A REAL TIME SYSTEM TO ANALYZE PATIENT’S CONDITION USING SECOND LAYER COMPUTING Dr.E.Dinesh,Assistant Professor Electronics and Communication Engineering M.Kumarasamy College of Engineering Karur, India dineshe.ece@mkce.ac.in Ms. K. Poovitha Electronics and Communication Engineering M.Kumarasamy College of Engineering Karur, India poovithapoovi1@gmail.com Ms.V. Pranikaa Electronics and Communication Engineering M.Kumarasamy College of Engineering Karur, India pranikaav24@gmail.com Ms.M. Rosini Electronics and Communication Engineering M. Kumarasamy College of Engineering Karur, India rosinimanivel@gmail.com Abstract: In the line of science, remote health monitoring is regarded as a hot topic. Regardless of the fact that there are more senior citizens, it is certain that a dispersed medical care system with remote monitoring and the goal of diminishing the rising cost of healthcare is urgently needed. Rapid detection and ongoing health monitoring can save up to 60% of lives. A wireless, wearable, affordable, and automatic health monitoring system is a good solution because of these factors. When needed, it can be challenging to check basic life factors like temperature, heart rate, gyro, oxygen level, etc. Using Arduino and a standard ESP8266, we will develop and construct an IOT-based patient health monitoring system. I. INTRODUCTION Fog computing is a concept that was developed to link devices and data centres. Fog computing has many applications, including real-time data collection, analysis, and facilitation from network-connected devices. Fog computing is not entirely located at the network's edge, despite the fact that it is becoming more virtualized and may offer internet connectivity among edge devices and cloud - based data centres. Fog computing can be deployed at draws on three levels: (1) data gathering from network edge (sensors, automobiles, highways, and ships), (2) numerous devices linking to a network and providing all input, and (3) the acquired data from the systems that should be evaluated within a few second, coupled with decision making. seen as a flexible global network architecture wherein entities with various qualities are combined to offer improved services In the field of healthcare, wireless sensor networks (wsn are a vital technology (WBANs)). One way to tell is by looking at your body's temp, pulse, Gyroscopic, and levels of blood oxygen. For viewing and diagnostic purposes, these data are transmitted to authorized customers via protocols like Wi-Fi. In healthcare monitoring, data from sensor nodes that employ cloud computing are analyzed and stored on remote cloud servers. There are other challenges, too, including latency sensitivity, large data transmission, and position awareness. Fog computing extends cloud services closer to end users by extending memory, handling, and connection to edge devices, enhancing network capacity, mobility, privacy, and security. Applications that require real-time or low latency performance are ideal for fog computing. For the management of health and safety, real-time environmental monitoring, visualization, and notification systems are being researched to offer a new perspective on reliable data collection, efficient visualization, and handling urgent situations. The number of senior people worldwide has increased recently, which has led to an increase in difficult health issues and higher clinical expenditures. People, especially the elderly, need to have their health remotely monitored. This may help to lower the additional expenses related to hospitals. On the other hand, conventional methods of healthcare monitoring are cumbersome and time-consuming. The creation of an efficient system for healthcare monitoring that lowers hospitalizations while also enhancing patients' life quality is therefore desired. For the management of health and safety, real-time environmental monitoring, visualizations, and notification systems are being researched to offer a new perspective on reliable data collection, efficient visualization, and handling urgent situations. The number of senior people worldwide has increased recently, which has led to an increase in difficult health issues and higher clinical expenditures. People, especially the elderly, need to have their health remotely monitored. This may help to lower the additional expenses related to hospitals. On the other hand, conventional methods of healthcare monitoring are cumbersome and time-consuming. As an outcome, there is a requirement for the creation of an efficient real time application that lowers hospitalizations while also enhancing patients' life satisfaction. In order to offer patients with high-quality care the practice of mobile health or m-health involves gathering health information from patients using accessible devices like smartphones and uploading it to a cloud server over the internet. The cloud may be used by hospitals insurance companies and other organizations to access these data the development of the m-health system is facilitated by the use of body sensor networks and wearable technology due to security concerns and the issue of network failure using a basic device system is not practical for many healthcare applications which risks the patient’s condition due to the delay in getting the patient data real-time health analysis is made possible by integrating m-health into the environment of a patient. Data delivery from sensing devices to the internet as well as cloud to hospitals is delayed when only the cloud platform is used for analysis and storage of healthcare data fog computing is therefore being employed in health care applications that require quick responses to emergencies and real-time operations implantable cardioverter defibrillators are being used by patients in order to maximize patient survival it gathers information on things like device functionality and physiological indications remotely tracking this data in real time enables early clinical variable diagnosis and helps treatment adjustments or device reconfiguration before patients are admitted to the hospital. Remotely tracking this data in real time enables early clinical variable diagnosis and helps treatment adjustments or device reconfiguration before patients are admitted to the hospital. Since remote health monitoring is more dependable, safe, affordable, and responsive to any failures, it is more effective than traditional one-on-one consultations. It also reduces the need for hospital visits and eliminates unpleasant surprises about the patient's health status. Medical assistants who monitor patients admitted to hospitals, particularly in Hospitalized Patients (ICUs), may make mistakes since it is impossible to completely eliminate human error. By extending cloud services to the edge of the network, fog computing is produced. Cloud computing is not an alternative for fog computing; rather, fog computing is an addition to it. Currently, heavy network traffic results in unacceptable latency and subpar services for end users, as well as a high bandwidth cost when moving lots of data to the cloud. To meet the needs of the big data era, it is crucial to restructure computer paradigms. According to this study, real-time applications that require a quick response time and minimal latency are perfect candidates for fog computing. This study demonstrates how fog computing lowers latency. According to this study, real-time applications that require a quick response time and minimal latency are perfect candidates for fog computing. This study demonstrates that fog computing, as opposed to cloud computing, minimizes latency, which is crucial in the domain of real-time healthcare. The goals of the suggested fog computing model include reducing latency when transmitting and sharing information signals with remote servers so that medical services can be provided more quickly in both the temporal and spatial dimensions. Machine learning is used as a result to analyze the data before it is interpreted. The suggested methods and procedures are described in great detail, including how they might operate in challenging circumstances and how they could be used in areas with the greatest demand for healthcare services. The rest of the essay is organized as follows: The relevant works completed during the study process are presented in Section 2, the suggested methodology is presented in Section 3, the findings and discussion are presented in Section 4, the conclusion is presented in Section 5, and finally, the reference article used in this data analysis is offered under reference section. II. RELATED WORK In a healthcare system, fog computing is an idea that is used. The use of bandwidth, Quality of Service, and notification alerts has demonstrated the efficacy of computing in healthcare monitoring. The deployment approach has also included a case study on utilizing ECG characteristics gleaned using clinical evidence at the network's edge. This study collects and sends data via Wi-Fi, Bluetooth, ZigBee, or 6LoWPAN communication protocols, including temperatures, humidity, patients’ locations, SpO2, Electro Encephalography (EEG), ECG, and EMG. The development of wearable technology in the field of healthcare is made possible by technological advancement. It is recommended to use everyday technologies like mobile phones as monitoring tools rather than using external sensors. Mobile phones are the only devices that can be used to remotely monitor patients due to their many built-in sensors, including a gyroscope, normal heart sensor, accelerometer, and more. Fog computing is necessary to support cloud data storage, networking, and processing, though. Examples of security breaches include impersonating, data theft, integrity of data, eavesdropping, and collusion. Sensor or Internet of Things (IoT)-derived clinical data is incredibly vulnerable to security breaches. Only allowed people would be able to access these records, which would be kept in the strictest of confidence. Because of security weaknesses, the data's secret is exposed to unauthorized persons. As a result, a strategy for tackling security flaws in health systems has been put out. This strategy involves a distributed healthcare architecture based on fog technology with numerous virtual computers dispersed locally for data processing and storage. Different types of data and requests are handled by each virtual machine. For emergency department systems, a Resource Preservation Net architecture has been developed and is integrated with special cloud and edge computing technologies. The Capacity Preservation Net is best suitable for real-time systems where the patient's average waiting time, length of stay (LoS), and resource utilization are crucial performance indicators. As a result, it turns out that this framework considerably improves the LoS, average waiting time, and resource usage. This study suggests that there will be a crucial justification for middleware integration in e-health systems. Middleware platform integration in health systems is meant to enhance the process of tracking a patient's or person's overall health. The study of cellphone medical information systems conducted locally is detailed in. This study includes a questionnaire survey, an analysis of people's opinions on how hospitals diagnose diseases, cost-effectiveness of treatments, and hospitals information systems. The survey results were used to complete the demand design and analysis of the cellphone medical information system. For hospitals, students, health professionals, and researchers, e-health and m-health services include disease diagnosis, risk prediction, therapeutic evaluation, health monitoring, teaching, and machinelearning model construction. The invention of a semantic e-health model called "k-Healthcare" that enables patients to effectively access medical data via smartphones was followed by a review of the literature on the effective usage of the healthcare domain. Khealthcare uses phones to sense and deliver data because the majority of current e-health and m-health systems do not use smartphone sensors to do so. The sensor layer, network layer, internet layer, and service layer are its four architectural layers. To provide effective services to lower levels, each layer serves a certain role. In particular, when a broad range of regions is covered and real-time decision-making scenarios are applied, this work concentrates on three specifications: mobility, actuation, and control of dependability and scalability. the application of cloud and fog computing to home healthcare. Additionally, this work presents the idea of edge computing in telehealth and remote patient health monitoring, which makes it easier for patients and healthcare providers to communicate. According this study, healthcare technology that combines cloud and fog computing delivers patients high-quality services. Additionally, this method proves how safe, dependable, and efficient it is. In contrast to clinic-centric therapy, an e-health system that is based on fog computing offers patient-centric healthcare. All authorities, including patients, hospitals, and services, are completely networked with one another. It has been demonstrated and recorded that switching from health center to patient-centric techniques has its advantages and disadvantages. According to this study, using e-health systems has the advantages listed below: Analysis and processing of big data, personalizing services, foreseeing and predicting future health issues so that patients can take necessary steps for prevention or curing, lifetime monitoring, seamless integration with different technologies regardless of their complexity, allencompassing (i.e., it can be used in a variety of purposes such as healthcare, exercise, beauty, safety, and so on), lifetime monitoring, and seamless integration with existing technologies. A sophisticated fog-based patients health monitoring system is on display. This technology's primary objective is to constantly monitor patients who need critical care at home. This strategy consists of five layers: gathering data, categorizing events, information mining, making decisions, and cloud storage. In order to provide improved services to the levels above it, each layer is responsible for carrying out specific tasks. This paper offers services like event identification using computing to provide valid response, temporal mining of patient health-related data based on event activating in the fog layer, and actual notification-based decision-making and data transmitted to professionals and hospitals when patients are in unsafe conditions. Use of a wearable Internet of Things (wIoT) system with fog assistance has enabled end-to-end analytics. In this study, a smart for gateway prototype for an intermediate layer was created using Intel Edison and a Raspberry Pi. This prototype aims provide the data condition, filtration, analytics, and transmission of pertinent data stored in the cloud for long-term archiving and monitoring of temporal variability. This prototype was put to the test using a system for smart e-textile gloves, and it was found that using knowledge-based models to translate real-world data into pertinent analytics improves the usability of the system. It may thus make it possible for wearable and the cloud to interact more effectively from beginning to end. 3.1. Fog Computing Fog computing operates in the space between devices and cloud computing. A new processing unit is introduced between the user and the cloud in order to improve latency, dependability, energy efficiency, and privacy protection. In addition to the benefits of cloud computing, fog computing offers compute, network support, storage capabilities, and actual information analysis. Fog computing also makes actual notification systems on consumer electronics possible. Contrary to cloud computing, fog computing immediately reaches users, whereas delay is the key issue with cloud computing. Fog computing is less effective than cloud computing since it uses fewer computers, smartphones, and other portable electronics. Data from all devices has been transmitted to fog computing devices, as illustrated in Figure 1, which then travel via several layers including (1) the data center/cloud layer, (2) the core domain/network layer, (3) the edge domain layer, (4) the smart sensors layer, and (5) the smart monitoring layer. To avoid data corruption, there is a security barrier between the end user device and the computer hardware. The information is then processed by fog computing devices. Preprocessing is the term for this. These are not sizable data sets. Only a little amount of data can be processed by fog computing devices. Another benefit of fog computing is that it provides a temporary storage layer where processed data may be kept before being sent to the cloud for additional processing. III. CONSTRAINTS ON FOG COMPUTING Fig 1 A fog computing network will be very challenging to maintain. If a failure arises in the network during data transfer, the maintenance personnel will take care of it. The main advantage is that the computational service can learn and adapt to the different consequences of fog computing. 3.2. Fog Computing in Health Monitoring A distinct standard utilized in the healthcare tracking system is fog computing. Fog computing reduces data volume and avoids network congestion while improving data processing. In order to measure specific signals and help patients get precise information, the remote healthcare system uses body sensors that are either integrated into the patient's body or strategically placed on the body. A specialized gadget collects data from those bodily sensors and also facilitates connection between the sensors and the monitoring equipment. IV PROPOSED METHODOLOGY The Patient Health Monitoring System Based on IoT The suggested setup describes using ESP8266 & Arduino. Our system may use sensors to measure and maintain a watch on a number of indications, such as temperature, heart rate, and blood oxygen levels, both in hospitals and at home. A heartbeat sensor is used to monitor the patient's heartbeat, while a temperature sensor is used to determine the patient's body temperature. SPO2 sensors are devices that monitor the oxygen saturation and quantity in your blood, respectively. The results can be recorded using Arduino. The Arduino processes the code, which is then shown on the LCD screen. A wireless connection is established and data is sent to an IoT device server via the ESP8266 Wi-Fi module. Lastly, IOT makes it possible to monitor data from anywhere in the world. In overpopulated countries like India, healthcare issues are becoming more and more common as the population grows and the need for medical care rises. While treatment costs are declining, the population's need for high-quality care is increasing. Health can now be remotely monitored by a machine, which is more dependable than manual monitoring, thanks to advancements in technology. It can aid in reducing the time required for individualized personal training while also improving the dependability of cuttingedge equipment. One form of fog computing that is influencing our daily lives is the use of wearable technology, which tracks everything and everyone in every imaginable way. The devices, which have a variety of sensors, can be worn by people. These devices keep an eye on a variety of human actions. Wearable technology In order to assure secure communication, there is a proven approach for trip arty, one-round key authenticated agreement that makes use of fog computing resources. This study suggests a novel computational architecture for scaling highperformance computing for prognosis and diagnostics, sensing, and remote real-time monitoring. 4.1. Sensor Network Layer In order to make fitness trackers comfortable for patients to use in order to measure a patient's temperature, pulse rate, and blood pressure, sensors such as temperature sensors, heartbeat sensors, and blood oxygen sensors are used in conjunction with a wearable device in which these sensors are integrated. All of these sensing apparatuses are a part of the sensor network layer. Using sensors, this layer locates and collects information on the patient's physiological parameters, including body temperature, heart rate, and systolic and diastolic blood pressure. Following that, this data is transmitted over wired or wireless communication protocols to fog computing equipment. 4.2. Fog Layer There are many dispersed nodes in the fog layer. Gateways are the name for these nodes. The gateway is a piece of equipment placed close to the sensors that enables network connectivity, storing, and computing. These sensors are responsible for recording events and providing information. Four functions are made possible by this layer: data collection from sensing devices, computational modeling for health-related decisions, career notification, and cloud data storage. In order to increase its intelligence, boost system dependability, reduce latency, get rid of network connectivity issues, and quicken decision-making processes, fog computing has implemented a remote data processing system. The characteristics of the fog layer are as follows: (i)Data gathering: Information is received for any further evaluation and decision-making from a variety of sensors attached to the wearable, such as temperature measurement, Electrocardiogram sensor systems, and blood pressure sensors. Screening, noise control, and preprocessing are done after data gathering. (ii)Data security: By gateways devices to the cloud, patient data collected from sensors will be transmitted. As a result, when developing a framework for healthcare monitoring, considerations for the safety and confidentiality of such info must be made. As a conclusion, a watermarking and encryption process has been developed to safeguard the suggested system. To protect the information from unauthorized access, it is encrypted into an unrecognizably different format. During the watermarking procedure, the data is concealed behind a picture without impacting its validity or visibility. (iii)In the suggested system, the patient's information is hidden behind the patient's facial image when being saved in the fog nodes or transferred to the cloud server. A suitable encryption method was then used to convert the watermarked image into a cypher image. This encrypted data cannot be read by unauthorized parties. It is necessary to save the data under patient's image since it cannot be opened until the authorized person gives their consent. Since the information is utilized for theft and is gathered by people to improve their blackmailing skills, it must be kept secret. According to the author, data must be reduced because storage capacity is a concern. It turns out that broadcasting the patient's image for every piece of data collected was overly overheard. By altering the model's inputs and the way the network is built, it is possible to make fog computing more reliable. 4.3. Cloud Layer Distributed servers, repositories, and resources make up the cloud layer. The cloud manager has the responsibility of managing every piece of hardware connected to a cloud layer and simplifying patient data collection, processing, and storage. This information can be used to analyze the patient's current health and medical history. The characteristics of the cloud layer are as follows: (i) Data storage: Following the fog layer's data analysis process, the processed data are transported to the cloud layer, which provides a huge storage capacity for keeping the patient healthcare data for future study by careers, physicians, hospitals, and insurance providers. (ii) Data analysis: For upcoming studies in the domain of clinical decision-making, the patient's health data in the cloud—which includes images of the ill areas, descriptions of the symptoms, therapies, and therapeutic plans—is studied. To comprehend the data better, a variety of machine learning algorithms and data visualization tools may be employed. (iii) Disease prediction: Depending on the patient's age, height, weight, and genetic makeup, it is possible to anticipate which diseases may affect them in the future. Based on the correlation of vital indicators, a machine learning algorithm may be used to forecast the expected percentage of disease. V DISCUSSION The suggested health monitoring framework's data flow (i) The sensor data is gathered and examined. (ii) Inappropriate sensor attachments, unwanted noise, and electromagnetic interferences are filtered out. To determine the patient's current health status, the data collected is assessed. (iii) A message will be sent to the doctors or caretakers of the patients who need help with their health state if any inconsistencies in the detected healthcare parameter values are found following data processing. (iv) The collected and analyzed data may be stored on the cloud so that researchers, medical professionals, or patients would be able to access it as needed in the future. To guarantee the security of the patient's data during transmission and storage, the information stored will be photo shopped with patient's photo and encrypted. (v) Since storage space is a major issue in the big data era, this information is compacted to decrease the space for storage required. (vi) The information is stored temporarily local in the fog in the case of a network failure. (vii) Placing a bridge system called a gateway in each location is the most often used technique for obtaining data from smart sensors. Data from sensors is received by a gateway, which transforms it into information that may be used. The sensors and the gateway both wirelessly transmit data. VI. RESULT (viii) Fog computing is used, among other things, in a smart electrical grid. In order to maintain cost effectiveness, smart cities must be able to adjust to changing demand, including ups and downs. This suggests that actual data on electricity supply and consumption is necessary for smart grids. Fog Computing Serves as The Best Choice Due to Its Following Features: CIRCUIT DIAGRAM (i Fog computing can offer improved delay performance since fog resources are situated between smart devices and cloud-based data centres. (ii)Fog computing requires tiny centres with little computation, communications, and storage capacities in comparison to cloud data centres; the expense of spreading micro fog centres close to end users will be very low. (iii)Because fog computing systems are highly scalable, even as end-user population grows, more micro fog centres may be deployed to meet the increased demand. Increased cloud data center deployment is unlikely because the expenses will be extremely expensive. Result 1 (iv)The services provided by fog computing are repeated and resilient. (v) Because fog resources are placed in close proximity to end users, they can act as mobile clouds. (vi) With fog computing, real-time services may reach great performance. (vii) The fog resources are capable of communicating with a wide range of cloud-based service providers. As an outcome, fog computing and its associated resources have become highly structured. (viii)Fog can be used to aggregate data. Resources for sending partially processed data, such as in place of actual data, to fog data centres for additional processing Result 2 VII. CONCLUSION This paper proposed a framework for fog-based health monitoring that uses fog gateways for medical decision based on information gathered from sensors like a temperature sensor, heartbeat sensor, and blood oxygen detector implanted in a handheld device to measure a person's temperature, heart rate, and the diastolic and systolic pressure. In the event of an emergency, these data are delivered to doctors or careers through the cloud after being encrypted and watermarked and maintained in the fog node unties enhances the utility of the suggested system. The enormous amount of data produced by these detectors is compressed and kept on the cloud platform for later use by medical facilities and research institutions. In this paper, the benefits of deploying fog computing services for clinical decision-making and monitoring healthcare are underlined. VIII. REFERENCES [1] N. Mani, A. Singh, and S. L. Nimmagadda, “An IoT guided healthcare monitoring system for managing real-time notifications by fog computing services,” Procedia Computer Science, vol. 167, no. 2, pp. 850–859, 2020. [2] C. S. Nandyala and H.-K. Kim, “From cloud to fog and IoT-based real-time U-healthcare monitoring for smart homes and hospitals,” International Journal of Smart Home, vol. 10, no. 2, pp. 187–196, 2016. [3] A. I. Taloba, R. Alanazi, O. R. Shahin, A. Elhadad, A. Abozeid, and R. M Abd El-Aziz, “Machine algorithm for heartbeat monitoring and arrhythmia detection based on ECG systems,” Computational Intelligence and Neuroscience, vol. 2021, Article ID 7677568, 9 pages, 2021. [4] T. N. Gia, M. Jiang, A.-M. Rahmani, T. Westerlud, and P. Liljeberg, “Fog computing in healthcare internet of things: A case study on ECG feature extraction,” in Proceedings of the IEEE international conference on computer and information technology; ubiquitous computing and communications; dependable, autonomic and secure computing; pervasive intelligence and computing, pp. 356–363, Liverpool, UK, October 2015. [5] A. Kiani, A. Salman, and Z. Riaz, “Real-time environmental monitoring, visualization, and notification system for construction H&S management,” Journal of Information Technology in Construction, vol. 19, no. 1, pp. 72–91, 2014. [6] F. Alanazi, A. Elhadad, S. Hamad, and A. Ghareeb, “Sensors data collection framework using mobile identification with secure data sharing model,” International Journal of Electrical and Computer Engineering, vol. 9, no. 5, 4258 pages, 2019. [7] H. H. Nguyen, F. Mirza, M. A. Naeem, and M. Nguyen, “A review on IoT healthcare monitoring applications and a vision for transforming sensor data into real-time clinical feedback,” in Proceedings of the IEEE 21st International conference on computer supported cooperative work in design (CSCWD), pp. 257–262, Wellington, New Zealand, July 2017. [8] M. Al-Khafajiy, L. Webster, T. Baker, and A. Waraich, “Towards fog driven IoT healthcare: challenges and framework of fog computing in healthcare,” in Proceedings of the 2nd international conference on future networks and distributed systems, pp. 1–7, Amman, Jordan, June 2018. [9] S. H. Almotiri, M. A. Khan, and M. A. Alghamdi, “Mobile health (m-health) system in the context of IoT,” in Proceedings of the IEEE 4th international conference on future internet of things and cloud workshops (FiCloudW), pp. 39–42, Vienna, Austria, August 2016. [10] A. Paul, H. Pinjari, W.-H. Hong, H. C. Seo, and S. Rho, “Fog computing-based IoT for health monitoring system,” Journal of Sensors, vol. 2018, no. 1, Article ID 1386470, 7 pages, 2018. [11] M. Bertini, L. Marcantoni, T. Toselli, and R. Ferrari, “Remote monitoring of implantable devices: should we continue to ignore it?” International Journal of Cardiology, vol. 202, no. 1, pp. 368–377, 2016. [12] I. Chiuchisan, H.-N. Costin, and O. Geman, “Adopting the internet of things technologies in health care systems,” in Proceedings of the International Conference and Exposition on Electrical and Power Engineering (EPE), pp. 532–535, Iasi, Romania, October 2014. [13] R. Deng, R. Lu, C. Lai, and T. H. Luan, “Towards power consumption-delay tradeoff by workload allocation in cloud-fog computing,” in Proceedings of the IEEE International Conference on Communications (ICC), pp. 3909–3914, London, UK, June 2015. [14] A. A. Mutlag, M. K. Abd Ghani, N. Arunkumar, M. A. Mohammed, and O. Mohd, “Enabling technologies for fog computing in healthcare IoT systems,” Future Generation Computer Systems, vol. 90, no. 1, pp. 62–78, 2019. [15] A. George, H. Dhanasekaran, J. P. Chittiappa, L. A. Challagundla, and S. S. Nikkam, “Internet of Things in health care using fog computing,” in Proceedings of the IEEE Long Island Systems, Applications and Technology Conference (LISAT), pp. 1–6, Farmingdale State College, USA, May 2018. [16] K. S. Awaisi, S. Hussain, M. Ahmed, A. A. Khan, and G. Ahmed, “Leveraging IoT and fog computing in healthcare systems,” IEEE Internet of Things Magazine, vol. 3, no. 2, pp. 52–56, 2020. [17] S. Oueida, Y. Kotb, M. Aloqaily, Y. Jararweh, and T. Baker, “An edge computing based smart healthcare framework for resource management,” Sensors, vol. 18, no. 12, p. 4307, 2018. [18] A. P. dos Santos, D. W. S. Lima, F. S. Freitas, and G. M. da Silva, “A motivational study regarding IoT and middleware for health systems,” in Proceedings of the The Tenth International Conference on Mobile Ubiquitous Computing, Systems, Services and Technologies, pp. 102–106, Venice, Italy, October 2016. [19] G. Sun, F. Yu, X. Lei, Y. Wang, and H. Hu, ““Research on mobile intelligent medical information system based on the internet of things technology,” in Proceedings of the 8th International Conference on Information Technology in Medicine and Education (ITME), pp. 260–266, Fuzhou, China, December 2016. [20] K. Ullah, M. A. Shah, and S. Zhang, “Effective ways to use Internet of Things in the field of medical and smart health care,” in Proceedings of the International conference on intelligent systems engineering (ICISE), pp. 372–379, Islamabad, Pakistan, January 2016.