Diagnosisformer: An efficient rolling bearing fault diagnosis method based on improved transformer

Y Hou, J Wang, Z Chen, J Ma, T Li - Engineering Applications of Artificial …, 2023 - Elsevier
Aiming at the problems of low accuracy and robustness of traditional deep learning fault
diagnosis methods, a novel attention-based multi-feature parallel fusion model …

Diachronic word embeddings and semantic shifts: a survey

A Kutuzov, L Øvrelid, T Szymanski, E Velldal - ar** an intelligent cloud attention network to support global urban green spaces map**
Y Chen, Q Weng, L Tang, L Wang, H **ng… - ISPRS Journal of …, 2023 - Elsevier
Urban green spaces (UGS) play an important role in understanding of urban ecosystems,
climate, environment, and public health concerns. Satellite derived UGS maps provide an …

Learning with recoverable forgetting

J Ye, Y Fu, J Song, X Yang, S Liu, X **, M Song… - … on Computer Vision, 2022 - Springer
Life-long learning aims at learning a sequence of tasks without forgetting the previously
acquired knowledge. However, the involved training data may not be life-long legitimate due …

[PDF][PDF] Classification of Images of Childhood Pneumonia using Convolutional Neural Networks.

AA Saraiva, NMF Ferreira, LL De Sousa, NJC Costa… - Bioimaging, 2019 - scitepress.org
In this paper we describe a comparative classification of Pneumonia using Convolution
Neural Network. The database used was the dataset Labeled Optical Coherence …

Leveraging contextual embeddings for detecting diachronic semantic shift

M Martinc, PK Novak, S Pollak - arxiv preprint arxiv:1912.01072, 2019 - arxiv.org
We propose a new method that leverages contextual embeddings for the task of diachronic
semantic shift detection by generating time specific word representations from BERT …

Class-incremental domain adaptation

JN Kundu, RM Venkatesh, N Venkat, A Revanur… - Computer Vision–ECCV …, 2020 - Springer
We introduce a practical Domain Adaptation (DA) paradigm called Class-Incremental
Domain Adaptation (CIDA). Existing DA methods tackle domain-shift but are unsuitable for …

Hierarchical graph transformer-based deep learning model for large-scale multi-label text classification

J Gong, Z Teng, Q Teng, H Zhang, L Du, S Chen… - IEEE …, 2020 - ieeexplore.ieee.org
Traditional methods of multi-label text classification, particularly deep learning, have
achieved remarkable results. However, most of these methods use word2vec technology to …

Hybrid covid-19 segmentation and recognition framework (hmb-hcf) using deep learning and genetic algorithms

HM Balaha, MH Balaha, HA Ali - Artificial Intelligence in Medicine, 2021 - Elsevier
Abstract COVID-19 (Coronavirus) went through a rapid escalation until it became a
pandemic disease. The normal and manual medical infection discovery may take few days …

SD-GAN: A style distribution transfer generative adversarial network for Covid-19 detection through X-ray images

T Kausar, Y Lu, A Kausar, M Ali, A Yousaf - IEEE Access, 2023 - ieeexplore.ieee.org
The Covid-19 pandemic is a prevalent health concern around the world in recent times.
Therefore, it is essential to screen the infected patients at the primary stage to prevent …