An IoT and Artificial Intelligence-based Patient Care System to Focus on COVID-19 Pandemic in Real-time

An IoT and Artificial Intelligence-based Patient Care System to Focus on COVID-19 Pandemic in Real-time

Vishal Goar¹, Nagendra Singh Yadav¹, Kumaresan P.², Chiranji Lal Chowdhary², XYZ³, ABC²,

¹ Govt. Engineering College Bikaner, Rajasthan, India

² VIT Vellore, Tamil Nadu, India

Abstract

World Health Organization has declared COVID-19 a pandemic. The COVID19 epidemic spread all over the world, although it was much less fatal than the Ebola and past SARS-COV outbreaks. Deaths and illnesses started to grow exponentially as nations around the globe struggled to control the spread of the COVID-19 virus. At the time of writing this article, 3,024,059 people are infected by COVID-19 cases, whereas the total number of deaths was more than 208,100 (https://www.who.int/emergencies/diseases/novel-coronavirus-2019). Like many other epidemic outbreaks, COVID-19 faces significant challenges, like the identification of the epidemic’s source of disease, control the spread rate, and adequate healthcare for all patients. Digital technology, particularly the Internet of Things, could be used as an essential tool to combat and control the spread of these pandemics to minimize the economic loss and disruption. The digital technology allowed health care professionals in identification and isolation to the source of the infection to prevent community transmission of the virus by remotely monitor the COVID-19 infected patients. We aim to provide a survey of the IoT system for patient care during COVID-19. We offer a short overview of recent advances and some associated challenges in IoT framework research contributions to track and prevent patients during COVID-19. We proposed a machine learning model using the k-Nearest Neighbor (KNN) Model for COVID-19 prediction. The model is implemented in the Hadoop framework by creating a local instance. The result of this paper proves maximum accuracy with the KNN algorithm. This article presents an overview of the need and effectiveness of the IoT and AI system for COVID-19 pandemics.

Keywords: Internet of Things; COVID-19; Pandemic; Wearable Sensors; Cloud Interface; Machine Learning.

1. Introduction

Coronavirus is a small family of viruses. It can cause serious diseases ranging from the common cold to Middle East Respiratory Syndrome (MERS-CoV) to Severe Acute Respiratory Syndrome (SARS-CoV). The novel coronavirus is a new type of virus in which behavior is unknown to the human body. Coronaviruses are a group of associated RNA viruses that cause disease in mammals and birds. In humans, these viruses cause respiratory tract infections that may range from mild to lethal. The new coronavirus infects people of all ages. Older people and people with pre-existing medical disorders such as heart disease, asthma, and diabetes seem to be more vulnerable to the virus being seriously ill. COVID-19 distributes by respiratory when the individual is tingling, sneezing, or talking to an infected person. People may also be tainted with their skin, mouths, and nose by touching a contaminated surface.  The WHO suggested people of all ages should take measures to protect themselves from the virus, such as proper hand hygiene and good respiratory hygiene [3,4, 8].

The fact that COVID-19 is predicted to have an important impact on the Chinese economy and other countries around the world, such as world economic recession, trade, disturbances in the supply chain, goods and logistics [2, 6, 10] can only be ignored. Internet of Things (IoT) systems use wide ranges of sensors collecting information to be transmitted over the internet to a central cloud-based computing platform for urban infrastructures, factories, or wearable devices. Machine Learning Analytics cloud-based software reduces huge amounts of data generated to user-friendly information.

IoT offers significant life-consistent advantages and has been an influential source of technology in healthcare. IoT has already gained access to the healthcare sector with an ever-increasing number of chronic diseases, with various applications, including telemedicine, connected imaging, hospital surveillance, drug tracking, connected protection, connected personnel, connected ambulances, etc.[13,14].

In many countries with 5G mobile networks, COVID-19 is expanding. But through radio waves or mobile networking, viruses cannot fly. The Internet of Things is an ensemble of interrelated computing devices, mechanical and digital machines that have unique identifiers and the ability to transmit data over a network without the need for human-to-human or computer-to-computer interaction [29]. Wearable sensors installed on end-user devices collect data for analytics and decision making that are sent to cloud servers.[24] Pervasive networking is the essence of IoT. Medical IoT or M IoT is a medical, communication, and biological mix [7].

The recent COVID-19 outbreak prompted IoT healthcare providers to quickly come up with solutions to meet the demand for high-quality virus protection services [11]. The rapidly growing COVID-19 has taken over the entire ecosystem of healthcare from pharmaceutical companies, drug suppliers, Vaccine developers, health insurers, and hospitals [5]. Applications such as primary care include remote patient management and virtual diagnosis, together with hospital surveillance, which is expected to gain traction over this period.

The best way to tracks pathogenicity is by using an early warning system and quickly becomes pandemic. However, urbanization raises its own set of problems with pandemic monitoring and control. In 2019, a study conducted at MIT used cell phone data to analyze the relationship between human mobility and dengue virus outbreaks in the city of Singapore from 2013 to 2014. Research showed that the spread of vector-borne diseases like dengue is a critical factor for human mobility even at short distances on the land. Models can be replicated to test how the epidemic spreads through concentrated movement. Health professionals should concentrate on patient zero quickly to identify all persons who are infected to quarantine the infected individual [35].

2. Dissecting an IoT Epidemic

IoT has various functional components, such as data collection, data transmission, analysis, and storage. Mobile sensors such as tablets, robots, or health monitors collect information from end-user hardware. The mobile data sent to the central cloud server for monitoring and decision making. The device needs diligent maintenance to avoid any unexpected malfunction [34]. After the disruptions by COVID-19, the priorities of IoT service providers strengthened health innovation. The speedy dissemination of COVID-19 reveals and intensifies many systemic problems in the government’s health response systems [9].

Increasing epidemics would further burden the network [12] and lead to a quarantining of potentially infected patients, chronically ill patients, and prevent cross-infection between the medical staff and patients. The Internet of Things is a modular, interactive technology that has experienced exponential growth in other industries such as automated manufacturing, wearable consumer electronics, and asset management [13].

3. Patient Care Monitoring Using IoT to ensure Quarantine enforcement

The scalability of IoT is also useful in tracking all patients with high-risk quarantine but not too extreme to guarantee hospital treatment. Door-to-door health care workers are also carrying out routine patient reviews. In one scenario, a health worker had patients standing on their balconies in the apartment so that a drone could test their temperatures with an infrared thermometer. IoT helps patients to take their temperature and upload the data to the cloud for analysis from their mobile devices [18,32]. Besides, IoT will support the overworked staff at the hospital. In medical conditions such as high blood pressure or diabetes, IoT used in ongoing monitoring of in-homes patients [19].

In hospitals, many patients tracked through telemetry. Some biometrics parameters, such as heartbeat and blood pressure, were transmitted from wearable and mobile devices into a central cloud server [23]. In this context, IoT can reduce the workload and increase medical personnel productivity, thereby reducing health workers ‘ vulnerability to infection [20]. IoT can also be used to ensure compliance with patients before quarantine reaches potentially infected persons. Public health staff must monitor which patients remain in quarantine and which patients have violated quarantine. The IoT data would help them track because of the infringement.

The next step to contain the pandemic is to identify and quarantine infected individuals quickly. Professionals in health care will use artificial intelligence-enabled sensors and integrated security cameras to track and enforce patient compliance in real-time [22]. GPS geofencing systems can easily detect and monitor all patients ‘ quarantine movements and avoid a further spread of mutual contamination. Autonomous driverless vehicles used to transport patients to hospitals and to eliminate more human contact in case of an emergency [26, 27].

A smartphone-based application will assist healthcare professionals with medicine specifications such as Predictive, Customized, Preventive, and Participatory. It will be connected to a single cloud-based portal that will be made accessible to all health professionals. This will include medical history, patient records, and their diagnosis [31]. Artificial Intelligence-based diagnosis can provide correct diagnosis and advice in real-time. This will enable health professionals to explore the skills as they need to operate better. The app would facilitate two-way communication between the patient and his or her doctors, thereby allowing for better use of resources. It will ensure long-term patient follow-up and avoid further group infection [30].

Wearable devices monitor body temperature, pulse oximeter, ECG, Heart rate, blood pressure and glucose level, and other variables. Doctors will be provided with the data required for diagnosis, which would also reduce the burden in hospitals that may run short of infected beds [27].  When the patient is tracked while he is in isolation, the resulting risk of further infection decreases significantly. Drones could also be used to supply drugs and essential resources, thus reducing human contact that would minimize new infections significantly. Patient carriers and ambulances may be disinfected with robots. The importance of patient communication, logging, wearable devices for tracking, designating, treating, routing, touch monitoring, and real-time information sharing cannot be emphasized anymore at this time, which will all fall within the IoT system [21,28].

4. Challenges in Governance and Delivery

Patient management is not the only aspect of the pandemic that the government has to deal with many other issues of the economy, governance, defense, supply chain, everyday life. It is essential to look after the health of the elderly, the daily wage labor, students, agriculture, and industries.

Artificial Intelligence Technology and Machine Learning methods can be used to look for new drugs to cure the virus. Food stores inevitably face enormous competition as consumers continue to purchase panic and stock up on merchandise. That adds severe stress to the supply chains of some stores. If those stores invest in digital e-commerce payments, they will be better prepared for disruption. 3D printing can be used for the fast development of hospital rooms and other medical devices to reduce the burden on health care facilities [33]. Online-educational institutes can use blockchain technology software to keep track of their students, their learning, and even grant digital certificates. Governments around the world can use site tracking data derived from smartphones to avoid any large-scale gathering of people during an epidemic and prevent the virus from spreading the population.

5. IoT Framework to Combat COVID-19 Pandemic

Several researchers, based on the context of the WHO protocol, suggested the IoT framework, as shown in Figure 1.  The framework is a combination of physical, network, middleware layers of service. The physical layer is the group of devices connected that have built-in sensors and transmitters. The network layer plays a vital function because it holds the signals transmitted to the cloud. The data is processed in the cloud using middleware software, and data are open to the caregivers and caretakers.

Figure 1. IoT Framework for COVID-19 Detection

Patients are required to be fitted with wearable sensors to determine the level of body temperature, pulse oximeter, ECG, heart rate, blood pressure, and glucose level measurements, and other variables [8].  These sensors are used to treat diseases such as COVID-19. These devices must be appropriately attached to the patient’s skin to obtain accurate results. Various physiological specifications and body parameters, as defined with physiological data, can be collected from sensors attached to the skin of the patient [31]. Hardware prototype is required to process the captured data and, to transmit the data, a wireless communication protocol must be integrated. The sensor size should be kept small along with the reduction of its weight so that it does not become an obstacle for patient movement [17].

Sensors running on batteries should be based on an energy-efficient system. It is expected that these batteries will have to work concurrently without using a charger and will not require a replacement battery. Data transmission is carried out by a network component that guarantees the data security and protection of all patient records and specifies that the patient records will reach the designated location-specific health centers. Bluetooth or ZigBee radio protocol can be an excellent choice to perform transmission channel activities [30].  The patients’ data can be transferred to health centers using a high-speed network or the internet so that data storage can be carried out efficiently. IoT sensors can be monitored and controlled by smartphones based on the availability of the internet communication protocol [15].

The wireless sensor network configures autonomic on its own in a health monitoring system so that it can change the sensor or sensor node depending on the total distance between the diagnosis center and the sensors to capture contiguous information for a more extended period [29]. If the priority is changed towards lower energy usage, limits may be set to avoid emergencies. The rest of the sensors can be shut down to save a life of sensors and battery consumption.  When there is excessive use of resources, the need for a low-power communication protocol is increased.

Bluetooth is the preferred mode of communication for short period communication with lower power consumption as it meets the different requirements for applications, i.e., Health care, recreation, Entertainment at home. With the advent of Bluetooth, components are snoozed at regular intervals, resulting in a reduction in energy consumption in terms of the number of bytes sent per energy joule. Low capacity WPAN protocols are used to connect Wireless Personal Area Network WPAN devices to the web [30].

6. Cloud-Based Data Storage and information sharing

Today’s smartphones have advanced features that allow the user to use the LTE and WIFI services at any time. For complex systems, these types of features loaded smartphones can act as concentrators. The concentrators do the job of collecting the data and sending it via data transmission into the cloud storage. Cloud data storage enables data availability and access at any time for the physicians concerned, or for data analytics-specific information purposes [16].

For situations where local resources cannot meet the needs of data storage and processing, the Cloud is designed to support such services. The Cloud allows local data storage and retrieval. This helps to perform clock-based critical work on patient medical data. It needs data availability at the point of time for data analytics so that data analytics can produce more effective results in terms of diagnostic information powered by cloud-based data storage. The cloud computing system is proposed as a viable approach as it can push healthcare applications with the aid of Personal Area Network due to often offline data. Wi-Fi is chosen to avoid data transmission latency for the critical task of the stored data to enable communication between the concentrators and the Cloud.

The data collected by the sensors will be stored in the Cloud to ensure centralized data access [20].  The processing of data performed in the Cloud is often evaluated using context-aware analysis in which the context represents the patient’s expected and present status. The medical history of the patient must be kept secure when the information is stored in the Cloud. The proper security and privacy measures should be followed to prevent unauthorized access when offline records are being transferred and stored on Cloud. The main challenge is data protection in the Cloud, but reliable cloud storage services can be successful [25].  The Cloud-based Layered architecture for suspected individuals during combating COVID-19 Pandemic is shown in Figure 2.

Figure 2. Layered Framework for Prediction of Suspected Individuals during COVID-19 Pandemic

7. Combat COVID-19 Pandemic using Artificial Intelligence

Prediction of diseases is one of the most critical tasks in data mining and learning for several years. In the medical field, there are so many works to predict certain illnesses. Hierarchical representation of the raw data with the little preprocessing and the recent success of deep learning in the various areas of machine learning provides more accurate results. For the diagnosis of diseases, AI algorithms such as KNN classification, ID3 Decision Tree, the Neural Network, and the Vector Support System supports and show different accuracies in prediction.

When it comes to bulk medical records, data analysis is a massive job. Machine learning algorithms do the study of the relevant sensor parameters and clinical data. The data collected by the wearable sensor goes through the process of machine learning for disease prediction analysis [33].

The system must be assured that the algorithms are sufficiently competent to recognize the unavoidable flow of data. While the analytical method in IoT Implementation is intended for the medical field, it is associated with several different hurdles. Firstly, new devices are launched in the medical field that involves periodic updates or modifications to these IoT based devices.  It will construct a significant effect on the database architecture, and IoT powered systems. For managing the continually changing data of the sensor, further development of machine learning algorithms is required. Second, there is a dependence on the condition of the patient, and the data varies from physician to physician. It is challenging to integrate the feedback that changes over some time. For creating ordinary training data for machine learning algorithms, the most excellent support lies in the principles of regression methods and their classification.

Finally, data from sensors creates a heterogeneous model, which is obtained from several inputs from different sources. Graphic-based models can be of great help when it comes to combining several input data into a core system that incorporates impressive customizations. The sensors capture numerical data, but when it comes to monitoring a patient and its health continually, medical data is plotted geographically. Visualization also plays a vital role when it comes to tracking health parameters.

8. Proposed Machine Learning Model for COVID-19 Diagnosis

Several algorithms, such as Naive Bayes, Decision Tree, and k-Nearest Neighbor (KNN), were used for COVID-19 Diagnosis based on the survey findings. We also proposed a classification model for KNN to improve the accuracy with the weighting step of the parameters. Only 3 parameters, such as body temperature, pulse oximeter, and heart rate, are used as they are instant and straightforward parameters and easily measurable. The result shows that the accuracy of these 3 parameters using the KNN algorithm is sufficiently good.

8.1 k-Nearest Neighbor (KNN) Model for COVID-19 prediction.

Hadoop instance is built on a local system with the installation of Apache Hadoop3.2.1 [37]. The source body parameter data obtained from the sensors were stored in the local network. On Hadoop Framework, we run the algorithm in the local server, and the results are retrieved from the MAPREDUE, where the output is stored in the local system. The following steps will run the algorithm, and the results will be generated based on the training data.

STEP 1: The body temperature, the heart rate, and the level of oxygen in the blood are collected from the coronavirus suspected patient and processed in the local system. The data is here known as the application test collection.

STEP 2: The retrieved data from the wearable sensors gets stored in the text file in the local file system.

STEP 3: A copy of the text file containing the test data is copied to the Hadoop system and saved in the Hadoop Distributed File System (HDFS).

STEP 4 The Jar file is initiated with the input of test and training data, where the KNN algorithm is designed and packed as the jar file.

STEP 5: KNN algorithm initiated and executed.

STEP 6: The output resulted from the MapReduce and inserted into the HDFCs as part-r-00000.

STEP 7: The output file is imported to the local file system from the Hadoop environment and saved.

STEP 8: The disease prediction result in the file is retrieved using the stream reader and represented to the caregivers and caretakers.

STEP 9: The disease is updated to the respective coronavirus suspected patient in the database table.

STEP 10: The symptoms input file and the result file retrieved from HDFS will be deleted from the local file system.

9 Conclusion and Future work

Several innovations and IoT modules improve the health care systems for pandemics or disease outbreaks. In this survey, a combination of IoT aspects and artificial intelligence algorithms are used to focus on the COVID-19 epidemic and the problems that need research in the future. Current technologies make the concept of IoT feasible but do not meet the requirements of scalability and efficiency. Consequently, the IT infrastructure development system requires rapid transformation so that there can be a connection between data collection and processing, along with storage components. Preventive isolation, disease surveillance equipment, and potentially contaminated patient care can be improved. Wearable sensors play a vital role in abstracting body parameter values for disease prediction.  Based on the findings, we proposed a KNN machine learning model and implemented on Hadoop framework to counter the COVID-19 coronavirus.  The model gives optimal results for the prediction of the suspected individuals.

The IoT layered architecture provides the derived data to the caretakers and caregivers. The biggest challenge is that the sensor produces heterogeneous data, but machine learning handles comparable data. The development of enhanced machine learning models to solve different sensor data on cloud systems may be an open research issue. We assume that, despite the industry’s interest in IoT applications, resolving this COVID-19 pandemic will be an influential driving factor in the coming years.

References

• World Health Organization. (2020). Coronavirus disease 2019 (COVID-19): situation report, 72.

• Remuzzi, A., & Remuzzi, G. (2020). COVID-19 and Italy: what next? The Lancet.
• Cascella, M., Rajnik, M., Cuomo, A., Dulebohn, S. C., & Di Napoli, R. (2020). Features, evaluation, and treatment coronavirus (COVID-19). In Statpearls [internet]. StatPearls Publishing.

• Fang, L., Karakiulakis, G., & Roth, M. (2020). Are patients with hypertension and diabetes mellitus at increased risk for COVID-19 infection?. The Lancet. Respiratory Medicine.

• Velavan, T. P., & Meyer, C. G. (2020). The COVID‐19 epidemic. Tropical medicine & international health, 25(3), 278.

• Zhou, F., Yu, T., Du, R., Fan, G., Liu, Y., Liu, Z., … & Guan, L. (2020). Clinical course and risk factors for mortality of adult inpatients with COVID-19 in Wuhan, China: a retrospective cohort study. The Lancet.

• Liu, Y., Gayle, A. A., Wilder-Smith, A., & Rocklöv, J. (2020). The reproductive number of COVID-19 is higher compared to the SARS coronavirus. Journal of travel medicine.

• Zheng, Y. Y., Ma, Y. T., Zhang, J. Y., & Xie, X. (2020). COVID-19 and the cardiovascular system. Nature Reviews Cardiology, 17(5), 259-260.

• Dong, E., Du, H., & Gardner, L. (2020). An interactive web-based dashboard to track COVID-19 in real-time. The Lancet infectious diseases.

• Sohrabi, C., Alsafi, Z., O’Neill, N., Khan, M., Kerwan, A., Al-Jabir, A., & Agha, R.

(2020). World Health Organization declares global emergency: A review of the 2019

novel coronavirus (COVID-19). International Journal of Surgery.

• Fauci, A. S., Lane, H. C., & Redfield, R. R. (2020). COVID-19 navigating the uncharted.

• Sullivan, H.T., Sahasrabudhe, S. Envisioning inclusive futures: technology-based

assistive sensory and action substitution. Futur. J. 87, 140–148 (2017).

• Yin, Y., Zeng, Y., Chen, X., Fan, Y.: The Internet of Things in healthcare: an overview.

1. Ind. Inf. Integr. 1, 3–13 (2016).

• Himadri Nath Saha, Supratim Auddy, Subrata Pal: Health Monitoring using Internet of Things (IoT), IEEE Journal pp.69–73, 2017.

• Sarfraz Fayaz Khan, “Health Care Monitoring System in Internet of Things (loT) by

Using RFID”, IEEE International Conference on Industrial Technology and

Management pp198-204, 2017.

• MoeenHassanalieragh; Alex Page TolgaSoyata; Gaurav Sharma,”Health Monitoring

and Management Using    Internet-of-Things (IoT)Sensing with Cloud-Based

Processing: Opportunities and Challenges”, 2015.

• Wang, X., Wang, J.T., Zhang, X., Song, J.: A multiple communication standards

compatible IoT system for medical usage. In: IEEE Faible Tension Faible

Consommation (FTFC), Paris, pp. 1–4 (2013).

• Xu, B., Xu, L.D., Cai, H., Xie, C., Hu, J., Bu, F.: Ubiquitous data accessing method in

IoT-based information system for emergency medical services. IEEE Trans. Ind.

Inf.10(2), 1578–1586 (2014).

• Kolici, V., Spaho, E., Matsuo, K., Caballe, S., Barolli, L. Xhafa, F.: Implementation of

a medical support system considering P2P and IoT technologies. In: Eighth International

Conference on Complex, Intelligent and Software Intensive Systems, Birmingham, pp.

101–106 (2014).

• Sandholm, T., Magnusson, B., Johnsson, B.A.: An ondemand WebRTC and IoT device

tunneling service for hospitals. In: International Conference on Future Internet of

Things and Cloud, Barcelona, pp. 53–60 (2014).

• Antonovici, D.A., Chiuchisan, I., Geman, O., Tomegea, A. Acquisition and

management   of biomedical data using Internet of Things concepts. In: International

Symposium on Fundamentals of Electrical Engineering, Bucharest, pp. 1–4 (2014).

• Krishnan, B., Sai, S.S., Mohanthy, S.B.: Real time internet application with distributed

flow environment for medical IoT. In: International Conference on Green Computing

and Internet of Things, Noida, pp. 832–837 (2015).

• Azariadi, D., Tsoutsouras, V., Xydis, S., Soudris, D.: ECG signal analysis and

arrhythmia detection on IoT wearable medical devices. In: 5th International Conference

on Modern Circuits and Systems Technologies, Thessaloniki, pp. 1–4 (2016).

• Mohan, A.: Cyber security for personal medical devices Internet of Things. In: IEEE

International Conference on Distributed Computing in Sensor Systems, Marina Del

Rey, CA, pp. 372–374 (2014).

• Yeh, L.Y., Chiang, P.Y., Tsai, Y.L., Huang, J.L.: Cloud based fine-grained health

information access control framework for lightweight IoT devices with dynamic

auditing and attribute revocation. IEEE Trans. Cloud Comput. PP(99), 1–13 (2015)

IoT-Based Health Monitoring System for Active and Assisted Living 19.

• Porambage, P., Braeken, A., Gurtov, A., Ylianttila, M. Spinsante, S.: Secure end-to-end

communication for constrained devices in IoT-enabled ambient assisted living systems.

In: IEEE 2nd World Forum on Internet of Things, Milan, pp. 711–714 (2015).

• Laubhan, K., Trent, M., Root, B., Abdelgawad, A., Yelamarthi, K.: A wearable portable

electronic travel aid for the blind. In: IEEE International Conference on Electrical,

Electronics, and Optimization Techniques (2016).

• Yelamarthi, K., DeJong, B.P., Laubhan, K.: A kinect-based vibrotactile feedback

system to assist the visually impaired. In: IEEE Midwest Symposium on Circuits and

Systems (2014).

• T. Chou, R. Rana, and W. Hu, “Energy efficient information collection in wireless

sensor networks using adaptive compressive sensing,” in IEEE 34th Conf.on Local
Computer Networks, LCN 2009., Oct 2009, pp. 443–450.

• Siekkinen, M. Hiienkari, J. Nurminen, and J. Nieminen, How low energy is

bluetooth low energy? Comparative measurements with zigbee/802.15.4,” in Wireless
Communications and Networking Conference Workshops (WCNCW), 2012 IEEE,

April 2012, pp. 232–237.

• Bui and M. Zorzi, “Health care applications: A solution based on the internet of

things,” in Proc. of the 4th Int. Symposium on Applied Sciences in Biomed. and Com.
Tech., ser. ISABEL ’11. New York, NY, USA: ACM, 2011,pp. 131:1–131:5.

• Li, S. Yu, Y. Zheng, K. Ren, and W. Lou, “Scalable and secure sharing of personal

health records in cloud computing using attribute based encryption,” IEEE Trans.

Parallel Distrib. Syst., vol. 24, no. 1, pp. 131–143, Jan. 2013.

• Bishop, Pattern recognition, and machine learning. New York, NY:Springer, 2006.

• https://iot-analytics.com/the-impact-of-COVID-19-on-the-internet-of-things/

• Mark Andrejevic, The new transparency: smartphone, data tracking and COVID-19,

March 09, 2020

• https://www.medgadget.com/2017/04/disposable-oxygen-level-monitoring-sensor-prevent-spread-infections.html.

• https://hadoop.apache.org/docs/current/hadoop-project-dist/hadoop-common/ClusterSetup.html