Heterogenous Computational Intelligence in Internet of Things

The development of data transfer techniques in the networking industry has enabled medical imaging to detect infection in patients, particularly in the COVID-19 pandemic. Wireless network virtualization is an intriguing concept that can reduce spectrum congestion and offer new network services. However, it has both technical and non-technical issues that need to be handled before it becomes a common technology. Future wireless network architecture must adhere to Quality of Service (QoS) requirements, and Deep Reinforcement Learning (DRL) has been developed as a potential approach to solve high-dimensional and continuous control issues effectively. DRL has shown great potential in IoT, edge, and SDN scenarios, but there are still domain-specific challenges that require further study.

Format: Hardback
Length: 300 pages
Publication date: 26 October 2023
Publisher: Taylor & Francis Ltd

The past few years have witnessed a remarkable surge in the development of data transfer techniques within the networking industry. This trend has been particularly evident in the context of the current COVID-19 pandemic, where the use of photos has proven invaluable in assisting clinicians in detecting infections in patients. The integration of Machine Learning (ML) and Artificial Intelligence (AI) has played a pivotal role in this regard, as medical imaging, such as lung X-rays for COVID-19 infection, has become crucial in the early detection of various diseases.

While both wired and wireless networking have seen improvements in terms of data transfer during the COVID-19 scenario, network congestion has become a significant challenge. However, an intriguing concept known as wireless network virtualization has emerged as a potential solution to reduce spectrum congestion and continuously offer new network services. The degree of virtualization and resource sharing varies between different paradigms, each presenting its own set of technical and non-technical issues that must be addressed before wireless virtualization becomes a common technology.

To ensure the success of wireless network virtualization, these issues require careful design and evaluation. Future wireless network architectures must adhere to a number of Quality of Service (QoS) requirements, ensuring that users receive the desired level of service and performance. Virtualization has also been extended to wireless networks, alongside conventional ones, by enabling multi-tenancy and tailored services with a wider range of carrier frequencies. This approach has the potential to improve efficiency and utilization, particularly in the IoT environment, where wireless users are heterogeneous and the network state is dynamic.

However, the rapid growth in dimensionality and computational complexity of wireless networks poses significant challenges to network control. As a result, Deep Reinforcement Learning (DRL) has emerged as a potential approach to solve high-dimensional and continuous control issues effectively. By leveraging Deep Neural Networks (DNNs), DRL algorithms can learn from experience and make decisions in real-time, adapting to changing network conditions and optimizing performance.

In conclusion, the development of data transfer techniques, including wireless network virtualization, ML/AI integration, and the use of medical imaging, has played a crucial role in addressing the challenges posed by the COVID-19 pandemic. While network congestion remains a concern, wireless network virtualization offers a promising solution to reduce spectrum congestion and provide new network services. DRL has the potential to solve complex control issues in wireless networks, particularly in the IoT environment, by leveraging the power of Deep Neural Networks. As the networking industry continues to evolve, it will be interesting to see how these technologies and approaches shape the future of communication and connectivity.

Weight: 740g
Dimension: 234 x 156 (mm)
ISBN-13: 9781032426372