Convolutional Neural Networks: A Survey

Krichen, Moez

doi:10.3390/computers12080151

Cited by 193 publications

(75 citation statements)

References 203 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The feature maps in lower levels are transmitted to higher-complexity layers [13]. Convolutional neural networks (CNN) use sparse interaction to signi cantly reduce the number of neurons compared to shallow neural networks [14]. Transfer learning using CNN based on Alex Net and Google Net for the ImageNet dataset is well known deep learning approach [15].…”

Section: Convolutional Neural Network (Cnn)mentioning

confidence: 99%

Brain tumor Radiogenomic Classification and Prediction of Glioblastoma Status using MRI Scans with Deep Learning Algorithms

AbdelAziz,

Dawood,

Hassan

et al. 2024

Preprint

View full text Add to dashboard Cite

Accurate Radiogenomic classification of brain tumors play an essential role in improving prognosis, diagnosis, and therapy strategy in glioblastoma patients. In this paper, we provide a novel MGMT Promoter Methylation Prediction (MGMT-PMP) approach that extracts latent features fused with radiomic data to predict the genetic subtype of glioblastoma. The novice rejection method has been shown to be highly effective at picking and isolating negative training cases from the original dataset. In this study, the fused feature vectors are used to train and test CNN classifiers. We examined classification performance for the first time in published form, using metrics such as accuracy, F1-score, and Matthews’s correlation coefficient. Jackknife tenfold cross-validation was used to train and evaluate the BraTS-2021 dataset validation. The maximum classification accuracy for detecting MGMT methylation status in glioblastoma patients is 99.13 percent. Deep learning feature extraction with Radiogenomic characteristics, merging imaging phenotypes and molecular structure, and using a rejection method were found to outperform in diagnosing the MGMT methylation status of glioblastoma patients. The approach connects genetic variance to radiomic characteristics, bridging two areas of research that may be valuable for clinical treatment planning and leading to better outcomes.

show abstract

Section: Convolutional Neural Network (Cnn)mentioning

confidence: 99%

Brain tumor Radiogenomic Classification and Prediction of Glioblastoma Status using MRI Scans with Deep Learning Algorithms

AbdelAziz,

Dawood,

Hassan

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The CNN, or Convolutional Neural Network, has a specific feed-forward structure with fundamental hidden layers. The convolution layer uses filters of varying sizes to generate detailed output characteristics, serving as inputs for the next layer [15]. Using the following equation, the convolution layer can be described as follows:…”

Section: Convolution Neural Networkmentioning

confidence: 99%

A hybrid approach for gearbox fault diagnosis based on deep learning techniques

Bessaoudi,

Habbouche,

Benkedjouh

et al. 2024

Preprint

View full text Add to dashboard Cite

Faults identification plays a vital role in improving the safety and reliability of industrial machinery. Deep learning has stepped into the scene as a promising approach for detecting faults, showcasing impressive performance in this regard. However, challenges such as noise and variable working conditions often limit the effectiveness of these approaches. This study addresses these limitations by employing a combination of signal processing methods and neural networks. Specifically, the proposed methodology incorporates maximum overlapping discrete wavelet packet decomposition (MODWPD) for raw vibratory signal, mel frequency cepstral coefficient mapping (MFCC) for time-frequency feature extraction, and a fusion of bidirectional long and short-term memory network with convolutional neural networks (CNN-BiLSTM) to capture local features and temporal dependencies in sequential data. The evaluation is conducted using two diverse experimental datasets, PHM2009 for mixed defects and Case Western Reserve University (CWRU) for bearing faults, under unexpected operating conditions. The proposed method is rigorously tested through stratified K-fold cross-validation, demonstrating superior performance compared to a leading state-of-the-art model.

show abstract

“…It has the characteristics of sparse connections, parameter sharing, and translation invariance, greatly minimizing the number of network parameters that need to be optimized, improving the training speed, and facilitating the extraction of partial features in images. CNN is able to capture spatial features and patterns in images using a hierarchical architecture of layers that perform convolution operations and extract features at different levels of abstraction [47]. So, this algorithm has remarkable advantages for image analysis and recognition.…”

Section: Cnn Modelmentioning

confidence: 99%

Aerosol Optical Depth Retrieval for Sentinel-2 Based on Convolutional Neural Network Method

Jiang,

Liu,

Jiao

2023

Atmosphere

View full text Add to dashboard Cite

Atmospheric aerosol significantly affects the climate environment and public health, and Aerosol Optical Depth (AOD) is a fundamental optical characteristic parameter of aerosols, so it is important to develop methods for obtaining AOD. In this work, a novel AOD retrieval algorithm based on a Convolutional Neural Network (CNN) method that could provide continuous and detailed aerosol distribution is proposed. The algorithm utilizes data from Sentinel-2 and Aerosol Robotic Network (AERONET) spanning from 2016 to 2022. The CNN AOD data are consistent with the AERONET measurements, with an R2 of 0.95 and RMSE of 0.049 on the test dataset. CNN demonstrates superior performance in retrieving AOD compared with other algorithms. CNN retrieves AOD well on high reflectance surfaces, such as urban and bare soil, with RMSEs of 0.051 and 0.042, respectively. CNN efficiently retrieves AOD in different seasons, but it performs better in summer and winter than in spring and autumn. In addition, to study the relationship between image size and model retrieval performance, image datasets of 32 × 32, 64 × 64 and 128 × 128 pixels were created to train and test the CNN model. The results show that the 128-size CNN performs better because large images contain rich aerosol information.

show abstract

Convolutional Neural Networks: A Survey

Cited by 193 publications

References 203 publications

Brain tumor Radiogenomic Classification and Prediction of Glioblastoma Status using MRI Scans with Deep Learning Algorithms

Brain tumor Radiogenomic Classification and Prediction of Glioblastoma Status using MRI Scans with Deep Learning Algorithms

A hybrid approach for gearbox fault diagnosis based on deep learning techniques

Aerosol Optical Depth Retrieval for Sentinel-2 Based on Convolutional Neural Network Method

Contact Info

Product

Resources

About