This monograph is based on the Ph. Thesis of the author . Its goal is twofold: First, it presents most researchwork that has been done during his Ph. This work. A platform of an m-Health monitoring system based on a cloud computing technology which contained three main layers was proposed in [ 55 ]; the platform was presented in Figure 7.
The Cloud Storage and Multiple Tenants Access Control Layer is the backbone of the platform, which receives healthcare data collected by sensors such as BG and sphygmomanometers in daily activities. The authors reduced the cost of storing and managing data by adopting the cloud framework.
Koha online catalog › Details for: Pervasive Healthcare Computing
Moreover, a multiple tenant access control module between tenant database and shared databased is implemented to enhance the security and privacy of patient data. The Healthcare Data Annotation Layer solves data heterogeneity issue that is commonly happened during data processing. Because equipment varied by hospitals, generated data are often heterogeneous, which increases the complexity of automatic healthcare data sharing and comprehending between medical agencies.
The authors proposed an open Linked Life Data LLD sets to annotate personal healthcare data and integrate dispersed data in a patient-centric pattern for the cloud application. The Healthcare Data Analysis Layer analyses healthcare data stored in the cloud to assist in clinical decision making because similar historical data are valuable assets to make a treatment plan for a similar illness case.
As shown in Figure 7 , mining algorithms are implemented to induce clinic paths from personal healthcare data. Each layer was specially designed to handle a predefined task, and it can be implemented to serve a variety of demands for healthcare using cloud platform and service-oriented architecture. This platform helped practitioners to observe and evaluate health conditions by transmitting raw sensors information from end-user to the cloud platform for processing and then displayed results to doctors [ 28 , 56 , 57 ].
However, the majority of the cloud data centres are geographically centralized and located far from end-users [ 58 ]. Thus, for applications that require immediate real-time feedback, like remote monitoring or telehealth, communication time between users and remote cloud servers cause significant issues such as high round-trip delay, network congestion, and other issues. As a result, recent technological evolution, such as fog computing and big data, extend cloud computing ability by supporting highly scalable computing platforms [ 59 ].
CISCO has first introduced the fog computing concept as a solution to extend the computing power and storage capacity of the cloud to the network edge [ 60 ]. Fog computing is closer to devices and has a dense geographical distribution, so applications and services can be placed at the edge of the local network, which reduces bandwidth usage and latency. In other words, it brings the cloud closer to its users. Thus, it enables data to be collected and processed locally, reduces network latency and bandwidth usage.
Table 4 compares different characteristics of cloud and fog computing. Based on the comparison, fog computing shows that it is more suitable for IoT healthcare systems compare to cloud computing. Different from traditional IoT based healthcare systems, the fog-assisted system can improve various aspects of IoT based healthcare systems like scalability, energy awareness, mobility, and reliability [ 61 , 62 , 63 , 64 ]. Fog computing architecture is a promising topic in cloud computing research.
Recently, a large number of architectures have been introduced for fog computing, and three tiers architecture is considered to be the predominant structure nowadays [ 65 ]. The basic fog computing architecture depicted in Figure 8 is split into the following three main layers:. It consists of several devices, such as sensors and smart devices. These devices are widely geographically distributed and are responsible for sensing the physical object and sending data to the upper layer for processing and storage.
Fog layer: The second layer is the fog layer located at the edge of the network, it contains a huge number of fog nodes, which commonly includes routers, gateways, access points, and base stations. Fog nodes are responsible for performing tasks such as scheduling, storing, and managing distributed computation.
Cloud layer: The cloud layer is responsible for permanent storage and extensive computational analysis of data. Unlike traditional cloud architectures, in fog computing, the cloud layer is accessed in a periodical and controlled manner, leading to efficient utilization of all available resources. In , a smart healthcare gateway for fog computing module was introduced [ 66 ]. More specifically, the authors concentrated on setting up a connection from household gateways to hospital gateways.
Through various experiments, they proved that fog computing has a vital role in supporting the smart gateway.
Recommended for you
In another research work, Rahmani [ 34 ] analyzed the role of fog computing in implementing healthcare monitoring framework, and they proposed a mediator layer to receive raw information from sensor devices and then stored them on the cloud. Finally, a fog computing based early detection of chronic disease system was proposed to prove the effectiveness of adding the fog layer to the framework.
In , a healthcare framework which named HealthFog was presented [ 67 ]. They mostly focused on improving and solving the electronic medical record EMR privacy problems. Next, cloud-based security software was added to the HealthFog to strengthen system security.
- Pervasive Healthcare Computing: EMR-EHR, Wireless and Health Monitoring;
- Clinical Sports Nutrition, 4th Edition.
- Pervasive Health (CSE 40816/60816).
In addition, a new concept, namely cryptographic primitive, was proposed to improve the effectiveness of HealthFog. In the same year, Kim [ 68 ] introduced a prototype of IoT health monitoring application using fog computing. In , Gia improved existing fog computing systems by analyzing bio-signals on the fog server side to support real-time systems [ 32 ]. In recent years, healthcare applications are shifting from cloud computing to fog computing. Table 5 shows recent healthcare applications based on fog computing.
Through this section, we explained in detail the cloud computing paradigm and primarily focused on fog computing architecture, which is a foundation for healthcare applications. We also compared several characteristics of cloud and fog computing and explained why fog computing is more suitable for healthcare applications. After that, a standard fog computing architecture which includes device layer, fog layer and cloud layer was described.
Finally, we discussed fog computing in healthcare by summarizing recently published papers that apply fog computing in healthcare applications. Before the dawn of IoT and cloud computing eras, physician-patient interactions were limited to in-person visits, telecommunications, and text communications. However, recently, IoT and cloud computing based healthcare systems make real-time applications in the healthcare sector possible, unleash the full potential of IoT and cloud computing in the healthcare, and support physicians in delivering excellent healthcare services.
IoT and cloud computing have increased patient engagement and satisfaction because communications between patients and doctors have become more accessible and more efficient. Furthermore, remote monitoring reduces the length of hospital stay and avoids hospital readmissions. As a result, these new technologies have significant impacts on reducing healthcare costs and improving treatment outcomes.
IoT and cloud computing technologies are improving the healthcare industry by contributing to the evolution of a new array of IoT-connected medical devices and improving people interaction in healthcare systems. More and more IoT and cloud computing based healthcare applications have been developed to serve patients, families, physicians, hospitals and insurance companies. We divide healthcare applications into two main groups to help readers gain a better understanding of this broad topic.
The first group addresses concepts that arise during the convergence of IoT and cloud computing in the healthcare, whereas the second group mostly concentrates on dividing healthcare applications into two specific categories: single parameter and multiple parameters application. The single parameter application deals with an illness or a particular disease, while the multiple parameters application is used to handle over one disease or condition together as a whole. Figure 9 illustrates some concepts and trending application in the healthcare industry. The classification is extendable and can be easily altered by appending more concepts with distinctive characteristics or applications, including single- as well as multiple-parameter solutions.
IoT and cloud computing are revolutionizing the healthcare industry by bringing numerous concepts to the research community, and each concept supports a group of healthcare applications. However, it is hard to draw a general explanation for the concept of IoT and cloud computing in healthcare. This paper defines concepts as trending solutions that have the prospect to be a cornerstone for a list of applications and solutions. As healthcare systems are being developed, new concepts are constantly added. They will eventually become essential platforms for healthcare applications.
The following sections highlight several fundamental concepts of IoT and cloud computing in the healthcare. AAL appears as a sub-area of ambient intelligence.
- Pervasive Healthcare Computing : EMR/EHR, Wireless and Health Monitoring?
- Pervasive Healthcare Computing Pervasive Healthcare Computing.
- Executing Democracy: Volume One: Capital Punishment & the Making of America, 1683-1807 (Rhetoric & Public Affairs)?
- The Rape of St. Peter.
- MAE DAYS.
It is a relatively new IT trend that places smart objects in the surrounding environment to provide assistance and care for seniors to live independently. Recently, research related to AAL has increased significantly thanks to advancements in sensor technology, as well as the availability of smart healthcare gadgets. Table 6 summaries general domains and typical sensors in recent studies about AAL. Three main domains in AAL are activity recognition, vital monitoring, and surrounding environment recognition.
Among them, activity recognition interests a large number of researches as it is crucial to support the well-being of elders, and detect potential threats that can happen to seniors. Data can be retrieved by practitioners to observe, diagnose, and treat patients effectively and on time. As a result, it has the potential to become the foundation for inventive IoT and cloud computing in healthcare applications in the future since it provides fully connected and mobility functions.
Recently, a platform for an m-Health health observing application based on cloud computing Cloud-MHMS was introduced [ 55 ]. The platform included many important layers; a multiple tenant access concept was introduced to secure data privacy in the data storage module. In the annotation module, a linked list was used to extend exchange EMR semantically. Finally, data mining and machine learning were performed to improve data analytic efficiently in the data analysis module. In recent years, the application of semantics and ontologies in healthcare systems to store and manage large amounts of medical data has increased [ 37 , 56 ].