Interpretation of intelligence in CNN-pooling processes: a methodological survey

N Akhtar, U Ragavendran - Neural computing and applications, 2020 - Springer
The convolutional neural network architecture has different components like convolution and
pooling. The pooling is crucial component placed after the convolution layer. It plays a vital …

Deep concatenated residual network with bidirectional LSTM for one-hour-ahead wind power forecasting

MS Ko, K Lee, JK Kim, CW Hong… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
This paper presents a deep residual network for improving time-series forecasting models,
indispensable to reliable and economical power grid operations, especially with high shares …

A deep one-dimensional convolutional neural network for microplastics classification using Raman spectroscopy

W Zhang, W Feng, Z Cai, H Wang, Q Yan… - Vibrational …, 2023 - Elsevier
Microplastics have emerged as major global environmental contaminations. Finding
accurate and effective identification methods for microplastics is of great significance. In this …

Deep independently recurrent neural network (indrnn)

S Li, W Li, C Cook, Y Gao - arxiv preprint arxiv:1910.06251, 2019 - arxiv.org
Recurrent neural networks (RNNs) are known to be difficult to train due to the gradient
vanishing and exploding problems and thus difficult to learn long-term patterns and …

Multi-task learning model based on recurrent convolutional neural networks for citation sentiment and purpose classification

A Yousif, Z Niu, J Chambua, ZY Khan - Neurocomputing, 2019 - Elsevier
Automated citation analysis is a method of identifying sentiment and purpose of citations in
the citing works. Most of the existing approaches use machine learning techniques to boost …

IndRNN based long-term temporal recognition in the spatial and frequency domain

B Zhao, S Li, Y Gao - Adjunct Proceedings of the 2020 ACM International …, 2020 - dl.acm.org
This paper targets the SHL recognition challenge, which focuses on the location-
independent and user-independent activity recognition using smartphone sensors. To …

Smartphone-sensors based activity recognition using IndRNN

S Li, C Li, W Li, Y Hou, C Cook - … of the 2018 ACM International Joint …, 2018 - dl.acm.org
Human activity recognition based on the smartphone sensors has the potential to impact a
wide range of applications such as healthcare, smart home, and remote monitoring. For …

An explicit self-attention-based multimodality CNN in-loop filter for versatile video coding

M Jia, Y Gao, S Li, J Yue, M Ye - Multimedia Tools and Applications, 2022 - Springer
The newest video coding standard, versatile video coding (VVC), has just been published
recently. While it greatly improves the performance over the last High Efficiency Video …

Narrow band time–frequency space matched passive detector for underwater signal

Y Haiyang, Z Zhichen, W Haiyan, W Yong - Applied Acoustics, 2021 - Elsevier
Passive target detection under low signal-to-noise ratio is essential in various underwater
circumstances, but difficult as lacking of targets' prior information, special propagation …

[HTML][HTML] Multi-channel delineation of intracardiac electrograms for arrhythmia substrate analysis using implicitly regularized convolutional neural network with wide …

J Hejc, R Redina, J Kolarova, Z Starek - Biomedical Signal Processing and …, 2024 - Elsevier
Objective Automated segmentation of intracardiac electrograms and extraction of
fundamental cycle length intervals is crucial for reproducible arrhythmia substrate analysis …