Yazar "Özer, Muhammed Mirac" seçeneğine göre listele

Listeleniyor 1 - 9 / 9
  • [ X ]
    Öğe
    A UAV Configuration Capable of Object Detection, Instant Communication and Real-Time Data Transmission
    (Springer Science and Business Media Deutschland GmbH, 2024) Özer, Muhammed Mirac
    A UAV design that can detect targets individually or in surveillance flight missions in a swarm formation is presented. For the mission in a swarm operation, the UAV is designed to communicate with the members of the swarm and work together to achieve the common objective. The necessary communication mechanism has been designed to adapt the UAV to the swarm, and it has been equipped with the necessary hardware to perform the task in coordination. To communicate with other UAVs and also to establish an effective communication with the ground control station, the interconnection and bandwidth need of the swarm has been addressed with a proper network architecture. For multi-hop communication, the transmission of packets over the network is executed based on the 802.11 s standard, thus ensuring that the images and videos of the detected targets are transmitted to the ground station in real-time, uninterrupted and without latency. With the topology-based communication network, the flight range is greatly expanded by allowing the swarm to transmit data. The results obtained are provided that the communication network connected to the equipment used can support direct point-to-point communication up to 1000 feet. In addition, the UAV swarm, which was developed to detect objects and to coordinate with the herd, was evaluated by being supported by a reliable communication network. The focus is on the ability of UAVs to predict the communication channel strength, and different deep learning optimization algorithms are used for this purpose. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
  • [ X ]
    Öğe
    An IoT-Based Modular Avionics and Electrical System for Nanosatellite Systems
    (Springer Science and Business Media Deutschland GmbH, 2023) Bakirci, Murat; Özer, Muhammed Mirac
    This study presents an avionics and electrical system design using reliable, high-performance hardware and sensors for advanced scientific experimentation missions compatible with air-land-sea vehicle platforms, particularly nanosatellite platforms. The nanosatellite avionics, which has a real-time operating system that supports frequently used interfaces, processes and manages sensory and physical data based on a central processor. It executes all operations by defining IoT requirements and computing connection parameters for IoT applications. The modular design brought into the system provides both ease of access and integration into the target platform, and also provides reliable storage for telemetry and flight data. Through the IoT station, it reliably receives information from the satellite and transmits it to smart devices while maintaining the desired signal quality. Moreover, through processing the data obtained from the sensors, critical information such as instant detection and tracking of systems errors are transmitted to the cloud, and as a result, proper control can be provided regardless of location. This critical data obtained from the cloud is straightforwardly tracked by the software platform. This design will provide the space technologies inventory as the basis for a new satellite platform and a system design for researchers to further develop. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
  • [ X ]
    Öğe
    Avionics and Communication Architecture Design for Intelligent Automated Fixed-Wing Armed Aircraft
    (Springer Science and Business Media Deutschland GmbH, 2024) Özer, Muhammed Mirac
    This study presents a detailed avionics architecture for a fixed-wing armed unmanned aerial vehicle (FWA) capable of detecting and tracking targets during a flight mission. Equipped with an artificial intelligence-based development board and a wide variety of sensors, the aerial platform is able to detect target aircraft with high accuracy. The images obtained by the aircraft are processed with YOLOv5x algorithm to detect the target aircraft. Target tracking processes were modeled assuming that the target was fixed first, and then generalized by taking into account that the target was actually moving. During the flight mission of the armed UAV, all telemetry data were transmitted seamlessly with the ground station within the communication range. In addition, FWA can be controlled manually via radio frequency (RF) control and data transfer is provided without delay. With the designed avionics and electrical system architecture, the FWA can fly fully autonomously, as well as perform different tasks such as image acquisition and instant data transfer with high accuracy. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
  • [ X ]
    Öğe
    Enhancing Ground Vehicle Route Planning with Multi-Drone Integration
    (Springer Science and Business Media Deutschland GmbH, 2024) Bakirci, Murat; Özer, Muhammed Mirac
    This study aims to address the challenge of coordinating time and location for route planning in ground vehicles during simultaneous disaster response missions, utilizing a hybrid genetic algorithm based on machine learning. The proposed method combines both precise and heuristic solutions by integrating exact solution approaches while managing multiple drones during concurrent response efforts. The research evaluates the performance of these methods and assesses the impact of using multiple drones on disaster response times. The results unequivocally demonstrate the effectiveness of the hybrid genetic algorithm in solving small-/medium-sized problems involving drones. Furthermore, the study examines variables such as the number of drones and battery life, thereby elaborating their influence on response times and aiding in strategic decision-making. Compared to the TSP solution, single drone integration reduced response time by 30%, while two drones achieved a 45% reduction, and three drones a 50% reduction. Furthermore, an increase in the number of drones has been accompanied by a decrease in the workload for each drone, allowing for a reduction in battery capacity requirements in an inversely proportional manner to the increase in the number of drones. Moreover, this research underscores the adaptability of the hybrid genetic algorithm (HGA) in addressing the Vehicle Routing Problem with Multiple Drones (VRP-mD), a complex simultaneous deployment issue involving ground vehicles and multiple drones. This finding represents a significant contribution, expanding the potential of hybrid algorithms in tackling larger and more intricate distribution challenges. This approach holds promise for broader applications in solving complex intervention problems. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
  • [ X ]
    Öğe
    Hybrid Genetic Algorithm Based on Machine Learning and Fitness Function Estimation Proposal for Ground Vehicle and Drone Cooperative Delivery Problem
    (Springer Science and Business Media Deutschland GmbH, 2024) Özer, Muhammed Mirac
    In this study, the development of a hybrid genetic algorithm, integrating machine learning and function estimation, presents a novel approach to address the simultaneous intervention challenge involving unmanned ground vehicles (UGVs) and unmanned aerial vehicles (UAVs). The adaptability of this hybrid genetic algorithm confers a notable advantage in managing drone scenarios. Notably, this work constitutes the inaugural attempt in the literature to devise an exact solution for the concurrent intervention of a UGV and a UAV, with the added innovation of minimizing intervention time. This pioneering methodology holds promise for extending the problem domain to encompass more realistic scenarios, thereby bridging a significant gap in the literature and furnishing a foundational framework for future research endeavors. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
  • [ X ]
    Öğe
    Internet of Things-Based Drone Case Study for Atmospheric Data Collection
    (Springer Science and Business Media Deutschland GmbH, 2024) Özer, Muhammed Mirac
    Although ground-based monitoring, manned aircrafts and satellites are used for atmospheric measurements, rapid and comprehensive data collection is not always possible near pollution sources due to the complexity of the areas to be measured, moving sources or physical obstacles. Therefore, drone solutions equipped with different sensors offer new approaches and research opportunities in air pollution and emissions monitoring, as well as on-site air quality monitoring to study atmospheric trends such as climate change. While the potential of unmanned aerial vehicles for air quality research has been identified, several challenges still need to be addressed, including flight durability, payload capacity, sensor consistency/accuracy and sensitivity. In this study, a rotary-wing drone architecture that utilizes artificial intelligence (AI), computer vision algorithms, as well as 4G-LTE IoT-based monitoring to collect atmospheric data, is presented. Designed as a new scalable platform to accommodate sensors suitable for flight control and communication requirements, the system has the ability to take off, fly and land with full autonomy. In case of possible communication interruption, it can switch to the fail- safe mode set in the ground control station. In addition to being able to make atmospheric measurements, a design has been developed in such a way that wide variety of parameters such as urban planning and development of smart cities, monitoring of industrial emissions, determination of pollution points in the city, redirection and management of traffic can be monitored in real time. The designed drone has a small, lightweight and low- cost multi-sensor system capable of measuring temperature, humidity, pressure, air velocity, noise, amount of UV, light intensity, PM2.5, PM10. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
  • [ X ]
    Öğe
    Involvement of Unmanned Aerial Vehicles and Swarm Intelligence in Future Modern Warfare: An Overview
    (Springer Science and Business Media Deutschland GmbH, 2024) Bakirci, Murat; Özer, Muhammed Mirac
    This study provides an overview of the potential uses of unmanned aerial vehicles and their swarm systems in future military technology. By examining the usage purposes in different application areas, the basic requirements of a common UAV design are investigated. Critical requirements have been determined, and it has been demonstrated that UAV systems with certain key features can be easily incorporated into swarm systems and used in future military applications. In addition, a common UAV that can be utilized in various applications has been developed, and constraints in the design and production stages have been determined. In this respect, the study provides a basis for similar studies to be carried out. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
  • [ X ]
    Öğe
    Predictive Modeling of Urban Air Pollution Using Machine Learning and Unmanned Aerial Vehicle Platforms
    (Springer Science and Business Media Deutschland GmbH, 2024) Özer, Muhammed Mirac
    Air pollution poses a significant threat to human health on a global scale, with prolonged exposure to elevated ozone levels being particularly detrimental, leading to chronic respiratory conditions such as bronchitis, emphysema, and asthma. Beyond these health impacts, high ozone concentrations impair the photosynthetic capacity of plants, resulting in decreased agricultural productivity. Ozone is also a critical pollutant that negatively influences air quality in urban environments. In this regard, accurately predicting short-term air pollution levels is crucial for alerting the public to potential health risks and implementing effective pollution control measures. This study illustrates the successful prediction of hourly air pollutant concentrations in a specific region through the application of machine learning algorithms. Real-time pollutant and meteorological data—including air temperature, wind speed, relative humidity, and air pressure—collected via an unmanned aerial vehicle (UAV) were effectively utilized to develop the short-term forecasting model. Various machine learning regression algorithms, such as random forest, decision tree, support vector regression, k-nearest neighbors, and multilayer perceptron regression, formed the foundation of this predictive model. The analysis indicates that the random forest regression algorithm outperforms others in forecasting ozone levels in a particular area. Additionally, the data obtained from the UAV significantly enhances the accuracy and reliability of the short-term prediction model. The high-precision, instantaneous data provided by the UAV offers a considerable advantage in refining air pollution prediction models. These findings contribute to the development of robust strategies for mitigating air pollution and represent a significant advancement in adopting a more proactive and anticipatory approach to managing air quality issues. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
  • [ X ]
    Öğe
    Transforming a Customized Drone into an Advanced Forensic Investigation Platform
    (Springer Science and Business Media Deutschland GmbH, 2024) Özer, Muhammed Mirac
    This study deals with the process of transforming a specially designed drone into an advanced forensic investigation platform. First, the details and features of the drone system design are analyzed. This design process is particularly notable for its lightweight structure, high maneuverability and long flight time. These features make the drone an ideal platform for forensic investigation operations. The system design also includes the integration of various sensors. These sensors include high-resolution cameras, imaging devices and air quality measurement sensors. In particular, the use of cameras provides detailed visual data during the forensic investigation process and optimizes evidence collection. Thermal imaging devices, on the other hand, work effectively at night and in harsh weather conditions, increasing the success of forensic investigation operations. In addition, air quality measurement sensors are used to detect explosives, harmful gases and other potentially hazardous substances. These sensors contribute to reliable results by automating the collection and analysis of air samples. In conclusion, this study presents a significant advancement in the field of forensic investigation, focusing on the system design and integration of sensors to enhance the usability of a specially designed drone in forensic investigation operations. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.