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

1,151 Results Found

  • Article
  • Open Access
19 Citations
7,385 Views
14 Pages

24 March 2022

Fully connected (FC) layers are used in almost all neural network architectures ranging from multilayer perceptrons to deep neural networks. FC layers allow any kind of symmetric/asymmetric interaction between features without making any assumption a...

(This article belongs to the Special Issue Fuzzy Techniques for Emerging Conditions & Digital Transformation)
  • Article
  • Open Access
15 Citations
3,710 Views
23 Pages

21 August 2020

Recently, there have been rapid advances in high-resolution remote sensing image retrieval, which plays an important role in remote sensing data management and utilization. For content-based remote sensing image retrieval, low-dimensional, representa...

(This article belongs to the Section Sensing and Imaging)
  • Communication
  • Open Access
3 Citations
2,142 Views
9 Pages

3 September 2023

We report a single-shot phase-detection method using deep learning in a holographic data-storage system. The error rate was experimentally confirmed to be reduced by up to three orders of magnitude compared with that in the conventional phase-determi...

  • Article
  • Open Access
15 Citations
3,332 Views
16 Pages

8 March 2024

Chest X-ray evaluation is challenging due to its high demand and the complexity of diagnoses. In this study, we propose an optimized deep learning model for the multi-label classification of chest X-ray images. We leverage pretrained convolutional ne...

(This article belongs to the Section E3: Mathematical Biology)
  • Article
  • Open Access
2,250 Views
18 Pages

26 February 2024

Obtaining accurate sound speed profiles (SSPs) in near-real-time is of great significance for ocean exploration, underwater communication and improving the performance of sonar systems. In response to the problem that traditional sound speed estimati...

(This article belongs to the Section Ocean Engineering)
  • Article
  • Open Access
1 Citations
1,104 Views
20 Pages

13 October 2025

This study proposes a sliding-mode-based adaptive control framework for symmetric quad-rotor altitude and attitude tracking under parametric uncertainties and mismatched disturbances. To address mismatched disturbances, a finite-time disturbance obse...

(This article belongs to the Section A: Computer Science)
  • Article
  • Open Access
6 Citations
6,396 Views
18 Pages

Accelerating Deep Neural Networks by Combining Block-Circulant Matrices and Low-Precision Weights

  • Zidi Qin,
  • Di Zhu,
  • Xingwei Zhu,
  • Xuan Chen and ,
  • Yinghuan Shi,
  • Yang Gao,
  • Zhonghai Lu,
  • Qinghong Shen,
  • Li Li and
  • Hongbing Pan
  • + 5 authors+ 0 author

As a key ingredient of deep neural networks (DNNs), fully-connected (FC) layers are widely used in various artificial intelligence applications. However, there are many parameters in FC layers, so the efficient process of FC layers is restricted by m...

(This article belongs to the Section Computer Science & Engineering)
  • Article
  • Open Access
1,192 Citations
48,124 Views
28 Pages

5 November 2015

Learning efficient image representations is at the core of the scene classification task of remote sensing imagery. The existing methods for solving the scene classification task, based on either feature coding approaches with low-level hand-engineer...

  • Article
  • Open Access
5 Citations
3,341 Views
20 Pages

Smooth Group L1/2 Regularization for Pruning Convolutional Neural Networks

  • Yuan Bao,
  • Zhaobin Liu,
  • Zhongxuan Luo and
  • Sibo Yang

13 January 2022

In this paper, a novel smooth group L1/2 (SGL1/2) regularization method is proposed for pruning hidden nodes of the fully connected layer in convolution neural networks. Usually, the selection of nodes and weights is based on experience, and the conv...

  • Article
  • Open Access
3 Citations
3,242 Views
13 Pages

20 September 2024

Medical named entity recognition (NER) focuses on extracting and classifying key entities from medical texts. Through automated medical information extraction, NER can effectively improve the efficiency of electronic medical record analysis, medical...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
2,009 Views
33 Pages

16 May 2023

Despite the success of deep learning models, it remains challenging for the over-parameterized model to learn good representation under small-sample-size settings. In this paper, motivated by previous work on out-of-distribution (OoD) generalization,...

(This article belongs to the Special Issue Advances in Computer Vision and Machine Learning)
  • Article
  • Open Access
3 Citations
3,607 Views
15 Pages

Performance Analysis of Deep Convolutional Network Architectures for Classification of Over-Volume Vehicles

  • S. Sofana Reka,
  • Venkata Dhanvanthar Murthy Voona,
  • Puvvada Venkata Sai Nithish,
  • Dornadula Sai Paavan Kumar and ,
  • Prakash Venugopal and
  • Visvanathan Ravi
  • + 1 author+ 0 author

16 February 2023

The number of vehicle accidents has increased in recent years due to overloaded goods carriers. Off-road driving, mountain roads, and sharp edges on a road are the main causes of an imbalance in overloaded trucks. In rural areas, where smaller roads...

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

19 October 2026

Interference recognition from time–frequency images requires lightweight models that can maintain recognition performance when signal parameters deviate from their nominal settings. We propose ASD-Net, a decreasing-group fully connected archite...

(This article belongs to the Section Microwave and Wireless Communications)
  • Article
  • Open Access
8 Citations
5,085 Views
14 Pages

Recurrent Deep Learning for Beam Pattern Synthesis in Optimized Antenna Arrays

  • Armando Arce,
  • Fernando Arce,
  • Enrique Stevens-Navarro,
  • Ulises Pineda-Rico and ,
  • Marco Cardenas-Juarez and
  • Abel Garcia-Barrientos
  • + 1 author+ 0 author

29 December 2024

This work proposes and describes a deep learning-based approach utilizing recurrent neural networks (RNNs) for beam pattern synthesis considering uniform linear arrays. In this particular case, the deep neural network (DNN) learns from previously opt...

(This article belongs to the Special Issue Advances in Wireless Communications Using Machine Learning and Deep Learning Techniques)
  • Article
  • Open Access
4 Citations
2,216 Views
21 Pages

10 December 2024

Many traditional fruit vendors still rely on manual sorting to pick out high-quality apples. This process is not only time-consuming but can also damage the apples. Meanwhile, automated detection technology is still in its early stage and lacks full...

  • Article
  • Open Access
22 Citations
6,180 Views
13 Pages

Machine Learning for Detecting Total Knee Arthroplasty Implant Loosening on Plain Radiographs

  • Man-Soo Kim,
  • Ryu-Kyoung Cho,
  • Sung-Cheol Yang,
  • Jae-Hyeong Hur and
  • Yong In

(1) Background: The purpose of this study was to investigate whether the loosening of total knee arthroplasty (TKA) implants could be detected accurately on plain radiographs using a deep convolution neural network (CNN). (2) Methods: We analyzed dat...

(This article belongs to the Special Issue Artificial Intelligence in Surgery)
  • Article
  • Open Access
10 Citations
4,446 Views
16 Pages

In this paper, the structure of a separable convolutional neural network that consists of an embedding layer, separable convolutional layers, convolutional layer and global average pooling is represented for binary and multiclass text classifications...

(This article belongs to the Collection Feature Innovation Papers)
  • Article
  • Open Access
167 Citations
13,984 Views
13 Pages

A Hybrid Deep CNN Model for Abnormal Arrhythmia Detection Based on Cardiac ECG Signal

  • Amin Ullah,
  • Sadaqat ur Rehman,
  • Shanshan Tu,
  • Raja Majid Mehmood and ,
  • Fawad and
  • Muhammad Ehatisham-ul-haq
  • + 1 author+ 0 author

1 February 2021

Electrocardiogram (ECG) signals play a vital role in diagnosing and monitoring patients suffering from various cardiovascular diseases (CVDs). This research aims to develop a robust algorithm that can accurately classify the electrocardiogram signal...

(This article belongs to the Special Issue Healthcare Monitoring and Management with Artificial Intelligence)
  • Article
  • Open Access
16 Citations
5,425 Views
21 Pages

2 November 2020

The convolutional neural networks (CNNs) are a computation and memory demanding class of deep neural networks. The field-programmable gate arrays (FPGAs) are often used to accelerate the networks deployed in embedded platforms due to the high computa...

(This article belongs to the Section Artificial Intelligence Circuits and Systems (AICAS))
  • Article
  • Open Access
6 Citations
3,216 Views
10 Pages

The Image Identification Application with HfO2-Based Replaceable 1T1R Neural Networks

  • Jinfu Lin,
  • Hongxia Liu,
  • Shulong Wang,
  • Dong Wang and
  • Lei Wu

25 March 2022

This paper mainly studies the hardware implementation of a fully connected neural network based on the 1T1R (one-transistor-one-resistor) array and its application in handwritten digital image recognition. The 1T1R arrays are prepared by connecting t...

(This article belongs to the Special Issue 2D Semiconducting Materials for Device Applications)
  • Article
  • Open Access
49 Citations
5,589 Views
20 Pages

Fully Dense Multiscale Fusion Network for Hyperspectral Image Classification

  • Zhe Meng,
  • Lingling Li,
  • Licheng Jiao,
  • Zhixi Feng and ,
  • Xu Tang and
  • Miaomiao Liang
  • + 1 author+ 0 author

19 November 2019

The convolutional neural network (CNN) can automatically extract hierarchical feature representations from raw data and has recently achieved great success in the classification of hyperspectral images (HSIs). However, most CNN based methods used in...

  • Feature Paper
  • Article
  • Open Access
7 Citations
2,583 Views
12 Pages

A Model for Identifying Soybean Growth Periods Based on Multi-Source Sensors and Improved Convolutional Neural Network

  • Jinyang Li,
  • Qingda Li,
  • Chuntao Yu,
  • Yan He and ,
  • Liqiang Qi,
  • Wenqiang Shi and
  • Wei Zhang
  • + 2 authors+ 0 author

28 November 2022

The identification of soybean growth periods is the key to timely take field management measures, which plays an important role in improving yield. In order to realize the discrimination of soybean growth periods under complex environments in the fie...

(This article belongs to the Section Precision and Digital Agriculture)
  • Article
  • Open Access
26 Citations
6,311 Views
23 Pages

13 June 2019

Classification responses provided by Multi Layer Perceptrons (MLPs) can be explained by means of propositional rules. So far, many rule extraction techniques have been proposed for shallow MLPs, but not for Convolutional Neural Networks (CNNs). To fi...

(This article belongs to the Special Issue Advances in Deep Learning)
  • Article
  • Open Access
33 Citations
4,171 Views
17 Pages

Intelligent Fault Diagnosis of Rolling Element Bearings Based on Modified AlexNet

  • Mohammad Mohiuddin,
  • Md. Saiful Islam,
  • Shirajul Islam,
  • Md. Sipon Miah and
  • Ming-Bo Niu

8 September 2023

The reliable and safe operation of industrial systems needs to detect and diagnose bearing faults as early as possible. Intelligent fault diagnostic systems that use deep learning convolutional neural network (CNN) techniques have achieved a great de...

  • Article
  • Open Access
5 Citations
3,967 Views
29 Pages

Optimization of Deep Neural Networks Using a Micro Genetic Algorithm

  • Ricardo Landa,
  • David Tovias-Alanis and
  • Gregorio Toscano

2 December 2024

This work proposes the use of a micro genetic algorithm to optimize the architecture of fully connected layers in convolutional neural networks, with the aim of reducing model complexity without sacrificing performance. Our approach applies the parad...

(This article belongs to the Section AI Systems: Theory and Applications)
  • Article
  • Open Access
6 Citations
1,823 Views
24 Pages

Aluminum alloy offers the advantages of being lightweight, high in strength, corrosion-resistant, and easy to process. It has a promising application prospect in large-span space structures, with its primary application form being single-layer reticu...

(This article belongs to the Section Building Materials, and Repair & Renovation)
  • Article
  • Open Access
9 Citations
5,000 Views
18 Pages

RETRACTED: Continual Learning Approach for Continuous Data Stream Analysis in Dynamic Environments

  • K. Prasanna,
  • Mudassir Khan,
  • Saeed M. Alshahrani,
  • Ajmeera Kiran and ,
  • P. Phanindra Kumar Reddy,
  • Mofadal Alymani and
  • J. Chinna Babu
  • + 2 authors+ 0 author

8 July 2023

Continuous data stream analysis primarily focuses on the unanticipated changes in the transmission of data distribution over time. Conceptual change is defined as the signal distribution changes over the transmission of continuous data streams. A dri...

(This article belongs to the Special Issue Advances in Big Data and Machine Learning)
  • Communication
  • Open Access
3 Citations
1,591 Views
11 Pages

Prediction of Power Fluctuations of Gaussian Beams After Transmission Through Turbulent Atmosphere

  • Zhihao Wan,
  • Jiayi Zhu,
  • Cheng Huang,
  • Zhimin He and ,
  • Jun Zeng,
  • Fuchang Chen,
  • Chaoqun Yu,
  • Yan Li,
  • Huanting Chen and
  • Huichuan Lin
  • + 7 authors+ 2 authors

22 November 2024

As laser beams propagate through free space, power fluctuation occurs due to atmospheric turbulence, which significantly increases the bit error rate of free-space optical communication. If the precise prediction of power fluctuations can be achieved...

(This article belongs to the Special Issue Laser Beam Propagation and Control)
  • Article
  • Open Access
45 Citations
11,269 Views
19 Pages

30 January 2021

The ship detection task using optical remote sensing images is important for in maritime safety, port management and ship rescue. With the wide application of deep learning to remote sensing, a series of target detection algorithms, such as faster re...

(This article belongs to the Special Issue Deep Learning in Remote Sensing: Sample Datasets, Algorithms and Applications)
  • Article
  • Open Access
8 Citations
4,000 Views
23 Pages

31 January 2022

The task of seismic data interpretation is a time-consuming and uncertain process. Machine learning tools can help to build a shortcut between raw seismic data and reservoir characteristics of interest. Recently, techniques involving convolutional ne...

(This article belongs to the Special Issue Data Science in Reservoir Modelling Workflows)
  • Article
  • Open Access
1,393 Views
15 Pages

18 March 2025

This paper considers a two-layer hierarchical network, where a server containing N files is connected to K1 mirrors and each mirror is connected to K2 users. Each mirror and each user has a cache memory of size M1 and M2 files, respectively. The serv...

(This article belongs to the Special Issue Network Information Theory and Its Applications)
  • Article
  • Open Access
7 Citations
2,344 Views
24 Pages

24 November 2023

During the water injection development process of highly deviated wells in low-permeability reservoirs, the water flooding distance between different layers of the same oil and water well is different due to the deviation of the well. In addition, th...

(This article belongs to the Topic Petroleum and Gas Engineering)
  • Article
  • Open Access
44 Citations
6,994 Views
22 Pages

DeepKnuckle: Deep Learning for Finger Knuckle Print Recognition

  • Ahmad S. Tarawneh,
  • Ahmad B. Hassanat,
  • Esra’a Alkafaween,
  • Bayan Sarayrah and ,
  • Sami Mnasri,
  • Ghada A. Altarawneh,
  • Malek Alrashidi,
  • Mansoor Alghamdi and
  • Abdullah Almuhaimeed
  • + 4 authors+ 0 author

Biometric technology has received a lot of attention in recent years. One of the most prevalent biometric traits is the finger-knuckle print (FKP). Because the dorsal region of the finger is not exposed to surfaces, FKP would be a dependable and trus...

(This article belongs to the Section Industrial Electronics)
  • Article
  • Open Access
5 Citations
3,254 Views
13 Pages

27 September 2024

This paper is concerned with an end-to-end electrocardiogram (ECG) signal transformation from a continuous-wave (CW) radar signal using a specialized deep learning model. For this purpose, the presented deep learning model is designed using convoluti...

(This article belongs to the Section Applied Biosciences and Bioengineering)
  • Communication
  • Open Access
38 Citations
4,534 Views
11 Pages

Hyperparameter Optimization for COVID-19 Pneumonia Diagnosis Based on Chest CT

  • Paulo Lacerda,
  • Bruno Barros,
  • Célio Albuquerque and
  • Aura Conci

20 March 2021

Convolutional Neural Networks (CNNs) have been successfully applied in the medical diagnosis of different types of diseases. However, selecting the architecture and the best set of hyperparameters among the possible combinations can be a significant...

(This article belongs to the Special Issue Biomedical Signal Processing for Disease Diagnosis)
  • Article
  • Open Access
1 Citations
1,004 Views
25 Pages

Pore Structure and Connectivity with Fractal Characterization in Deep Shale of the Wufeng–Longmaxi Formation, Luzhou Block: Insights from MAPS and NMR Technology

  • Jamil Khan,
  • Shengxian Zhao,
  • Jian Zhang,
  • Xuefeng Yang and ,
  • Bo Li,
  • Yuhang Zhang,
  • Shangbin Chen and
  • Xinyao Huang
  • + 3 authors+ 0 author

24 November 2025

The exploration potential, storage capacity, and exploitability of the deep shale-gas reservoirs are governed by various characteristics of their pore networks. Conventional methods cannot fully capture these features across scales, highlighting the...

(This article belongs to the Special Issue Exploration, Exploitation and Utilization of Coal and Gas Resources, 2nd Edition)
  • Article
  • Open Access
2 Citations
1,814 Views
23 Pages

A Lightweight Cross-Layer Smoke-Aware Network

  • Jingjing Wang,
  • Xinman Zhang and
  • Cong Zhang

5 July 2024

Smoke is an obvious sign of pre-fire. However, due to its variable morphology, the existing schemes are difficult to extract precise smoke characteristics, which seriously affects the practical applications. Therefore, we propose a lightweight cross-...

(This article belongs to the Special Issue Deep Learning for Computer Vision and Image Processing Sensors)
  • Article
  • Open Access
8 Citations
4,529 Views
15 Pages

3 June 2023

Entity relation extraction mainly extracts relations from text, which is one of the important tasks of natural language processing. At present, some special fields have insufficient data; for example, agriculture, the metallurgical industry, etc. The...

  • Article
  • Open Access
1 Citations
2,340 Views
14 Pages

SLRProp: A Back-Propagation Variant of Sparse Low Rank Method for DNNs Reduction

  • Asier Garmendia-Orbegozo,
  • Jose David Nuñez-Gonzalez and
  • Miguel Angel Anton

2 March 2023

Application of deep neural networks (DNN) in edge computing has emerged as a consequence of the need of real time and distributed response of different devices in a large number of scenarios. To this end, shredding these original structures is urgent...

(This article belongs to the Special Issue Computational Intelligence and Cyberphysical Systems in Sensing)
  • Article
  • Open Access
25 Citations
8,165 Views
23 Pages

Enhanced Credit Card Fraud Detection Using Deep Hybrid CLST Model

  • Madiha Jabeen,
  • Shabana Ramzan,
  • Ali Raza,
  • Norma Latif Fitriyani and ,
  • Muhammad Syafrudin and
  • Seung Won Lee
  • + 1 author+ 0 author

12 June 2025

The existing financial payment system has inherent credit card fraud problems that must be solved with strong and effective solutions. In this research, a combined deep learning model that incorporates a convolutional neural network (CNN), long-short...

(This article belongs to the Special Issue Machine Learning and Finance)
  • Article
  • Open Access
2 Citations
1,502 Views
21 Pages

5 December 2024

In practical engineering, due to quality inspections of connections between prefabricated components and construction errors, reserved reinforcing bars in the transition layer may be partially insufficient or even completely absent. This defect signi...

(This article belongs to the Section Corrosion)
  • Article
  • Open Access
64 Citations
8,634 Views
15 Pages

Gradient Boosting Machine and Object-Based CNN for Land Cover Classification

  • Quang-Thanh Bui,
  • Tien-Yin Chou,
  • Thanh-Van Hoang,
  • Yao-Min Fang and ,
  • Ching-Yun Mu,
  • Pi-Hui Huang,
  • Vu-Dong Pham,
  • Quoc-Huy Nguyen,
  • Do Thi Ngoc Anh and
  • Michael E. Meadows
  • + 6 authors+ 1 author

9 July 2021

In regular convolutional neural networks (CNN), fully-connected layers act as classifiers to estimate the probabilities for each instance in classification tasks. The accuracy of CNNs can be improved by replacing fully connected layers with gradient...

(This article belongs to the Special Issue Applications of Remote Sensing for Resources Conservation)
  • Article
  • Open Access
54 Citations
4,157 Views
14 Pages

18 November 2021

Rolling bearings are the most fault-prone parts in rotating machinery. In order to find faults in time and reduce losses, this paper presents an intelligent diagnosis method for rolling bearings. At present, the deep residual network (RESNET) is the...

  • Article
  • Open Access
13 Citations
6,097 Views
17 Pages

Single- and Cross-Lingual Speech Emotion Recognition Based on WavLM Domain Emotion Embedding

  • Jichen Yang,
  • Jiahao Liu,
  • Kai Huang,
  • Jiaqi Xia and ,
  • Zhengyu Zhu and
  • Han Zhang
  • + 1 author+ 0 author

Unlike previous approaches in speech emotion recognition (SER), which typically extract emotion embeddings from a trained classifier consisting of fully connected layers and training data without considering contextual information, this research intr...

(This article belongs to the Special Issue New Advances in Affective Computing)
  • Article
  • Open Access
44 Citations
6,873 Views
24 Pages

Breast Cancer Detection and Analytics Using Hybrid CNN and Extreme Learning Machine

  • Vidhushavarshini Sureshkumar,
  • Rubesh Sharma Navani Prasad,
  • Sathiyabhama Balasubramaniam,
  • Dhayanithi Jagannathan and ,
  • Jayanthi Daniel and
  • Seshathiri Dhanasekaran
  • + 1 author+ 0 author

26 July 2024

Early detection of breast cancer is essential for increasing survival rates, as it is one of the primary causes of death for women globally. Mammograms are extensively used by physicians for diagnosis, but selecting appropriate algorithms for image e...

(This article belongs to the Section Methodology, Drug and Device Discovery)
  • Article
  • Open Access
2 Citations
3,003 Views
14 Pages

13 August 2022

In this paper, we study the learnability of the Boolean inner product by a systematic simulation study. The family of the Boolean inner product function is known to be representable by neural networks of threshold neurons of depth 3 with only 2n+1 un...

(This article belongs to the Section Multidisciplinary Applications)
  • Article
  • Open Access
7 Citations
3,250 Views
14 Pages

Segmenting the Semi-Conductive Shielding Layer of Cable Slice Images Using the Convolutional Neural Network

  • Wen Zhu,
  • Fei Dong,
  • Beiping Hou,
  • Wesley Kenniard Takudzwa Gwatidzo and ,
  • Le Zhou and
  • Gang Li
  • + 1 author+ 0 author

14 September 2020

Being an important part of aerial insulated cable, the semiconductive shielding layer is made of a typical polymer material and can improve the cable transmission effects; the structural parameters will affect the cable quality directly. Then, the im...

(This article belongs to the Special Issue Advanced Measurement, Prediction, and Testing Techniques in Polymer Manufacturing, Processing, and End-Use)
  • Article
  • Open Access
9 Citations
3,826 Views
18 Pages

Dual-Channel Reconstruction Network for Image Compressive Sensing

  • Zhongqiang Zhang,
  • Dahua Gao,
  • Xuemei Xie and
  • Guangming Shi

4 June 2019

The existing compressive sensing (CS) reconstruction algorithms require enormous computation and reconstruction quality that is not satisfying. In this paper, we propose a novel Dual-Channel Reconstruction Network (DC-Net) module to build two CS reco...

(This article belongs to the Section Intelligent Sensors)
  • Article
  • Open Access
69 Citations
7,441 Views
16 Pages

A Deep-Learning Approach to ECG Classification Based on Adversarial Domain Adaptation

  • Lisha Niu,
  • Chao Chen,
  • Hui Liu,
  • Shuwang Zhou and
  • Minglei Shu

27 October 2020

Cardiovascular disease has become one of the main diseases threatening human life and health. This disease is very common and troublesome, and the existing medical resources are scarce, so it is necessary to use a computer-aided automatic diagnosis t...

  • Article
  • Open Access
4 Citations
3,225 Views
14 Pages

17 October 2020

One of the most important parts of a text-independent speaker verification system is speaker embedding generation. Previous studies demonstrated that shortcut connections-based multi-layer aggregation improves the representational power of a speaker...

(This article belongs to the Special Issue Human Computer Interaction for Intelligent Systems)

of 24