Tag: class imbalance

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 benchmark study combining entropy-guided partitioning, machine learning and fuzzy inference improved voice-based Parkinson’s disease classification on two public datasets.

INSIGHT combines mixed-distance clustering, cluster-aware oversampling and interpretability analyses to improve fraud detection in two financial transaction datasets.

A model-development study using 471 specialist nurse samples achieved an AUC of 0.766 for distinguishing stated transfer intentions, while highlighting ...

A deep-learning framework classified sleep stages from single-channel EEG with reported accuracies of 84.5% to 87.0% across three public datasets, ...

A hybrid CatBoost pipeline using synthetic sampling and optimized class weights achieved the strongest reported classification results in a 258-record ...

Researchers in China developed MP-CBA-YOLO, a morphology-preserving, class-balanced object detection method that grades ginseng roots with expert-level accuracy despite scarce ...

Researchers at VIT University propose AFI-ID, an intrusion detection framework that unifies adaptive feature selection with attention-based ensemble fusion, achieving ...

Researchers in India built a transformer-based deep learning system to detect anomalies in solar-wind power plants, achieving strong reconstruction accuracy ...

A 0.15-million-parameter attention-equipped neural network classifies nine wafer-map defect types with 99.88 percent accuracy on a CPU, combining latent-space augmentation ...