A distributed e-health management model with edge computing in healthcare framework

Автор: Majumder D., Kumar S.M.

Журнал: Cardiometry @cardiometry

Рубрика: Original research

Статья в выпуске: 22, 2022 года.

Бесплатный доступ

Edge healthcare system is recognized as an acceptable paradigm for resolving this problem. The IoMT is divided into two sub-networks - intraWBANs and beyond-WBANs - based on the physical bonds of WBANs. Given the features of the healthcare systems, medical emergency, AoI and power depreciation are the prices of MUs. Intra-WBANs, a cooperative game shapes the wireless channel resource allocation problem. The Nash negotiation solution is used to get the unique optimum point in Pareto. MUs are regarded reasonable and perhaps egoistic in non-WBANs. Another non-cooperative activity is therefore developed to reduce overall system costs. The assessments of the performance of the system-wide cost and of the number of MUs gaining from edge computer systems are done to illustrate the success of our solution. Finally, for further effort, numerous barriers to research and open questions are highlighted.

Еще

Smart healthcare, artificial intelligence, edge computing, fog computing

Короткий адрес: https://sciup.org/148324627

IDR: 148324627   |   DOI: 10.18137/cardiometry.2022.22.444455

Текст научной статьи A distributed e-health management model with edge computing in healthcare framework

Darpan Majumder, S. Mohan Kumar. A distributed e-health management model with edge computing in healthcare framework. Cardiometry; Issue 22; May 2022; p. 444-455; DOI: 10.18137/cardiometry.2022.22.444455; Available from:

The increasing burden of clinical illnesses and ageing populations mean that illness prevention is an essential healthcare necessity. Avoidance is not only described as a means of maintaining a better environment but also a technique of maintaining severe circumstances by means of regular exercises, nutrition management and periodic prevention. A growing number of chronic diseases and lack of treatment must be addressed by the future health care industry to meet patient needs[1]. The need of rapid, thorough and exact eHealth and smart health care integrating many forms of physical and medical information to identify the virus has been underlined lately by COVId-19.

The integration of modern technology in safeguarding policies and procedures can assist to identify possible health issues quickly and enable suitable actions such as simultaneous monitoring of treatments and the preparation of fresh evaluations to be planned. In 2019, the global intelligent health market is projected to reach USD 143,6 billion, an increase of 16,2% on average between 2020 and 2027. Smart healthcare is the framework for health systems that use technologies like wearable devices, IoT and the mobile Internet to enter health data and link individuals, resources and organizations. Smart healthcare means that we can conveniently access medical documents.

Various players, including medical practitioners, personnel, hospitals and research institutions are involved in intelligent medical therapy. It includes a dynamic environment with various aspects such as illness prevention and detection, evaluation and evaluation, healthcare administration, patient decision-making and medical research. Smart health services include automated networks such as IoT, mobile webs, cloud computing, big data, 5G but also artificial intelligence (AI), as well as advanced biotechnology.

With computer technology, automation and automated signal processing, sensors were increasingly integrated in various systems of our life. Data generated by sensors can assist physicians to identify crucial circumstances quicker and more reliably and can help patients learn more about their symptoms and potential treatments. Intrusive and non-inva-sive equipment – from gadgets to temperature reading, to dialysis process control – give patients and the health sector with personal and multimedia data and support. Signals such as electrocardiogram (ECGs), electroencéphalogram (EEGs), electroglotonograph (EGGs), Electroaculogram (EOGs), Electromyogram (EMGs), body’s temp, blood pressure (BP), as well as heart rate arrive in the form of 1D and 2D signals. Medical signals are also given. These medical signals can be used to monitor a patient with a health care monitoring system.

The IoT begins to link physicians and consumers slowly with the healthcare system. Echoes, BP readings, glucose sensors, EEGs, ECGs and more continue to investigate the well-being of individuals. Critical circumstances such as follow-up visits to doctors. Many health centres started using smart beds to detect the motion of a patient and adapt the bed to the right corner and position automatically. The Medical Things Internet (IoMT) pertains to the IoT utilised for medical applications. The IoMT can play an essential role in the development of a fully integrated health environment.

In rare cases, depending on only one form of medical information may not comply with the diagnostic standards of a certain condition. Multimodal medical signals for improved diagnoses can thus be used. Communications can be merged at several levels, such as the level of data, the level of function and classi-fication[3]. Many problems may arise while fusing signals. Signaling from several sensors, data caching, feature standardization, and classification fusion comprise these challenges[4]. Together with advancement of Machine learning and artificial intelligence (ML) techniques in the field of deep learning (DL) as well as wireless local area network technologies (wLANs)[5] intelligent health care has been transformed to provide patient and stakeholder satisfaction.

Due to the high computational performance of these technologies, high data volume, the accommodation of several terminal units and the addition of 5G and beyond 5G wireless technology, the medical industry has been able to manage numerous medical indicators from the same user – which at the time increase disease detection and prediction accuracy. Healthcare now employs IT to create intelligent and accurate treatment solutions that accelerate health diagnosis. Smart frameworks and automatic diagnostic medical diagnostic systems provide services in many contexts and situations such as hospitals, workplaces and homes, and transportation aids, which reduce the cost of doctor visits substantially and improve patient care overall[1].

There is a requirement for Intelligent health as the number of IoT healthcare devices deployed globally estimates to have reached over 162 billion as of 2020, IoT sensors and application for general healthcare having drastically changed the approach to health-care[1]. Smart IoT sensors wearable and embedded may gather data on the basis of user behaviors, mobility, and device use in real-time. Such samples are gathered and processed with ML or DL techniques to disclose hidden patterns in the data as well as track users to make a diagnosis and warn against critical condition. Cloud-based frameworks, which frequently use Big Data techniques, can achieve reliable and correct results for general IoT applications, and require quick reactions[2]–[4].

This data can be collected and processed using DL techniques. However, cloud-based implementations can have a major negative impact when there is a network failure or bandwidth delay, and this can result

ф : Cooperative bandwidth allocation (2) ‘ Broadcast offloading information

(2D : Decentralized offloading decision (4) ■ Send medical analysis results to hospital

Figure 1. General architecture of Edge based healthcare system

in health emergencies or even life loss[5] for critical medical ioT-based applications that require greater accuracy, reliable responses and robust behaviours. There has recently been a rising interest in advanced cloud architectures using cutting edge technology and cloud technology. The main aim of the combination is to maximise advantages in data gathering, interpretation, processing and analysis by the edge and fog computing capacities [6].

Such designs provide potential solutions to improve dependability and adaptability in healthcare dispersed applications, as smart device, sensor mapping and resource management are major concerns of intelligent IoT healthcare systems[5]. The objective of the study is therefore to show the advantages of edge computing for smart solutions for the distribution of smart IoT healthcare sensors and analysis. Edge intelligence may be utilized on intelligent appliances with sensors on them and on appliances on gateways near intelligent sensors: smart wearable equipment with sensors, such as smartphones and smart watch systems and gateway equipment such as micro-constrators are edge nodes. Fog computing may be deployed on different networks and incorporate powerful, bigger equipment like personal computers and smart sensor devices that are more remotely located.

Close proximity of users to sensors is frequently utilised for providing health services with better availability, less latency, and local awareness [7], both edge and fog computing architectures [5]. Many academics have suggested strategies based on hierarchical computing for the distribution and allocation of inference-based jobs across border and fog nodes to use such techniques as DL and ML, which may greatly enhance computing resources and computational capacities of edges. As the Internet of Things (IoT) develops rapidly, various museums and equipment for all-embrace services are connected. An Internet of Medical Things (IoMT) is an important application[1].

In current culture, MUs are hard on time for medical exams which encourage the progression of chronic illnesses, suffering from the dreadful stress of their everyday lives. Furthermore, the shortfall in wireless and local computer channels cannot meet the transmission requirements of explosive MUs and hinder future development of IoMTs. IoMT combines Wireless Body Area Networks into IoTs to overcome the hurdles. IoMT is possible to implement remote surveillance by the deployment of body sensors on MUs through extensive networks of health care. Unlike conventional therapy, IoMT enables MUs to travel freely without being restricted.

Despite the fact that different body sensors can monitor all-embracing medical data, explosive MUs – particularly people – are overwhelming existing healthcare facilities because of economic growth and population ageing. For medical testing, local computer resources are not adequate, given by mobile devices, as they are time-sensitive. The development of edge computing is really a viable paradigm to address this shortcoming. The burdens of edge computer and the latent workflow can be considerably reduced if the raw data monitored is offloaded to the edge servers.

In general, MUs concern a lot about diseases that might have significant repercussions and hospitals examine MUs all day long to prevent information which is also known as hunger for information from becoming obsolete. There are therefore numerous problems facing the health system. First, severe illnesses should be allocated high transmission priorities. Secondly, all sorts of data collected, including general illnesses, have to be updated on time in order to prevent hungering and concealed threats from information. Thirdly, the maximum displacement of hardware in the healthcare system must be considered without a constant power source, including body sensors, local devices, and edge servers.

This article builds an edge computer-based IoMT health system. The considered IoMT is devised into two sub-networks, namely intra-WBAN and outside WBANs, on the basis of the physical boundaries of WBANs. Local devices have been designated as a gateway and connect between two subnetworks with both the routing and the calculation capacities. In intra-WBAN, local equipment assigns body sensor transmission priority by managing the bandwidth in the Multiple Access orthogonal frequency division. The Nash negotiation solution is used to establish the best timetable. MUs opt to examine the raw observed data in addition to WBANs or to download it to edge servers. By using the Multiple Access Non-Orthogo-nal (NOMA) technology, the dissipation of energy and the suffering of interference by the channel multiplexing are compensated for. 5G communications use millimeter waves, and the transmission frequency is high, as opposed to cell communications. There are a large number of MUs split geographically, allowing a few MUs to download every edge computing server.

Since MUs are practical logical, a non-cooperative design was influenced.

Список литературы A distributed e-health management model with edge computing in healthcare framework

  • Alam, H. Malik, M. I. Khan, T. Pardy, A. Kuusik, and Y. Le Moullec, ‘‘A survey on the roles of communication technologies in IoT-based personalized healthcare applications,’’ IEEE Access, vol. 6, pp. 36611–36631, 2018.
  • Astrin, IEEE Standard for Local and Metropolitan Area Networks Part 15.6: Wireless Body Area Networks, IEEE Standard 802.15. 6, 2012.
  • Chen, W. Li, Y. Hao, Y. Qian, and I. Humar, ‘‘Edge cognitive computing based smart healthcare system,’’ Future Gener. Comput. Syst., vol. 86, pp. 403–411, Sep. 2018.
  • Dai, I. Spasic, B. Meyer, S. Chapman, and F. Andres, ‘‘Machine learning on mobile: An on-device inference app for skin cancer detection,’’ in Proc. 4th Int. Conf. Fog Mobile Edge Comput. (FMEC), Jun. 2019, pp. 301–305.
  • Feng et al., “Optimal Haptic Communications over Nanonetworks for E-Health Systems,” IEEE Trans. Industrial Informatics, vol. 15, no. 5, 2019, pp. 3016–27.
  • Greco, P. Ritrovato, and F. Xhafa, ‘‘An edge-stream computing infrastructure for real-time analysis of wearable sensors data,’’ Future Gener. Comput. Syst., vol. 93, pp. 515–528, Apr. 2019.
  • Gu et al., “Cost Efficient Resource Management in Fog Computing Supported Medical Cyber-Physical System,” IEEE Trans. Emerging Topics in Computing, vol. 5, no. 1, 2015, pp. 108–19.
  • Hartmann, U. S. Hashmi, and A. Imran, ‘‘Edge computing in smart health care systems: Review, challenges, and research directions,’’ Trans. Emerg. Telecommun Technol., early access, Aug. 2019, Art. no. e3710, doi: 10.1002/ett.3710.
  • Hegde, P. B. Suresha, J. Zelko, Z. Jiang, R. Kamaleswaran, M. A. Reyna, and G. D. Clifford, ‘‘Autotriage- an open source edge computing raspberry pi-based clinical screening system,’’ MedRxiv, to be published, doi: 10.1101/2020.04.09.20059840.
  • Kaur and A. Jasuja, ‘‘Health monitoring based on IoT using raspberry PI,’’ in Proc. Int. Conf. Comput., Commun. Autom. (ICCCA), May 2017, pp. 1335–1340.
  • Klonoff, ‘‘Fog computing and edge computing architectures for processing data from diabetes devices connected to the medical Internet of Things,’’ J. Diabetes Sci. Technol., vol. 11, no. 4, pp. 647–652, Jul. 2017.
  • Lin, C. Li, D. Tian, A. Ghoneim, M. S. Hossain, and S. U. Amin, ‘‘Artificial-intelligence-based data analytics for cognitive communication in heterogeneous wireless networks,’’ IEEE Wireless Commun., vol. 26, no. 3, pp. 83–89, Jun. 2019.
  • Liu, Y. Cao, Y. Luo, G. Chen, V. Vokkarane, M. Yunsheng, S. Chen, and P. Hou, ‘‘A new deep learning- based food recognition system for dietary assessment on an edge computing service infrastructure,’’ IEEE Trans. Services Comput., vol. 11, no. 2, pp. 249–261, Mar. 2018.
  • Miraz, M. Ali, P. S. Excell, and R. Picking, ‘‘A review on Internet of Things (IoT), Internet of everything (IoE) and Internet of nano things (IoNT),’’ in Proc. Internet Technol. Appl. (ITA), Sep. 2015, pp. 219–224.
  • Pace et al., “An Edge-Based Architecture to Support Efficient Applications for Healthcare Industry 4.0,” IEEE Trans. Industrial Informatics, vol. 15, no. 1, 2018, pp. 481–89.
  • Pazienza, G. Polimeno, F. Vitulano, and Y. Maruccia, ‘‘Towards a digital future: An innovative semantic IoT integrated platform for industry 4.0, healthcare, and territorial control,’’ in Proc. IEEE Int. Conf. Syst., Man Cybern. (SMC), Oct. 2019, pp. 587–592.
  • Queralta, T. N. Gia, H. Tenhunen, and T. Westerlund, ‘‘Edge-AI in LoRa-based health monitoring: Fall detection system with fog computing and LSTM recurrent neural networks,’’ in Proc. 42nd Int. Conf. Telecommun. Signal Process. (TSP), Jul. 2019, pp. 601–604.
  • Ram, B. Apduhan, and N. Shiratori, ‘‘A machine learning framework for edge computing to improve prediction accuracy in mobile health monitoring,’’ in Proc. Int. Conf. Comput. Sci. Appl., Cham, Switzerland: Springer, Jul. 2019, pp. 417–431.
  • Riazul Islam, D. Kwak, M. Humaun Kabir, M. Hossain, and K.-S. Kwak, ‘‘The Internet of Things for health care: A comprehensive survey,’’ IEEE Access, vol. 3, pp. 678–708, 2015.
  • Sareen, S. K. Gupta, and S. K. Sood, ‘‘An intelligent and secure system for predicting and preventing zika virus outbreak using fog computing,’’ Enterprise Inf. Syst., vol. 11, pp. 1–21, Jan. 2017.
  • Sood and I. Mahajan, ‘‘A fog-based healthcare framework for chikungunya,’’ IEEE Internet Things J., vol. 5, no. 2, pp. 794–801, Apr. 2018.
  • Wang, Y. Han, C. Wang, Q. Zhao, X. Chen, and M. Chen, ‘‘In-edge AI: Intelligentizing mobile edge computing, caching and communication by federated learning,’’ IEEE Netw., vol. 33, no. 5, pp. 156–165, Sep. 2019.
  • Yi et al., “Transmission Management of Delay-Sensitive Medical Packets in Beyond Wireless Body Area Networks: A Queueing Game Approach,” IEEE Trans. Mobile Computing, vol. 17, no. 9, 2018, pp. 2209–22.
  • Pattanaik, Balachandra, and S. Murugan. “Cascaded H-Bridge Seven Level Inverter using Carrier Phase Shifted PWM with Reduced DC sources.” International Journal of MC Square Scientific Research 9, no. 3 (2017): 30-39.
  • Murugan, S., Anjali Bhardwaj, and T. R. Ganeshbabu. “Object recognition based on empirical wavelet transform.” International Journal of MC Square Scientific Research 7, no. 1 (2015): 74-80.
  • Khan, Azizuddin, and Gyan Prakash. “Design and implementation of smart glass with voice detection capability to help visually impaired people.” International Journal of MC Square Scientific Research 9, no. 3 (2017): 54-59.
  • Prakash, Gyan, Bhaskar Vyas, and Venkata Reddy Kethu. “Secure & efficient audit service outsourcing for data integrity in clouds.” International Journal of MC Square Scientific Research 6, no. 1 (2014): 5-60.
Еще
Статья научная