and Unsupervised Training Set Selection

Image classification with limited data information

Contact Info

Product

Resources

About