An Artificial Intelligence Mechanism for the Prediction of Signal Strength in Drones to IoT Devices in Smart Cities
Mohamad Reda A. Refaai, Vinjamuri S. N. C. H. Dattu, H. S. Niranjana Murthy, P. Pramod Kumar, B. Kannadasan, Abdi Diriba
- 发表年份
- 2022
- 引用次数
- 8
- 访问权限
- 开放获取
摘要
Drones, the Internet of Things (IoT), and Artificial Intelligence (AI) could be used to create extraordinary responses to today’s difficulties in smart city challenges. A drone, which would be effectively a data-gathering device, could approach regions that become complicated, dangerous, or even impossible to achieve for individuals. In addition to interacting with one another, drones must maintain touch with some other ground-based entities, including IoT sensors, robotics, and people. Throughout this study, an intelligent approach for predicting the signal power from a drone to IoT applications in smart cities is presented in terms of maintaining internet connectivity, offering the necessary quality of service (QoS), and determining the drone’s transmission range offered. Predicting signal power and fading channel circumstances enables the adaptable transmission of data, which improves QoS for endpoint users/devices while lowering transmitting data power usage. Depending on many relevant criteria, an artificial neural network (ANN)-centered precise and effective method is provided to forecast the signal strength from such drones. The signal strength estimations are also utilized to forecast the drone’s flight patterns. The results demonstrate that the proposed ANN approach has an excellent correlation with the verification data collected through computations, with the determination of coefficient R2 values of 0.97 and 0.98, correspondingly, for changes in drone height and distances from a drone. Furthermore, the finding shows that signal distortions could be considerably decreased and strengthened.
关键词
相关论文
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002