International Journal of Renewable Energy Research, 2019
In solar central receiver (SCR) systems, camera-based tracking and control strategies have been w... more In solar central receiver (SCR) systems, camera-based tracking and control strategies have been widely developed and tested. The camera, usually with a single CCD, captures images of the sun reflected by thousands of heliostats on the central receiver. The captured images are then analysed to allow the evaluation of solar flux. For accurate analysis process, the camera must have a high dynamic range (HDR) to give real and accurate information about the captured scene. In the present article, a new methodology has been developed using a double-CCD optical camera for improvement of dynamic range of the captured solar flux image. An experimental calibration set-up is adopted for accurate estimation of the camera response function. The double-CCD camera is used for acquiring two images at the same instant with two different levels of exposure. The two captured images are then merged into a single HDR image using a new proposed weighting function. The enhanced optical performance of the proposed weighting function has been demonstrated by comparison with the previous HDR image generation weighting functions at different levels of illumination. Investigation of the capability of the proposed methodology for the analysis of beam accuracy and optical quality of SCR systems show that the present proposed method leads to more accurate solar flux analysis because of the improvement in the resolution of details of the final merged image.
In this research work, several vision-based algorithms have been proposed for automatic detection... more In this research work, several vision-based algorithms have been proposed for automatic detection, classification and tracking of multiple mobile objects as well as for automatic detection of stationary obstacles appearing in a sequence of images taken with an overhead camera. An adaptive background subtraction technique that models each pixel as a mixture of Gaussians has been developed for motion activity detection of dynamic objects, mobile robots and human beings moving in the scene. The computational cost and the memory requirement have been considerably reduced. The classification of dynamic objects as rigid or non-rigid has been based on the homogeneity analysis of the motion field. The rigidity-based classification of dynamic objects is aimed to avoid collisions of interfering humans with mobile robots, whereas identifying stationary obstacles is aimed to prevent collisions of dynamic objects with such obstacles. The identification of stationary obstacles has been based on s...
2021 IEEE 12th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), 2021
Online learning has emerged as powerful learning methods for the transformation from traditional ... more Online learning has emerged as powerful learning methods for the transformation from traditional education to open learning through smart learning platforms due to Covid-19 pandemic. Despite its effectiveness, many studies have indicated the necessity of linking online learning methods with the cognitive learning styles of students. The level of students always improves if the teaching methods and educational interventions are appropriate to the cognitive style of each student individually. Currently, psychological measures are used to assess students’ cognitive styles, but about the application in virtual environment, the matter becomes complicated. The main goal of this study is to provide an efficient solution based on machine learning techniques to automatically identify the students’ cognitive styles by analyzing their mouse interaction behaviors while carrying out online laboratory experiments. This will help in the design of an effective online laboratory experimentation system that is able to individualize the experiment instructions and feedback according to the identified cognitive style of each student. The results reveal that the KNN and SVM classifiers have a good accuracy in predicting most cognitive learning styles. In comparison to KNN, the enlarged studies ensemble the KNN, linear regression, neural network, and SVM reveal a 13% increase in overall total RMS error. We believe that this finding will enable educators and policy makers to predict distinct cognitive types in the assessment of students when they interact with online experiments. We believe that integrating deep learning algorithms with a greater emphasis on mouse location traces will improve the accuracy of our classifiers’ predictions.
Proceedings of the 2020 9th International Conference on Software and Information Engineering (ICSIE), 2020
Diabetes Mellitus is one of the modern world's most dominant diseases. This condition leads t... more Diabetes Mellitus is one of the modern world's most dominant diseases. This condition leads to a dangerous eye disease called Diabetic Retinopathy (DR), which eventually causes total blindness. The purpose of this research is the early detection of this condition to prevent further complications in the future. Over the past few years, Convolutional Neural Networks (CNNs) became very popular in resolving image processing and object detection problems for huge datasets. A cascaded model was proposed to detect the presence of DR and classify it into 4 stages, taking into consideration using a large dataset. Furthermore, preprocessing techniques such as normalization are applied, and finally, the input images are fed into a multi-layer Convolutional Neural Network. This method was utilized on 61,248 retinal images, which are a portion of the (EyePACS) dataset. It achieved a specificity of 96.1% for detecting the presence of the disease and 63.1% for determining its stage.
Proceedings of the 2020 9th International Conference on Software and Information Engineering (ICSIE), 2020
Diabetes Mellitus is one of the modern world's most dominant diseases. This condition leads t... more Diabetes Mellitus is one of the modern world's most dominant diseases. This condition leads to a dangerous eye disease called Diabetic Retinopathy (DR), which eventually causes total blindness. The purpose of this research is the early detection of this condition to prevent further complications in the future. Over the past few years, Convolutional Neural Networks (CNNs) became very popular in resolving image processing and object detection problems for huge datasets. A cascaded model was proposed to detect the presence of DR and classify it into 4 stages, taking into consideration using a large dataset. Furthermore, preprocessing techniques such as normalization are applied, and finally, the input images are fed into a multi-layer Convolutional Neural Network. This method was utilized on 61,248 retinal images, which are a portion of the (EyePACS) dataset. It achieved a specificity of 96.1% for detecting the presence of the disease and 63.1% for determining its stage.
2020 International Conference on Innovative Trends in Communication and Computer Engineering (ITCE), 2020
Precise focus is an essential step in astronomical research since an accurate measure of celestia... more Precise focus is an essential step in astronomical research since an accurate measure of celestial objects properties depends on it. This paper presents a performance comparison of different focus measure operators. The focus operators are applied to five sequences of star-clusters observations. These sequences are observed using the 74-inch telescope of Kottamia Astronomical Observatory (KAO). Each sequence contains in-focus and out-of-focus frames. The experimental results show that the Normalized Variance has the least distance between the best overall score and least standard error.
2008 International Conference on Computer Engineering & Systems, 2008
... EM Saad1, MH Awadalla', AM Hamdy'', H. I. Ali4 I Prof Dr. Engineer, elsayedmos... more ... EM Saad1, MH Awadalla', AM Hamdy'', H. I. Ali4 I Prof Dr. Engineer, [email protected] 2 Dr. Engineer, awadalla [email protected] 3 Dr. Engineer, [email protected] 4 Dr. Assistant ... [6] EM Saad, MH Awadalla, AM Hamdy, HI Ali, Robot Formations ...
Abstract This paper addresses the problem of developing intelligent multi-robot team capable of c... more Abstract This paper addresses the problem of developing intelligent multi-robot team capable of collaborating to achieve team objectives. The proposed work focuses on robot formations and how robot team-mates could face many complex situations. In order to do ...
This paper focuses on the development of intelligent multi-agent robot teams that are capable of ... more This paper focuses on the development of intelligent multi-agent robot teams that are capable of acting autonomously and of collaborating in a dynamic environment to achieve team objectives. Also it addresses the problem of achieving a global behavior by a group of simple and autonomous mobile robots. This behavior can be achieved by controlling the local interactions among the members of the robot teammates. A new vision based technique in the context of robot formation task is proposed. There is neither global information nor a predefined team leader available. Therefore, to get different robot formations, a distributed algorithm for robot controller is proposed. A simulated team of robots based on Webots simulator is constructed to validate the proposed approaches. Different robot formations' experiments are conducted. Therefore, the results show that the robot teams were able to achieve their objectives despite dynamic changes in the environment and variations in the capabi...
... 1, pp. 1-7, 2007. [10] EM Saad, MH Awadalla, AM Hamdy, HI Ali, Robot Formations using ... EMS... more ... 1, pp. 1-7, 2007. [10] EM Saad, MH Awadalla, AM Hamdy, HI Ali, Robot Formations using ... EMSaad was received the B.Sc degree in electrical (Communication) Eng., Cairo University at 1967, Dipl.-Ing, and Dr-Ing. ... University of Helwan. Medhat Awadalla has obtained his B.Sc. ...
Abstract This paper focuses on the development of wandering robot formations and shows the cooper... more Abstract This paper focuses on the development of wandering robot formations and shows the cooperation and coordination among the robot teammates to maintain the achieved formation regardless the complexity of the environment. To address these issues, this ...
This paper focuses on the development of wandering robot formations and shows the cooperation and... more This paper focuses on the development of wandering robot formations and shows the cooperation and coordination among the robot teammates to maintain the achieved formation regardless the complexity of the environment. To address these issues, this paper proposes a new behavior based robot architecture. This architecture is based on a novel technique for location determination using local sensing. The proposed architecture is implemented using the well known robot simulator Webots. Experiments for many difficult tasks such as the passage through narrow corridors, obstacle avoidance, swerving with large angles, and switching between different formations have been conducted. These Experiments prove the efficiency of the proposed controller. The obtained results show that the constructed formations are more stable and accurate even in cluttered and uncluttered environments.
Self-driving technology in general is becoming increasingly common and could revolutionize our tr... more Self-driving technology in general is becoming increasingly common and could revolutionize our transportation system. Also, selfdriving cars are on their way of being legal, but they still are not trusted enough to be used in real life due to a lack of their safety. In this paper, a self-driving car prototype is proposed which integrates between different technologies including some algorithms which are Road lane detection algorithm, disparity map algorithm to detect the distance between the car and other vehicles, and Anomalies detection using Support Vector Machine classification algorithm as it achieved a very high accuracy using our data set. To test the car prototype, a special road environment was built to fit the car. Using the disparity map algorithm and merging between these algorithms will result in achieving safety and reliability for the self-driving technology.
Fatty liver disease is considered a critical illness that should be diagnosed and detected at an ... more Fatty liver disease is considered a critical illness that should be diagnosed and detected at an early stage. In advanced stages, liver cancer or cirrhosis arise, and to identify this disease, radiologists commonly use ultrasound images. However, because of their low quality, radiologists found it challenging to recognize this disease using ultrasonic images. To avoid this problem, a Computer-Aided Diagnosis technique is developed in the current study, using Machine Learning Algorithms and a voting-based classifier to categorize liver tissues as being fatty or normal, based on extracting ultrasound image features and a voting-based classifier. Four main contributions are provided by our developed method: firstly, the classification of liver images is achieved as normal or fatty without a segmentation phase. Secondly, compared to our proposed work, the dataset in previous works was insufficient. A combination of 26 features is the third contribution. Based on the proposed methods, th...
2021 International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), 2021
The need for independent living is recognised in the case of visually impaired people who face a ... more The need for independent living is recognised in the case of visually impaired people who face a variety of issues, including social isolation.They are forced to live in strange environments with no means of assistance. Today’s tech world should supply them with this assistance for easier socialization. Our aim is to facilitate the life of visually impaired people who could lack the technology to help them in their lives. This project is proposed to focus on the development of a mobile application that uses voice commands and text to voice technology to enable users to interact with the mobile application. The user captures the item they want to identify using the smartphone’s camera and pick the image they want to upload for processing. The image chosen then will undergo through pre-processing techniques depending on the feature the user chose, the features include Money recognition CNN MobileNet architecture was used to analyze the Egyptian banknotes and Color and patterns recogni...
2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS), 2019
Internet-of-Thing (IOT) has been identified as one of the newest generation technologies from dif... more Internet-of-Thing (IOT) has been identified as one of the newest generation technologies from different fields. Among different technologies of IOT, Wireless sensor network (WSN) is one of the main technologies to be enhanced. Nowadays, Wireless Sensor Networks (WSN) has played vital role in the field of integrated Control and Safety system (ICSS) inside Oil and Gas plants including the centrifugal compressor system which is the main point of our paper.WSN is composed of a group of sensors and actuators which communicate through wireless channel in order to achieve required actions of sensing and performing tasks. ICSS is composed of both Safety instrumented control system (SIS) for emergency process conditions and Distributed control system (DCS) for normal process conditions. Hence, the main goal of this paper is to focus on processing of high priority SIS signals with respect to low priority DCS signals using Preemptive Earliest deadline first (EDF) scheduling algorithm to avoid ...
International Journal of Renewable Energy Research, 2019
In solar central receiver (SCR) systems, camera-based tracking and control strategies have been w... more In solar central receiver (SCR) systems, camera-based tracking and control strategies have been widely developed and tested. The camera, usually with a single CCD, captures images of the sun reflected by thousands of heliostats on the central receiver. The captured images are then analysed to allow the evaluation of solar flux. For accurate analysis process, the camera must have a high dynamic range (HDR) to give real and accurate information about the captured scene. In the present article, a new methodology has been developed using a double-CCD optical camera for improvement of dynamic range of the captured solar flux image. An experimental calibration set-up is adopted for accurate estimation of the camera response function. The double-CCD camera is used for acquiring two images at the same instant with two different levels of exposure. The two captured images are then merged into a single HDR image using a new proposed weighting function. The enhanced optical performance of the proposed weighting function has been demonstrated by comparison with the previous HDR image generation weighting functions at different levels of illumination. Investigation of the capability of the proposed methodology for the analysis of beam accuracy and optical quality of SCR systems show that the present proposed method leads to more accurate solar flux analysis because of the improvement in the resolution of details of the final merged image.
In this research work, several vision-based algorithms have been proposed for automatic detection... more In this research work, several vision-based algorithms have been proposed for automatic detection, classification and tracking of multiple mobile objects as well as for automatic detection of stationary obstacles appearing in a sequence of images taken with an overhead camera. An adaptive background subtraction technique that models each pixel as a mixture of Gaussians has been developed for motion activity detection of dynamic objects, mobile robots and human beings moving in the scene. The computational cost and the memory requirement have been considerably reduced. The classification of dynamic objects as rigid or non-rigid has been based on the homogeneity analysis of the motion field. The rigidity-based classification of dynamic objects is aimed to avoid collisions of interfering humans with mobile robots, whereas identifying stationary obstacles is aimed to prevent collisions of dynamic objects with such obstacles. The identification of stationary obstacles has been based on s...
2021 IEEE 12th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), 2021
Online learning has emerged as powerful learning methods for the transformation from traditional ... more Online learning has emerged as powerful learning methods for the transformation from traditional education to open learning through smart learning platforms due to Covid-19 pandemic. Despite its effectiveness, many studies have indicated the necessity of linking online learning methods with the cognitive learning styles of students. The level of students always improves if the teaching methods and educational interventions are appropriate to the cognitive style of each student individually. Currently, psychological measures are used to assess students’ cognitive styles, but about the application in virtual environment, the matter becomes complicated. The main goal of this study is to provide an efficient solution based on machine learning techniques to automatically identify the students’ cognitive styles by analyzing their mouse interaction behaviors while carrying out online laboratory experiments. This will help in the design of an effective online laboratory experimentation system that is able to individualize the experiment instructions and feedback according to the identified cognitive style of each student. The results reveal that the KNN and SVM classifiers have a good accuracy in predicting most cognitive learning styles. In comparison to KNN, the enlarged studies ensemble the KNN, linear regression, neural network, and SVM reveal a 13% increase in overall total RMS error. We believe that this finding will enable educators and policy makers to predict distinct cognitive types in the assessment of students when they interact with online experiments. We believe that integrating deep learning algorithms with a greater emphasis on mouse location traces will improve the accuracy of our classifiers’ predictions.
Proceedings of the 2020 9th International Conference on Software and Information Engineering (ICSIE), 2020
Diabetes Mellitus is one of the modern world's most dominant diseases. This condition leads t... more Diabetes Mellitus is one of the modern world's most dominant diseases. This condition leads to a dangerous eye disease called Diabetic Retinopathy (DR), which eventually causes total blindness. The purpose of this research is the early detection of this condition to prevent further complications in the future. Over the past few years, Convolutional Neural Networks (CNNs) became very popular in resolving image processing and object detection problems for huge datasets. A cascaded model was proposed to detect the presence of DR and classify it into 4 stages, taking into consideration using a large dataset. Furthermore, preprocessing techniques such as normalization are applied, and finally, the input images are fed into a multi-layer Convolutional Neural Network. This method was utilized on 61,248 retinal images, which are a portion of the (EyePACS) dataset. It achieved a specificity of 96.1% for detecting the presence of the disease and 63.1% for determining its stage.
Proceedings of the 2020 9th International Conference on Software and Information Engineering (ICSIE), 2020
Diabetes Mellitus is one of the modern world's most dominant diseases. This condition leads t... more Diabetes Mellitus is one of the modern world's most dominant diseases. This condition leads to a dangerous eye disease called Diabetic Retinopathy (DR), which eventually causes total blindness. The purpose of this research is the early detection of this condition to prevent further complications in the future. Over the past few years, Convolutional Neural Networks (CNNs) became very popular in resolving image processing and object detection problems for huge datasets. A cascaded model was proposed to detect the presence of DR and classify it into 4 stages, taking into consideration using a large dataset. Furthermore, preprocessing techniques such as normalization are applied, and finally, the input images are fed into a multi-layer Convolutional Neural Network. This method was utilized on 61,248 retinal images, which are a portion of the (EyePACS) dataset. It achieved a specificity of 96.1% for detecting the presence of the disease and 63.1% for determining its stage.
2020 International Conference on Innovative Trends in Communication and Computer Engineering (ITCE), 2020
Precise focus is an essential step in astronomical research since an accurate measure of celestia... more Precise focus is an essential step in astronomical research since an accurate measure of celestial objects properties depends on it. This paper presents a performance comparison of different focus measure operators. The focus operators are applied to five sequences of star-clusters observations. These sequences are observed using the 74-inch telescope of Kottamia Astronomical Observatory (KAO). Each sequence contains in-focus and out-of-focus frames. The experimental results show that the Normalized Variance has the least distance between the best overall score and least standard error.
2008 International Conference on Computer Engineering & Systems, 2008
... EM Saad1, MH Awadalla', AM Hamdy'', H. I. Ali4 I Prof Dr. Engineer, elsayedmos... more ... EM Saad1, MH Awadalla', AM Hamdy'', H. I. Ali4 I Prof Dr. Engineer, [email protected] 2 Dr. Engineer, awadalla [email protected] 3 Dr. Engineer, [email protected] 4 Dr. Assistant ... [6] EM Saad, MH Awadalla, AM Hamdy, HI Ali, Robot Formations ...
Abstract This paper addresses the problem of developing intelligent multi-robot team capable of c... more Abstract This paper addresses the problem of developing intelligent multi-robot team capable of collaborating to achieve team objectives. The proposed work focuses on robot formations and how robot team-mates could face many complex situations. In order to do ...
This paper focuses on the development of intelligent multi-agent robot teams that are capable of ... more This paper focuses on the development of intelligent multi-agent robot teams that are capable of acting autonomously and of collaborating in a dynamic environment to achieve team objectives. Also it addresses the problem of achieving a global behavior by a group of simple and autonomous mobile robots. This behavior can be achieved by controlling the local interactions among the members of the robot teammates. A new vision based technique in the context of robot formation task is proposed. There is neither global information nor a predefined team leader available. Therefore, to get different robot formations, a distributed algorithm for robot controller is proposed. A simulated team of robots based on Webots simulator is constructed to validate the proposed approaches. Different robot formations' experiments are conducted. Therefore, the results show that the robot teams were able to achieve their objectives despite dynamic changes in the environment and variations in the capabi...
... 1, pp. 1-7, 2007. [10] EM Saad, MH Awadalla, AM Hamdy, HI Ali, Robot Formations using ... EMS... more ... 1, pp. 1-7, 2007. [10] EM Saad, MH Awadalla, AM Hamdy, HI Ali, Robot Formations using ... EMSaad was received the B.Sc degree in electrical (Communication) Eng., Cairo University at 1967, Dipl.-Ing, and Dr-Ing. ... University of Helwan. Medhat Awadalla has obtained his B.Sc. ...
Abstract This paper focuses on the development of wandering robot formations and shows the cooper... more Abstract This paper focuses on the development of wandering robot formations and shows the cooperation and coordination among the robot teammates to maintain the achieved formation regardless the complexity of the environment. To address these issues, this ...
This paper focuses on the development of wandering robot formations and shows the cooperation and... more This paper focuses on the development of wandering robot formations and shows the cooperation and coordination among the robot teammates to maintain the achieved formation regardless the complexity of the environment. To address these issues, this paper proposes a new behavior based robot architecture. This architecture is based on a novel technique for location determination using local sensing. The proposed architecture is implemented using the well known robot simulator Webots. Experiments for many difficult tasks such as the passage through narrow corridors, obstacle avoidance, swerving with large angles, and switching between different formations have been conducted. These Experiments prove the efficiency of the proposed controller. The obtained results show that the constructed formations are more stable and accurate even in cluttered and uncluttered environments.
Self-driving technology in general is becoming increasingly common and could revolutionize our tr... more Self-driving technology in general is becoming increasingly common and could revolutionize our transportation system. Also, selfdriving cars are on their way of being legal, but they still are not trusted enough to be used in real life due to a lack of their safety. In this paper, a self-driving car prototype is proposed which integrates between different technologies including some algorithms which are Road lane detection algorithm, disparity map algorithm to detect the distance between the car and other vehicles, and Anomalies detection using Support Vector Machine classification algorithm as it achieved a very high accuracy using our data set. To test the car prototype, a special road environment was built to fit the car. Using the disparity map algorithm and merging between these algorithms will result in achieving safety and reliability for the self-driving technology.
Fatty liver disease is considered a critical illness that should be diagnosed and detected at an ... more Fatty liver disease is considered a critical illness that should be diagnosed and detected at an early stage. In advanced stages, liver cancer or cirrhosis arise, and to identify this disease, radiologists commonly use ultrasound images. However, because of their low quality, radiologists found it challenging to recognize this disease using ultrasonic images. To avoid this problem, a Computer-Aided Diagnosis technique is developed in the current study, using Machine Learning Algorithms and a voting-based classifier to categorize liver tissues as being fatty or normal, based on extracting ultrasound image features and a voting-based classifier. Four main contributions are provided by our developed method: firstly, the classification of liver images is achieved as normal or fatty without a segmentation phase. Secondly, compared to our proposed work, the dataset in previous works was insufficient. A combination of 26 features is the third contribution. Based on the proposed methods, th...
2021 International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), 2021
The need for independent living is recognised in the case of visually impaired people who face a ... more The need for independent living is recognised in the case of visually impaired people who face a variety of issues, including social isolation.They are forced to live in strange environments with no means of assistance. Today’s tech world should supply them with this assistance for easier socialization. Our aim is to facilitate the life of visually impaired people who could lack the technology to help them in their lives. This project is proposed to focus on the development of a mobile application that uses voice commands and text to voice technology to enable users to interact with the mobile application. The user captures the item they want to identify using the smartphone’s camera and pick the image they want to upload for processing. The image chosen then will undergo through pre-processing techniques depending on the feature the user chose, the features include Money recognition CNN MobileNet architecture was used to analyze the Egyptian banknotes and Color and patterns recogni...
2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS), 2019
Internet-of-Thing (IOT) has been identified as one of the newest generation technologies from dif... more Internet-of-Thing (IOT) has been identified as one of the newest generation technologies from different fields. Among different technologies of IOT, Wireless sensor network (WSN) is one of the main technologies to be enhanced. Nowadays, Wireless Sensor Networks (WSN) has played vital role in the field of integrated Control and Safety system (ICSS) inside Oil and Gas plants including the centrifugal compressor system which is the main point of our paper.WSN is composed of a group of sensors and actuators which communicate through wireless channel in order to achieve required actions of sensing and performing tasks. ICSS is composed of both Safety instrumented control system (SIS) for emergency process conditions and Distributed control system (DCS) for normal process conditions. Hence, the main goal of this paper is to focus on processing of high priority SIS signals with respect to low priority DCS signals using Preemptive Earliest deadline first (EDF) scheduling algorithm to avoid ...
Uploads
Papers by Alaa Hamdy