Intelligent Measurement in Unmanned Aerial Cyber Physical Systems for Traffic Surveillance (original) (raw)
Related papers
Neural Network and its Application
Deep neural networks (DNNs) are rapidly being used in safety-critical areas such as drone and aircraft control, supporting techniques for analyzing the safety of actions. Unfortunately, DNN analysis is NP-hard and existing algorithms become slower as the number of nodes in the DNN increases. Neural networks, a subset of artificial intelligence, have rapidly evolved, transforming the landscape of machine learning. Inspired by the structure and function of the human brain, these computational models have demonstrated exceptional capabilities in various applications. This research paper provides a comprehensive analysis of neural networks, encompassing their historical development, architectural components, training methodologies, real-world applications, existing challenges, and future directions.
Redundancy requirements for UAV (Unmanned Aerial Vehicle) are hardly faced due to the generally restricted amount of available space and allowable weight for the aircraft systems, limiting their exploitation. Essential equipment as the Air Data, Attitude and Heading Reference Systems (ADAHRS) require several external probes to measure significant data as the Angle of Attack or the Sideslip Angle. Previous research focused on the analysis of a patented technology named Smart-ADAHRS (Smart Air Data, Attitude and Heading Reference System) as an alternative method to obtain reliable and accurate estimates of the aerodynamic angles. This solution is based on an innovative sensor fusion algorithm implementing soft computing techniques and it allows to obtain a simplified inertial and air data system reducing external devices. In fact, only one external source of dynamic and static pressures is needed. This paper focuses on the benefits which would be gained by the implementation of this s...
Use of Unmanned Aerial Vehicles for Traffic Surveys
LOGI – Scientific Journal on Transport and Logistics
The paper deals with the topic of monitoring traffic using unmanned aerial vehicles. The main research goal was to test the possibility of using aerial vehicles for traffic engineering applications, especially for determining the traffic intensity on roads and for evaluating the data on traffic using video footage. The practical part of the paper focuses on the evaluation of data on traffic obtained by means of unmanned aerial vehicle at a selected intersection of roads. The data are evaluated using SW based on work with neural networks. A stationary system composed of an unmanned aircraft, camera system with a stabiliser, ground source with voltage converter, wire unwinding system and accessories were created by the staff of the ITB for the purpose of video recording the traffic from a 20-meter height. Such a tethered unmanned aerial system enabled a long-term operation in the air and a video recording lasting 1 hour at least.
Real-Time UAV Recognition Through Advanced Machine Learning for Enhanced Military Surveillance, 2025
In an era where the military utilization of Unmanned Aerial Vehicles (UAVs) has become essential for surveillance and operational operations, our study tackles the growing demand for real-time, accurate UAV recognition. The rise of UAVs presents numerous safety hazards, requiring systems that distinguish UAVs from non-threatening phenomena, such as birds. This research study conducts a comparative examination of advanced machine learning models, aiming to address the challenge of real-time aerial classification in diverse environmental conditions without model retraining. This research employs extensive datasets to train and validate models such as Neural Networks, Support Vector Machines, ensemble methods, and Gradient Boosting Machines. The fashions are evaluated based on accuracy, forgetfulness, and processing efficiency-criteria determining the viability of real-time operational scenarios. The findings indicate that Neural Networks exhibit enhanced performance, demonstrating exceptional accuracy in distinguishing UAVs from birds. This culminates in our primary assertion: Neural Networks possess vital operational security ramifications and can markedly enhance the allocation of defense resources. The findings significantly improve surveillance systems, highlighting the effectiveness of machine-learning methods in real-time UAV identification. Moreover, incorporating Neural Network systems into military defenses is recommended to enhance decision-making capabilities and security operations. Foresee forthcoming UAV developments and advocate for regular model updates to keep up with increasingly nimble and perhaps stealthier drone designs.
QUIST MIRABLE JETHRO, 2024
ARTIFICIAL INTELLIGENCE (AI) in Action: Empowering Drones. How AI is transforming Drones includes: Autonomous Flight, Enhanced Data Collection. UAVs or Unmanned Aerial Vehicles are aircraft operated without a human pilot on board. They can be remotely controlled or fly automatously using pre-programmed flight plans or more complex dynamic automation systems. Why UAVs? Agility and maneuverability. Cost-effectiveness compared to manned aircraft. Access to hazardous or remote areas. smaller in size and can achieve great speeds. Understanding Artificial Intelligence (AI). AI is Simulation of human intelligence in machines, enabling systems to learn, reason, make decisions. Key Areas for Drones: Machine learning, Algorithms learning from data and Computer vision: Enabling drones to "see" and understand. AI in Action: Empowering Drones. Applications: Search and Rescue. Search and Rescue with AI includes: Rapid coverage of large areas. Thermal imaging for finding people. Facial recognition for missing person identification (consider ethnical implications). Applications: Precision Agriculture. Revolutionizing Agriculture: Crop health monitoring: Identifying diseases and deficiencies. Precision Spraying: Optimize pesticide and fertilizer use. Automated field mapping and yield estimation. Applications: Infrastructure Inspection. Infrastructure Inspection with AI includes: Access to hard-to-reach areas. AI - powered damage detection (cracks, corrosion). Faster and more cost-effective inspections. Applications: Delivery Drones. The Future Delivery: Autonomous deliveries to remote areas. Faster and more efficient delivery items. Considerations: Safety, regulation, public perception. The Future of AI and Drones; Integration with LIDAR, 5G for enhanced capabilities. Expanding to disaster response, environmental monitoring, planetary exploration. Addressing ethical considerations (privacy, security). AI is revolutionizing UAV capabilities. Vast potential for various industries. Exciting future with endless possibilities
Advantages of Neural Network Based Air Data Estimation for Unmanned Aerial Vehicles
2017
Redundancy requirements for UAV (Unmanned Aerial Vehicle) are hardly faced due to the generally restricted amount of available space and allowable weight for the aircraft systems, limiting their exploitation. Essential equipment as the Air Data, Attitude and Heading Reference Systems (ADAHRS) require several external probes to measure significant data as the Angle of Attack or the Sideslip Angle. Previous research focused on the analysis of a patented technology named Smart-ADAHRS (Smart Air Data, Attitude and Heading Reference System) as an alternative method to obtain reliable and accurate estimates of the aerodynamic angles. This solution is based on an innovative sensor fusion algorithm implementing soft computing techniques and it allows to obtain a simplified inertial and air data system reducing external devices. In fact, only one external source of dynamic and static pressures is needed. This paper focuses on the benefits which would be gained by the implementation of this s...
Neural networks from the perspective of measurement systems
2003
The goal of this paper is to give an overview of neural networks from the viewpoint of measurements. It shows that neural networks can play an important role in measurement systems; for example they can be used in complex sensor's systems, and in utilization of the observation data, to build system's models. From the point of view of measurement systems
Neural Networks-based Virtual Sensors Methodology
In this work a Methodology framework for implanting Virtual Sensors using Neural Networks will be presented, including the statistical analysis techniques that can be used for studying and processing the data. The proposed Methodology is based upon Software Engineering, Knowledge-based systems and neural networks methodologies. This methodological framework includes both technical and economical feasibility to build the virtual sensors and considers important aspects as the available computational platform, historical data files, data processing requirements such as filtering, pruning, set of variables that must be selected for the best performance of the virtual sensor, etc. There are also presented the statistical consideration and the corresponding techniques for data analysis and processing. The methodology includes techniques as principal components, cluster analysis, factorial analysis, etc.
Towards High Confidence Cyberphysical Systems for Intelligent Transportation Systems
dre.vanderbilt.edu
Abstract: The transportation sector worldwide is significantly stressed due to the inability of the infrastructure to meet the demands of ever increasing traffic volumes. Traffic congestion problems continue to worsen, leading to substantial adverse economic and environmental impact. Increased volume and hazardous weather/road conditions lead to an increasing number of multi-vehicle accidents and fatalities. The Intelligent Transportation System (ITS) efforts across the world are aimed at addressing a range of problems including ...