Abstract
The medical advancement in recent years is addressing challenges of the dependent people like senior citizens, physically challenged, and cognitively impaired individuals by providing technical aids to promote a healthier society. The radical improvement in the digital world is trying to make their life smoother by creating a smart living environment via ambient assisted living (AAL) rather than hospitalization. In this chapter, an Edge-based AAL-IoT ecosystem is introduced with the prime objective of delivering telehealthcare to elderly and telerehabilitation to disabled individuals. The proposed framework focuses on developing smart home, an intelligent atmosphere for real-time monitoring in regard to meet the needs of independent and isolated individuals. The supporting technologies to leverage the edge computing concept, to enable scalability and reliability are also studied. A case study on proposed architecture for quarantined patient monitoring remotely in the event of epidemic or pandemic diseases is presented.
TopIntroduction
As claimed by WHO, the old age population above 60 years in the world will double from 12% to 22% shortly. As per 2017 report, the elder population aged above 60 years is 962 Million and is expected to reach more than twofold i.e., 2.1 Billion by 2050 dramatically (World Health Organization, February 5, 2018). For instance, if the elder people experience a better quality of life during their later years, then their value and ability will be more respected. On the other hand, if their dependency on others due to physical or mental health decline increases in these added years, then the impact will be negative.
As per the plan developed by WHO on aging and health, it is significant (i) To create awareness on healthy and active aging (ii) To design next-generation pervasive healthcare solutions based on elderly needs and preferences (iii) To provide long-term healthcare monitoring and (iv) To create an elder-friendly environment (World Health Organization, February 5, 2018). In addition to the age-related health risks, the surrounding also plays a major role in declining their risk of developing diseases such as improper intake of food, sleeping disorder, lack of physical activities, lack of simple exercises and so on.
According to the report issued by Market Research Future, it is indicated that the AAL market has produced 13 Billion USD over the period 2017 - 2027 and is estimated to reach 19% by 2027. One of the prime parts of the AAL market namely, the medical assistance system has achieved the highest 22% CAGR (Compound Annual Growth Rate) over the above estimated period (Market Research Future, April 2018). The advancement in the Internet of Things (IoT) technology and smart home technology, a huge growth of the elderly population, and a rapid increase in age-related chronic diseases are the driving factors for the rapid growth of the AAL market. In this regard, the role of healthcare service providers is going to be remarkable in the coming years.
In the present impending IoT era, almost every object or thing can be interrelated with each other in a large number, and it becomes an essential part of every domain of human life. With improved Internet connectivity, the proliferation of IoT enabled devices is expected to reach 75 Billion by the year 2025 (Statistica, 2016). As the booming IoT evolves, it has been adopted not only in many business sectors such as smart agriculture and farming, smart healthcare, automotive, industrial IoT, transportation but also for sophisticated applications like retail stores, luxurious hotels/inns, etc.
Similarly, cloud computing (Emeakaroha et al., 2015; Qabil et al., 2019) enables seamless integration of physical and smart devices by endorsing on-demand delivery of required computation, networking, and storage resources to analyze IoT big data, acquire deep insights and deliver intelligent value-added services to the end-users. Nevertheless, the raw data generated by the IoT devices have to traverse a long way through various intermediate networks to reach the remote cloud data center for further processing and analysis. So, cloud computing becomes unsuitable in meeting the diverse quality requirements such as low latency, limited bandwidth, intermittent connectivity and instant real-time response.
On that account, fog computing or fog networking, the term framed by Cisco (Cisco, 2015), a decentralized computing architecture is introduced to utilize the resources available at the edge of the network. The idea is extending cloud computing to make it idealized for IoT and other mission-critical or industrial applications. Edge computing (Yu et al., 2017) being a subset of Fog computing, has attracted many researchers to come up with real-time solutions. It has brought intelligence near to the end-user. When the data generation source and computation are closer by localizing data processing and storage then it will combat the latency, smoothing real-time interactions by affording instantaneous computing and immediate response.
In other words, the service requests and service consumers are one hop away distant to meet the real-time requirements of emerging services. Thus, edge computing and IoT are the significant elements of AAL, also known as welfare technology, to create a ubiquitous, assisted, and cost-effective architecture for the challenged and elderly people.
Key Terms in this Chapter
Response Time: The time duration between the users requesting the service and the service is actually consumed by them.
Data Aggregation/Filtering: The raw data collected from sensors is unstructured and contains noise. It has to be processed and computed to obtain structured data through a process called data aggregation or filtering.
QoS: Measurement of the overall service performance guaranteeing the minimal users’ requirements like latency, responsiveness, reliability, throughput, etc., while consuming a service.
Time-Critical Application: The application required real-time or almost zero delayed response is called time-critical or time-sensitive application.
Edge Intelligence: The devices available at the edge layer have some limited amount of computing resources which can be utilized and incorporated with machine learning or AI algorithms to perform real-time data analytics.
Wireless Sensor Network: It is a self-configured wireless network of sensors or sensing devices to collect physical or environmental data and send the data wirelessly to a central location to get connected to the external world.
Software-Defined Networking: Different from the traditional networking infrastructure, it moves intelligence from the network hardware devices to the centralized place called SDN controller by making all the hardware devices as dummy forwarding devices. The SDN controller where intelligence is available provides global network view and makes network management easier.
Data Analytics: The raw data collected by the IoT environment is analyzed in a cloud/edge server to find trends, hidden patterns, and knowledgeable insights.