Filtered Multicarrier Waveforms Classification: A Deep Learning-Based Approach

Zerhouni, Kawtar; Amhoud, El Mehdi; Chafii, Marwa

doi:10.1109/access.2021.3078252

Cited by 28 publications

(15 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can have significant impact in domains of image classification, image processing and image transmission over networks [41,42]. It will also have cyber-security impact in the domains of health care [43], cloud computing [44,45], image transmission using optical fibre [46][47][48] and deep learning [49].…”

Section: Impact Of Cd-ganmentioning

confidence: 99%

Chained Dual-Generative Adversarial Network: A Generalized Defense Against Adversarial Attacks

Singh¹,

Awasthi²,

Garg³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Neural networks play a significant role in the field of image classification. When an input image is modified by adversarial attacks, the changes are imperceptible to the human eye, but it still leads to misclassification of the images. Researchers have demonstrated these attacks to make production self-driving cars misclassify Stop Road signs as 45 Miles Per Hour (MPH) road signs and a turtle being misclassified as AK47. Three primary types of defense approaches exist which can safeguard against such attacks i.e., Gradient Masking, Robust Optimization, and Adversarial Example Detection. Very few approaches use Generative Adversarial Networks (GAN) for Defense against Adversarial Attacks. In this paper, we create a new approach to defend against adversarial attacks, dubbed Chained Dual-Generative Adversarial Network (CD-GAN) that tackles the defense against adversarial attacks by minimizing the perturbations of the adversarial image using iterative oversampling and undersampling using GANs. CD-GAN is created using two GANs, i.e., CDGAN's Sub-Resolution GAN and CDGAN's Super-Resolution GAN. The first is CDGAN's Sub-Resolution GAN which takes the original resolution input image and oversamples it to generate a lower resolution neutralized image. The second is CDGAN's Super-Resolution GAN which takes the output of the CDGAN's Sub-Resolution and undersamples, it to generate the higher resolution image which removes any remaining perturbations. Chained Dual GAN is formed by chaining these two GANs together. Both of these GANs are trained independently. CDGAN's Sub-Resolution GAN is trained using higher resolution adversarial images as inputs and lower resolution neutralized images as output image examples. Hence, this GAN downscales the image while removing adversarial attack noise. CDGAN's Super-Resolution GAN is trained using lower resolution adversarial images as inputs and higher resolution neutralized images as output images. Because of this, it acts as an Upscaling GAN while removing the adversarial attak noise. Furthermore, CD-GAN has a modular design such that it can be prefixed to any existing classifier without any retraining or extra effort, and 2542 CMC, 2023, vol.74, no.2 can defend any classifier model against adversarial attack. In this way, it is a Generalized Defense against adversarial attacks, capable of defending any classifier model against any attacks. This enables the user to directly integrate CD-GAN with an existing production deployed classifier smoothly. CD-GAN iteratively removes the adversarial noise using a multi-step approach in a modular approach. It performs comparably to the state of the arts with mean accuracy of 33.67 while using minimal compute resources in training.

show abstract

Section: Impact Of Cd-ganmentioning

confidence: 99%

Chained Dual-Generative Adversarial Network: A Generalized Defense Against Adversarial Attacks

Singh¹,

Awasthi²,

Garg³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…A better grasp of how YOLO works is still required. Kang et al [23] suggested a hybrid model using deep features and machine learning classifiers along with the combination of several deep learning approaches with classifiers such as SVM, RBF, KNN, and others [24]. The ensemble feature has aided in the modeling of improved performance.…”

Section: Related Workmentioning

confidence: 99%

Diagnosis of Brain Tumor Using Light Weight Deep Learning Model with Fine-Tuning Approach

Shelatkar

Garg

Shorfuzzaman

et al. 2022

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Brain cancer is a rare and deadly disease with a slim chance of survival. One of the most important tasks for neurologists and radiologists is to detect brain tumors early. Recent claims have been made that computer-aided diagnosis-based systems can diagnose brain tumors by employing magnetic resonance imaging (MRI) as a supporting technology. We propose transfer learning approaches for a deep learning model to detect malignant tumors, such as glioblastoma, using MRI scans in this study. This paper presents a deep learning-based approach for brain tumor identification and classification using the state-of-the-art object detection framework YOLO (You Only Look Once). The YOLOv5 is a novel object detection deep learning technique that requires limited computational architecture than its competing models. The study used the Brats 2021 dataset from the RSNA-MICCAI brain tumor radio genomic classification. The dataset has images annotated from RSNA-MICCAI brain tumor radio genomic competition dataset using the make sense an AI online tool for labeling dataset. The preprocessed data is then divided into testing and training for the model. The YOLOv5 model provides a precision of 88 percent. Finally, our model is tested across the whole dataset, and it is concluded that it is able to detect brain tumors successfully.

show abstract

“…Deep neural network is one of them and used for predicting the battery life in integration with IoT [44]. Three-step DNA sequence mining is also proposed for optimization of the search results using the machine learning approach [45][46][47][48].…”

Section: Research Goals and Objectivesmentioning

confidence: 99%

Millimeter Wave All-Around Antenna Based on Whispering Gallery Mode Dielectric Resonator for IoT-Based Applications

Kogut

Annino

Bakkali

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

This work is devoted to the study of the emitting properties of azimuthally inhomogeneous segmental dielectric resonators excited by whispering gallery modes. Due to the diffraction of the azimuthal waves on local nonhomogeneities located equidistantly along the azimuthal coordinate, intense electromagnetic radiation is achieved in the azimuthal sector of the angles 0°-360°. A prototype of an all-around emitting antenna based on basis of a segmental dielectric resonator is proposed, and its characteristics in the far zone are studied. It is shown that such an antenna forms a multilobe radiation pattern (72 lobes) in the circle sector of angles. The antenna gain in the lobes at the resonant frequency reaches 12 dB. Antenna optimization is achieved in the proposed method because of the large gain produced by the antenna. It is also analyzed that these types of radiation patterns observed by antennas are well used for the Internet of Things- (IoT-) based applications.

show abstract

Filtered Multicarrier Waveforms Classification: A Deep Learning-Based Approach

Cited by 28 publications

References 44 publications

Chained Dual-Generative Adversarial Network: A Generalized Defense Against Adversarial Attacks

Chained Dual-Generative Adversarial Network: A Generalized Defense Against Adversarial Attacks

Diagnosis of Brain Tumor Using Light Weight Deep Learning Model with Fine-Tuning Approach

Millimeter Wave All-Around Antenna Based on Whispering Gallery Mode Dielectric Resonator for IoT-Based Applications

Contact Info

Product

Resources

About