Intelligent Signal Processing and RF Energy Harvesting for State of art 5G and B5G Networks

Network monitoring systems play a crucial role in ensuring the efficient and secure operation of computer networks. With the rapid advancement of technology, network monitoring systems have also undergone significant developments in recent years. This paper presents a comprehensive review of the recent developments in network monitoring systems and highlights the associated challenges. We explore various aspects of network monitoring systems, including traffic analysis, anomaly detection, and security monitoring. Furthermore, we discuss emerging technologies such as machine learning, artificial intelligence, and blockchain that have been integrated into network monitoring systems. The challenges associated with scalability, real-time monitoring, and privacy preservation are also addressed. By examining the advancements and challenges in network monitoring systems, this paper aims to provide a comprehensive understanding of the current state of the field and identify future research directions.

On-body antenna design attracts a lot of attention of researchers from different sectors across the globe. In this connection, the healthcare professionals are keenly observing the evolution of biomedical systems from day one hoping that their apprehensions for the system gets resolved by the designers at the earliest. After the COVID-19 breakout, the body-centric communication (BCC) has gained attention of both the health care professionals and patients simultaneously. This paper is a step towards addressing the concerns of the health practitioners by providing the details of the evolution in the designs of on-body antennas and the recent advancements to the researchers working in the wireless body area network (WBAN) applications. Antennas have been categorized on the basis of antenna topology, operational bandwidth range, substrate material, reconfigurability etc. Metamaterial-based body worn antennas appear to be game changer in this domain as these structures ensure high gain, miniaturization and high radiation efficiency. An in-depth study is done for the specific absorption rate (SAR) for the wearable antennas. In addition to this, numerical modelling of the human body is also summarized.

This chapter presents a comprehensive report on the various categories of antenna modules needed for implementation of rectenna systems. It also discusses about the other key components of rectenna system like RF filter, matching circuits and rectifier networks. In recent days, rectenna occupied a prominent place because of the increased demand of power required for various applications. This chapter also addresses the key design issues of the rectenna like power conversion efficiency, output voltage levels, impedance matching techniques, simulation technologies and materials used for fabrication.

This chapter presents an extensive report on the different categories of antenna modules for the development of cognitive radio systems. It also discusses about the other key components of cognitive radio systems like RF filters, low noise amplifiers, analog to digital converters, reconfiguration mechanisms, digital signal processors, digital to analog converters, power amplifiers and band pass filters. Nowadays, RF spectrum is congested with many commercial bands. Hence, spectrum scarcity has been a major challenge to be addressed. The cognitive radio addresses this issue in an efficient manner. This chapter also presents materials used for fabrication and simulation technologies.

This chapter reports how to explore the techniques of energy saving which have already appeared since mobile communication era, like carrier/channel/symbol shutdown, etc., can be leveraged to moderate energy consumption in 5G. This chapter also improved deep sleep, symbol accumulation shutdown technologies, which had been introduced in 5G network. However, artificial intelligence and big data technique’s need to be introduced to form more accurate energy-saving strategy based on user traffic and other site-related conditions, which improves the efficiency as well as reduce the man power requirements. The mobile network traffic often experiences the troughs and peaks in terms of time distribution. The fundamental function employed to the whole mobile network is not the site-specific approach, which results to be less efficient because of the varied neighbouring site patterns and the traffic ignorance, particularly in the complex networks. Based on specific site traffic and other site-related condition, big data and AI technologies can be implemented to formulate more accurate strategy for energy saving in this scenario. The AI-driven network based on energy saving provides the solution which can help to forecast the load (traffic) of the base stations (BSs) centred on the conditions of the service type, user behaviour, historical traffic load on BS and the site coverage. AI technology can automatically configure the energy-saving strategy on the basis of coverage and configuration identification. Besides all this, the energy-saving solution centred on the AI-driven network can also certify the proper balance between the power consumption and the performance of the network based on appropriate training of the model.

Wireless communication technology is continually evolving to satisfy the expanding expectations of users. Existing wireless systems will see increased overhead as a result of this. This is reflected in the ongoing development of wireless networks to meet rising capacity demands. As the number of users grows, cellular bands become more congested; as a result, Extremely High Frequency (EHF) bands like mmWave are gaining popularity for use in cellular networks. In next-generation networks, millimeter-wave (mmWave) bands can handle multi-gigabit rates for high-bandwidth applications. These bands have some limits, such as the inability to travel great distances or penetrate buildings or other things. These limits can be used to enable more secure communication while also allowing for high-frequency reuse. This will make spectrum usage more efficient and help with the design of tightly packed systems. This paper reviews the basic concept of the 5G MMW microstrip antenna along with the spectrum defined by the Federal Communications Commission (FCC) for 5G. Also, the challenges and applications of the MMW are cited.

High-speed wireless communication has become an integral part of our present day to day life. From cellular mobile to satellite or WiMAX to Radio Astronomy, everywhere high-speed wireless data communication is in increasing demand, which was started by Maxwell, Hertz, and other eminent scientists. One of the basic advantages of wireless communication is the non-requirement of data transmission medium between transmitting antenna and receiving antenna. Since Marconi’s invention of radio devices, its emergence as broadcast radio to recent technology developments has made advanced antenna systems (ASS) a viable option for multi-user, multiple-input, multiple-output technology (MU-MIMO) deployments in 5G-NR wireless networks. In this chapter, authors have presented different types of antenna structures which are suitable for massive array applications (more than 8 channels), which have been investigated by the authors. Presently, microstrip-based antenna and antenna arrays are used widely, but due to their high fabrication cost and limitation of power handling capacity, investigations on dielectric antenna (travelling wave type) were carried out which provided ultra-wide band nature suitable for ASS in 5G Mobile Network in sub-6 GHz band.

The goal of a content-based image retrieval (CBIR) framework is to enable users to efficiently retrieve images from a large database based on the visual content of the images, rather than relying on metadata or annotations. CBIR systems are becoming more and more popular, finding their applications in a wide variety of fields like heath care, e-commerce, law enforcement, and searching digital libraries. Computing machines with CUDA architecture have powered deep learning-based techniques for efficient CBIR and, as such, CBIR systems have become fast with more accurate query results. This work is intended to provide an introduction to CBIR systems and different feature and learning-based techniques to perform CBIR. An overview of different datasets, evaluation metrics, and pros and cons of different CBIR techniques is presented. The paper concludes by discussing current research challenges and future opportunities to improve and apply CBIR to various fields.

Data has become one of the most valuable assets for organisations in all industries. Whether you work in IT, banking, e-commerce, retail, education, hotel management, or any other industry, data is critical to knowing how the organisation is operating, where improvements can be made, and how they can scale their operation. Data collection is the systematic process of acquiring and measuring information on variables of interest in order to answer specified research questions, test hypotheses, and evaluate outcomes. The fundamental reason for maintaining data integrity is to aid in the detection of flaws in the data gathering process, whether intentional (planned falsifications) or unintentional (systematic or random errors). This chapter gives a detailed summary of data collection, scrappers, crawlers, and APIs. It also gives a view of data pre-processing, data annotation, data evaluation, and also highlight its various challenges and issues.

Medical image segmentation plays a crucial role in the accurate diagnosis and treatment of various diseases, especially in the detection and diagnosis of brain tumors. Image segmentation is a critical task in MRI analysis, as it enables the identification and characterization of anatomical structures in the images. In recent years, numerous techniques have been proposed for brain tumor segmentation, ranging from traditional methods to deep learning-based approaches. With recent advancements, deep learning-based methods have shown promising results in brain tumor segmentation, with convolutional neural networks (CNNs) being the most commonly used approach in the medical image analysis community. In this paper, we provide a comprehensive study of deep learning-based segmentation of MRI images, covering the fundamental concepts, challenges, deep neural network architectures, and future directions.

Decentralized finance (DeFi) is a rapidly growing area of the blockchain and cryptocurrency space that enables the creation of financial applications and services on top of the decentralized infrastructure. This research paper explores the current state of DeFi, including its key features and benefits, as well as the challenges and risks associated with its implementation. The paper also examines various DeFi use cases, such as lending, borrowing, and trading, and analyzes the impact of DeFi on traditional financial institutions and the broader financial ecosystem. Additionally, the paper discusses the potential of DeFi to promote financial inclusion and democratize access to financial services. The paper includes a thorough review of existing literature on DeFi and its various applications, such as decentralized exchanges, lending and borrowing platforms, stablecoins, and more. Additionally, the paper discusses the risks and limitations associated with DeFi, including security concerns, lack of regulation, and scalability issues. Finally, the paper concludes by highlighting the future directions and opportunities for research in DeFi and its potential impact on the financial industry.