11
Semantic Web and Internet of Things in e-Health for Covid-19

Healthcare, in simple terms, means the monitoring and care of a person by detecting, diagnosing, treating and creating cures using a given dataset for any type of illness – mental or physical. Due to the outbreak of coronavirus and advancements in various technologies, healthcare systems have moved from traditional to e-health monitoring systems using the Internet of Things (IoT) and Semantic Web (SW). IoT is a collection of devices that are connected with systems and each other via the Internet using sensors, software and exchanging data. These devices perform in sync with the system and with each other to transfer data efficiently and quickly. The SW, otherwise known as Web 3.0, is the updated version of WWW that makes machines understand data present on the web. This data can be handled by creating specific flowcharts or knowledge graphs using various ontologies to extract useful information. Smart devices like wearables, smart TV and smart homes have enabled remote and continuous monitoring of individuals (who require constant medical attention) by collecting data continuously using sensors and transferring and storing it via the Cloud to the central system using IoT framework. These intelligent devices are helpful in managing essential readings of a patient’s blood pressure, heart rate, blood oxygen level, sugar level, body temperature and so on. The collected data is shared with medical practitioners and healthcare personnel for analysis and to decide the treatment accordingly. As these recorded data can be analyzed faster and more accurately, healthcare quality and access to care have been increasing while the cost of care has been decreasing. This chapter sheds light on a study on developing an e-health application using SW technologies and the IoT to diagnose and predict Covid-19. The primary aim is the analysis of various e-health applications and estimation of their efficiencies for Covid-19. Finally, how the intermingling of SW technologies with the IoT is done to design an efficient e-health system for the given problem statement is discussed.

11.1. Introduction

The world was introduced to a new kind of deadly virus when a variant of coronavirus, known as SARS-CoV-2, was found in Wuhan, China, in December 2019. The virus quickly caught WHO’s attention when it was found in more than 15 countries. Then, in March 2020, WHO declared coronavirus infection a pandemic (Pagnelli et al. 2021). The virus can spread via mouth or nose droplets and even via air (to some proximity). The situation of Covid has been controlled in most developed countries; however, the fight is still going on in developing countries and underdeveloped nations. Researchers design different architectures of IoT, and numerous applications are developed using SW technologies to fight against the Covid-19 pandemic.

IoT, short for the Internet of Things, includes intelligent devices which are connected via the Internet. These devices can transfer and receive data with low latency (Otoom et al. 2020). These devices also send the recorded data, collected using sensors, to a cloud server which can be accessed by various devices connected with the network. The usage of IoT devices has not been a new concept, as these devices were used way before the coronavirus pandemic shook the world. Various IoT architectures have helped in the remote and real-time monitoring of patients who could not be mentored or monitored in hospitals (Firouzi et al. 2021). IoT has also been utilized for tracking the real-time locations of various pieces of medical equipment such as wheelchairs, defibrillators, nebulizers, oxygen pumps and other monitoring devices. However, the IoT revolution came full force when the coronavirus pandemic started. IoT architectures were extensively used by hospitals, frontline workers, police, etc., to monitor, detect and diagnose patients infected with Covid-19 inside and outside hospitals (Kohler et al. 2020; Dogan et al. 2021).

IoT-based devices collect data of patients from all around the world. Still, this data is applicable only if it can be utilized effectively by researchers and scientists for designing systems and architecture to fight against the ongoing pandemic. The data should be readily available on the Cloud or online for researchers to test the efficiency and accuracy of their designed systems. Researchers are now using SW, otherwise known as Web 3.0, to arrange the data meaningfully (Jayachandran et al. 2020). SW technologies built applications using knowledge graphs and ontologies to make a computer understand the data, process it and classify it into well-defined sub-categories. The data collected from patients (IoT-based devices) can be directly supplied to SW-designed applications, which can be easily accessed by future researchers and scientists, as per their requirements.

Some studies conducted using ontology-based approaches before Covid-19 are as follows: an ontology framework to analyze the performance of a student as per their behavior (Ashokkumar et al. 2020), the amalgamation of web mining and SW technology to improve the molecular biology domain (Kate et al. 2014), an ontology-based agricultural informatics system was proposed for informing farmers with better farming practices (Mohanraj et al. 2016), analyzing the emotions of individuals using opinion mining ontology (Ganesan et al. 2019), and investigating the Information Retrieval system using an Ontology-Based Fuzzy Semantic system (Naren et al. 2019).

The subsequent sections discuss data set information for IoT and SW applications. Different architectures and frameworks are then discussed as regards their applications for Covid-19. Next, the section shows various shortcomings and challenges using IoT and SW technology and how researchers designed models to overcome these limitations. This chapter then includes a discussion about multiple IoT architecture and SW applications and how these technologies can be merged in the future for better performance of models. The chapter ends with a conclusion that discusses the prospects of this chapter.

11.2. Dataset

The primary purpose of designing an IoT architecture is to collect data about various parameters related to human health, which are vital for the problem at hand. State-of-the-art sensors were explicitly designed for collecting information about EKGs, heart rates, sugar levels, blood pressure (Pagnelli et al. 2021), brain signals, temperature (Bolock et al. 2021), face scans and movement of people (Kohler et al. 2020), in order to assist in various applications designed for stopping the spread of Covid-19. Some of these data are collected in real-time to provide telehealth, remote monitoring, e-health, etc. Other data are collected and stored in clouds to analyze the lockdown, quarantine and movement of individuals.

For SW applications, the data are readily available online about a specific topic, like biomedical and coronavirus, and can be used anywhere and by anyone to be accessed readily and without much effort. The primary focus of building SW applications is for providing meaning to the plethora of information about a particular topic using web ontology language (OWL), knowledge graphs, etc. Moreover, it establishes a relationship between various ontologies present for the same domain, like Covid-19. Many standard databases like gene ontology (GO) (Jayachandran et al. 2020), Infectious Disease Ontology (IDO) and Covid Infectious Disease Ontology (CIDO) (He et al. 2020) were utilized for designing various ontology-based applications, which are going to be discussed in later sections of the chapter.

11.3. Application of IoT for Covid-19

Due to the sudden increase of Covid cases, the poor infrastructure of hospitals in developing countries has posed a severe problem. The non-availability of proper medication and proper monitoring of infected patients have caused more deaths than estimated.

11.3.1. Continuous real-time remote monitoring

Firouzi et al. (2021) discusses the fact that the need for constant real-time remote monitoring has risen in this pandemic situation to help patients and healthcare workers. Hospitals have utilized wearable-IoT devices to monitor and track patients’ records effectively and identify the symptoms of Covid in non-infected people. Various studies defining a different architecture to overcome this problem have been discussed.

11.3.2. Remote monitoring using W-kit

Pagnelli et al. (2021) designed a three-layer IoT-based architecture, IoT-HMS, to monitor patients from home and hospitals. They developed a wearable kit (W-kit) to collect various data from the patients. This architecture could also collect info from third-party wearable devices like Apple watches with the patient’s consent.

11.3.3. Early identification and monitoring

Otoom et al. (2020) developed an IoT-based architecture to detect Covid-infected people and monitor recovered patients in real time. The framework is applied to five main components to detect the presence of coronavirus in people early. These data were supplied to eight machine learning algorithms, five of which showed more than 90% accuracy. The primary purpose of this architecture is to monitor the treatment response of patients who have recovered from Covid-19.

11.3.4. Continuous and reliable health monitoring

Filho et al. (2021) extended the above-proposed model for continuous health monitoring by integrating wearables devices with better sensors. They applied this framework to patients infected with Covid in Brazil. The proposed framework was deployed for ICU patients and expanded the approach to critical patient monitoring. Researchers also proposed a fog-based and Machine Learning-based system to improve their future proposed models.

11.3.5. ANN-assisted patient monitoring

Rathee et al. (2021) designed an IoT-based Artificial Neural Network (ANN) architecture to detect and monitor the Covid-infected individuals. This ANN architecture classified the patients into infected, non-infected, susceptible and exposed, quickly identifying infected patients and sending them for further treatment. The data were tested using five different machine learning algorithms, which were evaluated using two factors: classification time and accuracy. This architecture can be improved when a large amount of data is provided.

11.3.6. City lockdown monitoring

Kohler et al. (2020) proposed a three-layer decentralized IoT-based biometric architecture to monitor the movement of people during the lockdown. The proposed framework utilizes the state-of-the-art FDDB and WIDER FACE datasets for face detection. Face detection using the CNN-based model showed a better response than the above face detection model. The primary purpose of this proposed three-layer edge architecture is to restrict the movement of people. This system outperforms the previously defined cloud-based system.

11.3.7. Technologies for tracking and tracing

Firouzi et al. (2021) discuss how different technologies are used to track and trace the movement of people. These technologies include Bluetooth, GPS and ultrasonic-enabled applications for contact tracing. Contact tracing helps identify individuals who have had contact with infected people, places or objects. Governments have utilized various mobile applications like TraceTogether (Singapore), Aarogya Setu (India) and many others to track and curb the spread of coronavirus. The study also discusses different architectures designed by various researchers and scientists to help track and trace the movement of people.

11.3.8. Tracking and tracing suspected cases

Rajasekar (2021) designed an IoT-based architecture to automatically track and trace the movement of people using RFID and their mobile phones and to identify various points of contact. This framework would allow individuals who contact exposed people (knowingly or unknowingly) to follow quarantine or treatment procedures for both parties (if infected). The proposed system would help the government to curb the spread of infection during this pandemic. This model will help concerned authorities take necessary actions on the ignored suspected cases to prevent further transmission of Covid-19.

11.3.9. Anonymity preserving contact tracing model

Garg et al. (2020) proposed a novel IoT-based privacy contact tracing architecture. The framework utilized RFID proof-of-concept for moving contacts to identify flagged peoples, places or objects. The proposed model presented three blockchain contact tracing prototypes and delivered notifications to help achieve mass isolation while preserving individual privacy. This model helped understand human connectivity to enable policymakers to develop effective policies for future pandemics.

11.3.10. Cognitive radio-based IoT architecture

Chandrasekaran et al. (2020) proposed a cognitive-based IoT architecture to monitor and track patients, for better treatment and control, without spreading the infection to others. The proposed model could help governments devise better policies and provide online consultations based on a systematic database that predicts disease activity. This proposed technology is promising for rapid diagnosis and dynamic monitoring.

11.3.11. Analyzing reasons for the outbreak

Ramallo-González et al. (2021) designed a four-layer IoT-based architecture to help analyze reasons for the outbreak of Covid-19. IoT sensors collected patients’ body parameters and analyzed them using the CIoTVID model proposed in this study. The study helped policymakers, individuals and hospitals to fight against the propagation of Covid-19.

11.3.12. Analyzing Covid-19 cases using disruptive technology

Abdel-Basset et al. (2020) proposed an intelligent framework using IoT and IoMT based technology to diagnose and prevent the spread of Covid-19, especially in healthcare facilities like hospitals, isolation wards and Covid centers. The architecture utilized effective medical sensors in hospitals and at home to monitor the health of and diagnose disease severity in a person showing symptoms, using data collected from sensors. This proposed framework utilizes the most disruptive technologies currently available to limit the spread of Covid-19.

11.3.13. Post-Covid applications

The ongoing pandemic has made us realize that the world is not equipped to fight this situation. The architectures, as mentioned earlier, are designed to fight the current condition of Covid-19, but what about post-Covid? What steps can be taken to ensure our safety in the future?

11.3.13.1. Automated health monitoring and surveillance

Vedaei et al. (2020) and Tiwari and Abraham (2020) proposed an IoT-based healthcare and monitoring system for future pandemic situations. The three-layer framework designed allowed individuals to track their health parameters and monitor them through the designed mobile application. The COVID-SAFE framework, developed by researchers, could minimize the risk of coronavirus exposure.

11.3.13.2. Extensive use of IoT technology

Nasajpour et al. (2020) discuss IoT devices for early diagnosis, quarantine time and recovery. The study mentions the use of wearables, robots, drones, IoT buttons and smartphone applications. For early diagnosis, wearables like smart helmets, thermometers and glasses, along with mobile applications such as ncapp, stopcorona and mobiledetect, are used. For quarantine time, disinfectant drones, medical delivery drones with robots such as telerobots, collaborative robots and social robots were employed. Many mobile apps, namely social monitoring, selfie app, the stayhomesafe and civitas apps, were used. Lastly, wearables like the easy band, proximity band, surveillance, announcement and multipurpose drones after the recovery period were used. Various smartphone apps such as Aarogya Setu, TraceTogether and Hamagon were used by governments to track the movement of the general public.

11.4. Semantic Web applications for Covid-19

SW technologies are still under development, but with these technologies’ help, categorizing available patients’ data (present online) has been done effectively (Jayachandran et al. 2020; Nikiforova et al. 2022; Tiwari et al. 2022). SW applications try to make sense of a vast amount of data on the Cloud or Internet. It tries to define connections or relationships between various data and make it meaningful for machines and humans. SW technologies consist of knowledge graphs and ontology-based applications to divide data into proper categories and sub-categories based on the relationship or connection defined as per the requirements. SW, otherwise known as Web 3.0, is extensively used by researchers and scientists to design a link between previous research and ongoing research. The ontology-based approach has helped scientists to discover treatments, vaccines, repurpose drugs, etc., and even find cures for diseases that were thought untreatable, using the data present from previous clinical trials. How SW technology can be proved helpful for fighting against current and future pandemics is discussed below.

11.4.1. Ontological approach for drug development

Jayachandran et al. (2020) discuss how various research related to drug development at the time of outbreak of Covid could be made valid using ontological approaches. These ontology-based applications can help in assisting pharmacology, designing vaccines, medicine preparation, etc., using databases such as Gene Ontology (GO), Infectious Disease Ontology (IDO) and Vaccine Ontology (VO). These databases are readily available for all, accelerate drug development, target new drugs and vaccine development and are more reliable, faster and cheaper than traditional techniques. These ontological approaches focus more on gene and protein interaction in hosts and pathogens, which has also turned out to be superior to traditional techniques.

11.4.2. Early detection and diagnosis

Oyelade et al. (2020) proposed a Case-Based Reasoning (CBR) ontological approach to overcome the limitations of previous models. The feature extraction ontology and mapping, semantic and feature-based mathematical similarity computation and CBR framework for detection and classification of suspected cases were achieved effectively using the proposed model. The data used in this study focus on using data from recovered or infected cases rather than assuming parameter values. After testing 71 patients (67 adults and four children) and comparing them using the fuzzy-based approach, the result shows a significant improvement in classification and detection.

11.4.3. Knowledge-based pre-diagnosis system

Çelik Ertuğrul and Çelik Ulusoy (2021) proposed a rule-based expert system for monitoring and diagnosing cases using smartphones. When tested with 169 positive patients, this knowledge-based system showed similar results as the RT-PCR test for symptomatic cases. For asymptomatic cases, suggestions given by the proposed system showed a similar result as a healthcare expert, validating its effectiveness. This ontology-based system, OntCov19, can be used in places where experts are not readily available to diagnose the patient. Pre-diagnosis can be done using an individual’s phone without the assistance of an expert. This diagnosis is made online, and with expert data and data entered by a user, the system predicts the Covid status of the user.

11.4.4. Semantic-based searching for online learning resources

The necessity of online learning was realized during times such as those we are facing right now. Online learning went from just an alternative source to a mainstream learning solution for students and industries. Hence the need for a standard database system arose. Dien et al. (2020) proposed a semantic-based searching in learning resources. The proposed application included an ontology-based representation of learning resources. The searched queries were pre-processed using Support Vector Machine (SVM) to narrow down the search space, and the resultant questions sent to the appropriate ontology showed the required lectures. When tested with IT lectures, the proposed model showed a consistent and better solution than traditional search solutions.

11.4.5. Ontology-based physiological monitoring of students

Bolock et al. (2021) proposed an ontological framework for psychological monitoring of education during the ongoing pandemic. The proposed framework extends standard psychology-driven ontology, CCOnto, ascribing human behavior based on a situation to psychological states. Based on psychological theories and concepts, the CCOnto ontology automatically categorizes university students according to learning, worrying, mental health and much more. This framework targets the psychological aspects of Covid-19 on students.

11.4.6. Analysis of clinical trials

The exponential spread of Covid-19 forced scientists and researchers to conduct clinical trials at an unprecedented rate to curb the spread as soon as possible. This left scientists with repeated trials, which led to wastage of resources, which posed a big problem. Id (2020) proposed an ontology-based application interface that showed all the research related to Covid-19 be present on ClinicalTrials.gov. The study used Medical Subject Heading (MeSH) and Human Phenology Ontology (HPO) terms to categorize data and make them available on covidresearchtrials.com. Another study (Visweswaran et al. 2021) proposed an ontology-based Covid-19 application in the National Accrual to Clinical Trials (ACT) network using Electronic Health Records (EHR) of 14.5 million patients. This ontology uses the data harmonization technique and contains over 50,000 concepts related to Covid-19 trails.

11.4.7. Data annotation of EHRs

Keloth et al. (2020) proposed an ontology-based application, Initial Covid Interface Terminology (ICIT) and CIT_v0 – an extension of CIDO – to annotate a large amount of patient data. They designed a concatenation and anchoring approach to extract or mine essential data from clinical texts. The organized database helped extract data about signs and symptoms of Covid-19, and using concept mining with ML techniques opens the door for future research. Fries et al. (2021) proposed a framework, Trove, for weekly supervised entity classification of EHRs. The system uses medical ontologies and expert-generated rules to outperform the traditional method of creating manually-labeled training data. Trove analyzed the record of patients infected from Covid-19 presenting symptoms and risk factors.

11.4.8. Disease pattern study

Rawal et al. (2020) proposed a description logic-based ontology to study the disease patterns of Covid-19. The system removes ambiguity around the spread of Covid-19 and provides proper reasoning to facts. Description Logic (DL) is used to understand the spread, treatment and diagnosis, related to the family of viruses. A SW application is designed by converting the above information into ontological-based entities. The system proposes a solution to investigate the current pandemic to study the root cause of the spread and find disease patterns to help policymakers and governments effectively fight this situation.

11.4.9. Surveillance in primary care

To ensure transparency and consistency, de Lusignan et al. (2020) proposed an ontology application for surveillance of Covid-19 patients. The study is an extension of the RCGP Research and Surveillance Center (RSC) to monitor the situation of the ongoing pandemic. The proposed application studied the course of the current pandemic and showed the spread and effects of measures. The ontology application was developed using a three-step method, and a Covid identification algorithm was developed. The resultant application was able to identify 19,115 definite, 5226 probable and 74,293 possible cases in the RCGP sentinel network. The proposed system can be implemented for primary care, public health, virology, clinical research and informatics.

11.4.10. Performance assessment of healthcare services

Sayeb et al. (2021) proposed a unique semantic-based application to assess the performance of healthcare services provided in the wake of Covid-19. The study implemented an ontology called the Covid-19 Crisis Health Care Ontology Information System (C3-HIS) to support healthcare service management. The ontology responds quickly and effectively by providing a clear definition of healthcare services available. Patients were directed to specific healthcare services as per the competence and performance of the service available. For Covid-19 patients, the proposed system helped monitor a patient’s condition and provide healthcare services accordingly. Researchers proposed a web-based software solution to illustrate the effectiveness of the designed system and gather the appropriate healthcare workers for critical situations.

11.4.11. Vaccination drives and rollout strategies

Sreeganga et al. (2021) proposed an ontological-based approach to tackle the limitations of vaccine rollout strategies after looking at the system of the USA and India. Many roadblocks, such as large population, the health infrastructure, vaccine hesitancy, adequate supply, distribution, variation in demand, production capacity, regulatory issues, labor, decentralization for administrating the vaccine and science communication, have posed severe problems. The proposed system tries to solve these problems by implementing a supportive framework for vaccine rollout strategies. The study focuses on the vaccine rollout strategies of two countries to visualize the similarities and barriers in developing and developed countries. The unique design was mapped onto ontology and various monad maps and theme maps were generated for comparison. The study visualizes the gaps and barriers in their approach and proposes solutions to overcome them and make them more effective.

11.5. Limitations and challenges of IoT and SW models

Both IoT and SW models have some shortcomings when implemented for Covid-19. When it comes to IoT architecture, the most critical challenges for the current pandemic are as follows: security, privacy concerns, system integrity, sensors for wearables, unobstructed sensing and continuous sharing of information, data connection and transfer issues (Vedaei et al. 2020). The IoT frameworks proposed by researchers and scientists tried to overcome some of the issues but still need a lot of iterations for their work to improve the models. Researchers designed various IoT architectures, either by ignoring the problems entirely or by assuming some of the initial parameters to enhance the performance of the models with limitations. These models can be improved using more advanced algorithms and better accuracy devices in future implementations. SW technology is still a very new area of study. However, it has received serious attention from researchers and scientists due to its capabilities. The studies have shown that the use of SW technologies in various studies has increased exponentially in the last decade. The SW applications are limited in number and are still under development, but they are not immune to shortcomings and challenges. The interoperability issues, absence of generalized and standard databases, capturing data in a standard form and a connection between various databases (Bauer et al. 2021) are significant limitations of these models. Various researchers tried to decrease the effect of these shortcomings by utilizing standard ontology models designed explicitly for Covid-19, which included other related information from previous ontologies (on a need basis). Researchers also tried to give solutions for challenges related to efficiency, cost, largescale usage, availability, distribution and many more in order to tackle this pandemic situation as early as possible.

11.6. Discussion

IoT and SW applications have provided a big push for the fight against the new coronavirus (Covid-19) and have given people a chance to fight head-on. IoT architecture has provided the necessary help to save countless lives by providing continuous real-time monitoring, early identification, diagnosis, classification, tracking and tracing suspected cases and providing the appropriate solutions to post-pandemic situations. The models mentioned above helped governments to devise necessary guidelines and rules for people to cope with prolonged lockdown situations, stress created from the professional environment, work-from-home setups and have allowed better availability of healthcare solutions in their own homes. SW applications have helped researchers to recognize disease patterns and pre-diagnosis, early detection and treatment of Covid-19 (measures taken in the case of early detection) and people’s psychological monitoring. Moreover, they are utilizing the data from previous clinical trials, data annotation, drug discovery, surveillance and vaccine rollout strategies to assist in developing new and more efficient models to fight the current pandemic. The proposed frameworks helped policymakers to regulate effective procedures to minimize the spread of Covid-19 and navigate through the lockdown procedures, quarantine periods, global panic and distribution of vaccines.

11.7. Conclusion

This chapter sheds light on frameworks and architecture designed with the help of IoT and SW applications against the biggest fight of this century: the fight against Covid-19. The ongoing pandemic has made humans realize the extent of the loopholes present in our healthcare systems and how poorly our healthcare institutions can handle this situation. Nevertheless, scientists and researchers have learned a lot from this ongoing pandemic and have utilized state-of-the-art architectures to ensure our survival and make us ready for any future pandemic (although it may not be as vast as Covid-19 turned out to be). However, looking at the positive side, the revolution in IoT has been a boom in this challenging time, as Covid-19 forced scientists and healthcare management to implement innovative architectures to provide essential healthcare services to people. In addition, SW technologies are now on the right path to become the application technologies for tomorrow and assist humans and machines in understanding data better than before. Furthermore, the amalgamation of IoT and SW in future architecture would provide a more robust and secure model to handle this pandemic situation. Finally, this chapter could be referred to by young researchers and scientists who would like to contribute to this fight against an invisible force – Covid-19.

11.8. References

  1. Abdel-Basset, M., Chang, V., Nabeeh, N.A. (2020). An intelligent framework using disruptive technologies for COVID-19 analysis. Technological Forecasting and Social Change, 163. Available at: https://doi.org/10.1016/j.techfore.2020.120431.
  2. Ashokkumar, K., Naren, J., Rakshanasri, S.L., Ganesan, V. (2020). Ontological framework for analyzing student’s emotional behavior performance enhancement using Fuzzy Logic. International Journal of Psychosocial Rehabilitation, 24, 155–164.
  3. Bauer, D.C., Metke-Jimenez, A., Maurer-Stroh, S., Tiruvayipati, S., Wilson, L.O.W., Jain, Y., Perrin, A., Ebrill, K., Hansen, D.P., Vasan, S.S. (2021). Interoperable medical data: The missing link for understanding COVID-19. Transbound and Emerging Diseases, 68(4), 1753–1760.
  4. Bolock, A.E., Abdennadher, S., Herbert, C. (2021). An ontology-based framework for psychological monitoring in education during the COVID-19 pandemic. Frontiers in Psychology, 12(July), 1–16.
  5. Çelik Ertuğrul, D. and Çelik Ulusoy, D. (2021). A knowledge-based self-pre-diagnosis system to predict Covid-19 in smartphone users using personal data and observed symptoms. Expert Systems. Available at: https://doi.org/10.1111/exsy.12716.
  6. Chandrasekaran, B. and Fernandes, S. (2020). Since January 2020 Elsevier has created a COVID-19 resource centre with free information in English and Mandarin on the novel coronavirus. The COVID-19 resource centre is hosted on Elsevier Connect, the company’s public news and information website. Diabetes & Metabolic Syndrome, 14(4), 337–339.
  7. Dien, T.T., Van Trung, L., Thai-Nghe, N. (2020). An approach for semantic-based searching in learning resources. Proceedings of the 2020 12th International Conference on Knowledge and Systems Engineering, KSE 2020. Available at: https://doi.org/10.1109/KSE50997.2020.9287798.
  8. Dogan, O., Tiwari, S., Jabbar, M.A., Guggari, S. (2021). A systematic review on AI/ML approaches against COVID-19 outbreak. Complex & Intelligent Systems, 7(5), 2655–2678.
  9. Filho, I.D.M.B., Aquino, G., Malaquias, R.S., Girao, G., Melo, S.R.M. (2021). An IoT-based healthcare platform for patients in ICU beds during the COVID-19 outbreak. IEEE Access, 9, 27262–27277.
  10. Firouzi, F., Farahani, B., Daneshmand, M., Grise, K., Song, J., Saracco, R., Wang, L.L., Lo, K., Angelov, P., Soares, E. et al. (2021). Harnessing the power of smart and connected health to tackle COVID-19: IoT, AI, robotics, and blockchain for a better world. IEEE Internet of Things Journal, 8(16), 12826–12846. Available at: https://doi.org/10.1109/JIOT.2021.3073904.
  11. Fries, J.A., Steinberg, E., Khattar, S., Fleming, S.L., Posada, J., Callahan, A., Shah, N.H. (2021). Ontology-driven weak supervision for clinical entity classification in electronic health records. Nature Communications, 12(1). Available at: https://doi.org/10.1038/s41467-021-22328-4.
  12. Ganesan, V., Naren, J., Varun, V. (2019). Opinion mining with real time ontology streaming data. International Journal of Psychosocial Rehabilitation, 23, 346–357.
  13. Garg, L., Chukwu, E., Nasser, N., Chakraborty, C., Garg, G. (2020). Anonymity preserving IoT-based COVID-19 and other infectious disease contact tracing model. IEEE Access, 8, 159402–159414.
  14. He, Y., Yu, H., Ong, E., Wang, Y., Liu, Y., Huffman, A., Huang, H.-H., Beverley, J., Hur, J., Yang, X. et al. (2020). CIDO, a community-based ontology for coronavirus disease knowledge and data integration, sharing, and analysis. Scientific Data, 7(1), 1–5. Available at: https://doi.org/10.1038/s41597-020-0523-6.
  15. Id, S.A. (2020). Analysis of COVID-19 clinical trials: A data-driven, ontology-based, and natural language [Online]. Available at: https://doi.org/10.1371/journal.pone.0239694.
  16. Jayachandran, S.K. and Anusuyadevi, M. (2020). Decoding information on COVID–19: Ontological approach towards design possible therapeutics. Informatics in Medicine Unlocked, 22, 100486.
  17. Kate, A.V., Balakrishnan, H., Naren, J. (2014). Ontology mining in Molecular Biology domain (Lac Operon problem). Proceedings of IEEE International Conference on Computer Communication and Systems ICCCS14. Available at: 10.1109/ICCCS.2014. 7068157.
  18. Keloth, V.K., Zhou, S., Lindemann, L., Elhanan, G., Einstein, A.J., Geller, J., Perl, Y. (2020). Mining concepts for a COVID interface terminology for annotation of EHRs. Proceedings of the 2020 IEEE International Conference on Big Data, Big Data 2020. Available at: https://doi.org/10.1109/BigData50022.2020.9377981.
  19. Kolhar, M., Al-Turjman, F., Alameen, A., Abualhaj, M.M. (2020). A three layered decentralized IoT biometric architecture for city lockdown during Covid-19 outbreak. IEEE Access, 8, 163608–163617.
  20. de Lusignan, S., Liyanage, H., McGagh, D., Jani, B.D., Bauwens, J., Byford, R., Evans, D., Fahey, T., Greenhalgh, T., Jones, N. et al. (2020). COVID-19 surveillance in a primary care sentinel network: In-pandemic development of an application ontology. JMIR Public Health and Surveillance, 6(4). Available at: https://doi.org/10.2196/21434.
  21. Mohanraj, I. and Naren, J. (2016). The application of semantic web on agricultural domain – A state of art survey. 10th INDIACom; 2016 3rd International Conference on Computing for Sustainable Global Development, INDIACom, New Delhi, 16–18 March.
  22. Naren, J., Raja, R.J., Sannidhi, N., Ganesan, V. (2019). An investigation on ontology based fuzzy semantic information retrieval. International Journal of Psychosocial Rehabilitation, 23, 377–384.
  23. Nasajpour, M., Pouriyeh, S., Parizi, R.M., Dorodchi, M., Valero, M., Arabnia, H.R. (2020). Internet of Things for current COVID-19 and future pandemics: An exploratory study. J. Healthc. Inform., 4, 325–364.
  24. Nikiforova, A., Tiwari, S., Rovite, V., Klovins, J., Kante, N. (2022). Evaluation and visualization of healthcare semantic models. Evaluation, 323, 91773–91775.
  25. Otoom, M., Otoum, N., Alzubaidi, M.A., Etoom, Y. (2020). An IoT-based framework for early identification and monitoring of COVID-19 cases. Biomedical Signal Processing and Control, 62(2020), 102149.
  26. Oyelade, O.N. and Ezugwu, A.E. (2020). A case-based reasoning framework for early detection and diagnosis of novel coronavirus. Informatics in Medicine Unlocked, 20(2020), 100395.
  27. Paganelli, A.I., Velmovitsky, P.E., Miranda, P., Branco, A., Alencar, P., Cowan, D., Endler, M., Morita, P.P. (2021). A conceptual IoT-based early-warning architecture for remote monitoring of COVID-19 patients in wards and at home. Internet of Things, 40, 100399.
  28. Rajasekar, S.J.S. (2021). An enhanced IoT based tracing and tracking model for COVID-19 cases. SN Computer Science, 2(1), 2–5.
  29. Ramallo-González, A.P., González-Vidal, A., Skarmeta, A.F. (2021). Ciotvid: Towards an open IoT-platform for infective pandemic diseases such as COVID-19. Sensors (Switzerland), 21(2), 1–13.
  30. Rathee, G., Garg, S., Kaddoum, G., Wu, Y., Dushantha, D.N., Alamri, A. (2021). ANN assisted-IoT enabled COVID-19 patient monitoring. IEEE Access, 9, 42483–42492.
  31. Rawal, R., Goel, K., Gupta, C. (2020). COVID-19: Disease pattern study based on Semantic-Web approach using description logic. 2020 IEEE International Conference for Innovation in Technology, INOCON 2020, Bangalore, 6–8 November. Available at: https://doi.org/10.1109/INOCON50539.2020.9298278.
  32. Sayeb, Y., Jebri, M., Ghezala, H.B. (2021). Managing COVID-19 crisis using C3HIS ontology. Procedia Comput. Sci., 181, 1114–1121.
  33. Sreeganga, S.D., Chandra, A., Ramaprasad, A. (2021). Ontological analysis of Covid-19 vaccine roll out strategies: A comparison of India and the United States of America. International Journal of Environmental Research and Public Health, 18(14). Available at: https://doi.org/10.3390/ijerph18147483.
  34. Swayamsiddha, S. and Mohanty, C. (2020). Application of cognitive Internet of Medical Things for COVID-19 pandemic. Diabetes Metab. Syndr., 214(5), 911–915.
  35. Tiwari, S. and Abraham, A. (2020). Semantic assessment of smart healthcare ontology. International Journal of Web Information Systems, 16(4), 475–491. Available at: https://doi.org/10.1108/IJWIS-05-2020-0027.
  36. Tiwari, S., Ortiz-Rodriguez, O., Jabbar, M.A. (2022). Semantic models in IoT and eHealth applications. Elsevier, 380, 91773–91775.
  37. Vedaei, S.S., Fotovvat, A., Mohebbian, M.R., Rahman, G.M.E., Wahid, K.A., Babyn, P., Marateb, H.R., Mansourian, M., Sami, R. (2020). COVID-SAFE: An IoT-based system for automated health monitoring and surveillance in post-pandemic life. IEEE Access, 8, 188538–188551.
  38. Visweswaran, S., Samayamuthu, M.J., Morris, M., Weber, G.M., MacFadden, D., Trevvett, P., Klann, J.G., Gainer, V.S., Benoit, B., Murphy, S.N. et al. (2021). Development of a Coronavirus Disease 2019 (COVID-19) application ontology for the Accrual to Clinical Trials (ACT) network. JAMIA Open, 4(2), 1–6.

Note

  1. Chapter written by ANURAG and Naren JEEVA.
..................Content has been hidden....................

You can't read the all page of ebook, please click here login for view all page.
Reset
3.141.200.3