osama omer | Aswan University (original) (raw)
Papers by osama omer
International Journal of Telecommunications, Nov 4, 2023
Frontiers in artificial intelligence and applications, Oct 17, 2022
Lecture Notes in Computer Science, 2015
JES. Journal of engineering sciences, 2013
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.
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.
Electronics, Apr 16, 2021
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).
Traitement Du Signal, Nov 30, 2022
Applied intelligence, Apr 1, 2024
Research Square (Research Square), Jan 25, 2024
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...
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...
Intelligent Sustainable Systems
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.
Aswan University Journal of Sciences and Technology
The present study was carried out during the three successive seasons i.e.
Aswan University Journal of Sciences and Technology
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%.
Revue d'Intelligence Artificielle
International Journal of Telecommunications, Nov 4, 2023
Frontiers in artificial intelligence and applications, Oct 17, 2022
Lecture Notes in Computer Science, 2015
JES. Journal of engineering sciences, 2013
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.
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.
Electronics, Apr 16, 2021
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).
Traitement Du Signal, Nov 30, 2022
Applied intelligence, Apr 1, 2024
Research Square (Research Square), Jan 25, 2024
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...
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...
Intelligent Sustainable Systems
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.
Aswan University Journal of Sciences and Technology
The present study was carried out during the three successive seasons i.e.
Aswan University Journal of Sciences and Technology
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%.
Revue d'Intelligence Artificielle