Deep Mist A Framework for Healthcare

Big Data Management with Deep Learning

Assistance in Mist Computing
 Agenda
• Abstract
• Scope and Motivation
• Introduction
• Objective
• Problem Statement
• Proposed Work
• Architecture Diagram/Flow Diagram/Block Diagram
• Novel idea
• Modules
• Module Description

• References (Base paper hard copy to be submitted to the supervisor.)

 ABSTRACT
• The prevalence of heart disease has remained a major cause of mortalities
across the world and has been challenging for healthcare providers to detect
early symptoms of cardiac patients.
• To this end, several conventional machine learning models have gained
popularity in providing precise prediction of heart diseases by taking into
account the underlying conditions of patients.
• The drawbacks associated with these methods are a lack of generalization and
the convergence rate of these methods being much slower.
• As the healthcare data associated with these systems scale up leading to
healthcare big data issues, a Cloud Fog computing-based paradigm is
necessary to facilitate low-latency and energy-efficient computation of the
healthcare data.
• Deep Mist framework is suggested which exploits Deep Learning models
operating over Mist Computing infrastructure to leverage fast predictive
convergence, low-latency, and energy efficiency for smart healthcare systems
 Scope and Motivation
• The development of cutting-edge means of communication and storage,
the medical, agricultural, and other fields have significantly benefited from
incorporating smart gadgets into everyday life.
• we compare its outcomes over the heart disease dataset in convergence
with other benchmark models like Q-Reinforcement Learning (QRL) and
Deep Reinforcement Learning (DRL) algorithms and observe that the
proposed scheme outperforms all others.
 Introduction
• The development of cutting-edge means of communication and storage, the medical,
agricultural, and other fields have significantly benefited from incorporating smart gadgets
into everyday life . Things (IoT) has had a significant influence on our everyday life. The IoT is
often conceptualized as a network of interconnected computing systems that share
information to achieve specific goals. These systems often include sensors, actuators, and
processors .
• IoT-enabled devices employ sensing technologies to produce extensive data, which is then
transferred via fog computing or cloud computing to locations where deep learning
algorithms can be used to make decisions accurately. Fog computing, which includes cloud
computing standards, has become the foundation of an advanced economy relying on the
Internet to provide customer services .
• However, owing to the significant setback to speed of reaction, cloud computing is unsuitable
for applications that require regular feedback. Big data management in the context of this IoT,
fog, and cloud computing have all risen to prominence due to their user-friendliness and
ability to provide reaction features dependent on the tracked target applications.
• These new technologies give edge devices the ability to store, compute, and communicate
with each other. This improves mobility issues, security, and privacy along with optimizing
latency and network bandwidth so that fog computing can work well with real-time or
latency-sensitive applications
 Objective
• The IoT is often conceptualized as a network of interconnected computing
systems that share information to achieve specific goals. These systems
often include sensors, actuators, and processors.
• IoT-enabled devices employ sensing technologies to produce extensive
data, which is then transferred via fog computing or cloud computing to
locations where deep learning algorithms can be used to make decisions
accurately.
• Fog computing, which includes Toward Deep Learning Assisted Mist
Computing Framework cloud computing standards, has become the
foundation of an advanced economy relying on the Internet to provide
customer services.
• However, owing to the significant setback to speed of reaction, cloud
computing is unsuitable for applications that require regular feedback.
• Big data management in the context of this IoT, fog, and cloud computing
have all risen to prominence due to their user-friendliness and ability to
provide reaction features dependent on the tracked target applications.
 Problem Statement
• The exponential growth of healthcare data, coupled with the need for real-time
analysis and privacy-preserving techniques, presents a significant challenge in
managing healthcare big data effectively. Traditional computing architectures
struggle to provide timely insights while ensuring data security and compliance
with regulations.

• This project aims to develop a novel mist computing framework, DeepMist,

leveraging deep learning methodologies to address these challenges. DeepMist
will enable efficient and secure processing of healthcare big data, facilitating timely
decision-making and improving patient outcomes while adhering to strict privacy
and regulatory requirements.
 Proposed Work
• The proposed DeepMist framework is illustrated in this section along with an
emphasis on the integration of IoT application layer, mist computing layer, fog layer
and cloud layer.
• The DeepMist framework incorporates intelligence by exploiting the DQN
algorithm to facilitate prediction of heart disease in a distributed manner over the
mist computing devices. The proposed paradigm is four layered namely, the IoT
physical layer, communication layer, fog computing layer, and cloud computing
layer.
• The proposed DeepMist framework along with all its functional modules. We start
with illustrating the functionality corresponding to individual layers in a bottom up
approach. The IoT physical layer is placed at the bottom most layer and is further
subdivided into three sub-layers viz., IoT application layer, the mist computing
layer, and processing layer.
Architecture Diagram
 References
• [1]E. M. Dogo, A. F. Salami, C. O. Aigbavboa, and T. Nkonyana, ‘‘Taking
cloud computing to the extreme edge: A review of mist computing for
smart cities and industry 4.0 in Africa,’’ in Edge Computing: From Hype to
Reality. Springer, 2020, pp. 107–132.
• [2] S. Ketu and P. K. Mishra, ‘‘Cloud, fog and mist computing in IoT: An
indication of emerging opportunities,’’ IETE Tech. Rev., vol. 39, no. 3, pp.
713–724, May 2022.
• [3] E. Faze l, H. E.Najafabadi , M.Rezaei , and H. Leung, ‘‘Unlocking the
power of mist computing through clustering techniques in IoT networks,’’
Internet Things, vol. 22, Jul. 2023, Art. no. 100710.
• [4] V. K. Quy, N. van Hau, D. van Anh, and L. A. Ngoc, ‘‘Smart healthcare
IoT applications based on fog computing: Architecture, applications and
challenges,’’ Complex Intell. Syst., vol. 8, no. 5, pp. 3805–3815, Nov.
2023