الفهرس 
IntroductionOnly 14 pages are availabe for public view
 |  | from | 155 |  |  |
| | | from | 155 | | |
Abstract
The Internet of Things (IoT) is now widely used in a variety of industries, including smart cities, healthcare, and agriculture. IoT technologies like Lora WAN, SIGFOX, ZigBee, and others have made it more necessary than ever for organisations to switch from their legacy systems to IoT systems to improve performance. But IoT technology comes with different challenges including energy consumption, quality of service and bandwidth. IoT in agriculture can be considered as one of the most important and challenging IoT applications as a result of the necessity for significant energy and water usage to provide the appropriate crop yield. This is a big problem for farmers and the agricultural sector, which is looking for methods to boost output while lowering prices and having a less negative impact on the environment. The potential advantages of applying IoT in agriculture, however, are significant and range from more effective resource management to real-time crop condition monitoring, which may help optimise yields, increase crop quality, and decrease wastage. Therefore, it is essential to keep investigating the IoT’s potential in agriculture and coming up with creative solutions to solve problems as they arise.
This thesis explores the potential of artificial intelligence (AI) in improving the performance of IoT systems in smart agriculture, a field that is critical for energy conservation and sustainable food production while taking into consideration the performance of the IoT system by conserving bandwidth and enhancing the QOS over the IoT networks. The thesis is discussing the main design principles of IoT systems, and the methods used to optimize the system performance. It also presents a comprehensive study on predicting crop yield using deep learning algorithms, which can help farmers make informed decisions about resource allocation and optimize the yield and examines the use of convolutional neural networks (CNNs) for detecting and monitoring crop diseases, as well as real-time crop monitoring. By combining AI and IoT technologies, this thesis demonstrates how smart agriculture can significantly improve resource utilization, increase productivity, and reduce waste.
Moreover, the findings of this study can have significant implications for sustainable agriculture practices and food security, highlighting the potential of AI-powered IoT systems in addressing some of the most pressing challenges facing the agricultural industry today.