Tag: multi-label classification

A fine-tuned VGG16 network achieved 84.0 percent subset accuracy and an 85.2 percent micro-averaged F1-score on a held-out test set ...

FewShot AdaptiveMLC raised macro-F1 by 0.072 on a multi-label Bangla hate speech dataset by fine-tuning task-specific heads for minority labels ...

A nine-model benchmark found that knowledge-guided reflective prompting modestly improved average reconstruction of 22 Traditional Chinese Medicine tongue signs, while ...

Researchers have built an AI pipeline that digitizes paper-based complete blood count reports with PaddleOCR and uses tuned machine learning ...

A new FCN-GRU-Attention deep learning model with a confidence correction mechanism identifies overlapping composite power quality disturbances with over 99 ...

Researchers at Lorestan University have combined ant colony optimization, reinforcement learning, and opposition-based learning in a semi-supervised framework that improves ...

A machine learning framework combining random forest prediction, neural network defect screening, and evolutionary optimization raised casting qualification rates to ...

A sweeping new review in Vicinagearth charts the rise of multi-dimensional classification, the machine learning paradigm that labels objects along ...

The first PRISMA-compliant systematic review of classifier chains maps seventeen years of multi-label learning research, comparing 18 variants, formalizing error ...

Researchers at the University of Sassari have developed PSDFS, a feature-selection method that splits each feature into above- and below-mean ...