Mohammad A. El-Dosuky
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mohammad A. El-Dosuky has a total of 44 co-authors. Here are the top co-authors by number of shared publications:
M. Z. Rashad
12 shared publications- A. H. El-Bassiouny
Dep. of Mathematics Faculty of Sciences Mansoura University Egypt
7 shared publications - Taher Hamza
Department of Computer Sciences Faculty of Computers and Information sciences Mansoura University Egypt
7 shared publications T. T. Hamza
Faculty of Computers and Information Sciences Mansoura University Egypt
5 shared publications- Gamal H. Eladl
Mansoura University
4 shared publications A. H. El-Bassiouny
3 shared publications
Latest Publications
- Open Access
- 2 May 2025
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 14 (3) , 1830-1845
Breast cancer detection and classification using deep learning techniques based on ultrasound image
Breast cancer ranks as the most prevalent form of cancer diagnosed in women. Diagnosis faces several challenges, such as changes in the size, shape, and appearance of the breast, dense breast tissue, and lumps or thickening, especially if present in only one breast. The major challenge in the deep learning (DL) diagnosis of breast cancer is its non-uniform shape, size, and position, particularly with malignant tumors. Researchers strive through computer-aided diagnosis (CAD) systems and other methods to assist in detecting and classifying tumor types. This work proposes a DL system for analyzing medical images that improves the accuracy of breast cancer detection and classification from ultrasound (US) images. It reaches an accuracy of 99.29%, exceeding previous work. First, image processing is applied to enhance the quality of input images. Second, image segmentation is performed using the U-Net architecture. Third, many features are extracted using Mobilenet. Finally, classification is performed using visual geometry group 16 (VGG16). The accuracy of detection and classification using the proposed system was evaluated.
- 2 May 2025
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 14 (3) , 1830-1845
Open AccessBreast cancer detection and classification using deep learning techniques based on ultrasound image
Breast cancer ranks as the most prevalent form of cancer diagnosed in women. Diagnosis faces several challenges, such as changes in the size, shape, and appearance of the breast, dense breast tissue, and lumps or thickening, especially if present in only one breast. The major challenge in the deep learning (DL) diagnosis of breast cancer is its non-uniform shape, size, and position, particularly with malignant tumors. Researchers strive through computer-aided diagnosis (CAD) systems and other methods to assist in detecting and classifying tumor types. This work proposes a DL system for analyzing medical images that improves the accuracy of breast cancer detection and classification from ultrasound (US) images. It reaches an accuracy of 99.29%, exceeding previous work. First, image processing is applied to enhance the quality of input images. Second, image segmentation is performed using the U-Net architecture. Third, many features are extracted using Mobilenet. Finally, classification is performed using visual geometry group 16 (VGG16). The accuracy of detection and classification using the proposed system was evaluated.
- Open Access
- 10 January 2025
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (8) , 6233-6249
Explainable energy consumption and speed prediction in sustainable cities using deep learning
The idea of sustainable cities has drawn a lot of attention due to the quick expansion of metropolitan areas as well as the growing problems brought on by resource scarcity and climate change. Cities that prioritize sustainable practices are those that minimize their negative effects on the environment, maximize resource efficiency, and improve the standard of living for their citizens. Therefore, for sustainable cities, this paper uses the vehicle energy dataset (VED) to estimate travel times and calculate vehicle energy consumption. The dataset contains 12,609,170 road elevation tracks, 12,203,044 speed limit tracks, and 12,281,719 speed limit records with direction. An open-source routing engine called Valhalla is utilized to do a variety of tasks, including finding paths, matching maps, and creating maneuvers based on paths. The three primary stages of the suggested model are data pre-processing, feature extraction, and result interpretation. In the data pre-processing stage, null values are first eliminated and data normalization is implemented. Then, three techniques known as the gated recurrent unit (GRU), recurrent neural network (RNN), and long short-term memory (LSTM) are used to optimize the model. Finally, the results are interpreted through the use of SHAP (SHapley Additive explanations) in explainable artificial intelligence (XAI) techniques. The LSTM model yields the best prediction results, achieving 15.2662 RMSE, 11.7266 MAE, and 0.6696 R2 at 8 batch size, according to the evaluation results. Additional experiments are carried out in batch sizes of 8, 16, 32, and 64.The lowest metrics are produced by batch sizes of 64, while the best metrics are produced by batch sizes of 8.
- 10 January 2025
- Published by Springer Nature in Neural Computing and Applications
- Vol. 37 (8) , 6233-6249
Open AccessExplainable energy consumption and speed prediction in sustainable cities using deep learning
The idea of sustainable cities has drawn a lot of attention due to the quick expansion of metropolitan areas as well as the growing problems brought on by resource scarcity and climate change. Cities that prioritize sustainable practices are those that minimize their negative effects on the environment, maximize resource efficiency, and improve the standard of living for their citizens. Therefore, for sustainable cities, this paper uses the vehicle energy dataset (VED) to estimate travel times and calculate vehicle energy consumption. The dataset contains 12,609,170 road elevation tracks, 12,203,044 speed limit tracks, and 12,281,719 speed limit records with direction. An open-source routing engine called Valhalla is utilized to do a variety of tasks, including finding paths, matching maps, and creating maneuvers based on paths. The three primary stages of the suggested model are data pre-processing, feature extraction, and result interpretation. In the data pre-processing stage, null values are first eliminated and data normalization is implemented. Then, three techniques known as the gated recurrent unit (GRU), recurrent neural network (RNN), and long short-term memory (LSTM) are used to optimize the model. Finally, the results are interpreted through the use of SHAP (SHapley Additive explanations) in explainable artificial intelligence (XAI) techniques. The LSTM model yields the best prediction results, achieving 15.2662 RMSE, 11.7266 MAE, and 0.6696 R2 at 8 batch size, according to the evaluation results. Additional experiments are carried out in batch sizes of 8, 16, 32, and 64.The lowest metrics are produced by batch sizes of 64, while the best metrics are produced by batch sizes of 8.
- Open Access
Scheduling and Securing Drone Charging System Using Particle Swarm Optimization and Blockchain Technology
Unmanned aerial vehicles (UAVs) have emerged as a powerful technology for introducing untraditional solutions to many challenges in non-military fields and industrial applications in the next few years. However, the limitations of a drone’s battery and the available optimal charging techniques represent a significant challenge in using UAVs on a large scale. This problem means UAVs are unable to fly for a long time; hence, drones’ services fail dramatically. Due to this challenge, optimizing the scheduling of drone charging may be an unusual solution to drones’ battery problems. Moreover, authenticating drones and verifying their charging transactions with charging stations is an essential associated problem. This paper proposes a scheduling and secure drone charging system in response to these challenges. The proposed system was simulated on a generated dataset consisting of 300 drones and 50 charging station points to evaluate its performance. The optimization of the proposed scheduling methodology was based on the particle swarm optimization (PSO) algorithm and game theory-based auction model. In addition, authenticating and verifying drone charging transactions were executed using a proposed blockchain protocol. The optimization and scheduling results showed the PSO algorithm’s efficiency in optimizing drone routes and preventing drone collisions during charging flights with low error rates with an MAE = 0.0017 and an MSE = 0.0159. Moreover, the investigation to authenticate and verify the drone charging transactions showed the efficiency of the proposed blockchain protocol while simulating the proposed system on the Ethereum platform. The obtained results clarified the efficiency of the proposed blockchain protocol in executing drone charging transactions within a short time and low latency within an average of 0.34 s based on blockchain performance metrics. Moreover, the proposed scheduling methodology achieved a 96.8% success rate of drone charging cases, while only 3.2% of drones failed to charge after three scheduling rounds.
Open AccessScheduling and Securing Drone Charging System Using Particle Swarm Optimization and Blockchain Technology
Unmanned aerial vehicles (UAVs) have emerged as a powerful technology for introducing untraditional solutions to many challenges in non-military fields and industrial applications in the next few years. However, the limitations of a drone’s battery and the available optimal charging techniques represent a significant challenge in using UAVs on a large scale. This problem means UAVs are unable to fly for a long time; hence, drones’ services fail dramatically. Due to this challenge, optimizing the scheduling of drone charging may be an unusual solution to drones’ battery problems. Moreover, authenticating drones and verifying their charging transactions with charging stations is an essential associated problem. This paper proposes a scheduling and secure drone charging system in response to these challenges. The proposed system was simulated on a generated dataset consisting of 300 drones and 50 charging station points to evaluate its performance. The optimization of the proposed scheduling methodology was based on the particle swarm optimization (PSO) algorithm and game theory-based auction model. In addition, authenticating and verifying drone charging transactions were executed using a proposed blockchain protocol. The optimization and scheduling results showed the PSO algorithm’s efficiency in optimizing drone routes and preventing drone collisions during charging flights with low error rates with an MAE = 0.0017 and an MSE = 0.0159. Moreover, the investigation to authenticate and verify the drone charging transactions showed the efficiency of the proposed blockchain protocol while simulating the proposed system on the Ethereum platform. The obtained results clarified the efficiency of the proposed blockchain protocol in executing drone charging transactions within a short time and low latency within an average of 0.34 s based on blockchain performance metrics. Moreover, the proposed scheduling methodology achieved a 96.8% success rate of drone charging cases, while only 3.2% of drones failed to charge after three scheduling rounds.
- 16 December 2021
- Published by Springer Nature
- p. 3-13
A Deep Learning Based Cockroach Swarm Optimization Approach for Segmenting Brain MRI Images
- 16 December 2021
- Published by Springer Nature
- p. 3-13
A Deep Learning Based Cockroach Swarm Optimization Approach for Segmenting Brain MRI Images
- 29 March 2021
- Published by Springer Nature
- p. 375-384
Handling Industrial Consumer Rights by Using Blockchain
- 29 March 2021
- Published by Springer Nature
- p. 375-384
Handling Industrial Consumer Rights by Using Blockchain
- Open Access
- 1 December 2020
- Published by Egyptian Knowledge Bank in Mansoura Journal for Computer and Information Sciences
- Vol. 16 (2) , 1-9
Gene-Disease Association
Disease susceptibility prediction is defined as follows. Given training set S and a test case t∉S as a tuple (known as SNP,unknown disease), trying predicting the unknown disease with maximum accuracy. DisGeNET is a proponent dataset indisease susceptibility research. This paper reviews DisGeNET comprehensive information, before introducing a proposedsystem operating atop it. First, vetting the dataset by consolidation, and removing genes with effects beyond acertain threshold. Second, computing the empirical cumulative distribution function, using it for plotting and printing gene associations for many diseases such as, and not limited to, Alzheimer, Anemia, and Brain, breast cancer proposedmethods such as applying C4.5 & naïve Bayes give better accuracy then previous works
- 1 December 2020
- Published by Egyptian Knowledge Bank in Mansoura Journal for Computer and Information Sciences
- Vol. 16 (2) , 1-9
Open AccessGene-Disease Association
Disease susceptibility prediction is defined as follows. Given training set S and a test case t∉S as a tuple (known as SNP,unknown disease), trying predicting the unknown disease with maximum accuracy. DisGeNET is a proponent dataset indisease susceptibility research. This paper reviews DisGeNET comprehensive information, before introducing a proposedsystem operating atop it. First, vetting the dataset by consolidation, and removing genes with effects beyond acertain threshold. Second, computing the empirical cumulative distribution function, using it for plotting and printing gene associations for many diseases such as, and not limited to, Alzheimer, Anemia, and Brain, breast cancer proposedmethods such as applying C4.5 & naïve Bayes give better accuracy then previous works
- 18 May 2020
- Published by Springer Nature
- p. 631-639
Using IoT and Blockchain for Healthcare Enhancement
- 18 May 2020
- Published by Springer Nature
- p. 631-639
Using IoT and Blockchain for Healthcare Enhancement
- Open Access
- 3 April 2020
- Published by Center for Open Science in ArabiXiv
مرن : نظام تشغيل القرص باللغة العربية
مرن هو نظام تشغيل القرص باللغة الطبيعية ، و هو يشبه نظام DOS-MS الشهير ، إال أنه يمتازعليه باستخدام اللغة العربية في الواجهة ، أي واجهة عربية مئة في المائة ؛ حيث أن النظام ال يعتمد مطلقاعلى وحدة اإلخراج ( Console ( وكذلك باستخدام اللغة العربية – كـلغة طبيعية – في األوامر ، بدال منسطر األوامر )Line Command.
- 3 April 2020
- Published by Center for Open Science in ArabiXiv
Open Accessمرن : نظام تشغيل القرص باللغة العربية
مرن هو نظام تشغيل القرص باللغة الطبيعية ، و هو يشبه نظام DOS-MS الشهير ، إال أنه يمتازعليه باستخدام اللغة العربية في الواجهة ، أي واجهة عربية مئة في المائة ؛ حيث أن النظام ال يعتمد مطلقاعلى وحدة اإلخراج ( Console ( وكذلك باستخدام اللغة العربية – كـلغة طبيعية – في األوامر ، بدال منسطر األوامر )Line Command.
- Open Access
- 18 February 2020
- Published by Center for Open Science in ArabiXiv
بيان : نظام الاستعلامات في قواعد البيانات باللغة العربية
بيان هي نظام باللغة العربية( للتنقيب المعلوماتي )Mining Data ،)و هي تشبه وحدةالتحليل و باللغة اإلنجليزية )Querying English & Component Analysis )في نظامServer SQL Microsoft ، بل إنها تمضي قدما لتتشابه مع نظم التنقيب المعلوماتي المتقدمة ؛حيث تقدم إمكانية استخراج بيانات بشكل متقدم لا يقتصر على الاستعلام بأسماء األعمدة ، بل "تغوص" فيالجدول وتحلله ، لتسمح باالستعالم بأحد قيم الخاليا.
- 18 February 2020
- Published by Center for Open Science in ArabiXiv
Open Accessبيان : نظام الاستعلامات في قواعد البيانات باللغة العربية
بيان هي نظام باللغة العربية( للتنقيب المعلوماتي )Mining Data ،)و هي تشبه وحدةالتحليل و باللغة اإلنجليزية )Querying English & Component Analysis )في نظامServer SQL Microsoft ، بل إنها تمضي قدما لتتشابه مع نظم التنقيب المعلوماتي المتقدمة ؛حيث تقدم إمكانية استخراج بيانات بشكل متقدم لا يقتصر على الاستعلام بأسماء األعمدة ، بل "تغوص" فيالجدول وتحلله ، لتسمح باالستعالم بأحد قيم الخاليا.