Application of IoT and Edge Computing in Healthcare: Activity 4 Report

This report analyzes the application of IoT and edge computing in healthcare, focusing on the development and utilization of wearable smart-log patches equipped with IoT sensors. The study emphasizes the use of edge computing and the EC-BDLN (Bayesian deep learning network) algorithm for analyzing data collected from these sensors, enabling real-time monitoring of physical activities and health conditions. The report highlights the benefits of this approach, including improved response times and the potential for early diagnosis, particularly for individuals with various health issues. It also discusses the strengths of the technology, such as the use of multimedia technology and agile learning for real-time data analysis, while acknowledging the limitations, including security concerns and cost factors. The conclusion suggests that the EC-BDLN algorithm is a promising approach for health monitoring systems, validated through experimental results demonstrating its efficiency, accuracy, and energy consumption within distributed devices in an edge computing environment.

Activity 4 – IoT & Edge Computing in HealthCare
Introduction
Smart log based multi access physical monitoring systems are liable for determination of health
situations of humans along with other related problems within their lifestyle. Due to deficiencies
related with nutrients creates worsening of organs that leads to different health problems. It is
important that there has to be adequate physical monitoring system that will lead to monitor
activities for elimination of difficulties by making use of smart environment system (Farhani,
Firouzi and Chakrabarty, 2020). The major challenging task is to have effectual diagnosis with
respect to health conditions to access physical monitoring system. The wearable smart-log patch
with IoT (Internet of Things) sensors with multimedia technology is being developed. Along
with this, data computation within smart-log patch are analysed through usage of edge
computing with respect to EC-BDLN (Bayesian deep learning network). This will aid to infer as
well as identification of different physical data that is being gathered from human in an adequate
way for monitoring physical activities. The smart-log patch is regarded as evolutionary research
within checking physical monitoring systems via multimedia technologies.
Within the proposed idea, a wearable smart patch that have IoT sensors are liable
for transmission of data sets to edge platform through usage of LAN like
Bluetooth and Wi-Fi. Here, Bayesian deep learning network algorithm can be
utilised within distributed devices for edge computing environment. This assists
within inferring along with determination of distinct physical data that is being
gathered from human in a precise way to monitor physical activities. The analysis
will be done then patterns will be extracted related with health dataset (Sarker and
et. al, 2019). This is in normalised form that is being processed for minimisation of
data reliability as well as redundancy. This will have different layers which are
then integrated through utilisation of Bayesian network that will be illustrated in
form of signals and will be converted into numerical present in matrix. This is
being represented like a regression model which resembles flow of human brain
with restricted subset.
Who will have benefits from this
Each individual who have any sort of health issues can be benefitted
through the idea. The reason is that it takes time to generate report and transfer it
to individual but at that moment of time there condition may worsen. So, edge
platform will aid them as it is being executed by distributed networks that make
use of smart routers, high power capacities and storage units which are more apt
for multi access monitoring system. This will have an affirmative impact on
professionals as on time services or treatment can be provided to their patients.
Techniques that are being utilised
The distributed computing paradigm which is liable for bringing in computation as well as data
storage closer to location in which this is being required for improvisation of response time and
bandwidth is referred to as edge computing. It is liable for transforming ways in which data is
being managed, processed as well as delivered from various devices across the world. The
internet of things illustrate system that comprises of interconnected computing devices, digital
and mechanical machines which are liable for furnishing unique identity as well as transfer data
via usage of network without any interaction between human. Here, thing within internet of
thing can be person who have heart monitor implant, automobile with built-in sensors for
alerting driver when there is tire pressure is either low or other objects through which data can
be transferred via a network (Kim, Lee and Dustdar, 2019). The edge computing technology is
liable for bringing in data that is close to location in which data is needed through making use of
distributed device. Within wearable smart log patch that have IoT sensor aids within producing
accurate data related with physical activities of human physical system for monitoring health.
There are two methods which can be utilised for analysing monitored data, they are: expert
diagnosis and cloud storage for online diagnosis. But it is crucial that adequate warnings are
being given with respect to functioning of organs as it takes time for report generation.

Bayesian Deep Learning Structural Block
Strengths and limitations
The wearable smart-log patch comprises of internet of things sensor that have been
developed as well as designed through multimedia technology for overcoming the setback that
are being faced through usage of recent methods within physical monitoring system. Along with
this, when the system is making use of multimedia technology as well as edge computing
through usage of agile learning within real time data analysis through usage of internet of thing
sensors which are being hybridized along with Bayesian network for having precise predictions
related with inadequate working of organs (Kim, Lee and Dustdar, 2019). The EC-BNN
(Bayesian neural network) aids within inferring along identifying different physical information
that is being gathered from humans via high prediction within classification of physical activity
information or health datasets that are being deployed like a promising choices for solving the
issues.
The major limitation of the idea is security aspects which have to be taken into
consideration along with cost factor need to be reduced so that it becomes feasible to opt for
such kind of multi access physical monitoring system.
Electro Cardiogram (ECG) tracing
Conclusion
From above it can be concluded that, EC-BDLN algorithm is revolutionary
algorithm within health monitoring for multi access physical monitoring system
along with usage of multimedia technology. The wearable smart-log patch with
IoT sensors are developed as well as designed with respect to multimedia
technology for analysis of different activities of body like EMG, ECG,
temperature, EEG, blood, accelerator gyroscope and respiration of human physical
system. Along with this, optimisation parameters like mean residual, efficiency,
accuracy, energy consumption and delay are being validated experimentally via
EC-BDLN algorithm within distributed devices within edge computing
environment. This seems to be more promising approach for dealing with certain
health issues.
IoT & Edge Computing
References
Farahani, B., Firouzi, F. and Chakrabarty, K., 2020. Healthcare iot. In Intelligent
Internet of Things (pp. 515-545). Springer, Cham.
Kim, H., Lee, E.A. and Dustdar, S., 2019. Creating a Resilient IoT With Edge
Computing. Computer, 52(8), pp.43-53.
Sarker, V.K. and et. al, 2019, June. A survey on LoRa for IoT: Integrating edge
computing. In 2019 Fourth International Conference on Fog and Mobile
Edge Computing (FMEC) (pp. 295-300). IEEE.