Skip to Content
You are currently on the new version of our website. Access the old version .

195 Results Found

  • Article
  • Open Access
1 Citations
1,490 Views
16 Pages

31 December 2025

When training a neural network, the choice of activation function can greatly impact its performance. A function with a larger derivative may cause the coefficients of the latter layers to deviate further from the calculated direction, making deep le...

(This article belongs to the Section Information Theory, Probability and Statistics)
  • Article
  • Open Access
6 Citations
2,054 Views
15 Pages

Inkjet-printed circuits on flexible substrates are rapidly emerging as a key technology in flexible electronics, driven by their minimal fabrication process, cost-effectiveness, and environmental sustainability. Recent advancements in inkjet-printed...

  • Article
  • Open Access
25 Citations
7,142 Views
13 Pages

Convolutional neural networks (CNNs) are widely used among the various deep learning techniques available because of their superior performance in the fields of computer vision and natural language processing. CNNs can effectively extract the localit...

(This article belongs to the Section Machine Learning)
  • Article
  • Open Access
6 Citations
5,147 Views
15 Pages

30 June 2020

In this paper, we propose a new network model using variational learning to improve the learning stability of generative adversarial networks (GAN). The proposed method can be easily applied to improve the learning stability of GAN-based models that...

(This article belongs to the Special Issue Deep Learning Applied to Image Processing)
  • Article
  • Open Access
32 Citations
5,928 Views
19 Pages

10 February 2023

The Squeeze-and-Excitation (SE) structure has been designed to enhance the neural network performance by allowing it to execute positive channel-wise feature recalibration and suppress less useful features. SE structures are generally adopted in a pl...

  • Feature Paper
  • Article
  • Open Access
353 Views
26 Pages

27 May 2026

In this paper, we establish the global existence and uniqueness of strong solutions to the one-dimensional vacuum free boundary problem for the isentropic compressible liquid crystal equations under the influence of gravity with large initial data, w...

  • Article
  • Open Access
2 Citations
2,978 Views
21 Pages

BinVPR: Binary Neural Networks towards Real-Valued for Visual Place Recognition

  • Junshuai Wang,
  • Junyu Han,
  • Ruifang Dong and
  • Jiangming Kan

25 June 2024

Visual Place Recognition (VPR) aims to determine whether a robot or visual navigation system locates in a previously visited place using visual information. It is an essential technology and challenging problem in computer vision and robotic communit...

(This article belongs to the Section Navigation and Positioning)
  • Article
  • Open Access
6 Citations
3,256 Views
19 Pages

PermLSTM: A High Energy-Efficiency LSTM Accelerator Architecture

  • Yong Zheng,
  • Haigang Yang,
  • Yiping Jia and
  • Zhihong Huang

Pruning and quantization are two commonly used approaches to accelerate the LSTM (Long Short-Term Memory) model. However, the traditional linear quantization usually suffers from the problem of gradient vanishing, and the existing pruning methods all...

(This article belongs to the Section Circuit and Signal Processing)
  • Article
  • Open Access
9 Citations
3,552 Views
19 Pages

30 October 2019

Exo-atmospheric infrared (IR) point target discrimination is an important research topic of space surveillance systems. It is difficult to describe the characteristic information of the shape and micro-motion states of the targets and to discriminate...

(This article belongs to the Special Issue Emerging Artificial Intelligence (AI) Technologies for Learning)
  • Article
  • Open Access
12 Citations
3,083 Views
15 Pages

An Indoor Localization System Using Residual Learning with Channel State Information

  • Chendong Xu,
  • Weigang Wang,
  • Yunwei Zhang,
  • Jie Qin and ,
  • Shujuan Yu and
  • Yun Zhang
  • + 1 author+ 0 author

7 May 2021

With the increasing demand of location-based services, neural network (NN)-based intelligent indoor localization has attracted great interest due to its high localization accuracy. However, deep NNs are usually affected by degradation and gradient va...

(This article belongs to the Section Signal and Data Analysis)
  • Article
  • Open Access
25 Citations
4,033 Views
18 Pages

Efficient Skip Connections-Based Residual Network (ESRNet) for Brain Tumor Classification

  • Ashwini B.,
  • Manjit Kaur,
  • Dilbag Singh,
  • Satyabrata Roy and
  • Mohammed Amoon

17 October 2023

Brain tumors pose a complex and urgent challenge in medical diagnostics, requiring precise and timely classification due to their diverse characteristics and potentially life-threatening consequences. While existing deep learning (DL)-based brain tum...

(This article belongs to the Special Issue Artificial Intelligence in Clinical Medical Imaging)
  • Article
  • Open Access
24 Citations
4,749 Views
26 Pages

An Improved Bees Algorithm for Training Deep Recurrent Networks for Sentiment Classification

  • Sultan Zeybek,
  • Duc Truong Pham,
  • Ebubekir Koç and
  • Aydın Seçer

26 July 2021

Recurrent neural networks (RNNs) are powerful tools for learning information from temporal sequences. Designing an optimum deep RNN is difficult due to configuration and training issues, such as vanishing and exploding gradients. In this paper, a nov...

(This article belongs to the Special Issue Computational Intelligence and Soft Computing: Recent Applications)
  • Article
  • Open Access
3 Citations
3,027 Views
22 Pages

3 April 2024

The theory of forward–backward stochastic differential equations occupies an important position in stochastic analysis and practical applications. However, the numerical solution of forward–backward stochastic differential equations, espe...

(This article belongs to the Section E1: Mathematics and Computer Science)
  • Article
  • Open Access
1 Citations
798 Views
36 Pages

13 March 2026

Industrial-Internet security faces a core challenge: improving detection accuracy for critical minority-class network attacks. The existing intrusion detection methods based on Conditional Generative Adversarial Nets (CGANs) aim to achieve data balan...

  • Feature Paper
  • Article
  • Open Access
62 Citations
8,426 Views
8 Pages

24 April 2020

Convolutional neural networks (CNNs) have made great achievements on computer vision tasks, especially the image classification. With the improvement of network structure and loss functions, the performance of image classification is getting higher a...

(This article belongs to the Special Issue Advanced Intelligent Imaging Technology Ⅱ)
  • Article
  • Open Access
26 Citations
4,273 Views
20 Pages

Contourlet-CNN for SAR Image Despeckling

  • Gang Liu,
  • Hongzhaoning Kang,
  • Quan Wang,
  • Yumin Tian and
  • Bo Wan

19 February 2021

A multiscale and multidirectional network named the Contourlet convolutional neural network (CCNN) is proposed for synthetic aperture radar (SAR) image despeckling. SAR image resolution is not higher than that of optical images. If the network depth...

(This article belongs to the Section Remote Sensing Image Processing)
  • Article
  • Open Access
1 Citations
1,798 Views
17 Pages

20 December 2024

Diagnosing faults in wheelset bearings is critical for train safety. The main challenge is that only a limited amount of fault sample data can be obtained during high-speed train operations. This scarcity of samples impacts the training and accuracy...

(This article belongs to the Section Multidisciplinary Applications)
  • Article
  • Open Access
8 Citations
3,655 Views
21 Pages

Research and Application of ROM Based on Res-PINNs Neural Network in Fluid System

  • Yuhao Liu,
  • Junjie Hou,
  • Ping Wei,
  • Jie Jin and
  • Renjie Zhang

22 January 2025

In the design of fluid systems, rapid iteration and simulation verification are essential, and reduced-order modeling techniques can significantly improve computational efficiency and accuracy. However, traditional Physics-Informed Neural Networks (P...

(This article belongs to the Topic Applications of Machine Learning in Large-Scale Optimization and High-Dimensional Learning)
  • Article
  • Open Access
7 Citations
3,788 Views
15 Pages

CostNet: A Concise Overpass Spatiotemporal Network for Predictive Learning

  • Fengzhen Sun,
  • Shaojie Li,
  • Shaohua Wang,
  • Qingjun Liu and
  • Lixin Zhou

Predicting the futures from previous spatiotemporal data remains a challenging topic. There have been many previous works on predictive learning. However, mainstream models suffer from huge memory usage or the gradient vanishing problem. Enlightened...

  • Article
  • Open Access
96 Citations
8,156 Views
20 Pages

5 December 2019

The current literature of remote sensing (RS) scene classification shows that state-of-the-art results are achieved using feature extraction methods, where convolutional neural networks (CNNs) (mostly VGG16 with 138.36 M parameters) are used as featu...

(This article belongs to the Section Remote Sensing Image Processing)
  • Article
  • Open Access
9 Citations
4,244 Views
15 Pages

ReLU Neural Networks and Their Training

  • Ge Luo,
  • Xugang Wang,
  • Weizun Zhao,
  • Sichen Tao and
  • Zheng Tang

22 December 2025

Among various activation functions, the Rectified Linear Unit (ReLU) has become the most widely adopted due to its computational simplicity and effectiveness in mitigating the vanishing-gradient problem. In this work, we investigate the advantages of...

(This article belongs to the Section E: Applied Mathematics)
  • Article
  • Open Access
10 Citations
4,907 Views
25 Pages

Multi-Level Feature Extraction Networks for Hyperspectral Image Classification

  • Shaoyi Fang,
  • Xinyu Li,
  • Shimao Tian,
  • Weihao Chen and
  • Erlei Zhang

4 February 2024

Hyperspectral image (HSI) classification plays a key role in the field of earth observation missions. Recently, transformer-based approaches have been widely used for HSI classification due to their ability to model long-range sequences. However, the...

(This article belongs to the Special Issue Object Detection and Information Extraction Based on Remote Sensing Imagery)
  • Article
  • Open Access
16 Citations
5,087 Views
18 Pages

Optimizing Recurrent Neural Networks: A Study on Gradient Normalization of Weights for Enhanced Training Efficiency

  • Xinyi Wu,
  • Bingjie Xiang,
  • Huaizheng Lu,
  • Chaopeng Li and ,
  • Xingwang Huang and
  • Weifang Huang
  • + 1 author+ 0 author

27 July 2024

Recurrent Neural Networks (RNNs) are classical models for processing sequential data, demonstrating excellent performance in tasks such as natural language processing and time series prediction. However, during the training of RNNs, the issues of van...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
40 Citations
6,594 Views
22 Pages

1 May 2021

The high-fidelity attenuation of random ground penetrating radar (GPR) noise is important for enhancing the signal-noise ratio (SNR). In this paper, a novel network structure for convolutional denoising autoencoders (CDAEs) was proposed to effectivel...

(This article belongs to the Special Issue Advanced Techniques for Ground Penetrating Radar Imaging)
  • Article
  • Open Access
64 Citations
7,778 Views
16 Pages

30 October 2018

The Recurrent Neural Network (RNN) utilizes dynamically changing time information through time cycles, so it is very suitable for tasks with time sequence characteristics. However, with the increase of the number of layers, the vanishing gradient occ...

  • Article
  • Open Access
2 Citations
3,333 Views
9 Pages

27 May 2020

Regarding the sequence learning of neural networks, there exists a problem of how to capture long-term dependencies and alleviate the gradient vanishing phenomenon. To manage this problem, we proposed a neural network with random connections via a sc...

  • Article
  • Open Access
1,545 Views
22 Pages

Welding Image Data Augmentation Method Based on LRGAN Model

  • Ying Wang,
  • Zhe Dai,
  • Qiang Zhang and
  • Zihao Han

19 June 2025

This study focuses on the data bottleneck issue in the training of deep learning models during the intelligent welding control process and proposes an improved model called LRGAN (loss reconstruction generative adversarial networks). First, a five-la...

(This article belongs to the Section Robotics and Automation)
  • Article
  • Open Access
2 Citations
1,464 Views
20 Pages

An Invariant of Riemannian Type for Legendrian Warped Product Submanifolds of Sasakian Space Forms

  • Fatemah Abdullah Alghamdi,
  • Lamia Saeed Alqahtani,
  • Ali H. Alkhaldi and
  • Akram Ali

21 November 2023

In the present paper, we investigate the geometry and topology of warped product Legendrian submanifolds in Sasakian space forms D2n+1(ϵ) and obtain the first Chen inequality that involves extrinsic invariants like the mean curvature and the length o...

(This article belongs to the Special Issue Differential Geometry: Structures on Manifolds and Submanifolds)
  • Article
  • Open Access
11 Citations
3,611 Views
14 Pages

23 November 2022

This paper proposes a novel method monitoring network packets to classify anomalies in industrial control systems (ICSs). The proposed method combines different mechanisms. It is flow-based as it obtains new features through aggregating packets of th...

(This article belongs to the Special Issue Artificial Intelligence and Deep Learning in Sensors and Applications)
  • Article
  • Open Access
4 Citations
2,953 Views
18 Pages

A Scalable Bayesian Sampling Method Based on Stochastic Gradient Descent Isotropization

  • Giulio Franzese,
  • Dimitrios Milios,
  • Maurizio Filippone and
  • Pietro Michiardi

28 October 2021

Stochastic gradient sg-based algorithms for Markov chain Monte Carlo sampling (sgmcmc) tackle large-scale Bayesian modeling problems by operating on mini-batches and injecting noise on sgsteps. The sampling properties of these algorithms are determin...

(This article belongs to the Special Issue Approximate Bayesian Inference)
  • Article
  • Open Access
8 Citations
1,687 Views
31 Pages

Detection of Subarachnoid Hemorrhage Using CNN with Dynamic Factor and Wandering Strategy-Based Feature Selection

  • Jewel Sengupta,
  • Robertas Alzbutas,
  • Tomas Iešmantas,
  • Vytautas Petkus and ,
  • Alina Barkauskienė,
  • Vytenis Ratkūnas,
  • Saulius Lukoševičius,
  • Aidanas Preikšaitis,
  • Indre Lapinskienė and
  • Algis Džiugys
  • + 9 authors+ 4 authors

30 October 2024

Objectives: Subarachnoid Hemorrhage (SAH) is a serious neurological emergency case with a higher mortality rate. An automatic SAH detection is needed to expedite and improve identification, aiding timely and efficient treatment pathways. The existenc...

(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
  • Article
  • Open Access
1 Citations
859 Views
16 Pages

16 March 2026

The proliferation of next-generation Internet infrastructures and the Internet of Things (IoT) has exponentially increased network traffic complexity. While deep learning (DL)-based intrusion detection systems (IDSs) show immense potential, they pers...

(This article belongs to the Section Cybersecurity)
  • Article
  • Open Access
17 Citations
4,322 Views
20 Pages

Electric Load Forecasting Based on Deep Ensemble Learning

  • Aoqiang Wang,
  • Qiancheng Yu,
  • Jinyun Wang,
  • Xulong Yu and ,
  • Zhici Wang and
  • Zhiyong Hu
  • + 1 author+ 0 author

28 August 2023

Short-to-medium-term electric load forecasting is crucial for grid planning, transformation, and load scheduling for power supply departments. Various complex and ever-changing factors such as weather, seasons, regional economic structures, and enter...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
7 Citations
5,774 Views
21 Pages

18 April 2018

Recurrent neural networks (RNNs) remain challenging, and there is still a lack of long-term memory or learning ability in sequential data classification and prediction. In this paper, we propose a flexible recurrent model, BIdirectional COnvolutional...

  • Article
  • Open Access
9 Citations
2,681 Views
9 Pages

Progress towards Analytically Optimal Angles in Quantum Approximate Optimisation

  • Daniil Rabinovich,
  • Richik Sengupta,
  • Ernesto Campos,
  • Vishwanathan Akshay and
  • Jacob Biamonte

26 July 2022

The quantum approximate optimisation algorithm is a p layer, time variable split operator method executed on a quantum processor and driven to convergence by classical outer-loop optimisation. The classical co-processor varies individual application...

(This article belongs to the Special Issue Quantum Computing Algorithms and Computational Complexity)
  • Article
  • Open Access
40 Citations
6,166 Views
19 Pages

Going Deeper with Densely Connected Convolutional Neural Networks for Multispectral Pansharpening

  • Dong Wang,
  • Ying Li,
  • Li Ma,
  • Zongwen Bai and
  • Jonathan Cheung-Wai Chan

7 November 2019

In recent years, convolutional neural networks (CNNs) have shown promising performance in the field of multispectral (MS) and panchromatic (PAN) image fusion (MS pansharpening). However, the small-scale data and the gradient vanishing problem have be...

(This article belongs to the Section Remote Sensing Image Processing)
  • Article
  • Open Access
6 Citations
3,927 Views
13 Pages

Efficient Fire Detection with E-EFNet: A Lightweight Deep Learning-Based Approach for Edge Devices

  • Haleem Farman,
  • Moustafa M. Nasralla,
  • Sohaib Bin Altaf Khattak and
  • Bilal Jan

4 December 2023

Fire detection employing vision sensors has drawn significant attention within the computer vision community, primarily due to its practicality and utility. Previous research predominantly relied on basic color features, a methodology that has since...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
275 Views
17 Pages

25 September 2026

This paper addresses the depth regulation of an inspection-class remotely operated vehicle whose hydrodynamic model is uncertain and whose environment applies a persistent, non-vanishing wave disturbance. A neural-network learning term added to a pro...

(This article belongs to the Section Ocean Engineering)
  • Article
  • Open Access
18 Citations
5,023 Views
26 Pages

15 March 2024

Fault data under real operating conditions are often difficult to collect, making the number of trained fault data small and out of proportion to normal data. Thus, fault diagnosis symmetry (balance) is compromised. This will result in less effective...

(This article belongs to the Topic Predictive Analytics and Fault Diagnosis of Machines with Machine Learning Techniques)
  • Article
  • Open Access
251 Citations
12,407 Views
18 Pages

Learning a Dilated Residual Network for SAR Image Despeckling

  • Qiang Zhang,
  • Qiangqiang Yuan,
  • Jie Li,
  • Zhen Yang and
  • Xiaoshuang Ma

29 January 2018

In this paper, to break the limit of the traditional linear models for synthetic aperture radar (SAR) image despeckling, we propose a novel deep learning approach by learning a non-linear end-to-end mapping between the noisy and clean SAR images with...

(This article belongs to the Special Issue Learning to Understand Remote Sensing Images)
  • Article
  • Open Access
16 Citations
6,778 Views
20 Pages

In this paper, we propose a new architecture of densely connected convolutional networks for pan-sharpening (DCCNP). Since the traditional convolution neural network (CNN) has difficulty handling the lack of a training sample set in the field of remo...

  • Article
  • Open Access
5 Citations
2,432 Views
13 Pages

An Improved Adam’s Algorithm for Stomach Image Classification

  • Haijing Sun,
  • Hao Yu,
  • Yichuan Shao,
  • Jiantao Wang and ,
  • Lei Xing,
  • Le Zhang and
  • Qian Zhao
  • + 2 authors+ 0 author

21 June 2024

Current stomach disease detection and diagnosis is challenged by data complexity and high dimensionality and requires effective deep learning algorithms to improve diagnostic accuracy. To address this challenge, in this paper, an improved strategy ba...

  • Article
  • Open Access
17 Citations
4,943 Views
11 Pages

A Lightweight CNN Architecture for Automatic Modulation Classification

  • Zhongyong Wang,
  • Dongzhe Sun,
  • Kexian Gong,
  • Wei Wang and
  • Peng Sun

2 November 2021

Automatic modulation classification (AMC) algorithms based on deep learning (DL) have been widely studied in the past decade, showing significant performance advantage compared to traditional ones. However, the existing DL methods generally behave wo...

(This article belongs to the Special Issue Intelligent Signal Processing and Communication Systems)
  • Article
  • Open Access
16 Citations
6,543 Views
15 Pages

13 December 2022

Loss functions, such as the IoU Loss function and the GIoU (Generalized Intersection over Union) Loss function have been put forward to replace regression loss functions commonly used in regression loss calculation. GIoU Loss alleviates the vanishing...

(This article belongs to the Special Issue Advances in Deep Learning III)
  • Article
  • Open Access
2 Citations
2,390 Views
17 Pages

28 May 2023

This article proposes a video prediction network called STMP-Net that addresses the problem of the inability of Recurrent Neural Networks (RNNs) to fully extract spatiotemporal information and motion change features during video prediction. STMP-Net...

(This article belongs to the Section Intelligent Sensors)
  • Article
  • Open Access
10 Citations
4,596 Views
40 Pages

In multivariate and multistep time series prediction research, we often face the problems of insufficient spatial feature extraction and insufficient time-dependent mining of historical series data, which also brings great challenges to multivariate...

(This article belongs to the Special Issue Machine Learning in Data Analytics and Prediction)
  • Article
  • Open Access
19 Citations
4,252 Views
17 Pages

24 February 2021

The training of a deep learning model requires a large amount of data. In case of sidescan sonar images, the number of snippets from objects of interest is limited. Generative adversarial networks (GAN) have shown to be able to generate photo-realist...

(This article belongs to the Special Issue Underwater Computer Vision and Image Processing)
  • Article
  • Open Access
1 Citations
2,983 Views
17 Pages

11 May 2023

Graph convolutional network (GCN) architecture is the basis of many neural networks and has been widely used in processing graph-structured data. When dealing with large and sparse data, deeper GCN models are often required. However, the models suffe...

  • Article
  • Open Access
9 Citations
3,293 Views
18 Pages

13 April 2023

Investigating forest phenology prediction is a key parameter for assessing the relationship between climate and environmental changes. Traditional machine learning models are not good at capturing long-term dependencies due to the problem of vanishin...

  • Feature Paper
  • Article
  • Open Access
22 Citations
8,192 Views
18 Pages

Machine Learning-Based Dynamic Modeling for Process Engineering Applications: A Guideline for Simulation and Prediction from Perceptron to Deep Learning

  • Carine M. Rebello,
  • Paulo H. Marrocos,
  • Erbet A. Costa,
  • Vinicius V. Santana and ,
  • Alírio E. Rodrigues,
  • Ana M. Ribeiro and
  • Idelfonso B. R. Nogueira
  • + 2 authors+ 0 author

27 January 2022

A misusage of machine learning (ML) strategies is usually observed in the process systems engineering literature. This issue is even more evident when dynamic identification is performed. The root of this problem is the gradient explode and vanishing...

(This article belongs to the Section Process Control, Modeling and Optimization)

of 4