Twenty years of machine-learning-based text classification: A systematic review

A Palanivinayagam, CZ El-Bayeh, R Damaševičius - Algorithms, 2023‏ - mdpi.com
Machine-learning-based text classification is one of the leading research areas and has a
wide range of applications, which include spam detection, hate speech identification …

Few-shot learning for facial expression recognition: a comprehensive survey

CL Kim, BG Kim - Journal of Real-Time Image Processing, 2023‏ - Springer
Facial expression recognition (FER) is utilized in various fields that analyze facial
expressions. FER is attracting increasing attention for its role in improving the convenience …

Nature vs. nurture: Feature vs. structure for graph neural networks

DC Thang, HT Dat, NT Tam, J Jo, NQV Hung… - Pattern Recognition …, 2022‏ - Elsevier
Graph neural networks take node features and graph structure as input to build
representations for nodes and graphs. While there are a lot of focus on GNN models …

Data augmentation for rolling bearing fault diagnosis using an enhanced few-shot Wasserstein auto-encoder with meta-learning

Z Pei, H Jiang, X Li, J Zhang, S Liu - Measurement Science and …, 2021‏ - iopscience.iop.org
Despite the advance of intelligent fault diagnosis for rolling bearings, in industries, data-
driven methods still suffer from data acquisition and imbalance. We propose an enhanced …

Few-shot short-text classification with language representations and centroid similarity

W Liu, J Pang, N Li, F Yue, G Liu - Applied Intelligence, 2023‏ - Springer
Aiming at the problems of insufficient labelled samples and low-generalization performance
in text classification tasks, this paper studies text classification problems under the condition …

Deep meta-learning and variational autoencoder for coupling fault diagnosis of rolling bearing under variable working conditions

C Che, H Wang, R Lin, X Ni - Proceedings of the Institution of …, 2022‏ - journals.sagepub.com
Considering the characteristics of rolling bearing such as variable working conditions,
unbalanced fault sample size, and multiple coupling fault types, it is a great challenge to …

Transfer learning and source domain restructuring-based BiLSTM approach for building energy consumption prediction

Y Yan, F Wang, C Tian, W Xue, L Lin… - International Journal of …, 2025‏ - Taylor & Francis
Currently, building energy consumption prediction typically relies on vast amounts of
historical data. However, for newly constructed buildings, the scarcity of data leads to …

IDA-NET: Individual Difference aware Medical Image Segmentation with Meta-Learning

Z Zhang, G Yin, Z Ma, Y Tan, B Zhang… - Pattern Recognition …, 2025‏ - Elsevier
Individual differences in organ size and spatial distribution can lead to significant variations
in the content of medical images at similar anatomical locations. These case-level …

A Chinese few-shot text classification method utilizing improved prompt learning and unlabeled data

T Hu, Z Chen, J Ge, Z Yang, J Xu - Applied Sciences, 2023‏ - mdpi.com
Insufficiently labeled samples and low-generalization performance have become significant
natural language processing problems, drawing significant concern for few-shot text …

HDGN: Heat diffusion graph network for few-shot learning

Q Tan, Z Wu, J Lai, Z Liang, Z Ren - Pattern Recognition Letters, 2023‏ - Elsevier
A heat diffusion graph network (HDGN) is proposed in this paper, which retains more similar
graph signals in the spectral domain, for few-shot learning. Convolution on the graph is …