osama omer | Aswan University (original) (raw)

Papers by osama omer

Research paper thumbnail of Design and Implementation of a Diagnostic Solid Propellant Fuel System Based on Laser Illuminator

International Journal of Telecommunications, Nov 4, 2023

Research paper thumbnail of Image Super-Resolution Based on Alternative Registration, Blur Identification and Reconstruction

Research paper thumbnail of Referenceless Image Quality Assessment Utilizing Deep Transfer-Learned Features

Frontiers in artificial intelligence and applications, Oct 17, 2022

Research paper thumbnail of Efficient Resolution Enhancement Algorithm for Compressive Sensing Magnetic Resonance Image Reconstruction

Lecture Notes in Computer Science, 2015

Research paper thumbnail of Region Based Medical Image Registration Approach Using a Modified Artificial Immune System

JES. Journal of engineering sciences, 2013

Research paper thumbnail of Reconstruction of High Resolution Computed Tomography Image from Sinogram Space Using Adaptive Row Projection

International journal of bio-science and bio-technology, Feb 28, 2014

We deal with the reconstruction of the high-resolution (HR) computed tomography (CT) image from t... more We deal with the reconstruction of the high-resolution (HR) computed tomography (CT) image from the CT projection data (Sinogram). Spatial resolution is one of the important parameters of CT images. Spatial resolution is a measure of how close to each other two objects that can still be distinguished. The spatial resolution of CT images depends on the field of view which in turn depends on the number of projections and the number of samples per projection. One way to increase the spatial resolution of the reconstructed images is to reduce the pixel size; however, this may require hardware alteration. Another way to increase the spatial resolution is to apply super-resolution (SR) technique on the lowresolution (LR) images. The conventional method for resolution enhancement is to apply SR technique as a post-process after LR CT images reconstruction. One drawback of this conventional method is that; performing two consequence steps, reconstruction and SR, requires more parameters to be tuned. Unlike the conventional method, we propose to simultaneously estimate HR image with the reconstruction step from the CT projection data, which indeed reduce the overall processing time and the required tuned parameters. On the other hand, even if the back-projection (BP) method is attractive because of its simplicity and low computational cost, it produces sub-optimal images with respect to artifacts, resolution, and noise. On contrast, iterative image reconstruction allows to easily model constraints and to incorporate prior knowledge which leads to better image quality. Therefore, in this paper, we employ the iterative reconstruction based on regularized Kaczmarz minimization algorithm, for its fast convergence, in the resolution enhancement as a post-process as well as simultaneous reconstruction and resolution enhancement methods.

Research paper thumbnail of Promising Deep Semantic Nuclei Segmentation Models for Multi-Institutional Histopathology Images of Different Organs

International Journal of Interactive Multimedia and Artificial Intelligence, 2021

Nuclei segmentation in whole-slide imaging (WSI) plays a crucial role in the field of computation... more Nuclei segmentation in whole-slide imaging (WSI) plays a crucial role in the field of computational pathology. It is a fundamental task for different applications, such as cancer cell type classification, cancer grading, and cancer subtype classification. However, existing nuclei segmentation methods face many challenges, such as color variation in histopathological images, the overlapping and clumped nuclei, and the ambiguous boundary between different cell nuclei, that limit their performance. In this paper, we present promising deep semantic nuclei segmentation models for multi-institutional WSI images (i.e., collected from different scanners) of different organs. Specifically, we study the performance of pertinent deep learning-based models with nuclei segmentation in WSI images of different stains and various organs. We also propose a feasible deep learning nuclei segmentation model formed by combining robust deep learning architectures. A comprehensive comparative study with existing software and related methods in terms of different evaluation metrics and the number of parameters of each model, emphasizes the efficacy of the proposed nuclei segmentation models.

Research paper thumbnail of Efficient Stain-Aware Nuclei Segmentation Deep Learning Framework for Multi-Center Histopathological Images

Electronics, Apr 16, 2021

Research paper thumbnail of Performance Evaluation of mm-Wave RoF Systems Using APSK Modulation

Radio over fiber (RoF) technology is considered a promising broadband technology especially when ... more Radio over fiber (RoF) technology is considered a promising broadband technology especially when it merged with the large unused bandwidth of millimeter-wave (mm-wave) frequencies. Selecting an appropriate modulation format for mm-wave RoF system will specify the overall performance of the system. In this paper, we proposed using amplitude phase shift keying (APSK) digital modulation for mm-wave RoF system. APSK is considered an attractive modulation scheme for digital transmission over fiber due to the power and spectral efficiencies as well as its robustness against nonlinear distortions. In comparison to the other digital modulations, simulation results show that APSK achieved a low peak-to-average power ratio (PAPR) and very limited power loss compared to quadrature amplitude modulation (QAM). But the bit error rate (BER) shows that QAM modulation has a slightly lower BER than APSK for high signal-to-noise ratio (SNR).

Research paper thumbnail of Beat-by-Beat ECG Monitoring from Photoplythmography Based on Scattering Wavelet Transform

Traitement Du Signal, Nov 30, 2022

Research paper thumbnail of Video-based beat-by-beat blood pressure monitoring via transfer deep-learning

Applied intelligence, Apr 1, 2024

Research paper thumbnail of Low Complexity Cooperative Active and Passive Beamforming multi-RIS assisted Communication Networks

Research Square (Research Square), Jan 25, 2024

Research paper thumbnail of Subject-Independent per Beat PPG to Single-Lead ECG Mapping

Information

In this paper, a beat-based autoencoder is proposed for mapping photoplethysmography (PPG) to a s... more In this paper, a beat-based autoencoder is proposed for mapping photoplethysmography (PPG) to a single-lead electrocardiogram (single-lead ECG) signal. The main limiting factors represented in uncleaned data, subject dependency, and erroneous beat segmentation are regarded. The dataset is cleaned by a two-stage clustering approach. Rather than complete single–lead ECG signal reconstruction, a beat-based PPG-to-single-lead-ECG (PPG2ECG) conversion is introduced for providing a simple lightweight model that meets the computational capabilities of wearable devices. In addition, peak-to-peak segmentation is employed for alleviating errors in PPG onset detection. Furthermore, subject-dependent training is highlighted as a critical factor in training procedures because most existing work includes different beats/signals from the same subject’s record in both training and testing sets. So, we provide a completely subject-independent model where the testing subjects’ records are hidden in t...

Research paper thumbnail of Blood Pressure Estimation from Photoplythmography Using Hybrid Scattering–LSTM Networks

One of the most significant indicators of heart and cardiovascular health is blood pressure (BP).... more One of the most significant indicators of heart and cardiovascular health is blood pressure (BP). Blood pressure (BP) has gained great attention in the last decade. Uncontrolled high blood pressure increases the risk of serious health problems, including heart attack and stroke. Recently, machine/deep learning is leveraged for learning the BP from Photoplethysmography (PPG) signals. Hence, continuous BP monitoring can be introduced based on simple wearable contact sensors or even remotely sensed from a proper camera away from the clinical setup. However, the available training dataset imposes many limitations besides the other difficulties related to the PPG time series as high-dimensional data. This work presents beat-by-beat continuous PPG-based BP monitoring while accounting for the aforementioned limitations. For a better exploration of beats’ features, we propose to use wavelet scattering transform as a better descriptive domain to cope with the limitation of the training datas...

Research paper thumbnail of Robust Facial-Based Inter-Beat Interval Estimation Through Spectral Signature Tracking and Periodic Filtering

Intelligent Sustainable Systems

Research paper thumbnail of An efficient and reliable OFDM channel state estimator using deep learning convolutional neural networks

JES. Journal of engineering sciences, Sep 5, 2023

Orthogonal frequency division multiplexing (OFDM) wireless systems rely heavily on channel state ... more Orthogonal frequency division multiplexing (OFDM) wireless systems rely heavily on channel state estimation (CSE) to mitigate the effects of multipath channel fading. Achieving a high data rate with OFDM technology requires efficient CSE and accurate signal detection. In contrast to more traditional CSE methods that depend on a model-based strategy, machine learning (ML)-based CSE techniques have attracted increased interest in recent years due to their data-driven, learning-based flexibility. In light of this, a deep learning (DL) convolutional neural network (CNN) is utilized to acquire reliable CSE over OFDM wireless system Rayleigh-fading channels. The suggested CSE utilizes offline training to gather channel information from transmit/receive pairs. In addition, it employs pilots to provide additional guidance on channels of communication. The proposed CNN-based estimator is compared to conventional estimation approaches and state-of-the-art DL channel estimators using SER analysis. The simulation results show that the proposed CNN estimator provides far superior SER performance compared to the conventional LS and MMSE estimation methods. Also, the proposed CNN CSE performs similarly to the DL BiLSTM estimator with restricted training pilots (8). Furthermore, CNN CSE beats DL BiLSTM with enough training pilots (64). The simulation findings also confirm that the suggested CNN-based CSE is efficient/reliable with (16 and 8) or without cycle prefixes (CP). This, in turn, reduces the bandwidth required to convey the same quantity of data. In addition, there is no background knowledge of the channel's statistics in the proposed estimator. Consequently, the proposed method shows potential for addressing CSE issues in OFDM systems with a significant spectrum resource reduction.

Research paper thumbnail of Selection response for grain yield and its components in one segregating population of bread wheat (Triticum aestivum. L)

Aswan University Journal of Sciences and Technology

The present study was carried out during the three successive seasons i.e.

Research paper thumbnail of Diabetic retinopathy detection in eye fundus images using deep transfer learning and robust feature extractors

Aswan University Journal of Sciences and Technology

Research paper thumbnail of Solar Cell Anomaly Detection Based on Wavelet Scattering Transform and Artificial Intelligence

Aswan University Journal of Sciences and Technology

The detection of the anomalies of the solar cells is done by testing the cells in the lab. Howeve... more The detection of the anomalies of the solar cells is done by testing the cells in the lab. However, this method is time consuming and expensive. The analysis of infrared solar cell images can reveal its status by classifying infrared images into anomaly and non-anomaly classes. The anomality can be due to many reasons. Therefore, it is required to not only classify image into anomaly and non-anomaly, but also, detect the anomality type. The image-based solar cell anomaly detection methods appearing in the literature used either machine learning or deep learning techniques. The main disadvantages of these methods are the lack of sufficient dataset and/or utilizing inappropriate features for classification. Machine learning requires robust feature extractor which are independent on the imaging condition. On the other hand, deep learning techniques doesn't require feature extractor, however, results depend on the implemented filters in the network i.e the network architecture. In this proposal, we deal with multi-class anomaly detection from infrared images by using better representation of the images features by using Wavelet scattering Transform (WST). The WST coefficients are stable under signal deformations and globally invariant to signal translation and rotation. Based on the simulation results, the proposed method achieved an average accuracy of 99.98%.

Research paper thumbnail of Deep Learning Networks for Non-Destructive Detection of Food Irradiation

Revue d'Intelligence Artificielle

Research paper thumbnail of Design and Implementation of a Diagnostic Solid Propellant Fuel System Based on Laser Illuminator

International Journal of Telecommunications, Nov 4, 2023

Research paper thumbnail of Image Super-Resolution Based on Alternative Registration, Blur Identification and Reconstruction

Research paper thumbnail of Referenceless Image Quality Assessment Utilizing Deep Transfer-Learned Features

Frontiers in artificial intelligence and applications, Oct 17, 2022

Research paper thumbnail of Efficient Resolution Enhancement Algorithm for Compressive Sensing Magnetic Resonance Image Reconstruction

Lecture Notes in Computer Science, 2015

Research paper thumbnail of Region Based Medical Image Registration Approach Using a Modified Artificial Immune System

JES. Journal of engineering sciences, 2013

Research paper thumbnail of Reconstruction of High Resolution Computed Tomography Image from Sinogram Space Using Adaptive Row Projection

International journal of bio-science and bio-technology, Feb 28, 2014

We deal with the reconstruction of the high-resolution (HR) computed tomography (CT) image from t... more We deal with the reconstruction of the high-resolution (HR) computed tomography (CT) image from the CT projection data (Sinogram). Spatial resolution is one of the important parameters of CT images. Spatial resolution is a measure of how close to each other two objects that can still be distinguished. The spatial resolution of CT images depends on the field of view which in turn depends on the number of projections and the number of samples per projection. One way to increase the spatial resolution of the reconstructed images is to reduce the pixel size; however, this may require hardware alteration. Another way to increase the spatial resolution is to apply super-resolution (SR) technique on the lowresolution (LR) images. The conventional method for resolution enhancement is to apply SR technique as a post-process after LR CT images reconstruction. One drawback of this conventional method is that; performing two consequence steps, reconstruction and SR, requires more parameters to be tuned. Unlike the conventional method, we propose to simultaneously estimate HR image with the reconstruction step from the CT projection data, which indeed reduce the overall processing time and the required tuned parameters. On the other hand, even if the back-projection (BP) method is attractive because of its simplicity and low computational cost, it produces sub-optimal images with respect to artifacts, resolution, and noise. On contrast, iterative image reconstruction allows to easily model constraints and to incorporate prior knowledge which leads to better image quality. Therefore, in this paper, we employ the iterative reconstruction based on regularized Kaczmarz minimization algorithm, for its fast convergence, in the resolution enhancement as a post-process as well as simultaneous reconstruction and resolution enhancement methods.

Research paper thumbnail of Promising Deep Semantic Nuclei Segmentation Models for Multi-Institutional Histopathology Images of Different Organs

International Journal of Interactive Multimedia and Artificial Intelligence, 2021

Nuclei segmentation in whole-slide imaging (WSI) plays a crucial role in the field of computation... more Nuclei segmentation in whole-slide imaging (WSI) plays a crucial role in the field of computational pathology. It is a fundamental task for different applications, such as cancer cell type classification, cancer grading, and cancer subtype classification. However, existing nuclei segmentation methods face many challenges, such as color variation in histopathological images, the overlapping and clumped nuclei, and the ambiguous boundary between different cell nuclei, that limit their performance. In this paper, we present promising deep semantic nuclei segmentation models for multi-institutional WSI images (i.e., collected from different scanners) of different organs. Specifically, we study the performance of pertinent deep learning-based models with nuclei segmentation in WSI images of different stains and various organs. We also propose a feasible deep learning nuclei segmentation model formed by combining robust deep learning architectures. A comprehensive comparative study with existing software and related methods in terms of different evaluation metrics and the number of parameters of each model, emphasizes the efficacy of the proposed nuclei segmentation models.

Research paper thumbnail of Efficient Stain-Aware Nuclei Segmentation Deep Learning Framework for Multi-Center Histopathological Images

Electronics, Apr 16, 2021

Research paper thumbnail of Performance Evaluation of mm-Wave RoF Systems Using APSK Modulation

Radio over fiber (RoF) technology is considered a promising broadband technology especially when ... more Radio over fiber (RoF) technology is considered a promising broadband technology especially when it merged with the large unused bandwidth of millimeter-wave (mm-wave) frequencies. Selecting an appropriate modulation format for mm-wave RoF system will specify the overall performance of the system. In this paper, we proposed using amplitude phase shift keying (APSK) digital modulation for mm-wave RoF system. APSK is considered an attractive modulation scheme for digital transmission over fiber due to the power and spectral efficiencies as well as its robustness against nonlinear distortions. In comparison to the other digital modulations, simulation results show that APSK achieved a low peak-to-average power ratio (PAPR) and very limited power loss compared to quadrature amplitude modulation (QAM). But the bit error rate (BER) shows that QAM modulation has a slightly lower BER than APSK for high signal-to-noise ratio (SNR).

Research paper thumbnail of Beat-by-Beat ECG Monitoring from Photoplythmography Based on Scattering Wavelet Transform

Traitement Du Signal, Nov 30, 2022

Research paper thumbnail of Video-based beat-by-beat blood pressure monitoring via transfer deep-learning

Applied intelligence, Apr 1, 2024

Research paper thumbnail of Low Complexity Cooperative Active and Passive Beamforming multi-RIS assisted Communication Networks

Research Square (Research Square), Jan 25, 2024

Research paper thumbnail of Subject-Independent per Beat PPG to Single-Lead ECG Mapping

Information

In this paper, a beat-based autoencoder is proposed for mapping photoplethysmography (PPG) to a s... more In this paper, a beat-based autoencoder is proposed for mapping photoplethysmography (PPG) to a single-lead electrocardiogram (single-lead ECG) signal. The main limiting factors represented in uncleaned data, subject dependency, and erroneous beat segmentation are regarded. The dataset is cleaned by a two-stage clustering approach. Rather than complete single–lead ECG signal reconstruction, a beat-based PPG-to-single-lead-ECG (PPG2ECG) conversion is introduced for providing a simple lightweight model that meets the computational capabilities of wearable devices. In addition, peak-to-peak segmentation is employed for alleviating errors in PPG onset detection. Furthermore, subject-dependent training is highlighted as a critical factor in training procedures because most existing work includes different beats/signals from the same subject’s record in both training and testing sets. So, we provide a completely subject-independent model where the testing subjects’ records are hidden in t...

Research paper thumbnail of Blood Pressure Estimation from Photoplythmography Using Hybrid Scattering–LSTM Networks

One of the most significant indicators of heart and cardiovascular health is blood pressure (BP).... more One of the most significant indicators of heart and cardiovascular health is blood pressure (BP). Blood pressure (BP) has gained great attention in the last decade. Uncontrolled high blood pressure increases the risk of serious health problems, including heart attack and stroke. Recently, machine/deep learning is leveraged for learning the BP from Photoplethysmography (PPG) signals. Hence, continuous BP monitoring can be introduced based on simple wearable contact sensors or even remotely sensed from a proper camera away from the clinical setup. However, the available training dataset imposes many limitations besides the other difficulties related to the PPG time series as high-dimensional data. This work presents beat-by-beat continuous PPG-based BP monitoring while accounting for the aforementioned limitations. For a better exploration of beats’ features, we propose to use wavelet scattering transform as a better descriptive domain to cope with the limitation of the training datas...

Research paper thumbnail of Robust Facial-Based Inter-Beat Interval Estimation Through Spectral Signature Tracking and Periodic Filtering

Intelligent Sustainable Systems

Research paper thumbnail of An efficient and reliable OFDM channel state estimator using deep learning convolutional neural networks

JES. Journal of engineering sciences, Sep 5, 2023

Orthogonal frequency division multiplexing (OFDM) wireless systems rely heavily on channel state ... more Orthogonal frequency division multiplexing (OFDM) wireless systems rely heavily on channel state estimation (CSE) to mitigate the effects of multipath channel fading. Achieving a high data rate with OFDM technology requires efficient CSE and accurate signal detection. In contrast to more traditional CSE methods that depend on a model-based strategy, machine learning (ML)-based CSE techniques have attracted increased interest in recent years due to their data-driven, learning-based flexibility. In light of this, a deep learning (DL) convolutional neural network (CNN) is utilized to acquire reliable CSE over OFDM wireless system Rayleigh-fading channels. The suggested CSE utilizes offline training to gather channel information from transmit/receive pairs. In addition, it employs pilots to provide additional guidance on channels of communication. The proposed CNN-based estimator is compared to conventional estimation approaches and state-of-the-art DL channel estimators using SER analysis. The simulation results show that the proposed CNN estimator provides far superior SER performance compared to the conventional LS and MMSE estimation methods. Also, the proposed CNN CSE performs similarly to the DL BiLSTM estimator with restricted training pilots (8). Furthermore, CNN CSE beats DL BiLSTM with enough training pilots (64). The simulation findings also confirm that the suggested CNN-based CSE is efficient/reliable with (16 and 8) or without cycle prefixes (CP). This, in turn, reduces the bandwidth required to convey the same quantity of data. In addition, there is no background knowledge of the channel's statistics in the proposed estimator. Consequently, the proposed method shows potential for addressing CSE issues in OFDM systems with a significant spectrum resource reduction.

Research paper thumbnail of Selection response for grain yield and its components in one segregating population of bread wheat (Triticum aestivum. L)

Aswan University Journal of Sciences and Technology

The present study was carried out during the three successive seasons i.e.

Research paper thumbnail of Diabetic retinopathy detection in eye fundus images using deep transfer learning and robust feature extractors

Aswan University Journal of Sciences and Technology

Research paper thumbnail of Solar Cell Anomaly Detection Based on Wavelet Scattering Transform and Artificial Intelligence

Aswan University Journal of Sciences and Technology

The detection of the anomalies of the solar cells is done by testing the cells in the lab. Howeve... more The detection of the anomalies of the solar cells is done by testing the cells in the lab. However, this method is time consuming and expensive. The analysis of infrared solar cell images can reveal its status by classifying infrared images into anomaly and non-anomaly classes. The anomality can be due to many reasons. Therefore, it is required to not only classify image into anomaly and non-anomaly, but also, detect the anomality type. The image-based solar cell anomaly detection methods appearing in the literature used either machine learning or deep learning techniques. The main disadvantages of these methods are the lack of sufficient dataset and/or utilizing inappropriate features for classification. Machine learning requires robust feature extractor which are independent on the imaging condition. On the other hand, deep learning techniques doesn't require feature extractor, however, results depend on the implemented filters in the network i.e the network architecture. In this proposal, we deal with multi-class anomaly detection from infrared images by using better representation of the images features by using Wavelet scattering Transform (WST). The WST coefficients are stable under signal deformations and globally invariant to signal translation and rotation. Based on the simulation results, the proposed method achieved an average accuracy of 99.98%.

Research paper thumbnail of Deep Learning Networks for Non-Destructive Detection of Food Irradiation

Revue d'Intelligence Artificielle