Browsing by Author "Cheikhrouhou, Omar"
Now showing 1 - 10 of 17
Results Per Page
Sort Options
- AI-based Pilgrim Detection using Convolutional Neural NetworksPublication . Jabra, Marwa Ben; Ammar, Adel; Koubaa, Anis; Cheikhrouhou, Omar; Hamam, HabibPilgrimage represents the most important Islamic religious gathering in the world where millions of pilgrims visit the holy places of Makkah and Madinah to perform their rituals. The safety and security of pilgrims is the highest priority for the authorities. In Makkah, 5000 cameras are spread around the holy mosques for monitoring pilgrims, but it is almost impossible to track all events by humans considering the huge number of images collected every second. To address this issue, we propose to use an artificial intelligence technique based on deep learning and convolutional neural networks to detect and identify Pilgrims and their features. For this purpose, we built a comprehensive dataset for the detection of pilgrims and their genders. Then, we develop two convolutional neural networks based on YOLOv3 and Faster-RCNN for the detection of Pilgrims. Experiment results show that Faster RCNN with Inception v2 feature extractor provides the best mean average precision over all classes (51%). A video demonstration that illustrates a real-time pilgrim detection using our proposed model is available at [1].
- An Analytical Hierarchy Process-Based Approach to Solve the Multi-Objective Multiple Traveling Salesman ProblemPublication . Trigui, Sahar; Cheikhrouhou, Omar; Koubâa, Anis; Zarrad, Anis; Youssef, HabibWe consider the problem of assigning a team of autonomous robots to target locations in the context of a disaster management scenario while optimizing several objectives. This problem can be cast as a multiple traveling salesman problem, where several robots must visit designated locations. This paper provides an analytical hierarchy process (AHP)-based approach to this problem, while minimizing three objectives: the total traveled distance, the maximum tour, and the deviation rate. The AHP-based approach involves three phases. In the first phase, we use the AHP process to define a specific weight for each objective. The second phase consists in allocating the available targets, wherein we define and use three approaches: market-based, robot and task mean allocation-based, and balanced-based. Finally, the third phase involves the improvement in the solutions generated in the second phase. To validate the efficiency of the AHP-based approach, we used MATLAB to conduct an extensive comparative simulation study with other algorithms reported in the literature. The performance comparison of the three approaches shows a gap between the market-based approach and the other two approaches of up to 30%. Further, the results show that the AHP-based approach provides a better balance between the objectives, as compared to other state-of-the-art approaches. In particular, we observed an improvement in the total traveled distance when using the AHP-based approach in comparison with the distance traveled when using a clustering-based approach.
- Analytical Hierarchy Process based Multi-Objective Multiple Traveling Salesman ProblemPublication . Cheikhrouhou, Omar; Koubâa, Anis; Zaard, AnisThe paper addresses the problem of assigning robots to target locations in the context of a disaster management scenario, while minimizing a set of pre-defined objectives. The problem is formulated as a Multi-objective Multiple Traveling Salesman Problem. A three-phase mechanism based on Analytical Hierarchy Process (AHP) is proposed. In the first phase, AHP is used to systematically define weights for each objective. In the second phase, the robots contend for the allocation of available targets using three different approaches. In the third phase, an improvement phase is carried out to refine the targets’ allocation. A Matlab simulation studies is used to examine the performance of the proposed solutions with three objective functions namely the total traveled distance, the maximum tour and the deviation rate. The comparison between the three proposed approaches shows that, for large scenario, the marketbased approach gives the best solution over the RTMA and the Balanced approach. Moreover, the comparison of the proposed multi-objective approach with the mono-objective one shows that our proposed approach outperforms the mono-objective one in the global cost when considering the three objectives. A slightly additional cost in the
- BlockLoc: Secure Localization in the Internet-of-Things using BlockchainPublication . Cheikhrouhou, Omar; Koubaa, AnisSeveral IoT applications are tightly dependent on the locations of the devices. However, localization algorithms can be easily compromised by injecting false locations. In this paper, we propose a Blockchain-based secure localization algorithm for the Internet of Things (IoT). The algorithm uses a public ledger (Blockchain) that contains nodes position and the list of their neighbor nodes. This ledger is shared among the IoT devices. Once an IoT device is localized its new position and the list of neighbor nodes are added to the Blockchain. This shared localization data will be used later by other IoT devices for their localization process. To avoid the attack where a malicious node sends a fake position, the correctness of the claimed position are verified before adding it to the Blockchain. Moreover, data exchanged between nodes (IoT devices) are signed to guarantee their authenticity and integrity. The integration of these security mechanisms into the localization process permits to exclude false data and therefore reduces the localization error. The simulation results show that adding the proposed security mechanism improves the localization accuracy of the algorithm when running in the presence of malicious nodes.
- A Cloud Based Disaster Management SystemPublication . Cheikhrouhou, Omar; Koubaa, Anis; Zarrad, AnisThe combination of wireless sensor networks (WSNs) and 3D virtual environments opens a new paradigm for their use in natural disaster management applications. It is important to have a realistic virtual environment based on datasets received from WSNs to prepare a backup rescue scenario with an acceptable response time. This paper describes a complete cloud-based system that collects data from wireless sensor nodes deployed in real environments and then builds a 3D environment in near real-time to reflect the incident detected by sensors (fire, gas leaking, etc.). The system’s purpose is to be used as a training environment for a rescue team to develop various rescue plans before they are applied in real emergency situations. The proposed cloud architecture combines 3D data streaming and sensor data collection to build an efficient network infrastructure that meets the strict network latency requirements for 3D mobile disaster applications. As compared to other existing systems, the proposed system is truly complete. First, it collects data from sensor nodes and then transfers it using an enhanced Routing Protocol for Low-Power and Lossy Networks (RLP). A 3D modular visualizer with a dynamic game engine was also developed in the cloud for near-real time 3D rendering. This is an advantage for highly-complex rendering algorithms and less powerful devices. An Extensible Markup Language (XML) atomic action concept was used to inject 3D scene modifications into the game engine without stopping or restarting the engine. Finally, a multi-objective multiple traveling salesman problem (AHP-MTSP) algorithm is proposed to generate an efficient rescue plan by assigning robots and multiple unmanned aerial vehicles to disaster target locations, while minimizing a set of predefined objectives that depend on the situation. The results demonstrate that immediate feedback obtained from the reconstructed 3D environment can help to investigate what–if scenarios, allowing for the preparation of effective rescue plans with an appropriate management effort.
- A clustering market-based approach for multi-robot emergency response applicationsPublication . Trigui, Sahar; Koubâa, Anis; Cheikhrouhou, Omar; Qureshi, Basit; Youssef, HabibIn this paper, we address the problem of multi-robot systems in emergency response applications, where a team of robots/drones has to visit affected locations to provide rescue services. In the literature, the most common approach is to assign target locations individually to robots using centralized or distributed techniques. The problem is that the computation complexity increases significantly with the number of robots and target locations. In addition, target locations may not be assigned uniformly among the robots. In this paper, we propose, CMMTSP, a clustering market-based approach that first groups locations into clusters, then assigns clusters to robots using a market-based approach. We formulate the problem as multipledepot MTSP and address the multi-objective optimization of three objectives namely, the total traveled distance, the maximum traveled distance and the mission time. Simulations show that CM-MTSP provides a better balance among the three objectives as compared to a single objective optimization, in particular an enhancement of the mission time, and reduces the execution time to at least 80% as compared to a greedy approach.
- Dronemap Planner: A Service-Oriented Cloud-Based Management System for the Internet-of-DronesPublication . Koubaa, Anis; Qureshi, Basit; Sriti, Mohamed-Foued; Allouch, Azza; Javed, Yasir; Alajlan, Maram; Cheikhrouhou, Omar; Khalgui, Mohamed; Tovar, EduardoLow-cost Unmanned Aerial Vehicles (UAVs), also known as drones, are increasingly gaining interest for enabling novel commercial and civil Internet-of-Things (IoT) applications. However, there are still open challenges that restrain their real-world deployment. First, drones typically have limited wireless communication ranges with the ground stations preventing their control over large distances. Second, these low-cost aerial platforms have limited computation and energy resources preventing them from running heavy applications onboard. In this paper, we address this gap and we present Dronemap Planner (DP), a service-oriented cloud-based drone management system that controls, monitors and communicates with drones over the Internet. DP allows seamless communication with the drones over the Internet, which enables their control anywhere and anytime without restriction on distance. In addition, DP provides access to cloud computing resources for drones to offload heavy computations. It virtualizes the access to drones through Web services (SOAP and REST), schedules their missions, and promotes collaboration between drones. DP supports two communication protocols: (i.) the MAVLink protocol, which is a lightweight message marshaling protocol supported by commodities Ardupilot-based drones. (ii.) the ROSLink protocol, which is a communication protocol that we developed to integrate Robot Operating System (ROS)-enabled robots into the IoT. We present several applications and proof-of-concepts that were developed using DP. We demonstrate the effectiveness of DP through a performance evaluation study using a real drone for a real-time tracking application.
- FL-MTSP: a fuzzy logic approach to solve the multi-objective multiple traveling salesman problem for multi-robot systemsPublication . Trigui, Sahar; Cheikhrouhou, Omar; Koubâa, Anis; Baroudi, Uthman; Youssef, HabibThis paper considers the problem of assigning target locations to be visited by mobile robots. We formulate the problem as a multiple-depot multiple traveling salesman problem (MD-MTSP), an NP-Hard problem instance of the MTSP. In contrast to most previous works, we seek to optimize multiple performance criteria, namely the maximum traveled distance and the total traveled distance, simultaneously. To address this problem, we propose, FL-MTSP, a new fuzzy logic approach that combines both metrics into a single fuzzy metric, reducing the problem to a single-objective optimization problem. Extensive simulations show that the proposed fuzzy logic approach outperforms an existing centralized Genetic Algorithm (MDMTSP_GA) in terms of providing a good trade-off of the two performance metrics of interest. In addition, the execution time of FL-MTSP was shown to be always faster than that of the MDMTSP_GA approach, with a ratio of 89 %.
- FL-MTSP: a fuzzy logic approach to solve the multi-objective multiple traveling salesman problem for multi-robot systemsPublication . Trigui, Sahar; Cheikhrouhou, Omar; Koubâa, Anis; Baroudi, Uthman; Youssef, HabibThis paper considers the problem of assigning target locations to be visited by mobile robots. We formulate the problem as a multiple-depot multiple traveling salesman problem (MD-MTSP), an NP-Hard problem instance of the MTSP. In contrast to most previous works, we seek to optimize multiple performance criteria, namely the maximum traveled distance and the total traveled distance, simultaneously. To address this problem, we propose, FL-MTSP, a new fuzzy logic approach that combines both metrics into a single fuzzy metric, reducing the problem to a single-objective optimization problem. Extensive simulations show that the proposed fuzzy logic approach outperforms an existing centralized Genetic Algorithm (MDMTSP_GA) in terms of providing a good trade-off of the two performance metrics of interest. In addition, the execution time of FL-MTSP was shown to be always faster than that of the MDMTSP_GA approach, with a ratio of 89 %.
- Integration and Applications of Fog Computing and Cloud Computing Based on the Internet of Things for Provision of Healthcare Services at HomePublication . Ijaz, Muhammad; Li, Gang; Lin, Ling; Cheikhrouhou, Omar; Hamam, Habib; Noor, AlamDue to the COVID-19 pandemic, the world has faced a significant challenge in the increase of the rate of morbidity and mortality among people, particularly the elderly aged patients. The risk of acquiring infections may increase during the visit of patients to the hospitals. The utilisation of technology such as the “Internet of Things (IoT)” based on Fog Computing and Cloud Computing turned out to be efficient in enhancing the healthcare quality services for the patients. The present paper aims at gaining a better understanding and insights into the most effective and novel IoT-based applications such as Cloud Computing and Fog Computing and their implementations in the healthcare field. The research methodology employed the collection of the information from the databases such as PubMed, Google Scholar, MEDLINE, and Science Direct. There are five research articles selected after 2015 based on the inclusion and exclusion criteria set for the study. The findings of the studies included in this paper indicate that IoT-based Fog Computing and Cloud Computing increase the delivery of healthcare quality services to patients. The technology showed high efficiency in terms of convenience, reliability, safety, and cost-effectiveness. Future studies are required to incorporate the models that provided the best quality services using the Fog and Cloud Computation techniques for the different user requirements. Moreover, edge computing could be used to significantly enhance the provision of health services at home.