A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications

L Alzubaidi, J Bai, A Al-Sabaawi, J Santamaría… - Journal of Big Data, 2023 - Springer
Data scarcity is a major challenge when training deep learning (DL) models. DL demands a
large amount of data to achieve exceptional performance. Unfortunately, many applications …

Phase-to-pattern inverse design paradigm for fast realization of functional metasurfaces via transfer learning

R Zhu, T Qiu, J Wang, S Sui, C Hao, T Liu, Y Li… - Nature …, 2021 - nature.com
Metasurfaces have provided unprecedented freedom for manipulating electromagnetic
waves. In metasurface design, massive meta-atoms have to be optimized to produce the …

A neural network based price sensitive recommender model to predict customer choices based on price effect

SS Chen, B Choubey, V Singh - Journal of Retailing and Consumer …, 2021 - Elsevier
The impact of price and price changes should not be ignored while designing algorithms for
predicting customer choice. Consumer preferences should be modeled with consideration of …

Improved quantile convolutional neural network with two-stage training for daily-ahead probabilistic forecasting of photovoltaic power

Q Huang, S Wei - Energy Conversion and Management, 2020 - Elsevier
Probabilistic forecasting is significant in coping with the strong uncertainty of photovoltaic
(PV) power, which provides the occurrence scope and corresponding probability information …

Ultrasonic lamination defects detection of carbon fiber composite plates based on multilevel LSTM

F Zhang, L Wang, W Ye, Y Li, F Yang - Composite Structures, 2024 - Elsevier
During the production of carbon fiber composites (CFC), various forming methods and
complex processes can introduce different types of defects, with lamination defects being a …

Designing optimal convolutional neural network architecture using differential evolution algorithm

A Ghosh, ND Jana, S Mallik, Z Zhao - Patterns, 2022 - cell.com
Convolutional neural networks (CNNs) are deep learning models used widely for solving
various tasks like computer vision and speech recognition. CNNs are developed manually …

Dc-cyclegan: bidirectional ct-to-mr synthesis from unpaired data

J Wang, QMJ Wu, F Pourpanah - Computerized Medical Imaging and …, 2023 - Elsevier
Magnetic resonance (MR) and computer tomography (CT) images are two typical types of
medical images that provide mutually-complementary information for accurate clinical …

Automated maxillofacial segmentation in panoramic dental x-ray images using an efficient encoder-decoder network

Z Kong, F Xiong, C Zhang, Z Fu, M Zhang, J Weng… - Ieee …, 2020 - ieeexplore.ieee.org
The panoramic dental X-ray images are an essential diagnostic tool used by dentists to
detect the symptoms in an early stage and develop appropriate treatment plans. In recent …

An attentive-based generative model for medical image synthesis

J Wang, QMJ Wu, F Pourpanah - International Journal of Machine …, 2023 - Springer
Magnetic resonance (MR) and computer tomography (CT) imaging are valuable tools for
diagnosing diseases and planning treatment. However, limitations such as radiation …

Deep learning for satellites based spectrum sensing systems: A low computational complexity perspective

X Ding, T Ni, Y Zou, G Zhang - IEEE Transactions on Vehicular …, 2022 - ieeexplore.ieee.org
We investigate a satellites-based spectrum sensing system in the presence of low signal-to-
noise ratio (SNR) conditions. Such a low SNR is also called SNR wall in the energy …