Study on Unbalanced Binary Classification with Unknown Misclassification Costs

Gao, Jianlei; Gong, Lin; Wang, J. Y.; Mo, Zhenchong

doi:10.1109/ieem.2018.8607671

Cited by 8 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use the ADAM optimizer 47 and a loss function of binary cross entropy with logits loss 48 . We find that giving a higher weight to learning positive predictions stabilizes training and accelerates convergence 49 .…”

Section: Training Model By the Rough Manually Labeled Datamentioning

confidence: 80%

U-Net Based Vortex Detection in Bose-Einstein Condensates with Automatic Correction for Manually Mislabeled Data

Ye,

Huang,

Liu

2023

Preprint

View full text Add to dashboard Cite

Quantum vortices in Bose-Einstein condensates (BECs) are essential phenomena in condensed matter physics, and precisely locating their positions, especially the vortex core, is a prerequisite for studying their properties. With the rise of machine learning, there is a potential to expedite the localization process and provide accurate predictions. However, traditional machine learning requires a considerable amount of manual data annotation, leading to uncontrollable accuracy. In this paper, we utilize the U-Net method to detect vortex positions accurately at the pixel level and propose an Automatic Correction Labeling (ACL) approach to optimize the acquisition of data sets for vortex localization in BECs. This approach addresses inaccuracies in the labeled vortex positions and improves the accuracy of vortex localization, especially the vortex core positions, while enhancing the tolerance for human labeling. The main process involves Rough Labeling -- Machine Learning -- Probability Region Search -- Data Relabeling -- Machine Learning again. The objective of ACL is to obtain more accurate labeled data for model retraining. Through vortex localization experiments conducted in a two-dimensional Bose-Einstein condensate, our results demonstrate the following: 1. Even under conditions of biased and missing manual annotations, U-Net can still accurately locate vortex positions; 2. Vortices exhibit certain regularities, and training U-Net with a small number of samples yields excellent predictive results; 3. The machine learning vortex locator based on the iterative ACL method effectively corrects errors in manually annotated data, significantly improving the model's performance metrics, thus enhancing the precision and metrics of vortex localization. This substantial advancement in the application of machine learning in vortex localization provides an effective approach for vortex dynamics localization. Furthermore, this method of obtaining more accurate approximate human labels through machine learning offers new insights for machine learning in other types of image recognition problems.

show abstract

Section: Training Model By the Rough Manually Labeled Datamentioning

confidence: 80%

U-Net Based Vortex Detection in Bose-Einstein Condensates with Automatic Correction for Manually Mislabeled Data

Ye,

Huang,

Liu

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…We use the ADAM optimizer 48 and a loss function of binary cross entropy with logits loss 49 . We have determined that giving a higher weight to learning positive predictions stabilizes training and accelerates convergence 50 , stabilizes training and accelerates convergence 50 . , where white circles in (a) correspond to the manual labeling and red dots in (b) to the prediction of the trained model.…”

Section: Training Model By the Rough Manually Labeled Datamentioning

confidence: 99%

U-net based vortex detection in Bose–Einstein condensates with automatic correction for manually mislabeled data

Ye,

Huang,

Liu

2023

Sci Rep

View full text Add to dashboard Cite

Quantum vortices in Bose–Einstein condensates (BECs) are essential phenomena in condensed matter physics, and precisely locating their positions, especially the vortex core, is a precondition for studying their properties. With the rise of machine learning, there is a possibility to expedite the localization process and provide accurate predictions. However, traditional machine learning requires particular considerable amount of manual data annotation, leading to uncontrollable accuracy. In this paper, we utilize the U-Net method to detect vortex positions accurately at the pixel level and propose an Automatic Correction Labeling (ACL) approach to optimize the acquisition of data sets for vortex localization in BECs. This approach addresses inaccuracies in the labeled vortex positions and improves the accuracy of vortex localization, especially the vortex core positions, while enhancing the tolerance for human mislabeling. The main process involves Rough Labeling$$\rightarrow $$→Machine Learning$$\rightarrow $$→Probability Region Search$$\rightarrow $$→Data Relabeling$$\rightarrow $$→Machine Learning again. The objective of ACL is to secure more accurate labeled data for model retraining. Through vortex localization experiments conducted in a two-dimensional Bose-Einstein condensate, our results establish the following: 1. Even under conditions of biased and missing manual annotations, U-Net can still accurately locate vortex positions; 2. Vortices exhibit certain regularities, and training U-Net with a small number of samples yields excellent predictive consequences; 3. The machine learning vortex locator based on the ACL method effectively corrects errors in manually annotated data, significantly improving the model’s performance metrics, thus enhancing the precision and metrics of vortex localization. This substantial advancement in the application of machine learning in vortex localization provides an effective way for vortex dynamics localization. Furthermore, this method of obtaining more accurate positions of approximate human labels through machine learning offers new insights for machine learning in other types of image recognition problems.

show abstract

“…The equal class distribution in the target variable is a critical issue to avoid the miss-classification problem since fraud transactions are uncommon in most datasets. ML algorithms can easily find their regularities in large datasets compared to small datasets [25]. The overlapped attribute values also create problems in a large number of transactions.…”

Section: Literature Reviewmentioning

confidence: 99%

Ensemble Learning with Supervised Machine Learning Models to Predict Credit Card Fraud Transactions

Baker¹,

Mahmood²,

Shaker³

2022

RIA

View full text Add to dashboard Cite

In recent years, the highly boosting development in e-commerce technologies made it possible for people to select the most desirable items from shops and stores worldwide while being at home. Credit card frauds transactions are common nowadays because of online payments. Online transactions are the root cause of fraudulent credit card activity, bringing enormous financial losses. Financial institutions must install an automatic deterrent mechanism to check these fraudulent actions. The fraudulent transactions do not follow a specific pattern and continuously change their shape and behavior. This paper aims to use ensemble learning with supervised Machine Learning (ML) models to predict the occurrence of fraud transactions. The experimental study has been evaluated on the open-source Kaggle credit card fraud detection dataset. The performance of the proposed model is measured in terms of accuracy score, confusion matrix, and classification report. The results were state-of-the-art using the voting ensemble learning technique shows that it can be get the best results using PCA with 100.0% accuracy, 97.3% precision, 73.5% recall, and 83.7% f1-score against other ML classifiers.

show abstract

Study on Unbalanced Binary Classification with Unknown Misclassification Costs

Cited by 8 publications

References 6 publications

U-Net Based Vortex Detection in Bose-Einstein Condensates with Automatic Correction for Manually Mislabeled Data

U-Net Based Vortex Detection in Bose-Einstein Condensates with Automatic Correction for Manually Mislabeled Data

U-net based vortex detection in Bose–Einstein condensates with automatic correction for manually mislabeled data

Ensemble Learning with Supervised Machine Learning Models to Predict Credit Card Fraud Transactions

Contact Info

Product

Resources

About