Image quality assessment for machine learning tasks using meta-reinforcement learning

Saeed, Shaheer U.; Fu, Yunguan; Stavrinides, Vasilis; Baum, Zachary M. C.; Yang, Qianye; Rusu, Mirabela; Fan, Richard E.; Sonn, Geoffrey A.; Noble, J. Alison; Barratt, Dean C.; Hu, Yipeng

doi:10.1016/j.media.2022.102427

Cited by 31 publications

(14 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A deep learning structure suitable for IMU-based HAR was introduced in the DVE, and a predictor was added to construct the data valuation algorithm. In previous studies [ 26 , 29 , 30 ], vision-related public datasets were used primarily, because the purpose of the data valuation algorithm was limited to improve image classification. In this study, HAR data, which is multivariate timeseries data derived from human movements, is targeted.…”

Section: Discussionmentioning

confidence: 99%

“…Hendrycks [ 28 ] corrected the labels of corrupted label data using a clean validation set and re-trained the model using the corrected training data. Saeed [ 29 ] used a neural network-based task predictor for image segmentation and classification to update the neural network-based image quality assessment (IQA) controller for medical image data. The authors performed meta-reinforcement learning for newly added data or meta-task data to fine-tune the IQA controller network using the task performance of the predictor.…”

Section: Introductionmentioning

confidence: 99%

“…This method exhibited better performance and efficiency than LOO [ 25 ] and Data Shapley [ 26 ]. Previous data valuation algorithm studies [ 26 , 29 , 30 ] primarily dealt with public image datasets and insufficiently dealt with other types of data, such as time series data and data with a small number of samples.…”

Section: Introductionmentioning

confidence: 99%

“…The IMU-based HAR algorithm, which is a type of pattern recognition algorithm, recognizes the type and quality of motion based on the IMU data collected using wearable devices. Previous studies on data valuation algorithms have primarily utilized vision-based public datasets [ 26 , 29 , 30 ]. However, IMU-based HAR data have not been investigated yet.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Data Valuation Algorithm for Inertial Measurement Unit-Based Human Activity Recognition

Kim

Lee

2022

Sensors

View full text Add to dashboard Cite

This paper proposes a data valuation algorithm for inertial measurement unit-based human activity recognition (IMU-based HAR) data based on meta reinforcement learning. Unlike previous studies that received feature-level input, the algorithm in this study added a feature extraction structure to the data valuation algorithm, and it can receive raw-level inputs and achieve excellent performance. As IMU-based HAR data are multivariate time-series data, the proposed algorithm incorporates an architecture capable of extracting both local and global features by inserting a transformer encoder after the one-dimensional convolutional neural network (1D-CNN) backbone in the data value estimator. In addition, the 1D-CNN-based stacking ensemble structure, which exhibits excellent efficiency and performance on IMU-based HAR data, is used as a predictor to supervise model training. The Berg balance scale (BBS) IMU-based HAR dataset and the public datasets, UCI-HAR, WISDM, and PAMAP2, are used for performance evaluation in this study. The valuation performance of the proposed algorithm is observed to be excellent on IMU-based HAR data. The rate of discovering corrupted data is higher than 96% on all datasets. In addition, classification performance is confirmed to be improved by the suppression of discovery of low-value data.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Data Valuation Algorithm for Inertial Measurement Unit-Based Human Activity Recognition

Kim

Lee

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…According to professional organizations such as the Radiological Society of North America and the American Association of Physicists in Medicine, the systematic curation of high-quality image datasets affects AI development speed [ 52 ]. Therefore, caution should be taken not to use low-quality image data, including low-resolution, excessively small, and noisy images, for analysis and evaluation [ 53 ].…”

Section: Machine Learning Algorithms Trained On Image Datamentioning

confidence: 99%

Use of Machine Learning in Stroke Rehabilitation: A Narrative Review

Choo

Lee

2022

Brain Neurorehabil

View full text Add to dashboard Cite

A narrative review was conducted of machine learning applications and research in the field of stroke rehabilitation. The machine learning models commonly used in medical research include random forest, logistic regression, and deep neural networks. Convolutional neural networks (CNNs), a type of deep neural network, are typically used for image analysis. Machine learning has been used in stroke rehabilitation to predict recovery of motor function using a large amount of clinical data as input. Recent studies on predicting motor function have trained CNN models using magnetic resonance images as input data together with clinical data to increase the accuracy of motor function prediction models. Additionally, a model interpreting videofluoroscopic swallowing studies was developed and investigated. In the future, we anticipate that machine learning will be actively used to treat stroke patients, such as predicting the occurrence of depression and the recovery of language, cognitive, and sensory function, as well as prescribing appropriate rehabilitation treatments.

show abstract

Segmentation by Registration-Enabled SAM Prompt Engineering Using Five Reference Images

Chen,

Ivanova,

Saeed

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Image quality assessment for machine learning tasks using meta-reinforcement learning

Cited by 31 publications

References 38 publications

Data Valuation Algorithm for Inertial Measurement Unit-Based Human Activity Recognition

Data Valuation Algorithm for Inertial Measurement Unit-Based Human Activity Recognition

Use of Machine Learning in Stroke Rehabilitation: A Narrative Review

Segmentation by Registration-Enabled SAM Prompt Engineering Using Five Reference Images

Contact Info

Product

Resources

About