Artificial Intelligence

The ACDC dataset contains short-axis cardiac magnetic resonance imaging (MRI) images which are obtained from 100 patients. For each image, segmentation labels are provided for the left ventricle (LV), myocardium (Myo), and right ventricle (RV). From these, 70, 10, and 20 patient cases are randomly selected as the training, validation, and test sets, respectively.

This is the dataset of the paper: A Non-Invasive Circuit Breaker Arc Duration Measurement Method with Improved Robustness Based on Vibration–Sound Fusion and Convolutional Neural Network (https://doi.org/10.3390/en16186551). Here is the abstract of the paper. Previous studies have shown that the contact wear estimation of circuit breakers can be based on the accumulative arc duration. However, one problem that remains unresolved is how to reliably measure the arc duration.

While it is well known that population differences from genetics, sex, race, and environmental factors contribute to disease, AI studies in medicine have largely focused on locoregional patient cohorts with less diverse data sources. Such limitation stems from barriers to large-scale data share and ethical concerns over data privacy. Federated learning (FL) is one potential pathway for AI development that enables learning across hospitals without data share.

This data set is from the pictures collected at the industrial production site of the power adapter.The dataset contains surface defects such as scratches, glue spills, dirt, dirty spots, and off-frame labels that occur during the production process of the power adapter.  The original dataset contains 235 images with a height and width of 2448 and 2048, which are annotated in VOC2007 format. These defects were categorized into five classes: label, mark, scratch, smudge, and spill, with each class containing 32, 38, 58, 80, and 32 images.