An AI-Assisted Smart Healthcare System Using 5G Communication

Technology’s fast growth has profoundly impacted myriad areas, including healthcare. Implementing 5G networks offering high-speed and low-latency communication capabilities is one of the most promising technical developments. Parallel to this, artificial intelligence (AI) has become a robust data analysis and decision-making tool. This paper examines how 5G and AI are combined in the context of intelligent healthcare systems. T5G green communication systems must overcome several challenges to satisfy the need for more user capacity, faster network speeds, cheaper pricing, and less resource use. By applying 5G standards, data rates, and device dependability for Industry 4.0 applications may be significantly increased. Advanced security and decreased unauthenticated assaults from various platforms are also covered in the paper. An outline of prospective new technologies and security improvements was provided to safeguard 5G-based intelligent healthcare networks. This paper identifies several research issues and potential future directions for secure 5G-based smart healthcare. This article discusses Industry 4.0, 5G standards, and new research in future wireless communications to explore current research concerns related to 5G technology. A brand-new architecture is also suggested in the paper for Industry 4.0 and 5G-enabled intelligent healthcare systems. Our method achieves an average improvement of 25% compared to existing techniques. Furthermore, we observe a 20% reduction in computational costs, making it a more efficient solution for real-world applications. These findings underscore the practical value of our research and pave the way for improved healthcare applications in 5G communication.


I. INTRODUCTION
The way we communicate, engage, and use technology is about to change because of the combination of Artificial Intelligence (AI) technology and the fifth-generation (5G) wireless networks.The power of super-fast, low-latency connectivity is combined with sophisticated algorithms and decision-making abilities when 5G and AI are used together.
The associate editor coordinating the review of this manuscript and approving it for publication was Bo Pu .This introduction will address this convergence's advantages, uses, and difficulties while exploring the possibilities of 5G using artificial intelligence.The huge amounts of data produced by AI applications require an infrastructure that can handle them, and 5G networks deliver previously unheardof speeds, capacity, and dependability.5G allows real-time communication and seamless connectivity thanks to its high data transfer rates and low latency.It provides the groundwork for a wide range of AI-powered services and applications.Several opportunities exist across numerous domains when AI is integrated with 5G networks.Healthcare is one industry where real-time AI analysis of massive amounts of medical data enables telemedicine, individualized healthcare, and remote patient monitoring.In the transportation industry, AI algorithms with 5G connectivity can improve the security and effectiveness of autonomous cars by allowing object detection, real-time decision-making, and vehicle-to-vehicle communication.Through intelligent systems and real-time data analysis, smart cities can use 5G and AI to optimize traffic management, increase energy efficiency, and improve urban planning.Predictive maintenance, robotics, and real-time monitoring are three ways industries can use AI-driven 5G networks to boost efficiency, productivity, and safety.Using AI and 5G together is crucial for public safety and emergency response.AI systems may analyze video feeds, spot anomalies, and provide real-time situational awareness to enable quicker and more efficient response times.A more secure and effective user experience can be delivered by AI-powered 5G networks, which can also improve financial services by enabling fraud detection, individualized suggestions, and quick financial transactions.However, there are several difficulties with the combination of AI with 5G.Due to the vast volume of data being produced and analyzed, privacy and security issues about data are raised.Gaining confidence and comprehending AI system decisions require algorithm openness and explainability.Additionally, a significant amount of processing power, infrastructure investment, and legal considerations are needed to deploy and administer AI models in 5G networks.Combining artificial intelligence (AI) and fifthgeneration (5G) networks opens up a wide range of creative applications in many industries.In this part, we give a table detailing the various 5G AI applications, emphasizing their benefits.The first is Smart Healthcare, where AI-powered 5G networks enable telemedicine, real-time analysis of medical data, and remote patient monitoring, leading to better diagnosis and individualized healthcare.Another use for AI algorithms in 5G networks is autonomous vehicles, where they improve real-time decision-making, object detection, and vehicle-to-vehicle communication for safer and more effective autonomous driving.For sustainable and habitable cities, the 5G and AI combination offers intelligent traffic control, energy optimization, environmental monitoring, and effective urban planning.Industrial Automation uses AI-enabled 5G networks to enable robotics, real-time monitoring, and predictive maintenance, increasing industrial processes' effectiveness, productivity, and safety.Through enhanced video analytics, facial recognition, and real-time situational awareness made possible by AI algorithms in 5G networks, public safety, and emergency response are improved.5G networks powered by AI are advantageous for smart grids because they improve power distribution monitoring, control, and optimization, resulting in effective energy management and grid stability.5G networks and AI enable high-bandwidth, low-latency connections for immersive gaming, remote collaboration, and virtual training, enhancing augmented and virtual reality experiences.Precision agriculture increases crop yields, resource efficiency, and sustainability by utilizing AI-powered 5G networks for real-time monitoring, agricultural data processing, and autonomous machinery.By enabling fraud detection, individualized suggestions, risk assessment, and quick financial transactions, AI algorithms in 5G networks assist the financial services industry and improve consumer experiences.To meet the enormous connectivity and management needs of Internet of Things (IoT) devices, connectivity, and management employ AI-driven 5G networks, ensuring effective data processing and wise decision-making.We emphasize the various fields where these technologies intersect to produce game-changing solutions by organizing the applications of 5G employing AI in table format.We will examine each application in depth in the following parts, going through its advantages, practical considerations, and future research objectives.Through this investigation, we hope to demonstrate the enormous potential of 5G and AI integration for fostering innovation and progress in various industries.
• Smart Healthcare AI-powered 5G networks enable remote patient monitoring, telemedicine, and real-time medical data analysis for improved diagnosis and personalized healthcare.
• Autonomous Vehicles AI algorithms in 5G networks enhance real-time decision-making, object recognition, and vehicle communication, leading to safer and more efficient autonomous driving.
• Smart Cities 5G with AI enables intelligent traffic management, energy optimization, environmental monitoring, and efficient urban planning for sustainable and livable cities.
• Industrial Automation AI-powered 5G networks facilitate predictive maintenance, robotics, and real-time monitoring, enhancing industrial efficiency, productivity, and safety.
• Enhanced Public Safety AI algorithms in 5G networks enable advanced video analytics, facial recognition, and real-time situational awareness, improving public safety and emergency response.
• Smart Grids AI-driven 5G networks enhance the monitoring, control, and optimization of power distribution, enabling efficient energy management and grid stability.
• Augmented and Virtual Reality 5G networks combined with AI enable high-bandwidth, low-latency connections for immersive experiences, gaming, remote collaboration, and virtual training.
• Precision Agriculture AI-powered 5G networks enable real-time monitoring, analysis of agricultural data, and autonomous machinery, enhancing crop yields, resource utilization, and sustainability.
• Financial Services AI algorithms in 5G networks enable fraud detection, personalized recommendations, risk assessment, and efficient financial transactions for enhanced customer experiences.• Internet of Things (IoT) Connectivity and Management AI-driven 5G networks handle the massive connectivity and management requirements of IoT devices, ensuring efficient data processing and intelligent decision-making.
One of the cornerstones of 5G's success is beamforming, a sophisticated transmission technique that tailors the direction of wireless signals with unprecedented precision.Unlike traditional omnidirectional broadcasting, where signals spread indiscriminately in all directions, beamforming empowers 5G networks to concentrate energy in specific directions.This is achieved through the manipulation of signal phase and amplitude from multiple antennas, resulting in stronger and more reliable connections, reduced interference, and enhanced spectral efficiency.
While beamforming is a standout feature of 5G's physical layer, it is complemented by a constellation of auxiliary technologies that collectively amplify the network's capabilities.Multiple-Input Multiple-Output (MIMO) configurations enable the use of multiple antennas for simultaneous transmission and reception, boosting data rates and signal reliability.Massive MIMO, an extension of MIMO, leverages an abundance of antennas to serve numerous users concurrently, fostering efficient resource allocation.Non-Orthogonal Multiple Access (NOMA) optimizes spectrum utilization by allowing multiple users to share the same time and frequency resources, enabling better connectivity in crowded environments.Full-duplex communication empowers devices to transmit and receive data simultaneously, increasing efficiency and reducing latency.
These tables comprehensively overview the key aspects of integrating 5G Industry norms and artificial Intelligence (AI) in an IoT system.They cover connectivity, edge computing, data analytics, decision-making, security, privacy, resource optimization, and industry-specific applications.The state-ofthe-art in the areas of artificial intelligence (AI), industry 4.0, and 5G will be covered in this paper [5].theintegration of 5G and AI in healthcare also poses challenges and considerations.The security and privacy of patient data become crucial concerns as the volume and sensitivity of medical information being transmitted and analyzed increase.Robust security measures and compliance with data protection regulations are essential to ensure the confidentiality and integrity of patient data.Furthermore, ethical considerations surrounding AI algorithms and decision-making processes must be addressed to ensure healthcare practices' transparency, fairness, and accountability.In summary, the convergence of 5G industry norms and artificial intelligence presents a paradigm shift in healthcare.The high-speed and low-latency capabilities of 5G networks, coupled with the analytical power of AI algorithms, enable the development of smart healthcare systems that can significantly improve patient care, enhance clinical decisionmaking, and drive preventive healthcare strategies.However, careful attention must be given to security, privacy, and ethical considerations to ensure these technologies' responsible and beneficial implementation in healthcare settings.
The convergence of 5G, Massive MIMO (Multiple-Input Multiple-Output), and artificial Intelligence (AI) has the potential to revolutionize the performance and capabilities of the Internet of Things (IoT).As IoT expands and connects an ever-growing number of devices, the need for advanced technologies to address its challenges becomes crucial.This detailed analysis explores how the combination of 5G, Massive MIMO, and AI can work together synergistically to enhance IoT performance.5G, the next generation of wireless communication technology, introduces a range of capabilities that are specifically designed to meet the requirements of IoT applications.With its high-speed, low-latency, and high device density support, 5G provides the foundation for seamless connectivity and efficient data transfer among IoT devices.Moreover, Massive MIMO, a key technology in 5G networks, leverages many antennas to improve spectral efficiency and increase network capacity.This enables simultaneous communication with numerous IoT devices, enhancing overall network performance.In parallel, Artificial Intelligence plays a pivotal role in optimizing IoT performance.AI algorithms can process massive amounts of data from IoT devices and extract valuable insights, patterns, and trends.This enables data-driven decisionmaking, predictive analytics, and real-time optimizations for various IoT applications.AI also contributes to IoT security by identifying anomalies, analyzing behaviors, and predicting potential threats, thereby enhancing IoT ecosystems' overall resilience and robustness.IoT performance can be significantly enhanced by combining the strengths of 5G, Massive MIMO, and AI.The increased bandwidth, reduced latency, and improved network capacity of 5G networks enable seamless connectivity and efficient data transmission.Massive MIMO complements 5G by optimizing spectral efficiency and accommodating the massive number of connected IoT devices.Meanwhile, AI-driven data analytics and intelligent network management enhance IoT performance by extracting insights, optimizing resources, and ensuring secure and reliable operation.
Section I presents the enormous potential of 5G and AI integration for fostering innovation and progress in various industries.Section II presents the related work on Enabling technologies connected with 5G in IoT applications.Section III examines the methodology with experimental result.Section IV presents the simulation result of different network configuration parameters and 5G Multi-tier network configurations.Section V discusses the research gap, and next section presents the conclusion of the paper.

A. CONTRIBUTION OF RESEARCH WORK
Our research study makes the following significant contributions: • The main focus is to provide a general understanding of the recent research and help newcomers to understand the essential modules and trends.
• The Paper presents a 5G-based smart healthcare architecture with advanced MIMO.
• Discuss advanced security and reduced unauthenticated attacks from different platforms.
• An overview of existing security issues' fixes and potential new technologies and fixes for the security of 5G-based smart healthcare networks were presented.
• Finally, the paper highlights a number of research concerns as well as possible future research areas for 5G-based smart healthcare security.

B. INTRODUCTION TO IoT AND ITS CHALLENGES
Introduction to IoT and its Challenges Provide an overview of the Internet of Things (IoT) and its challenges in terms of connectivity, scalability, and data processing.The paper discuss the need for advanced technologies like 5G, Massive MIMO, and AI to address these challenges and unlock the full potential of IoT.

C. UNDERSTANDING 5G TECHNOLOGY
Explain the key features and capabilities of 5G technology, such as high data rates, ultra-low latency, and massive device connectivity.The paper discuss how 5G networks are designed to support the requirements of IoT applications and enable seamless communication between IoT devices.

D. EXPLORING MASSIVE MIMO
Describe the concept of Massive Multiple-Input Multiple-Output (MIMO) technology and its role in 5G networks.The paper discuss how Massive MIMO utilizes a large number of antennas to improve spectral efficiency, increase capacity, and enhance overall network performance, thereby benefiting IoT applications.

E. LEVERAGING 5G FOR ENHANCED IOT CONNECTIVITY
Analyze how 5G networks provide enhanced connectivity for IoT devices.The paper discuss the use of 5G's increased bandwidth and reduced latency to support a massive number of connected devices, enable real-time communication, and facilitate seamless data transfer in IoT ecosystems.

F. AI-DRIVEN IoT DATA ANALYTICS
Explain how Artificial Intelligence (AI) techniques can be applied to IoT data analytics.The paper discuss the use of AI algorithms for real-time data processing, pattern recognition, and predictive analytics, enabling actionable insights and improved decision-making for IoT applications.

G. AI-ENABLED NETWORK MANAGEMENT
Explore the role of AI in managing and optimizing IoT networks.The paper discuss how AI algorithms can be used for intelligent resource allocation, dynamic network optimization, and predictive maintenance, resulting in improved network performance and efficient utilization of IoT resources.

H. ENHANCING IOT SECURITY WITH AI AND 5G
Address the critical aspect of IoT security and the role of AI and 5G in enhancing it.The paper discuss how AI can be leveraged for anomaly detection, behavior analysis, and threat prediction to identify and mitigate security risks in IoT networks.Explain how 5G's advanced security features can complement AI-driven security measures for robust IoT security.

I. EDGE COMPUTING AND 5G-ENABLED AI
The paper discuss the synergy between edge computing, 5G, and AI in enhancing IoT performance.Explain how edge computing, empowered by 5G connectivity and AI capabilities, enables real-time data processing at the network edge, reducing latency, enhancing reliability, and supporting time-sensitive IoT applications.

II. RELATED WORK
The paper [29] presents the application of Artificial Intelligence (AI) has changed H-IoT systems at nearly every level.The fog/edge concept brings processing power closer to the deployed network, hence minimising several issues.While big data provides for the management of massive amounts of data.Furthermore, Software Defined Networks (SDNs) add flexibility to the system, while blockchains discover the most unique use cases in H-IoT systems.The Internet of Nano Things (IoNT) and Tactile Internet (TI) are driving H-IoT application innovation.This article investigates how these technologies are reshaping H-IoT systems, as well as the future path for increasing Quality of Service (QoS) using these new technologies.
The study presented [12] a smart-healthcare system based on Edge-Cognitive-Computing (ECC).Using cognitive computing, this system can monitor and analyse individuals' physical health.It also modifies the computing resource allocation of the whole edge computing network holistically based on each user's health-risk grade.The trials reveal that the ECC-based healthcare system gives a better user experience and adequately optimises computer resources, while also dramatically boosting patient survival rates in a sudden emergency.
This article [23] discusses people's contributions to IOT in the healthcare sector, as well as the application and future problems of IOT in terms of medical services in healthcare.We expect that our research will be valuable to scholars and practitioners in the field, assisting them in understanding the enormous potential of IoT in the medical sector and identifying important problems in IOMT.This approach will also aid scholars in their understanding of IOT applications in the healthcare arena.This work will assist scholars in comprehending the historical contribution of IOT in the healthcare business.
The proposed [10] outcome of the paper is to build a system to provide world-class medical aid to patients even in the most remote areas where there are no hospitals by connecting over the internet and gaining information about their health status via the wearable devices provided in the kit that use a raspberry pi microcontroller to record the patient's heart rate and blood pressure.In the event of a medical emergency, the system should notify the patient's family members and doctor of the patient's current health state and complete medical information.Using data mining, the obtained information may be utilised to analyse and forecast chronic ailments or other diseases such as heart attacks in the early stages.
The proposed architecture [18] incorporates the following core technologies: a 5G-IPv6 communication network, a context-aware health situation identification-based similarity measure, and a secure data exchange mechanism based on blockchain.Finally, a prototype system for monitoring hypertensive heart disease has been built, showing its usefulness in a real-world setting.When combined with the data of 45 patients, the prototype system can identify health problems with 96.34% accuracy, 92.46% sensitivity, and 93.62% specificity, while considerably lowering latency and enhancing data sharing security.
In this research, the paper presents [1] a clustering technique based on game theory (i.e., mixed strategy) to pick optimum cluster heads (CHs) and transmit data from a cluster head (CH) to a base station (BS).The simulation reveal that our suggested method outperforms the LEACH protocol in terms of network lifespan and energy usage.We utilised the MATLAB environment to simulate our suggested system and compare it to the LEACH technique.
Utilizing computer-based intelligence tactics has gained the attention of many experts in the last ten years due to their variety of benefits.Future communications will benefit in a few ways from the use of artificial intelligence in 5G and, by extension, IoT.Based on an understanding of the key advances in 5G, [19] has reviewed several interesting research topics in simulated intelligence for 5G developments.In addition, they focused on establishing plan standards for the improvement of the 5G network [15], optimum resource designation, speed increases for the 5G actual layer brought together, joint enhancement of the start and finish of the actual layer, etc.The resource management solutions for 5G and IoT networks based on machine learning and deep learning have been reviewed in-depth and from top to bottom by [19] and [21].Reference [3] examined how IoT-produced data is managed for machine learning research and highlighted the existing challenges in helping wise decisions in the IoT environment.IoT apps can take advantage of other IoT applications in an adaptive way according to the proposed framework.
To manage the IoT gateway bottleneck and improve control performance, [31] presented a two-level control system with primary and secondary levels.The control delay of significant nodes could be decreased by the authors by 30.56%.For SDN-based cloud IoT networks,suggested architecture for an intelligent intrusion detection system achieves a potential improvement in anomaly detection and handling bottleneck problem.Although latency was not taken into account as a performance metric, the authors were able to reduce the load imbalance between SDN controllers.In their suggested energy-efficient SDN controller architecture, [37] achieved high throughput, low energy consumption, and low delay in an IoT environment.
In order to improve the security and energy optimisation of IoT devices, [24] presented an architecture for IoT networks that combines BC technology with SDN controller.62Although the authors were able to achieve high security, low latency, and low energy usage, the SDN controller becomes overworked trying to stop selfish nodes.
To reduce network latency and boost reliability, [34] suggested an action and reward-based algorithm for SDNassisted wireless power distribution in the IoT environment.In order to tackle COVID-19 utilising a drone application and established an edge intelligence architecture with 6G-enabled services.Although the architecture was well suited for 6G features, communication overhead remained a concern.An SDN-based IoT architecture was presented by [4] to address COVID-19 scenarios.Throughput, reaction time, and packet failure rate were used as the basis for the result analysis; latency was not taken into account.The authors used the 5G network for highly mobile UAV equipment to accomplish security, trust, and effective network connectivity, but energy efficiency remained a problem.In a heterogeneous IoT context, prediction-based strategy to manage the load on the SDN control plane and distribute traffic efficiently.
The paper [17] presented strong zero-watermarking technique based on federated learning to address the teledermatology healthcare framework's privacy and security concerns.Federated learning is used to train the sparse autoencoder network in this technique.To extract image characteristics from a dermatological medical picture, a trained sparse autoencoder network is used.Two-dimensional Discrete Cosine Transform (2D-DCT) is applied to image characteristics in order to determine low-frequency transform coefficients for zero-watermarking.When compared to alternative zero-watermarking systems, experimental findings reveal that the suggested scheme is more resilient to conventional and geometric attacks and provides greater performance.
The paper [6] presented the Software Defined Networking (SDN) technology, which is used to realise mobility management for NDN, is one of the plausible options.The separation of the network control plane and the data plane is important to SDN.The data plane is responsible for data transmission, whereas the control plane is in charge of network control.The network control plane and data plane are detached, resulting in a more programmable environment and the opportunity for external applications to determine network behaviour.The key characteristics of the SDN, such as programmability, flexibility, and centralised control, make it a simple and scalable network.To address the issue of NDN mobility, we suggest the development of a software-defined mobility architecture for NDN, in which the SDN plays a role.
The paper [13] proposed a complete assessment of the Metaverse for healthcare, focusing on the current state of the art, the enabling technologies for implementing the Metaverse for healthcare, prospective applications, and associated initiatives.The problems in adapting the Metaverse for healthcare applications are also noted, and some solutions are presented as future research paths.
The paper [30] described The federated learning-based system collects model updates from two clients and trains the Deep Neural Network (DNN) model on the dataset separately.Each customer checks the findings three times to reduce the over-fitting issue.Experiments demonstrate that the DNN model has an accuracy of 80.09%, indicating that the proposed framework has the capability of detecting sidechannel assaults.
The paper [33] presented the Modular Encryption Standard (MES) and layered modelling of security mechanisms.The performance study demonstrates that the suggested work outperforms other frequently used algorithms for health information security in the MCC environment in terms of higher performance and supplementary qualitative security assuring features.
The paper [22] describes a generalised collaborative framework called the collaborative shared healthcare plan (CSHCP) for assessing people's cognitive health and fitness utilising ambient intelligence applications and machine learning techniques.CSHCP supports daily physical activity recognition, monitoring, and evaluation, as well as the development of a shared healthcare plan through cooperation among many stakeholders, including doctors, patient guardians, and close community circles.
Future Portability Management (MM) arrangements in the cell network will be examined in a new study by [11].The suggested method includes reducing delays during handoff and testing versatile management in both low-speed and highspeed scenarios in order to reduce delays and enhance QoS performance.
Lean radio resource management engineering has been provided by [32] that combines cutting-edge advances in machine learning with a lot of data that is already present in the network from estimates and framework perceptions.
In [2] handle the network aspects with a smaller scope, such as erroneous expectations and unexpected network conditions.For the purpose of assisting RAN in making resource planning decisions, RSS can expertly switch the weighting of the expectation and online choice modules depending on the amount of authentic traffic data that is readily available.By taking into account the emerging 5G models and administration kinds (eMBB, mMTC, URLLC), has provided a brief overview of the patterns in versatile management.The author focused on the advancements in portability management that were made in fagging as a result of unique design elements, taking into account the requirements of various vertical use cases that would lead to the required throughput, inactivity, and adaptability.
In order to investigate their complexities for 5G correspondences, [31] have provided updated estimates for bunching towers dependent on location and for pressing base band unit groups based on the projection of adaptability and traffic designs.
In-depth research on the most recent cutting-edge resource management ideas for this engineering has been published by [8].Radio resource management (RRM) and computational resource management (CRM) strategies were used to categorise the resource management techniques.Then, based on the investigative methodologies used, both of the operations were additionally categorised and assessed.
Reference [39] have presented a review investigation of various advancement strategies that were being looked at for addressing resource challenges in 5G and IoT.The classes discussed these arrangements and their advantages and disadvantages while looking at fresh and exciting exploration directions.One of the areas under consideration specifically noted how range accessibility had a tendency to.
A summary of the justifications for combining massive MIMO, NOMA, and interleave division multiple entrances (IDMA) in a connected system has been provided by [40].The authors emphasize multiple client acquisition, which alludes to the benefits of allowing multiple user transmission in massive MIMO.Such addition can result in rate increases on tens or even several occasions.The existing designs' reliance on exact channel state data (CSI) presents the main challenge in achieving multi-client acquisition.
According to [9], huge MIMO has advantages in terms of limit and energy effectiveness.Regarding phantom efficiency and energy productivity, execution evaluations of large MIMO were provided.The significant challenges for the practical implementation of massive MIMO were discussed in detail.
By taking into account the emerging 5G models and administration kinds (eMBB, mMTC, URLLC), [25] have provided a brief overview of the patterns in versatile management.The author focused on the advancements in portability management that were made in fagging as a result of unique design elements, taking into account the requirements of various vertical use cases that would lead to the required throughput, inactivity, and adaptability.In order to investigate their complexities for 5G correspondences, [31] have offered new estimates for pressing baseband unit groups based on the forecast of versatility and traffic designs and for bunching towers reliant on the place.
In-depth research on the most recent cutting-edge resource management ideas for this engineering has been published by [8].Radio resource management (RRM) and computational resource management (CRM) strategies were used to categorize the resource management techniques.Then, based on the investigative methodologies used, both of the operations were additionally categorized and assessed.Form the above survey, it is evident that Quality of Service (QoS) and latency requirements for IoT devices can vary significantly based on the specific industry or sector they are deployed in.Different industries have distinct use cases, operational needs, and regulatory considerations that impact their QoS and latency requirements.Brief details of the different sectors for the IOT needs are depicted in Table 7.

III. METHODOLOGY AND RESULT ANALYSIS
It starts with identifying the needs and requirements, followed by system design, data collection, processing, communication, integration, testing, deployment, evaluation, and continuous improvement.Following this methodology can help ensure a systematic and effective integration process, leading to a successful implementation of the smart health care system utilizing 5G and AI technologies.
IoT systems with WSN support are useful for many different things.Each SHS application shares a necessity for energy efficiency, or the on-field sensor nodes' decreased energy consumption.In addition, SHS applications must meet critical standards for communication latency, security, and QoS performance.The suggested design for a smart healthcare system, represented in Figure 2, includes many levels of Industry 4.0 (IoT) standards, including edge, fog, and storage layers.The amount of nodes that periodically gather patient data from various body sensors make up the edge layer.Patients who have body sensors installed are identified by the red nodes.The fog nodes at the fog layer received the medical data wirelessly provided from the edge layer.The edge devices send the locally gathered data to the fog node.Routers, access points, gateways, and base stations may all function as fog nodes.Data from the fog nodes is finally received by the storage layer for storage and analysis.Many programmes access, analyse, and make decisions using cloud storage services.
Since the 5G standard is necessary for network communications, we develop the 5G communication lines using the parameters listed below for performance evaluation and simulation.This paper's goal is to analyse the performance of current 5G resource management methods for networks that support the Internet of Things.We've used techniques like the Multi-Traffic Internet of Things [8].The approaches are used in accordance with the methodology described.In macrocells, parameters of Base Station (bs) operating power are configured as: A macro = 28.76 and B macro = 396.67W,respectively.In small cells, parameters of bs operating power are confgured as A macro = 8.98 and B macro = 84.80W, respectively.The lifetime of Macro BS (mbs) Tmacro lifetime and Small BS (sbs).Tsmall lifetime are assumed as 12 and 7 years, respectively.Other parameters are listed in Table 9.

IV. SIMULATION RESULT
Simulation outcomes By creating networks of various tiny cells in accordance with the other simulation parameters listed in Table 8, we put the techniques into practise in NS2.
108346 VOLUME 11, 2023 Authorized licensed use limited to the terms of the applicable license agreement with IEEE.Restrictions apply.

A. AVERAGE DELAY
The average delay in a 5G Industry norms Artificial Intelligence (AI) enabled smart health care system refers to the average time it takes for data packets to travel from the source to the destination.This delay can vary depending on various factors such as network congestion, data processing time, and the distance between the source and destination.The average delay can be calculated by collecting data on packet transmission times and then calculating the average over a certain period or across multiple test scenarios.This value provides insights into the overall efficiency and responsiveness of the smart health care system, with lower values indicating faster data transmission and reduced latency, which are desirable for real-time health care applications.It is important to note that the specific average delay values will vary depending on the system design, network conditions, and the workload placed on the system.Thus, conducting performance evaluations and simulations specific to the targeted smart health care system is necessary to obtain accurate and relevant average delay measurements.
Typical delay This statistic figures out how long it typically takes for a packet to travel from its origin at all sources to its destination nodes.It's calculated as: where N is number of total transmission links, d t is transmission delay of i th link, d p is propagation delay of i th link, d c is processing delay of i th link, and d q is transmission delay of i th link.

B. AVERAGE ENERGY CONSUMPTION
To determine the specific average energy consumption in a smart health care system, a comprehensive assessment or measurement of energy usage needs to be conducted.This can involve monitoring power consumption of individual components, such as IoT devices and network infrastructure, as well as estimating the energy consumption associated with AI algorithms and data processing.
The energy consumption can be quantified in terms of power consumption (in watts) or energy consumption (in joules) over a defined period.By collecting data on energy usage from different components of the system and calculating the average energy consumption, insights can be gained regarding the overall energy efficiency of the smart health care system.
It computes the average energy consumption by entire network after the end of simulation by measuring the remaining consumed energy of all nodes.The total energy consumed E tot is computed as: where E initia and E consumed are initial and consumed energy of ith node, respectively.N is total number of nodes in network.
The average consumed energy is computed as:

C. PACKET DELIVERY RATIO (PDR)
It is important to note that the specific packet delivery ratio values will depend on factors such as network conditions, data volume, system configuration, and the efficiency of the communication infrastructure and AI algorithms employed.Therefore, conducting performance evaluations and simulations specific to the targeted smart health care system is necessary to obtain accurate and relevant packet delivery ratio measurements.The percentage of packets transmitted by the various sources of the various traffic patterns and received by the destinations is calculated.
where, P r is number of received packets and P g number of generated packets.

D. AVERAGE THROUGHPUT
A higher average throughput indicates a system that can handle a larger volume of data and transmit it more efficiently.
In the context of a smart health care system, a higher average throughput is desirable as it allows for timely and reliable communication of health-related data, such as patient records, imaging data, or real-time monitoring information.The total number of packets sent per second-or the total number of messages delivered per second-is calculated using this statistic.In Kbps, the typical throughput is: where R is complete received packets at all destination nodes, T 2 is simulation stop time and T 1 simulation start time.The table below shows the result of average throughput, average communication latency, average energy consumption, and average PDR.
In an era of unprecedented technological advancement, the convergence of cutting-edge technologies is reshaping industries across the spectrum, and healthcare is no exception.The intersection of 5G network standards and artificial intelligence (AI) has given rise to a new paradigm in healthcare: the Smart Healthcare System.This transformative synergy holds the promise of revolutionizing medical services, patient care, and healthcare management in ways previously thought unimaginable.The marriage of 5G network norms and AI capabilities to create smart healthcare systems represents a monumental step forward for the healthcare industry.By fostering real-time connectivity, data-driven insights, and personalized care, this fusion addresses critical healthcare challenges and sets the stage for a future where timely and efficient healthcare is accessible to all.As 5G networks continue to expand and AI technologies mature, the synergy between the two has the potential to reshape the healthcare landscape, ultimately leading to better patient outcomes and improved quality of life.The integration of AI and 5G in smart health care systems also enhances the efficiency and effectiveness of resource management.AI algorithms can optimize the allocation and utilization of network resources, such as bandwidth and computing power, based on real-time demands and priorities.This ensures that critical health data is prioritized, network congestion is minimized, and resources are utilized in the most efficient manner.Moreover, AIdriven energy optimization techniques can help reduce energy consumption in IoT devices and networks, prolonging battery life and promoting sustainability.
However, adopting 5G Industry norms and AI in the smart healthcare system also brings challenges and considerations.Data privacy, security, interoperability, and ethical use of AI must be carefully addressed to maintain patient confidentiality and build trust in these advanced healthcare systems.Furthermore, collaborations between healthcare providers, technology vendors, and regulatory bodies are essential to establish standardized protocols, ensure interoperability among devices and systems, and overcome potential barriers to the widespread implementation of 5G and AI in healthcare.
The integration of AI and 5G in healthcare promises remarkable benefits, it also raises critical considerations, such as data privacy, security, and the need for robust infrastructure.Addressing these challenges is paramount to ensure the responsible and ethical implementation of Smart Healthcare Systems.By harnessing the potential of AI and 5G, healthcare stakeholders can embark on a journey towards a future where patient care is more personalized, accessible, and efficient than ever before.
Fig. 4 and Fig. 5 shows the different 5G network in Helathcare system.Those are CDF and sub-6GHz 5G networks.The Cumulative Distribution Function (CDF) can be used to analyze the throughput performance in a 5G network.Throughput refers to the rate at which data can be transmitted over a network and is typically measured in bits per second (bps) or megabits per second (Mbps).To analyze the throughput using CDF, you would gather data on the achieved throughput values for a set of users or locations within the 5G network.Then, you can calculate the CDF to understand the distribution of throughput values and the probability of achieving certain throughput levels.In the context of sub-6GHz 5G networks, sub-6GHz refers to the frequency range below 6 gigahertz (GHz) in which 5G networks can operate.These lower-frequency bands are known for their wider coverage and better penetration through obstacles compared to higher-frequency bands.Sub-6GHz signals can propagate over longer distances and provide wider coverage compared to higher-frequency bands.This makes them suitable for providing connectivity in suburban and rural areas.CDF stands for Cumulative Distribution Function.It is a mathematical function commonly used in probability theory and statistics to describe the distribution of a random variable.The CDF gives the probability that a random variable is less than or equal to a certain value.
Fig. 6 and 7 define the Edge Server 10MB and Edge Server 100MB.These configurations refer to the processing capacity or throughput capabilities of the edge servers.However, it is important to note that specific configurations and measurements can vary depending on the network architecture and deployment strategy.itis challenging to provide specific density measurements for Edge Server 10 and Edge Server 100MB in 5G networks.The density of edge servers can vary significantly depending on the specific network requirements, deployment strategies, and the characteristics of the target area In a detailed analysis of how 5G, Massive MIMO, and AI work together to enhance IoT performance, mathematical formulas can be used to model and quantify the effects of these technologies on various performance metrics.Here are some examples of mathematical formulas that can be employed in such an analysis: Channel Capacity Calculation: The channel capacity (C) of a wireless communication system can be determined using the Shannon Capacity formula: where: C is the channel capacity in bits per second (bps) B is the bandwidth available for communication in hertz (Hz) SINR is the Signal-to-Interference-plus-Noise Ratio, representing the ratio of the desired signal power to the combined interference  and noise power.This formula can be used to analyze how the implementation of Massive MIMO and advanced 5G features impact the achievable channel capacity in an IoT network.
The paper explores the multifaceted ways in which AI-powered Smart Healthcare Systems, bolstered by the high-performance features of 5G networks, are poised to reshape healthcare delivery.We will delve into the key advantages and potential applications of this transformative synergy, including faster and more reliable data transfer, remote patient monitoring, telemedicine and virtual consultations, AI-driven diagnostics, predictive analytics, surgical assistance, efficient resource management, and improved emergency response.Latency Analysis: The latency (L) of an IoT system, including the communication delay and 108350 VOLUME 11, 2023 Authorized licensed use limited to the terms of the applicable license agreement with IEEE.Restrictions apply.processing time, can be estimated using the following formula: L = T trans + T prop + T proc (7) where: T trans is the transmission time, calculated as the ratio of the data size (D) to the data transmission rate (R): T prop is the propagation time, which is the time taken for the signal to travel from the source to the destination T proc is the processing time, representing the time required for data processing at the source and destination nodes.This formula can be utilized to assess how the integration of AI algorithms and optimizations in 5G and Massive MIMO systems affects the overall latency of IoT communications.Energy Efficiency Evaluation: The energy efficiency (EE) of an IoT system can be quantified using the following formula: EE = Data throughput /Power consumption (9) where: Data throughput (Data throughput ) represents the amount of data transmitted or processed per unit time Power consumption (Power consumption ) denotes the energy consumed by the system during the same time period.This formula can be utilized to evaluate how the integration of AI techniques, 5G network enhancements, and Massive MIMO technology impacts the energy efficiency of IoT devices and networks.These are just a few examples of mathematical formulas that can be employed in the detailed analysis of how 5G, Massive MIMO, and AI work together to enhance IoT performance.The specific formulas used will depend on the performance metrics under consideration and the objectives of the analysis.
Smart Healthcare Systems leverage the capabilities of AI to analyze vast amounts of medical data, facilitate real-time communication, and enable seamless integration of various healthcare processes.With the advent of 5G communication, the possibilities for healthcare optimization have expanded exponentially, offering high-speed data transfer, low latency, and the ability to connect a multitude of devices and systems with unparalleled reliability.In conclusion, the integration of 5G Industry norms and Artificial Intelligence in the smart health care system holds immense potential for transforming healthcare delivery.The combination of high-speed connectivity, real-time data analysis, and intelligent decision-making enables improved patient care, enhanced remote monitoring, personalized medicine, and optimized resource utilization.However, careful consideration must be given to ethical, privacy, and security aspects to ensure the responsible and effective implementation of these technologies.With proper planning, collaboration, and innovation, 5G Industry norms and AI have the power to revolutionize healthcare and provide a new era of connected and intelligent health care systems.

V. RESEARCH GAPS DISCUSSION
Analysis of research gaps in 5G standards for IoT applications involves identifying areas where further research is needed to address challenges and limitations.Here are some key research gaps in this domain:

A. INTEROPERABILITY AND STANDARDIZATION
There is a need for standardized protocols and interfaces to ensure seamless interoperability between IoT devices and 5G networks.Research is required to develop and optimize protocols that facilitate the integration of diverse IoT devices, platforms, and technologies with 5G networks, enabling efficient communication and data exchange.

B. SCALABILITY AND NETWORK CAPACITY
As the number of IoT devices connected to 5G networks continues to grow exponentially, research is needed to address scalability challenges.This includes investigating techniques for efficient device management, network resource allocation, and traffic management to accommodate the increasing IoT device density and data traffic demands.

C. ENERGY EFFICIENCY
IoT devices often operate on limited power sources and require energy-efficient solutions to prolong battery life.
108352 VOLUME 11, 2023 Authorized licensed use limited to the terms of the applicable license agreement with IEEE.Restrictions apply.
Research gaps exist in developing energy-efficient communication protocols, power management techniques, and resource optimization strategies for IoT devices operating within the 5G network environment.When evaluating the quantitative performance metrics of energy efficiency, several metrics can be considered.
• Energy Consumption: Measure the total energy consumed by the 5G network infrastructure, including base stations, core network components, and data centers.This metric can be expressed in kilowatt-hours (kWh) or joules (J).
• Energy Efficiency Ratio: Calculate the energy efficiency ratio, which is the ratio of the data transmitted/received to the energy consumed.It can be expressed in bits per joule (bps/J) or megabits per watt (Mbps/W).A higher energy efficiency ratio indicates a more efficient use of energy for data transmission.
• Traffic Energy Efficiency: Assess energy efficiency based on the amount of energy consumed per unit of data traffic handled by the network.It is calculated by dividing the total energy consumed by the network over a given period by the total amount of data traffic transmitted/received during that period.

D. SECURITY AND PRIVACY
Security is a critical concern in IoT applications, and the integration of 5G introduces additional security challenges.
Research is needed to develop robust security mechanisms and privacy-preserving techniques that protect IoT devices, networks, and sensitive data from emerging threats such as unauthorized access, data breaches, and malicious attacks.

E. QUALITY OF SERVICE (QoS) AND LATENCY
Different IoT applications have varying QoS requirements, and meeting these requirements is crucial for reliable and real-time data transmission.Research is needed to optimize QoS provisioning in 5G networks for IoT applications, considering factors such as latency reduction, traffic prioritization, and network optimization to ensure seamless and high-performance connectivity.

F. COST AND ECONOMIC CONSIDERATIONS
The deployment of 5G networks for IoT applications involves significant costs, including infrastructure investments, device deployment, and maintenance.Research is needed to analyze the cost-effectiveness of 5G-enabled IoT deployments, develop economic models, and explore innovative business models that consider the diverse requirements and constraints of different IoT applications.From these results, We discovered that none of the protocols in use managed to accomplish the full performance trade-off.Analysis of research gaps Applying the 5G standards to IoT applications raises issues about managing radio resource optimisation and interference, according to the current state of 5G as analysed in this study and the simulation findings produced.
• In this situation, the conventional approaches to managing radio resource and interference in single-level networks may not be effective, necessitating further research into the interference management problem.
• Massive MIMO and 5G technologies now in use are unable to handle the heterogeneity and scalability issues of the Internet of Things.
• When employing 5G for multi-traffic data transfer in the IoT, it is a difficult task to take into account the resource-constrained IoT devices.
• The simulation findings demonstrated that there are no performance trade-offs amongst techniques, i.e., no particular approach stands out as superior than the others.

VI. CONCLUSION AND FUTURE WORK
This research analyzes how 5G, Massive MIMO, and AI work together to enhance IoT performance.This paper reviews current studies and discusses the research needs for a future roadmap based on those findings.We have also used 5G and IoT techniques to create a unique paradigm for smart healthcare monitoring.The approach was implemented and tested utilizing the most modern 5G interference and resource management techniques.The process was implemented and used the most current 5G interference and resource management techniques.The simulation findings highlight the areas for more investigation.The findings will guide the optimization of IoT systems, ensuring improved connectivity, reduced latency, enhanced energy efficiency, and efficient data processing in the evolving landscape of advanced wireless technologies.In the context of future work for an AI-Assisted Smart Healthcare System using 5G communication, several areas can be explored to further enhance the system's capabilities and address potential challenges.Here are some potential avenues for future research which aims to examine the synergistic effects of 5G, Massive MIMO, Real-time Monitoring and Intervention and Enhanced AI Algorithms on bolstering the performance of IoT.By exploring these areas in future work, the AI-Assisted Smart Healthcare System can continue to evolve and make significant contributions in improving healthcare delivery, patient outcomes, and overall healthcare ecosystem.

FIGURE 1 .
FIGURE 1. Development of innovative applications and services in the era of 5G.

FIGURE 2 .
FIGURE 2. System design for smart healthcare system using 5G and IoT.

FIGURE 3 .
FIGURE 3. 5G industry norms artificial intelligence for smart healthcare system.

FIGURE 4 .
FIGURE 4. Throughput measurements on mmWave 5G networks of a smart healthcare system.

FIGURE 5 .
FIGURE 5. Throughput measurements by sub-6GHz 5G networks of a smart healthcare system.

FIGURE 6 .
FIGURE 6. Density measurements of edge server,10MB in 5G networks of a smart healthcare system.

FIGURE 7 .
FIGURE 7. Density measurements of edge server,100MB in 5G networks of a smart healthcare system.

FIGURE 8 .
FIGURE 8. Performance of throughput and latency.

TABLE 1 .
Connectivity and edge computing.

TABLE 2 .
Data analytics and decision-making.

TABLE 3 .
Security and privacy.

TABLE 4 .
Resource optimization and efficiency.

TABLE 6 .
5G with AI for IoT application.

TABLE 7 .
IoT use cases and/or applications relative to the relevant sector-based quantitative performance metrics.

TABLE 8 .
Methodological step on 5G industry norms artificial intelligence-enabled communication systems.

TABLE 11 .
Outcome of average throughput, average communication delay, average energy consumption, and PDR(%).

TABLE 12 .
Application requirement and proposed system in 5G.

TABLE 13 .
Requirement of 5G norms AI for smart healthcare system.