Abdullah Elewi
Mersin University, Computer Engineering Department, Faculty Member
Research Interests:
Research Interests:
Research Interests:
Research Interests: Computer Science, Feature Selection, Product Labeling, Hierarchical Agglomerative Clustering, Automatic Feature Selection, and 7 moreHierarchical Clustering, Feature Evaluation and Selection, String Similarity Metrics, Similarity Metrics, Feature Subset Selection, Hierarchical Clustering Mechanism, and product clustering
Despite asymmetric multiprocessor platforms are considered power-efficient multiprocessor architectures, efficient task partitioning (assignment) plays a crucial role in achieving more energy efficiency at these multiprocessor platforms.... more
Despite asymmetric multiprocessor platforms are considered power-efficient multiprocessor architectures, efficient task partitioning (assignment) plays a crucial role in achieving more energy efficiency at these multiprocessor platforms. This paper considers the problem of energy-aware static partitioning of periodic real-time tasks on asymmetric multiprocessor platforms. The paper introduces a comparative evaluation of Bin-Packing (BP) techniques and variants when the Dynamic Voltage/Frequency Scaling (DVFS) is not supported by the platform and when practical full-chip DVFS with multiple Operating Performance Points (OPPs) is supported. Also, the paper introduces the energy models for each case and proposes a condition to determine which OPP will be chosen that misses no deadline and saves energy. The simulation results showed the most energy-efficient partitioning technique for each case.
Research Interests:
Asymmetric multiprocessor systems are considered power-efficient multiprocessor architectures. Furthermore, efficient task allocation (partitioning) can achieve more energy efficiency at these asymmetric multiprocessor platforms. This... more
Asymmetric multiprocessor systems are considered power-efficient multiprocessor architectures. Furthermore, efficient task allocation (partitioning) can achieve more energy efficiency at these asymmetric multiprocessor platforms. This article addresses the problem of energy-aware static partitioning of periodic real-time tasks on asymmetric multiprocessor (multicore) embedded systems. The article formulates the problem according to the Dynamic Voltage and Frequency Scaling (DVFS) model supported by the platform and shows that it is an NP-hard problem. Then, the article outlines optimal reference partitioning techniques for each case of DVFS model with suitable assumptions. Finally, the article proposes modifications to the traditional bin-packing techniques and designs novel techniques taking into account the DVFS model supported by the platform. All algorithms and techniques are simulated and compared. The simulation shows promising results, where the proposed techniques reduced th...
Research Interests:
In this study, information about real-time systems and their approaches is given. Flexible, tight and rigid application types of real-time systems are mentioned and a real-time system is modeled. How to apply a real-time system to an... more
In this study, information about real-time systems and their approaches is given. Flexible, tight and rigid application types of real-time systems are mentioned and a real-time system is modeled. How to apply a real-time system to an embedded Linux version is researched, information about the most widely used open-source approaches, RTLinux, Xenomai and RTAI, and information about the fully interrupt supported kernel (PREEMPT_RT) to be run on Jatson Nano is given. Demonstrated step-by-step implementation of real-time kernel compilation with full interrupt support to the version of Linux on Jetson Nano with the appropriate Linux patch. In this study, the old and new cores were tested with the cyclictest program and the results were presented. Thus, the system to run real-time applications on Jatson Nano has been prepared.
In the design of embedded systems, it is very important to reduce energy consumption and thus prolong battery life in everywhere existed battery-powered embedded systems. Dynamic voltage scaling (DVS) processors, which support many... more
In the design of embedded systems, it is very important to reduce energy consumption and thus prolong battery life in everywhere existed battery-powered embedded systems. Dynamic voltage scaling (DVS) processors, which support many operating voltages and speeds, can efficiently reduce energy consumption by making appropriate decisions on the processor speed/voltage during the scheduling of real time tasks. This paper addresses the problem of energy efficient real time task scheduling where the tasks are dependent due to exclusive access shared resources. Furthermore, the paper proposes enhancements over the existing dual speed switching algorithm (DSA) where the proposed algorithm achieves more energy saving and has the capability to function with both SRP and DPCP protocols.
Research Interests:
In this study, Rate Monotonic (RM) and Earliest Deadline First (EDF) algorithms, running on single processor real time systems, are discussed. These algorithms have been evaluated and compared using open-source MCRTsim simulator.
Research Interests:
Efficient task partitioning plays a crucial role in achieving high performance at multiprocessor platforms. This paper addresses the problem of energy-aware static partitioning of periodic realtime tasks on heterogeneous multiprocessor... more
Efficient task partitioning plays a crucial role in achieving high performance at multiprocessor platforms. This paper addresses the problem of energy-aware static partitioning of periodic realtime tasks on heterogeneous multiprocessor platforms. A Particle Swarm Optimization variant based on Min-min technique for task partitioning is proposed. The proposed approach aims to minimize the overall energy consumption, meanwhile avoid deadline violations. An energy-aware cost function is proposed to be considered in the proposed approach. Extensive simulations and comparisons are conducted in order to validate the effectiveness of the proposed technique. The achieved results demonstrate that the proposed partitioning scheme significantly surpasses previous approaches in terms of both number of iterations and energy savings.
Research Interests:
This paper presents a new approach to utilize smart technology in a practical and meaningful manner to make finding seats easier for audiences in cinema halls. Generally, the audiences come to cinema halls late and they cannot find their... more
This paper presents a new approach to utilize smart technology in a practical and meaningful manner to make finding seats easier for audiences in cinema halls. Generally, the audiences come to cinema halls late and they cannot find their exact seats easily, because there are many places to sit and many small signs (numbers, letters etc.) to define them. Especially, the low lighting of these halls makes seeing seat’s number and/or letter much harder. Due to these reasons, smart cinema seat system has been designed by using lights inside the seats which can catch the attention of people. The system is based on an Arduino microcontroller board with a group of sensors and an Android application that can communicate with the microcontroller and server database of the cinema. The lights and sensors have been connected to Arduino microcontroller board and the board has been controlled with the Android application (App) via Bluetooth protocol. The proposed system is a novel idea for smart t...
Research Interests:
Computer vision aims to provide computers with vision capabilities similar to humans. Humans use their eyes and their brains to see and understand the world and objects around them. For visually impaired individuals, these capabilities... more
Computer vision aims to provide computers with vision capabilities similar to humans. Humans use their eyes and their brains to see and understand the world and objects around them. For visually impaired individuals, these capabilities are lost or damaged in different degrees. Their eyes cannot discharge vision responsibilities. This paper aims to design and implement a portable system to help visually impaired individuals in perceiving objects and people around them and estimating their distance precisely. The proposed system uses a CNN-based real-time object detection technique called YOLO (You Look Only Once) with a single camera mounted on Raspberry Pi board. The system also estimates the distance of the detected objects and deliver these data to visually impaired person in audible form. The results show that the system can detect a person and predict his/her distance with 98.8% accuracy.
The distance estimation of objects from a single camera can play a crucial role in many real-life applications, such as mobile robot navigation, autonomous vehicles and camera-based assistive devices for visually impaired people. This... more
The distance estimation of objects from a single camera can play a crucial role in many real-life applications, such as mobile robot navigation, autonomous vehicles and camera-based assistive devices for visually impaired people. This paper addresses the problem of distance estimation of people from a monocular camera. The paper proposes using face features, in addition to body features, with various regression algorithms to estimate the distance from a camera. These features are extracted from the bounding boxes of the people, detected in camera images. Two datasets, an ideal manual one and a practical automatic one, have been built for training and validation purposes. Various metrics, including a novel one proposed in this paper, have been utilized to evaluate the different regression models. The results reveal that the distance estimation errors have been significantly reduced using the body and face features together for all used regression algorithms, and a distance precision ...
Providing multitasking on ubiquitous microcontroller platforms has great applications in different aspects of daily life. This paper presents a design and implementation of a real-time embedded driver assistance system using Arduino Uno... more
Providing multitasking on ubiquitous microcontroller platforms has great applications in different aspects of daily life. This paper presents a design and implementation of a real-time embedded driver assistance system using Arduino Uno as deployment platform. Multiple real-time tasks for assisting a car driver are designed and implemented using three different real-time kernels; FreeRTOS, OS48 and Simulink Desktop Real-Time. The configurations and settings of the proposed system are given in details. The paper aims to show and compare the performance of the proposed Arduino system using FreeRTOS, OS48 and Simulink Desktop Real-Time as different real-time kernels. The results show that the proposed system is quite simple, cost effective, and flexible to be developed by incorporating more or less tasks.
Artan motorlu arac sayilari, sehir ici trafik ve park sorunlarina neden olmaktadir. Bu yuzden suruculere, park yeri konusunda yardimci olacak otomatik park sistemlerine gereksinim duyulmaktadir. Boylece suruculer zamandan ve yakittan... more
Artan motorlu arac sayilari, sehir ici trafik ve park sorunlarina neden olmaktadir. Bu yuzden suruculere, park yeri konusunda yardimci olacak otomatik park sistemlerine gereksinim duyulmaktadir. Boylece suruculer zamandan ve yakittan tasarruf ederler ve ayrica trafik sikisikligi engellenir. Ayrica, otoparklarin dinamik sekilde ucretlendirilmesi ile park alanlarinin verimli kullanilmasi saglanir. Bu da yogunluk yasanan alanlarin trafigini azaltir. Nesnelerin interneti kullanilarak gelistirilen yeni uygulamalar, hayatimizin bircok alaninda onemli rol oynamaktadir. Ornegin basit akilli aletlerden akilli sehirlere, tarima, endustriden sagliga kadar bircok alanda nesnelerin interneti kavrami uygulanabilmektedir. Akilli sehircilik kapsaminda trafik ve park durumu, sensorler tarafindan alinip, trafik yogunluk haritasi cikarilarak arac suruculeri bilgilendirilebilmektedir. Bu makalede, akilli park sistemleri incelenmis, farkli modeller ve teknolojiler arastirilmis ve ilgili ornekler verilmistir.
Research Interests:
Research Interests:
Embedded real-time systems are one of the most successful application areas of Unified Modeling Language. State diagrams are one of the Unified Modeling Language techniques used for behavior modeling. State machines are used to model the... more
Embedded real-time systems are one of the most successful application areas of Unified Modeling Language. State diagrams are one of the Unified Modeling Language techniques used for behavior modeling. State machines are used to model the controlling and sequencing of a system. This is especially important for real-time embedded systems that are highly state-dependent. The instantaneous actions of state-based systems depend not only on system input but also on what happened before in the system. For this reason, it is important to model real-time embedded systems with state machines in order to achieve more accurate results. In this study, the use and types of state machines for modeling real-time embedded systems are examined by explaining code-diagram alternating examples.
Research Interests:
The paper introduces a novel feature selection algorithm for labeling identical products collected from online web resources. Product labeling is important for clustering similar or same products. Products blindly crawled over the web... more
The paper introduces a novel feature selection algorithm for labeling identical products collected from online web resources. Product labeling is important for clustering similar or same products. Products blindly crawled over the web sources, such as online sellers, have unstructured data due to having features expressed in different representations and formats. Such data result in feature vectors whose representation is unknown and non-uniform in length. Thus, product labeling, as a challenging problem, needs efficient selection of features that best describe the products. In this paper, an efficient feature selection algorithm is proposed for product labeling problem. Hierarchical clustering is used with the state of the art similarity metrics to assess the performance of the proposed algorithm. The results show that the proposed algorithm increases the performance of product labeling significantly. Furthermore, the method can be applied to any clustering algorithm that works on unstructured data.
Keywords—Product labeling; product clustering; feature selection; similarity metrics; hierarchical clustering
Keywords—Product labeling; product clustering; feature selection; similarity metrics; hierarchical clustering
Research Interests: Feature Selection, Product Labeling, Hierarchical Agglomerative Clustering, Automatic Feature Selection, Hierarchical Clustering, and 6 moreFeature Evaluation and Selection, String Similarity Metrics, Similarity Metrics, Feature Subset Selection, Hierarchical Clustering Mechanism, and product clustering
Asymmetric multiprocessor systems are considered power-efficient multiprocessor architectures. Furthermore, efficient task allocation (partitioning) can achieve more energy efficiency at these asymmetric multiprocessor platforms. This... more
Asymmetric multiprocessor systems are considered power-efficient multiprocessor architectures. Furthermore, efficient task allocation (partitioning) can achieve more energy efficiency at these asymmetric multiprocessor platforms. This article addresses the problem of energy-aware static partitioning of periodic real-time tasks on asymmetric multiprocessor (multicore) embedded systems. The article formulates the problem according to the Dynamic Voltage and Frequency Scaling (DVFS) model supported by the platform and shows that it is an NP-hard problem. Then, the article outlines optimal reference partitioning techniques for each case of DVFS model with suitable assumptions. Finally, the article proposes modifications to the traditional bin-packing techniques and designs novel techniques taking into account the DVFS model supported by the platform. All algorithms and techniques are simulated and compared. The simulation shows promising results, where the proposed techniques reduced the energy consumption by 75% compared to traditional methods when DVFS is not supported and by 50% when per-core DVFS is supported by the platform.
Efficient task mapping plays a crucial role in saving energy in asymmetric multiprocessor platforms. This paper considers the problem of energy-aware static mapping of periodic real-time dependent tasks sharing resources on asymmetric... more
Efficient task mapping plays a crucial role in saving energy in asymmetric multiprocessor platforms. This paper considers the problem of energy-aware static mapping of periodic real-time dependent tasks sharing resources on asymmetric multi/many-core embedded systems. The paper extends an existing synchronization-aware bin-packing (BP) variant when the full-chip dynamic voltage and frequency scaling (DVFS) is supported by the asymmetric multicore platform. Then, the paper proposes another BP variant when DVFS is not supported. The simulation results showed that the proposed BP variant can reduce energy consumption significantly in the presence of shared resources.
Despite asymmetric multiprocessor platforms are considered power-efficient multiprocessor architectures, efficient task partitioning (assignment) plays a crucial role in achieving more energy efficiency at these multiprocessor platforms.... more
Despite asymmetric multiprocessor platforms are considered power-efficient multiprocessor architectures, efficient task partitioning (assignment) plays a crucial role in achieving more energy efficiency at these multiprocessor platforms. This paper considers the problem of energy-aware static partitioning of periodic real-time tasks on asymmetric multiprocessor platforms. The paper introduces a comparative evaluation of Bin-Packing (BP) techniques and variants when the Dynamic Voltage/Frequency Scaling (DVFS) is not supported by the platform and when practical full-chip DVFS with multiple Operating Performance Points (OPPs) is supported. Also, the paper introduces the energy models for each case and proposes a condition to determine which OPP will be chosen that misses no deadline and saves energy. The simulation results showed the most energy-efficient partitioning technique for each case.
Reducing energy consumption is a critical issue in the design of battery-powered embedded systems to prolong battery life. With dynamic voltage scaling (DVS) processors, energy consumption can be reduced efficiently by making appropriate... more
Reducing energy consumption is a critical issue in the design of battery-powered embedded systems to prolong battery life. With dynamic voltage scaling (DVS) processors, energy consumption can be reduced efficiently by making appropriate decisions on the processor speed/voltage during the scheduling of real time tasks. This paper addresses the problem of energy efficient real-time task scheduling over earliest deadline first (EDF) scheduling policy where the tasks are dependent due to shared resources. Furthermore, the paper proposes enhancements over the existing multi-speed (MS) algorithm where the proposed algorithm achieves more energy saving and has the capability to function with both stack resource policy (SRP) and dynamic priority ceiling protocol (DPCP) as resource access protocols.
Research Interests:
Research Interests:
Reducing energy consumption is a critical issue in the design of battery-powered embedded systems to prolong battery life. With dynamic voltage scaling (DVS) processors, energy consumption can be reduced efficiently by making appropriate... more
Reducing energy consumption is a critical issue in the design of battery-powered embedded systems to prolong battery life. With dynamic voltage scaling (DVS) processors, energy consumption can be reduced efficiently by making appropriate decisions on the processor speed/voltage during the scheduling of real time tasks. This paper addresses the problem of energy efficient real-time task scheduling over earliest deadline first (EDF) scheduling policy where the tasks are dependent due to shared resources. Furthermore, the paper proposes enhancements over the existing multi-speed (MS) algorithm where the proposed algorithm achieves more energy saving and has the capability to function with both stack resource policy (SRP) and dynamic priority ceiling protocol (DPCP) as resource access protocols.