Mitalipova Ainura Nurmamatovna

Background: Smart city technology solutions have recently ramped up the utilization of drones with Internet of Things (IoT) technologies for improving smart city systems. IoT sensors combined with real-time communication ad hoc network drones are also another area with great potential including traffic monitoring, environment management, disaster management, etc. Nevertheless, issues regarding energy consumption and density, the number of nodes that can be incorporated into the network, as well as the issue of avoiding collisions between the signal sent by one node with the signals that may be transmitted by other nodes are still observed as essential impediments to the wide application of WSNs. Objective: The article seeks to propose and assess algorithms for operating drone-IoT systems whilst dealing with issues like energy efficiency, real-time data communication, avoiding mid-air collisions, and dealing with the increasing number of systems in crowded urban areas. Methods: This study utilizes a two-time algorithm technique that was adopted from the prior study. The first algorithm provides a method for speed and position control of drones, ensuring that the distance between the drones is sufficient and not violable. The second algorithm is centered on energy reduction, which selects the precise energy usage by employing path planning in real time. The effectiveness of these algorithms was determined using simulation models with respect to metrics including latency, energy consumption, and scalability. Results: The proposed system revealed the systems’ improvements in energy efficiency, fewer collisions, and strong scalability of drone management. Main conclusions possible to conclude during the experiment reveal the system’s generic aptitude to the different urban situations and its stability in changing traffic conditions. Conclusion: The article presents a scalable and efficient solution for extending drone applications to smart cities using IoT platforms. In this way, the results can serve as the further theoretical and experimental base for investigating the trends of management and the infrastructure of cities.

Background : Security has been a major issue of discussion due to increase in the number and sophistication of Cyber threats in the modern era. Conventional approaches to threat identification might face difficulties in a number of things, namely the relevancy and the ability to process new and constantly evolving threats. Machine learning (ML) and deep learning (DL) based Approaches present AI as a potential solution to the problem of efficient threat detection.   Objective : The article aims to compare the RF, SVM, CNNs, and RNNs models’ performance, computational time, and resilience in identifying potential cyber threats, such as malware, phishing, and DoS attacks.   Methods : The proposed models were trained as well as evaluated on the NSL-KDD and CICIDS 2017 datasets. This was done based on common scheme indicators including accuracy, precision, recollection, F1 measure, detection rate of efficiency, AUC-ROC, False Alarm Rate (FAR), and the stability to adversaries. Rating of computational efficiency was defined by training time and memory consumption.   Results : The findings indicate that the CNNs gave the best accuracy (96%) and resisted perturbation better, and the RF showed good performance with little computational load. RNNs have been proved effective in sequential data analysis and SVM also performed fairly well on binary data classification although there is a problem of scalability.   Conclusion : CNNs used in AI models are the best solutions to protection from the threats in the cybersecurity space. Nevertheless, some of them still require computational optimization in order to make those beneficial in scenarios with a limited usage of computational resources. It is suggested that these findings can be used in the context of subsequent research and practical applications.