erfan khosravian

Space exploration and satellite deployment drive modern technological advancements. They are crucial for global communication, navigation, and scientific discovery. Satellites form the backbone of interstellar communication, ensuring reliable data transfer in both civilian and defense sectors. However, as space missions grow more complex, maintaining their integrity and security becomes a major challenge.Unmanned Aerial Vehicles (UAVs) play a key role in space missions. They assist in satellite deployment, orbital inspections, and inter-satellite communication. Yet, these cyber-physical systems face evolving cybersecurity threats that could jeopardize mission-critical tasks. Traditional intrusion detection systems struggle to counter the complex and dynamic cyber threats targeting UAVs in harsh space environments.This paper introduces a novel Deep Reinforcement Learning model to predict and mitigate cyber risks in space-related UAV missions. Using a publicly available dataset that combines cyber and physical UAV data, the model predicts multi-step threats such as Denial of Service, Replay, Evil Twin, and False Data Injection. This enables proactive threat mitigation. Compared to traditional machine learning models—Support Vector Machines, Random Forests, and Recurrent Neural Networks—the proposed model achieves superior performance, with 99.34% accuracy and an AUC score of 0.99.

Wireless sensor networks (WSNs) are crucial for environmental monitoring, particularly for assessing air quality. However, optimizing energy consumption remains a significant challenge due to the limited energy resources of the sensor nodes, which adversely affects the network's performance and lifespan. This study aims to enhance the longevity and efficiency of WSNs by implementing metaheuristic algorithms, specifically Ant Lion Optimization (ALO) and Cheetah Optimization (CO), for effective energy management through clustering strategies. Utilizing simulations, we compared the performance of ALO against CO in terms of energy efficiency, network lifespan, and resilience within heterogeneous network conditions. The results indicate that ALO optimizes data transmission by reducing network traffic through efficient cluster communication. Additionally, ALO's scalability enables the network to adapt to changing sensor deployments, while data aggregation at the cluster head level further minimizes energy consumption. This load balancing ensures a more even distribution of energy usage, further ALO outperforms CO by extending network lifespan, improving energy management, and providing better scalability. The findings suggest that ALO is a robust approach for optimizing clustering and energy consumption in WSNs.

The highest level in Endsley's situation awareness model is called projection when the status of elements in the environment is shortly predicted. In cybersecurity situation awareness, the projection for an Advanced Persistent Threat (APT) requires to predict the next step of the APT.The threats are constantly changing and becoming more complex. As supervised and unsupervised learning methods require APT datasets for projecting the next step of APTs, they cannot identify unknown APT threats.In reinforcement learning methods, the agent interacts with the environment, which might project the next step of known and unknown APTs. So far, reinforcement learning has not been used to project the next step of APTs.In reinforcement learning, the agent uses the previous states and actions to approximate the best action of the current state. When the number of states and actions is abundant, the agent employs a neural network to approximate the best action of each state.This paper presents a deep reinforcement learning system to project the next step of APTs. As there exists some relation between attack steps, we employ the Long Short Term Memory method to approximate the best action of each state. In our proposed system, based on the current situation, we project the next steps of APT threats.We have evaluated our proposed system on the DAPT2020 dataset. Based on the evaluations performed on the mentioned dataset, six criteria F1, accuracy, precision, recall, loss, and average time were obtained, which are 0.9533, 0.9736, 0.9352, 0.97, 0.0143, and 0.05749(seconds), respectively.

Situation awareness (SA) refers to the perception of environmental elements within a specific volume of time and space, understanding their meaning, and projecting their near future status. This model has three levels: perception of the current situation, comprehension of the current situation, and projection of future status. SA is a term used to describe an individual’s level of awareness and understanding of "what is happening". Therefore, SA serves as the first step in decision-making, providing an understanding of "what is happening" and "what is likely to happen". In practice, safe decision-making depends on the continuous extraction of technical and environmental information, integrating knowledge, and forming a coherent mental picture to guide perception and predict future events. The use of this concept is essential for several reasons. First, situation awareness systems improve the accuracy of decisions by providing up-to-date and comprehensive information about the environment. These systems, by delivering precise data and analyses, reduce human errors and ensure that decision-makers consider all relevant factors and data, leading to more accurate decisions.  Moreover, situation awareness increases decision-making speed. These systems quickly identify environmental changes and process large volumes of data in a short time, providing decision-makers with relevant information rapidly, which leads to timely and swift decisions.
In recent years, the application of SA has gained prominence in Unmanned Aerial Vehicles (UAVs), where continuous extraction of technical and environmental information is vital for safe and efficient operations. UAVs rely on real-time data integration to form coherent mental models that guide perception, enhance decision-making, and predict future events, thus improving operational safety and efficiency. The use of SA systems in UAVs is essential for several reasons. First, they enhance decision accuracy by providing comprehensive, up-to-date information about the environment, reducing human errors and ensuring that all relevant data are considered, and increases decision making speed. Hence, in this paper, we examine and evaluate various decision-making methods in situation awareness systems by focusing on UAV application.

The integration of artificial intelligence (AI) into unmanned aerial vehicles (UAVs) has substantially advanced these platforms' capabilities, particularly in enhancing situational awareness. This paper presents a comprehensive survey and review of AI-driven techniques aimed at improving situational awareness in UAVs. We begin by defining situational awareness and its essential components—perception, comprehension, and projection—within the context of UAV operations. Subsequently, we explore various AI methodologies, including machine learning, deep learning, computer vision, natural language processing, and data fusion, that are employed to augment UAVs' capabilities to perceive and interpret their environments. The paper examines diverse AI-enhanced UAV situational awareness applications across military, civilian, and commercial domains. Critical applications include advanced surveillance, target acquisition, search and rescue missions, environmental monitoring, traffic and crowd monitoring, infrastructure inspection, and delivery services. Additionally, we discuss the technical and operational challenges associated with implementingAI in UAVs, such as data quality, real-time processing, environmental impacts, and scalability. Ethical and legal considerations are also addressed, including privacy concerns and regulatory issues. In addition to a thorough review of the current literature, we provide detailed case studies highlighting successful AI implementations in UAVs, offering practical insights and lessons learned. We also identify emerging technologies and future research opportunities with the potential to advance the field, suchas innovations in sensor technology and AI algorithms. Our findings underscore the transformative potential of AI in enhancing the situational awareness of UAVs, paving the way for more intelligent, autonomous, and effective aerial systems. This survey serves as a valuable resource for researchers, practitioners, and policymakers interested in understanding and leveraging the intersection of AI and UAV technology for various applications.

Improving the mechanical properties of the 3D printed parts by a 3D printer based on fused filament fabrication by continuous fibers (carbon, glass, and aramid) has been the focus of many researchers. Due to the nature of additive manufacturing processes that produce the parts layer by layer, in most of the research, continuous fibers are layered on a 2D surface. Robots with high degrees of freedom have been used in cases where fibers are placed on curved surfaces. In this research, a method for deposition of the continuous glass fibers on a curved surface is presented. This method is implemented on a simple and cheap 3D printer. The presented method is based on modifying the G-code, creating a rotating axis for the nozzle, and applying and using computer-aided design and manufacturing techniques. Finally, by 3D scanning of the printed sample and comparing it with the 3D model, the amount of deviation and tolerance of the surface form is determined. The obtained experimental results indicate the effectiveness of the presented method for the deposition of continuous fibers on curved surfaces. With the presented system, continuous fibers are deposited on a curved surface that consists of paths with different degrees of curvature, by simultaneous impregnation of fiber and polymer. Comparing the scanned sample with the printed sample shows that the maximum deviation is 0.1 mm. This error is acceptable due to the nature of shrinkage and distortion of thermoplastic polymer materials in forming processes according to the DIN 16901 standard.

Research conducted to date on structures having auxetic properties has focused on macroscopic scale and molecular analyses, and very few studies have examined auxetic models applicable to everyday objects. Auxetic pressure springs were used in this paper to produce a numerical model and to verify the quality of the furniture seats. Based on their surface stiffness and contact pressure distribution, system stiffness was determined. By performing a numerical study, the impact of seat modification with foam on the comfort of the seat when it was utilized was assessed. Furthermore, numerical modelling can effectively simulate complex, multilayer systems made out of materials with nonlinear characteristics, enabling rapid prototyping of these systems.

This study aimed to investigate the influence of rotational and traverse speeds on the friction stir welding (FSW) of aerospace-grade aluminum alloys. To achieve this, a thermo-mechanically coupled 3D finite element analysis (FEM) was employed to analyze the impact of these speeds on temperature and strain. Additionally, tensile tests were conducted on welded joints fabricated using varying tool rotational and traverse speeds to examine the effects of welding speed on the tensile properties of the specimens. The results revealed that high welding speeds had a detrimental effect on the mechanical properties of the weld samples. Samples produced using an optimal rotational speed of 1200 rpm and a traverse speed of 40 mm exhibited a tensile strength of 346 MPa, which accounts for approximately 64% of the strength seen in the base material.

Amidst the continuous expansion of global commerce and the urgent need for expedited order delivery within distribution networks and online customer service platforms, the demand for air cargo transportation has reached unprecedented levels, complementing traditional distribution channels such as land and sea. Consequently, this sector has garnered considerable attention in recent years. One of the primary challenges encountered in aerial distribution networks pertains to the routing problem for unmanned aerial vehicles (UAVs), which necessitates considerations of enhanced customer satisfaction and network constraints. To address this challenge, this paper commences by introducing the routing problem alongside customer and network constraints, subsequently presenting their mathematical formulations. Notably, the dynamic behavior of aerial robots poses a significant constraint in this context, which has been inadequately addressed in existing research on routing problems within distribution and customer service networks. This deficiency is attributed to the involvement of flight dynamics equations, complicating the problem significantly. In this study, the nonlinear equations governing aerial robots for customer service are reformulated in state space representation. Subsequently, the routing problem, incorporating the state space equations of flying robots and considerations of customer and network constraints, is tackled using a genetic optimization algorithm—an optimal solver. Following the solution process using the genetic algorithm, the results are elucidated in terms of optimal routes. Simulation outcomes validate the efficacy of the proposed approach in meeting all problem requirements and objectives, thereby presenting a viable solution for routing large-scale aerial networks.

The Internet of Drones (IoD) is a decentralized network that connects drones to controlled airspace. The connection of drones in these networks is through the Internet of Things. Hence, these networks are vulnerable to all the security and privacy threats that affect IoT networks. In addition, as the application of these networks is highly sensitive in many cases, there are greater potential security threats. The components of these networks work together to identify new and advanced threats. One of the ways to identify new and advanced threats in these networks is distributed machine learning where the data is sent to a central server to learn the general model. This model violates the privacy of network components. It also has a very high level of communication. On the other hand, the central server as the only point of failure may have many problems. In this case, federated learning helps distributed and decentralized networks to share their local model instead of sending their local and secret data. Since the shared models may also disclose some information, we propose a secure and privacy-preserving protocol based on homomorphic encryption. The protocol proposed was for federal learning model and detection of new and advanced threats in the Internet of Drones.

Heat transfer is an important and influential factor in the design of internal combustion engines. Accurate prediction of heat transfer has a great impact on the design of cooling systems of internal combustion engines. The simulation of internal combustion engines for their thermal analysis is done using computational fluid dynamics along with boiling simulation. This article investigates the subcooled boiling flow of pure water in a small channel and its dependence on different parameters such as working pressure, heat flux, and mass flux. The subcooling temperature of the inlet fluid is of interest. Numerical simulations were performed using axisymmetric models and the effect of different grid sizes on the accuracy of the results was investigated. The bubble separation diameter was also studied and its relationship with pressure, heat flux, mass flux, and temperature under the inlet coolant was analyzed. Finally, a database of generated simulation results and predictive models for bubble dynamics using machine learning algorithms were presented.

Today, technology is presented for various reasons and is considered as a candidate for investment. Firms have to obtain technology for growth, competitiveness, product and service presentation and governmental conditions, and many other reasons. One of the areas of science and technology that has a significant impact on improving living standards and serving the citizens is the aviation industry which has an important role in improving the standard of living with the development in commercial and public sectors. One of the most important characteristics of this emerging industry is the multiplicity of application of new technologies, including composite structures technology. Entry of composite structures into the aviation industry is for meeting its exceptional and unique needs, and it can be said that the perfect position and continuation of aviation industry development depends on the technology acquisition of composites and the relevant progress. Due to the highly sanction, aviation companies must have agility and the ability to exploit transient environmental opportunities, but companies’ resources are limited on the other hand. In this research, the most important issues and challenges on facing the technology acquisition are discussed. Finally, the model of technology acquisition based on sanction is derived and implemented on composite process technologies.