Mohamed Zorkany
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Mohamed Zorkany has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Ayman El-Sayed
Computer Science and Engineering Department, Faculty of Electronic Engineering, Menoufia University, Menouf, Egypt
3 shared publications - Emad Abd-Elrahman
National Telecommunication Institute
3 shared publications Ramadan Gad
3 shared publications- Ahmed I. Galal
Faculty of Engineering, Minia University, Minia 61519, Egypt
2 shared publications - Mahmoud Hussein
Department of Electronics, National Telecommunication Institute (NTI), Cairo 11768, Egypt
2 shared publications Nawal El-Fishawy
2 shared publications
Latest Publications
- Open Access
- 30 September 2025
- Published by Journal of Biological Methods in Health Psychology Research
- Vol. 13 (3) , e81240023
LoRA-MedSim: An Enhanced Multimodal Framework for Clinical Reasoning and Realistic Patient-Doctor Interaction
Background Present-day medical artificial intelligence (AI) models for medical visual question answering and report generation frequently function passively. Rather than simulating the dynamic nature of clinical workflow, they primarily respond to direct commands. This restricts their applicability in real-world healthcare settings, where complex reasoning and multi-turn dialogue are crucial. Objective This paper proposes a novel multimodal framework, based on Low-Rank Adaptation (LoRA), that simulates authentic doctor–patient interactions. The objective is to develop an AI assistant capable of participating in multi-turn diagnostic conversations with improved reasoning, interpreting radiological images, and addressing patient queries. Methods We used a curated and enriched version of the VQA-Med CLEF 2019 dataset to perform LoRA fine-tuning on a large-scale vision–language model. To train the model for both visual diagnosis and natural language interaction, the dataset was supplemented with simulated patient queries, radiological reports, and follow-up questions. Results Compared with baseline and prompt-based methods, our model demonstrated superior performance. It achieved higher accuracy and lower loss values while producing outputs that were more interpretable across both textual and visual domains. The model’s capacity to manage intricate, multi-turn diagnostic queries was further validated through structured assessments. Conclusion The proposed framework represents a significant advancement toward AI assistants designed for therapeutic settings. By integrating dialogue-based reasoning with multimodal understanding, it bridges the gap between passive AI tools and active diagnostic agents capable of interacting with patient data in real-world clinical scenarios.
- 30 September 2025
- Published by Journal of Biological Methods in Health Psychology Research
- Vol. 13 (3) , e81240023
Open AccessLoRA-MedSim: An Enhanced Multimodal Framework for Clinical Reasoning and Realistic Patient-Doctor Interaction
Background Present-day medical artificial intelligence (AI) models for medical visual question answering and report generation frequently function passively. Rather than simulating the dynamic nature of clinical workflow, they primarily respond to direct commands. This restricts their applicability in real-world healthcare settings, where complex reasoning and multi-turn dialogue are crucial. Objective This paper proposes a novel multimodal framework, based on Low-Rank Adaptation (LoRA), that simulates authentic doctor–patient interactions. The objective is to develop an AI assistant capable of participating in multi-turn diagnostic conversations with improved reasoning, interpreting radiological images, and addressing patient queries. Methods We used a curated and enriched version of the VQA-Med CLEF 2019 dataset to perform LoRA fine-tuning on a large-scale vision–language model. To train the model for both visual diagnosis and natural language interaction, the dataset was supplemented with simulated patient queries, radiological reports, and follow-up questions. Results Compared with baseline and prompt-based methods, our model demonstrated superior performance. It achieved higher accuracy and lower loss values while producing outputs that were more interpretable across both textual and visual domains. The model’s capacity to manage intricate, multi-turn diagnostic queries was further validated through structured assessments. Conclusion The proposed framework represents a significant advancement toward AI assistants designed for therapeutic settings. By integrating dialogue-based reasoning with multimodal understanding, it bridges the gap between passive AI tools and active diagnostic agents capable of interacting with patient data in real-world clinical scenarios.
- Open Access
- 16 May 2025
- Published by Conscientia Beam in Review of Computer Engineering Research
- Vol. 12 (2) , 22-47
Integrating artificial intelligence with the Internet of Things for state-of-the-art medical care systems
The goal of this study is to investigate the AIoT the integration of artificial intelligence (AI) and the Internet of Things (IoT) in healthcare systems and to create a thorough research plan that will look at different machine learning approaches in IoT-based e-health systems. Using a survey-based methodology, this study independently investigates the current uses of machine learning and the Internet of Things in the healthcare industry. It emphasizes how effective these technologies are and how integrating AIoT could lead to benefits. Initial results show that although AI and IoT work well together in a variety of IT applications, their combination in healthcare with AIoT offers more potential. In order to enhance continuous monitoring of data and decision-making procedures in e-health systems, the study identifies important gaps and opportunities for developing machine learning algorithms. With an emphasis on overcoming obstacles and seizing opportunities to maximize e-health systems, the knowledge gathered from this study can direct future advancements in AIoT for healthcare. For IT developers and healthcare experts hoping to successfully deploy AIoT systems, this will have real-world repercussions.
- 16 May 2025
- Published by Conscientia Beam in Review of Computer Engineering Research
- Vol. 12 (2) , 22-47
Open AccessIntegrating artificial intelligence with the Internet of Things for state-of-the-art medical care systems
The goal of this study is to investigate the AIoT the integration of artificial intelligence (AI) and the Internet of Things (IoT) in healthcare systems and to create a thorough research plan that will look at different machine learning approaches in IoT-based e-health systems. Using a survey-based methodology, this study independently investigates the current uses of machine learning and the Internet of Things in the healthcare industry. It emphasizes how effective these technologies are and how integrating AIoT could lead to benefits. Initial results show that although AI and IoT work well together in a variety of IT applications, their combination in healthcare with AIoT offers more potential. In order to enhance continuous monitoring of data and decision-making procedures in e-health systems, the study identifies important gaps and opportunities for developing machine learning algorithms. With an emphasis on overcoming obstacles and seizing opportunities to maximize e-health systems, the knowledge gathered from this study can direct future advancements in AIoT for healthcare. For IT developers and healthcare experts hoping to successfully deploy AIoT systems, this will have real-world repercussions.
- Open Access
- 21 December 2022
- Published by Springer Nature in Research Square
Real-Time Outdoor Localization Improvement for IoT Anchor Nodes
Real-time localization improvement is needed in most Internet of Things (IoT) applications that require accurate knowledge of the physical location of IoT devices, especially in the areas that having a weak GPS signals or in moving objects like smart bike-sharing, robots, and off- roads vehicles. Recently, most outdoor localizations use a hybrid mechanism integrating some IoT devices occupying with GPS (Anchor Nodes) and others IoT devices with wireless sensors nodes like LoRaWAN (without GPS-Unknown node). This hybrid method employed to achieve low power consumption and low cost solution. Our proposed work focuses on determining the Anchor node locations with high accuracy to enhance the overall accuracy of all IoT nodes. To achieve this goal, the installation of low power consummations and low-cost localization sensors modules will be used in the proposed Anchor IoT node. These modules as inertial measuring unit (IMU) will integrate with a low cost Global Positioning System (GPS) module to enhance the locations accuracy of these IoT devices. Then, the proposed method will be implemented on AVR microcontroller (ATMega 128) to develop an IoT enhanced localization unit. The general structure of the proposed method from a mathematical point of view is presented with recursive algorithm update equations. Moreover, this paper will show how the IoT device’s state can be known accurately and at a high update rate (100Hz, 10 milliseconds).
- 21 December 2022
- Published by Springer Nature in Research Square
Open AccessReal-Time Outdoor Localization Improvement for IoT Anchor Nodes
Real-time localization improvement is needed in most Internet of Things (IoT) applications that require accurate knowledge of the physical location of IoT devices, especially in the areas that having a weak GPS signals or in moving objects like smart bike-sharing, robots, and off- roads vehicles. Recently, most outdoor localizations use a hybrid mechanism integrating some IoT devices occupying with GPS (Anchor Nodes) and others IoT devices with wireless sensors nodes like LoRaWAN (without GPS-Unknown node). This hybrid method employed to achieve low power consumption and low cost solution. Our proposed work focuses on determining the Anchor node locations with high accuracy to enhance the overall accuracy of all IoT nodes. To achieve this goal, the installation of low power consummations and low-cost localization sensors modules will be used in the proposed Anchor IoT node. These modules as inertial measuring unit (IMU) will integrate with a low cost Global Positioning System (GPS) module to enhance the locations accuracy of these IoT devices. Then, the proposed method will be implemented on AVR microcontroller (ATMega 128) to develop an IoT enhanced localization unit. The general structure of the proposed method from a mathematical point of view is presented with recursive algorithm update equations. Moreover, this paper will show how the IoT device’s state can be known accurately and at a high update rate (100Hz, 10 milliseconds).
- Open Access
Smart Cognitive IoT Devices Using Multi-Layer Perception Neural Network on Limited Microcontroller
The Internet of Things (IoT) era is mainly dependent on the word “Smart”, such as smart cities, smart homes, and smart cars. This aspect can be achieved through the merging of machine learning algorithms with IoT computing models. By adding the Artificial Intelligence (AI) algorithms to IoT, the result is the Cognitive IoT (CIoT). In the automotive industry, many researchers worked on self-diagnosis systems using deep learning, but most of them performed this process on the cloud due to the hardware limitations of the end-devices, and the devices obtain the decision via the cloud servers. Others worked with simple traditional algorithms of machine learning to solve these limitations of the processing capabilities of the end-devices. In this paper, a self-diagnosis smart device is introduced with fast responses and little overhead using the Multi-Layer Perceptron Neural Network (MLP-NN) as a deep learning technique. The MLP-NN learning stage is performed using a Tensorflow framework to generate an MLP model’s parameters. Then, the MLP-NN model is implemented using these model’s parameters on a low cost end-device such as ARM Cortex-M Series architecture. After implementing the MLP-NN model, the IoT implementation is built to publish the decision results. With the proposed implemented method for the smart device, the output decision based on sensors values can be taken by the IoT node itself without returning to the cloud. For comparison, another solution is proposed for the cloud-based architecture, where the MLP-NN model is implemented on Cloud. The results clarify a successful implemented MLP-NN model for little capabilities end-devices, where the smart device solution has a lower traffic and latency than the cloud-based solution.
Open AccessSmart Cognitive IoT Devices Using Multi-Layer Perception Neural Network on Limited Microcontroller
The Internet of Things (IoT) era is mainly dependent on the word “Smart”, such as smart cities, smart homes, and smart cars. This aspect can be achieved through the merging of machine learning algorithms with IoT computing models. By adding the Artificial Intelligence (AI) algorithms to IoT, the result is the Cognitive IoT (CIoT). In the automotive industry, many researchers worked on self-diagnosis systems using deep learning, but most of them performed this process on the cloud due to the hardware limitations of the end-devices, and the devices obtain the decision via the cloud servers. Others worked with simple traditional algorithms of machine learning to solve these limitations of the processing capabilities of the end-devices. In this paper, a self-diagnosis smart device is introduced with fast responses and little overhead using the Multi-Layer Perceptron Neural Network (MLP-NN) as a deep learning technique. The MLP-NN learning stage is performed using a Tensorflow framework to generate an MLP model’s parameters. Then, the MLP-NN model is implemented using these model’s parameters on a low cost end-device such as ARM Cortex-M Series architecture. After implementing the MLP-NN model, the IoT implementation is built to publish the decision results. With the proposed implemented method for the smart device, the output decision based on sensors values can be taken by the IoT node itself without returning to the cloud. For comparison, another solution is proposed for the cloud-based architecture, where the MLP-NN model is implemented on Cloud. The results clarify a successful implemented MLP-NN model for little capabilities end-devices, where the smart device solution has a lower traffic and latency than the cloud-based solution.
- Open Access
- 1 January 2022
- Published by Walter de Gruyter GmbH in International Journal on Smart Sensing and Intelligent Systems
- Vol. 15 (1)
Real time IoT mobile anchor nodes outdoor localization mechanism
Recently, most outdoor localizations use a hybrid mechanism that integrating some IoT devices occupying with GPS (Anchor Nodes) and other wireless sensor nodes like LoRaWAN (without GPS-Unknown node). This hybrid method employed to achieve low power consumption and low cost solution. Our proposed framework focuses on determining the Mobile Anchor node locations with high accuracy to enhance the overall accuracy of all IoT nodes. To achieve this goal, the installation of low power consummations and low-cost localization sensors modules will be used in the proposed Anchor IoT node. These modules are the inertial measuring unit (IMU) and the low cost Global Positioning System (GPS). Then, this method will be implemented on AVR microcontroller (ATMega 128) to develop an IoT enhanced localization unit. The achieved results for our proposal show how the IoT device's state can be known accurately and at a high update rate (100 Hz, 10 milliseconds).
- 1 January 2022
- Published by Walter de Gruyter GmbH in International Journal on Smart Sensing and Intelligent Systems
- Vol. 15 (1)
Open AccessReal time IoT mobile anchor nodes outdoor localization mechanism
Recently, most outdoor localizations use a hybrid mechanism that integrating some IoT devices occupying with GPS (Anchor Nodes) and other wireless sensor nodes like LoRaWAN (without GPS-Unknown node). This hybrid method employed to achieve low power consumption and low cost solution. Our proposed framework focuses on determining the Mobile Anchor node locations with high accuracy to enhance the overall accuracy of all IoT nodes. To achieve this goal, the installation of low power consummations and low-cost localization sensors modules will be used in the proposed Anchor IoT node. These modules are the inertial measuring unit (IMU) and the low cost Global Positioning System (GPS). Then, this method will be implemented on AVR microcontroller (ATMega 128) to develop an IoT enhanced localization unit. The achieved results for our proposal show how the IoT device's state can be known accurately and at a high update rate (100 Hz, 10 milliseconds).
- Open Access
- 7 March 2021
- Published by MDPI AG in Electronics
- Vol. 10 (5) , 622
Design of a Memristor-Based Digital to Analog Converter (DAC)
A memristor element has been highlighted in recent years and has been applied to several applications. In this work, a memristor-based digital to analog converter (DAC) was proposed due to the fact that a memristor has low area, low power, and a low threshold voltage. The proposed memristor DAC depends on the basic DAC cell, consisting of two memristors connected in opposite directions. This basic DAC cell was used to build and simulate both a 4 bit and an 8 bit DAC. Moreover, a sneak path issue was illustrated and its solution was provided. The proposed design reduced the area by 40%. The 8 bit memristor DAC has been designed and used in a successive approximation register analog to digital converter (SAR-ADC) instead of in a capacitor DAC (which would require a large area and consume more switching power). The SAR-ADC with a memristor-based DAC achieves a signal to noise and distortion ratio (SNDR) of 49.3 dB and a spurious free dynamic range (SFDR) of 61 dB with a power supply of 1.2 V and a consumption of 21 µW. The figure of merit (FoM) of the proposed SAR-ADC is 87.9 fj/Conv.-step. The proposed designs were simulated with optimized parameters using a voltage threshold adaptive memristor (VTEAM) model.
- 7 March 2021
- Published by MDPI AG in Electronics
- Vol. 10 (5) , 622
Open AccessDesign of a Memristor-Based Digital to Analog Converter (DAC)
A memristor element has been highlighted in recent years and has been applied to several applications. In this work, a memristor-based digital to analog converter (DAC) was proposed due to the fact that a memristor has low area, low power, and a low threshold voltage. The proposed memristor DAC depends on the basic DAC cell, consisting of two memristors connected in opposite directions. This basic DAC cell was used to build and simulate both a 4 bit and an 8 bit DAC. Moreover, a sneak path issue was illustrated and its solution was provided. The proposed design reduced the area by 40%. The 8 bit memristor DAC has been designed and used in a successive approximation register analog to digital converter (SAR-ADC) instead of in a capacitor DAC (which would require a large area and consume more switching power). The SAR-ADC with a memristor-based DAC achieves a signal to noise and distortion ratio (SNDR) of 49.3 dB and a spurious free dynamic range (SFDR) of 61 dB with a power supply of 1.2 V and a consumption of 21 µW. The figure of merit (FoM) of the proposed SAR-ADC is 87.9 fj/Conv.-step. The proposed designs were simulated with optimized parameters using a voltage threshold adaptive memristor (VTEAM) model.
- Open Access
Internet of Things (IoT) Platform for Multi-Topic Messaging
IoT-based applications operate in a client–server architecture, which requires a specific communication protocol. This protocol is used to establish the client–server communication model, allowing all clients of the system to perform specific tasks through internet communications. Many data communication protocols for the Internet of Things are used by IoT platforms, including message queuing telemetry transport (MQTT), advanced message queuing protocol (AMQP), MQTT for sensor networks (MQTT-SN), data distribution service (DDS), constrained application protocol (CoAP), and simple object access protocol (SOAP). These protocols only support single-topic messaging. Thus, in this work, an IoT message protocol that supports multi-topic messaging is proposed. This protocol will add a simple “brain” for IoT platforms in order to realize an intelligent IoT architecture. Moreover, it will enhance the traffic throughput by reducing the overheads of messages and the delay of multi-topic messaging. Most current IoT applications depend on real-time systems. Therefore, an RTOS (real-time operating system) as a famous OS (operating system) is used for the embedded systems to provide the constraints of real-time features, as required by these real-time systems. Using RTOS for IoT applications adds important features to the system, including reliability. Many of the undertaken research works into IoT platforms have only focused on specific applications; they did not deal with the real-time constraints under a real-time system umbrella. In this work, the design of the multi-topic IoT protocol and platform is implemented for real-time systems and also for general-purpose applications; this platform depends on the proposed multi-topic communication protocol, which is implemented here to show its functionality and effectiveness over similar protocols.
Open AccessInternet of Things (IoT) Platform for Multi-Topic Messaging
IoT-based applications operate in a client–server architecture, which requires a specific communication protocol. This protocol is used to establish the client–server communication model, allowing all clients of the system to perform specific tasks through internet communications. Many data communication protocols for the Internet of Things are used by IoT platforms, including message queuing telemetry transport (MQTT), advanced message queuing protocol (AMQP), MQTT for sensor networks (MQTT-SN), data distribution service (DDS), constrained application protocol (CoAP), and simple object access protocol (SOAP). These protocols only support single-topic messaging. Thus, in this work, an IoT message protocol that supports multi-topic messaging is proposed. This protocol will add a simple “brain” for IoT platforms in order to realize an intelligent IoT architecture. Moreover, it will enhance the traffic throughput by reducing the overheads of messages and the delay of multi-topic messaging. Most current IoT applications depend on real-time systems. Therefore, an RTOS (real-time operating system) as a famous OS (operating system) is used for the embedded systems to provide the constraints of real-time features, as required by these real-time systems. Using RTOS for IoT applications adds important features to the system, including reliability. Many of the undertaken research works into IoT platforms have only focused on specific applications; they did not deal with the real-time constraints under a real-time system umbrella. In this work, the design of the multi-topic IoT protocol and platform is implemented for real-time systems and also for general-purpose applications; this platform depends on the proposed multi-topic communication protocol, which is implemented here to show its functionality and effectiveness over similar protocols.
- Open Access
- 9 June 2020
- Published by Bentham Science Publishers Ltd. in The Open Transportation Journal
- Vol. 14 (1) , 86-98
Vehicle To Vehicle “V2V” Communication: Scope, Importance, Challenges, Research Directions and Future
Day after day Internet of Things (IOT) has become essential in our lives with a lot of research directions and technologies, one of these directions is the Intelligent Transportation System (ITS) which is important for traffic management, and safety. One of its main points is the Vehicle-To-Vehicle (V2V) communication which is essential for the ITS full automated process as it decreases the number of hits between the vehicles and the access points on the roads. V2V is important for the developing countries which does not include Road Side Units (RSUs), so in this research we will go through V2V research directions to explore the current models, and to find out the advantages and challenges of implementing V2V.
- 9 June 2020
- Published by Bentham Science Publishers Ltd. in The Open Transportation Journal
- Vol. 14 (1) , 86-98
Open AccessVehicle To Vehicle “V2V” Communication: Scope, Importance, Challenges, Research Directions and Future
Day after day Internet of Things (IOT) has become essential in our lives with a lot of research directions and technologies, one of these directions is the Intelligent Transportation System (ITS) which is important for traffic management, and safety. One of its main points is the Vehicle-To-Vehicle (V2V) communication which is essential for the ITS full automated process as it decreases the number of hits between the vehicles and the access points on the roads. V2V is important for the developing countries which does not include Road Side Units (RSUs), so in this research we will go through V2V research directions to explore the current models, and to find out the advantages and challenges of implementing V2V.
- Open Access
- 1 January 2019
- Published by Egyptian Knowledge Bank in Menoufia Journal of Electronic Engineering Research
- Vol. 28 (1) , 1-18
Iris Template Localization over Internet of Things (IoT)
Internet of Things (IoT) is growing vastly and survive technology.So; it needs authentication solutions (as iris recognition) to bringsafety, and convenience in data and network sharing in the internetof things era. Iris segmentation is most critical stage in the irisrecognition system. Some challenges to localize iris such asocclusion by eyelids, eyelashes, and corneal or specular reflection.This paper proposes, a modified algorithm based on maskingtechnique; to localize iris. It solves the limitation of the iris data lossand inconsistencies factors, for capturing conditions and differentresolution images. This method gives satisfactory results in factorsof accuracy and execution time to be used over IoT. Thesegmentation success rate is more than 99.545(%), and executiontime in worst case 0.758 (sec).The obtained results improve theefficiency of the proposed iris recognition method and improve IoTsecurity and authentication.
- 1 January 2019
- Published by Egyptian Knowledge Bank in Menoufia Journal of Electronic Engineering Research
- Vol. 28 (1) , 1-18
Open AccessIris Template Localization over Internet of Things (IoT)
Internet of Things (IoT) is growing vastly and survive technology.So; it needs authentication solutions (as iris recognition) to bringsafety, and convenience in data and network sharing in the internetof things era. Iris segmentation is most critical stage in the irisrecognition system. Some challenges to localize iris such asocclusion by eyelids, eyelashes, and corneal or specular reflection.This paper proposes, a modified algorithm based on maskingtechnique; to localize iris. It solves the limitation of the iris data lossand inconsistencies factors, for capturing conditions and differentresolution images. This method gives satisfactory results in factorsof accuracy and execution time to be used over IoT. Thesegmentation success rate is more than 99.545(%), and executiontime in worst case 0.758 (sec).The obtained results improve theefficiency of the proposed iris recognition method and improve IoTsecurity and authentication.
- 1 December 2018
- Published by Elsevier in Future Generation Computer Systems
- Vol. 89, 178-191
Iris Recognition Using Multi-Algorithmic Approaches for Cognitive Internet of things (CIoT) Framework
- 1 December 2018
- Published by Elsevier in Future Generation Computer Systems
- Vol. 89, 178-191
Iris Recognition Using Multi-Algorithmic Approaches for Cognitive Internet of things (CIoT) Framework