Since the release of ChatGPT, numerous studies have highlighted the remarkable performance of Cha... more Since the release of ChatGPT, numerous studies have highlighted the remarkable performance of ChatGPT, which often rivals or even surpasses human capabilities in various tasks and domains. However, this paper presents a contrasting perspective by demonstrating an instance where human performance excels in typical tasks suited for ChatGPT, specifically in the domain of computer programming. We utilize the IEEExtreme Challenge competition as a benchmark — a prestigious, annual international programming contest encompassing a wide range of problems with different complexities. To conduct a thorough evaluation, we selected and executed a diverse set of 102 challenges, drawn from five distinct IEEExtreme editions, using three major programming languages: Python, Java, and C++. Our empirical analysis provides evidence that contrary to popular belief, human programmers maintain a competitive edge over ChatGPT in certain aspects of problem-solving within the programming context. In fact, we...
The multi-robot task allocation problem is a fundamental problem in robotics research area. The p... more The multi-robot task allocation problem is a fundamental problem in robotics research area. The problem roughly consists of finding an optimal allocation of tasks among several robots to reduce the mission cost to a minimum. As mentioned in Chap. 6, extensive research has been conducted in the area for answering the following question: Which robot should execute which task? In this chapter, we design different solutions to solve the MRTA problem. We propose four different approaches: an improved distributed market-based approach (IDMB), a clustering market-based approach (CM-MTSP), a fuzzy logic-based approach (FL-MTSP), and Move-and-Improve approach. These approaches must define how tasks are assigned to the robots. The IDBM, CM-MTSP, and Move-and-Improve approaches are based on the use of an auction process where bids are used to evaluate the assignment. The FL-MTSP is based on the use of the fuzzy logic algebra to combine objectives to be optimized.
Global path planning consists in finding a path between two locations in a global map. It is a cr... more Global path planning consists in finding a path between two locations in a global map. It is a crucial component for any map-based robot navigation. The navigation stack of the Robot Operating System (ROS) open-source middleware incorporates both global and local path planners to support ROS-enabled robot navigation. Only two basic algorithms are defined for the global path planner including Dijkstra and carrot planners. However, more intelligent global planners have been defined in the literature but were not integrated in ROS distributions. The contribution of this work consists in integrating the \(RA^{*}\) path planner, defined in Chap. 3, into the ROS global path planning component as a plugin. We demonstrate how to integrate new planner into ROS and present their benefits. Extensive experimentations are performed on simulated and real robots to show the effectiveness of the newly integrated planner as compared to ROS default planner.
Deep learning (DL) has shown outstanding performances in many fields, including remote sensing (R... more Deep learning (DL) has shown outstanding performances in many fields, including remote sensing (RS). DL is turning into an essential tool for the RS research community. Recently, many cloud platforms have been developed to provide access to large-scale computing capacity, consequently permitting the usage of DL architectures as a service. However, this opened the door to new challenges associated with the privacy and security of data. The RS data used to train the DL algorithms have several privacy requirements. Some of them need a high level of confidentiality, such as satellite images related to public security with high spatial resolutions. Moreover, satellite images are usually protected by copyright, and the owner may strictly refuse to share them. Therefore, privacy-preserving deep learning (PPDL) techniques are a possible solution to this problem. PPDL enables training DL on encrypted data without revealing the original plaintext. This study proposes a hybrid PPDL approach fo...
Unmanned aerial vehicles (UAVs) equipped with computer vision capabilities have been widely utili... more Unmanned aerial vehicles (UAVs) equipped with computer vision capabilities have been widely utilized in several remote sensing applications, such as precision agriculture, environmental monitoring, and surveillance. However, the commercial usage of these UAVs in such applications is mostly performed manually, with humans being responsible for data observation or offline processing after data collection due to the lack of on board AI on edge. Other technical methods rely on the cloud computation offloading of AI applications, where inference is conducted on video streams, which can be unscalable and infeasible due to remote cloud servers’ limited connectivity and high latency. To overcome these issues, this paper presents a new approach to using edge computing in drones to enable the processing of extensive AI tasks onboard UAVs for remote sensing. We propose a cloud–edge hybrid system architecture where the edge is responsible for processing AI tasks and the cloud is responsible for...
The multi-robot task allocation is a fundamental problem in robotics research area. Indeed, robot... more The multi-robot task allocation is a fundamental problem in robotics research area. Indeed, robots are typically intended to collaborate together to achieve a given goal. This chapter studies the performance of the IDBM, CM-MTSP, FL-MTSP, and Move-and-Improve approaches. In order to highlight the performance of the proposed schemes, we compared each one to appropriate existing ones. IDMB was compared with the RTMA [1], CM-MTSP was compared with single-objective and greedy algorithms, and FL-MTSP was compared with a centralized approach based on genetic algorithm and with NSGA-II algorithm. To validate the efficiency of the Move-and-Improve distributed algorithm, we first conducted extensive simulations and evaluated its performance in terms of the total traveled distance and the ratio of overlaped targets under different settings. The simulation results show that IDMB and Move-and-Improve algorithms produce near-optimal solutions. Also, CM-MTSP and FL-MTSP provide a good trade-off b...
Video streaming-based real-time vehicle identification and license plate recognition systems are ... more Video streaming-based real-time vehicle identification and license plate recognition systems are challenging to design and deploy in terms of real-time processing on edge, dealing with low image resolution, high noise, and identification. This paper addresses these issues by introducing a novel multi-stage, real-time, deep learning-based vehicle identification and license plate recognition system. The system is based on a set of algorithms that efficiently integrate two object detectors, an image classifier, and a multi-object tracker to recognize car models and license plates. The information redundancy of Saudi license plates’ Arabic and English characters is leveraged to boost the license plate recognition accuracy while satisfying real-time inference performance. The system optimally achieves real-time performance on edge GPU devices and maximizes models’ accuracy by taking advantage of the temporally redundant information of the video stream’s frames. The edge device sends a no...
2021 IEEE Third International Conference on Cognitive Machine Intelligence (CogMI)
Unmanned Aerial Vehicle (UAV) detection for public safety protection is becoming a critical issue... more Unmanned Aerial Vehicle (UAV) detection for public safety protection is becoming a critical issue in non-fly zones. There are plenty of attempts of the UAV detection using single stream (day or night vision). In this paper, we propose a new hybrid deep learning model to detect the UAV s in day and night visions with a high detection precision and accurate bounding box localization. The proposed hybrid deep learning model is developed with cosine annealing and re-thinking transformation to improve the detection precision and accelerate the training convergence. To validate the hybrid deep learning model, real-world experiments are conducted outdoor in daytime and nighttime, where a surveillance video camera on the ground is set up for capturing the UAV. In addition, the UAV-Catch open database is adopted for offline training of the proposed hybrid model, which enriches training datasets and improves the detection precision. The experimental results show that the proposed hybrid deep learning model achieves 65 % in terms of the mean average detection precision given the input videos in day and night visions.
A brain tumour is one of the major reasons for death in humans, and it is the tenth most common t... more A brain tumour is one of the major reasons for death in humans, and it is the tenth most common type of tumour that affects people of all ages. However, if detected early, it is one of the most treatable types of tumours. Brain tumours are classified using biopsy, which is not usually performed before definitive brain surgery. An image classification technique for tumour diseases is important for accelerating the treatment process and avoiding surgery and errors from manual diagnosis by radiologists. The advancement of technology and machine learning (ML) can assist radiologists in tumour diagnostics using magnetic resonance imaging (MRI) images without invasive procedures. This work introduced a new hybrid CNN-based architecture to classify three brain tumour types through MRI images. The method suggested in this paper uses hybrid deep learning classification based on CNN with two methods. The first method combines a pre-trained Google-Net model of the CNN algorithm for feature ext...
Recently, the rapid transmission of Coronavirus 2019 (COVID-19) is causing a significant health c... more Recently, the rapid transmission of Coronavirus 2019 (COVID-19) is causing a significant health crisis worldwide. The World Health Organization (WHO) issued several guidelines for protection against the spreading of COVID-19. According to the WHO, the most effective preventive measure against COVID-19 is wearing a mask in public and crowded areas. It is quite difficult to manually monitor and determine people with masks and no masks. In this paper, different deep learning architectures were used for better results evaluations. After extensive experimentation, we selected a custom model having the best performance to identify whether people wear a face mask or not and allowing an easy deployment on a small device such as a Jetson Nano. The experimental evaluation is performed on the custom dataset that is developed from the website (See data collection section) after applying different masks on those images. The proposed model in comparison with other methods produced higher accuracy...
Since the release of ChatGPT, numerous studies have highlighted the remarkable performance of Cha... more Since the release of ChatGPT, numerous studies have highlighted the remarkable performance of ChatGPT, which often rivals or even surpasses human capabilities in various tasks and domains. However, this paper presents a contrasting perspective by demonstrating an instance where human performance excels in typical tasks suited for ChatGPT, specifically in the domain of computer programming. We utilize the IEEExtreme Challenge competition as a benchmark — a prestigious, annual international programming contest encompassing a wide range of problems with different complexities. To conduct a thorough evaluation, we selected and executed a diverse set of 102 challenges, drawn from five distinct IEEExtreme editions, using three major programming languages: Python, Java, and C++. Our empirical analysis provides evidence that contrary to popular belief, human programmers maintain a competitive edge over ChatGPT in certain aspects of problem-solving within the programming context. In fact, we...
The multi-robot task allocation problem is a fundamental problem in robotics research area. The p... more The multi-robot task allocation problem is a fundamental problem in robotics research area. The problem roughly consists of finding an optimal allocation of tasks among several robots to reduce the mission cost to a minimum. As mentioned in Chap. 6, extensive research has been conducted in the area for answering the following question: Which robot should execute which task? In this chapter, we design different solutions to solve the MRTA problem. We propose four different approaches: an improved distributed market-based approach (IDMB), a clustering market-based approach (CM-MTSP), a fuzzy logic-based approach (FL-MTSP), and Move-and-Improve approach. These approaches must define how tasks are assigned to the robots. The IDBM, CM-MTSP, and Move-and-Improve approaches are based on the use of an auction process where bids are used to evaluate the assignment. The FL-MTSP is based on the use of the fuzzy logic algebra to combine objectives to be optimized.
Global path planning consists in finding a path between two locations in a global map. It is a cr... more Global path planning consists in finding a path between two locations in a global map. It is a crucial component for any map-based robot navigation. The navigation stack of the Robot Operating System (ROS) open-source middleware incorporates both global and local path planners to support ROS-enabled robot navigation. Only two basic algorithms are defined for the global path planner including Dijkstra and carrot planners. However, more intelligent global planners have been defined in the literature but were not integrated in ROS distributions. The contribution of this work consists in integrating the \(RA^{*}\) path planner, defined in Chap. 3, into the ROS global path planning component as a plugin. We demonstrate how to integrate new planner into ROS and present their benefits. Extensive experimentations are performed on simulated and real robots to show the effectiveness of the newly integrated planner as compared to ROS default planner.
Deep learning (DL) has shown outstanding performances in many fields, including remote sensing (R... more Deep learning (DL) has shown outstanding performances in many fields, including remote sensing (RS). DL is turning into an essential tool for the RS research community. Recently, many cloud platforms have been developed to provide access to large-scale computing capacity, consequently permitting the usage of DL architectures as a service. However, this opened the door to new challenges associated with the privacy and security of data. The RS data used to train the DL algorithms have several privacy requirements. Some of them need a high level of confidentiality, such as satellite images related to public security with high spatial resolutions. Moreover, satellite images are usually protected by copyright, and the owner may strictly refuse to share them. Therefore, privacy-preserving deep learning (PPDL) techniques are a possible solution to this problem. PPDL enables training DL on encrypted data without revealing the original plaintext. This study proposes a hybrid PPDL approach fo...
Unmanned aerial vehicles (UAVs) equipped with computer vision capabilities have been widely utili... more Unmanned aerial vehicles (UAVs) equipped with computer vision capabilities have been widely utilized in several remote sensing applications, such as precision agriculture, environmental monitoring, and surveillance. However, the commercial usage of these UAVs in such applications is mostly performed manually, with humans being responsible for data observation or offline processing after data collection due to the lack of on board AI on edge. Other technical methods rely on the cloud computation offloading of AI applications, where inference is conducted on video streams, which can be unscalable and infeasible due to remote cloud servers’ limited connectivity and high latency. To overcome these issues, this paper presents a new approach to using edge computing in drones to enable the processing of extensive AI tasks onboard UAVs for remote sensing. We propose a cloud–edge hybrid system architecture where the edge is responsible for processing AI tasks and the cloud is responsible for...
The multi-robot task allocation is a fundamental problem in robotics research area. Indeed, robot... more The multi-robot task allocation is a fundamental problem in robotics research area. Indeed, robots are typically intended to collaborate together to achieve a given goal. This chapter studies the performance of the IDBM, CM-MTSP, FL-MTSP, and Move-and-Improve approaches. In order to highlight the performance of the proposed schemes, we compared each one to appropriate existing ones. IDMB was compared with the RTMA [1], CM-MTSP was compared with single-objective and greedy algorithms, and FL-MTSP was compared with a centralized approach based on genetic algorithm and with NSGA-II algorithm. To validate the efficiency of the Move-and-Improve distributed algorithm, we first conducted extensive simulations and evaluated its performance in terms of the total traveled distance and the ratio of overlaped targets under different settings. The simulation results show that IDMB and Move-and-Improve algorithms produce near-optimal solutions. Also, CM-MTSP and FL-MTSP provide a good trade-off b...
Video streaming-based real-time vehicle identification and license plate recognition systems are ... more Video streaming-based real-time vehicle identification and license plate recognition systems are challenging to design and deploy in terms of real-time processing on edge, dealing with low image resolution, high noise, and identification. This paper addresses these issues by introducing a novel multi-stage, real-time, deep learning-based vehicle identification and license plate recognition system. The system is based on a set of algorithms that efficiently integrate two object detectors, an image classifier, and a multi-object tracker to recognize car models and license plates. The information redundancy of Saudi license plates’ Arabic and English characters is leveraged to boost the license plate recognition accuracy while satisfying real-time inference performance. The system optimally achieves real-time performance on edge GPU devices and maximizes models’ accuracy by taking advantage of the temporally redundant information of the video stream’s frames. The edge device sends a no...
2021 IEEE Third International Conference on Cognitive Machine Intelligence (CogMI)
Unmanned Aerial Vehicle (UAV) detection for public safety protection is becoming a critical issue... more Unmanned Aerial Vehicle (UAV) detection for public safety protection is becoming a critical issue in non-fly zones. There are plenty of attempts of the UAV detection using single stream (day or night vision). In this paper, we propose a new hybrid deep learning model to detect the UAV s in day and night visions with a high detection precision and accurate bounding box localization. The proposed hybrid deep learning model is developed with cosine annealing and re-thinking transformation to improve the detection precision and accelerate the training convergence. To validate the hybrid deep learning model, real-world experiments are conducted outdoor in daytime and nighttime, where a surveillance video camera on the ground is set up for capturing the UAV. In addition, the UAV-Catch open database is adopted for offline training of the proposed hybrid model, which enriches training datasets and improves the detection precision. The experimental results show that the proposed hybrid deep learning model achieves 65 % in terms of the mean average detection precision given the input videos in day and night visions.
A brain tumour is one of the major reasons for death in humans, and it is the tenth most common t... more A brain tumour is one of the major reasons for death in humans, and it is the tenth most common type of tumour that affects people of all ages. However, if detected early, it is one of the most treatable types of tumours. Brain tumours are classified using biopsy, which is not usually performed before definitive brain surgery. An image classification technique for tumour diseases is important for accelerating the treatment process and avoiding surgery and errors from manual diagnosis by radiologists. The advancement of technology and machine learning (ML) can assist radiologists in tumour diagnostics using magnetic resonance imaging (MRI) images without invasive procedures. This work introduced a new hybrid CNN-based architecture to classify three brain tumour types through MRI images. The method suggested in this paper uses hybrid deep learning classification based on CNN with two methods. The first method combines a pre-trained Google-Net model of the CNN algorithm for feature ext...
Recently, the rapid transmission of Coronavirus 2019 (COVID-19) is causing a significant health c... more Recently, the rapid transmission of Coronavirus 2019 (COVID-19) is causing a significant health crisis worldwide. The World Health Organization (WHO) issued several guidelines for protection against the spreading of COVID-19. According to the WHO, the most effective preventive measure against COVID-19 is wearing a mask in public and crowded areas. It is quite difficult to manually monitor and determine people with masks and no masks. In this paper, different deep learning architectures were used for better results evaluations. After extensive experimentation, we selected a custom model having the best performance to identify whether people wear a face mask or not and allowing an easy deployment on a small device such as a Jetson Nano. The experimental evaluation is performed on the custom dataset that is developed from the website (See data collection section) after applying different masks on those images. The proposed model in comparison with other methods produced higher accuracy...
Uploads
Papers by Adel Ammar