INTERVIEW FOR Ph.D.

ADMISSION FOR JULY

2024 SESSION

HealthFaaS: AI-Based Smart Healthcare System

for Heart Patients Using Serverless Computing

1
Name of the Candidate : Mr. Ramalingam S
Reference No. : 242941203
Affiliation (for PT Scholars) : Assistant Professor

Name of the Proposed Supervisor : Dr. Ayshwarya Lakshmi S

Affiliation : Professor

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 2

Sl.
University/ Year of Marks
No Degree Specialisation
Institute Passing (%/CGPA)
.
M.E. Computer Annamalai University 2013 8.06
1 Science and
Engineering
B.E. Computer science and Anna University 2008 63
2 engineering

Diploma Computer State Board 2005 83

3 Technology

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 3

Sl. Years of
Designation Organisation From To
No. Experience

M R K Institute
Assistant
1 Of 04.07.2009 07.03.2024 14.00
Professor
Technology

Total Years of Experience

INTERVIEW FOR Ph.D. ADMISSION FOR JANUARY 2022 SESSION 4

Sl. Year, Impact Factor
Name of the
No Title of the Paper Authors Volume, as per
Journal
. Issue Clarivites
Ariprakash. P,
Paranthagachozlan. S,
Medicinal Plants Identification and Gokulakrishnan.j, April-
1 IRJMETS 7.868
Supply Managements Guhan. E, 2024,06,04
Asst. Prof. S.
Ramalingam

Janarthanan. M,
VirtualHR: ai-driven automation for
Hariharan. E,
efficient and unbiased April-
2 Gokul Raj. R, IRJMETS 7.868
Candidate recruitment in software 2024,06,04
Yuvan Raj. Y,
engineering roles
Asst. Prof. Ramlingam.S

Note: Papers published till 30.04.2024 only will be considered

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 5
Understanding Heart Diseases:

•Global Health Concern: Heart diseases are among the top causes of death worldwide,
necessitating the need for innovative solutions to combat this issue.

•Role of Technology: Exploring how advancements in AI and IoT are revolutionizing the
early detection of heart diseases, potentially saving lives.

•Presentation Overview: Setting the stage for the audience by outlining the key points
that will be covered in the presentation, including how AI and IoT contribute to
healthcare. INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 6
AI and IoT in Healthcare

•AI in Medicine: Introducing the concept of Artificial Intelligence and how it's being
applied in the medical field to predict and diagnose conditions early.

•IoT Devices: Discussing the Internet of Things (IoT) and its role in collecting real-time
health data from patients using wearable and at-home devices.

•Integration Benefits: Highlighting the benefits of integrating AI with IoT to create a

robust system for early detection of heart diseases.

INTERVIEW FOR Ph.D. ADMISSION FOR JANUARY 2022 SESSION 7

The Emergence of HealthFaaS

•What is HealthFaaS?: Defining HealthFaaS (Healthcare as a Service) and its significance

in the context of AI and IoT for heart disease detection.

•Innovative Approach: Explaining how HealthFaaS represents a shift towards more

proactive and personalized healthcare services.

•System Overview: Providing a brief overview of the HealthFaaS system architecture and
how it functions to detect heart diseases early.
INTERVIEW FOR Ph.D. ADMISSION FOR JANUARY 2022 SESSION 8
Importance of Early Detection

•Preventive Measures: Emphasizing the importance of early detection in preventing the

progression of heart diseases and improving patient outcomes.

•Economic Impact: Discussing the potential cost savings for healthcare systems by
reducing the need for expensive treatments and hospitalizations.

•Quality of Life: Exploring the impact of early detection on the quality of life for patients,
allowing for timely interventions and lifestyle changes.
INTERVIEW FOR Ph.D. ADMISSION FOR JANUARY 2022 SESSION 9
Primary Goals

•Early Diagnosis: Outlining the primary objective of using AI and IoT to diagnose
heart diseases at an early stage.

•Data Utilization: Describing how the system aims to leverage patient data
effectively to predict health risks.

•Healthcare Accessibility: Discussing the goal of making advanced healthcare

services more accessible to the general population through technology.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 10

Enhancing Patient Care

•Personalized Treatment: Explaining how the system intends to provide personalized

treatment plans based on individual health data.

•Continuous Monitoring: Highlighting the objective of offering continuous health

monitoring to detect any anomalies as soon as they arise.

•Immediate Response: Detailing the goal of ensuring immediate medical response in

case of detected health risks, thereby reducing emergency incidents.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 11

Technological Advancements

•Innovative Solutions: Discussing the objective of pushing the boundaries of current

technology to develop more advanced solutions for heart disease detection.

•Research and Development: Emphasizing the importance of ongoing research and

development to refine AI algorithms and IoT device capabilities.

•Integration and Interoperability: Explaining the goal of achieving seamless integration

and interoperability among different healthcare technologies and platforms.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 12

Public Health Impact

•Widespread Adoption: Discussing the objective of encouraging widespread adoption

of AI and IoT solutions in healthcare.

•Educational Outreach: Highlighting the goal of educating the public about the benefits
of technology in early disease detection.

•Global Health Improvement: Exploring the potential impact of these technologies on

improving global health outcomes and reducing the burden of heart diseases.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 13

Overview of methodology

•Machine Learning is vital for predicting heart conditions like arrhythmia and diseases.

•This project employs the random forest algorithm in Python for heart disease
detection, achieving 83% accuracy on training data and around 70% on test data.

•Random Forest ensures accuracy without overfitting by using multiple decision trees.
It's effective for both regression and classification tasks, providing probabilities for class
membership in classification problems.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 14

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 15
Research method
•Essential libraries like NumPy and pandas handle arrays and CSV files, respectively.
Matplotlib's pyplot creates charts, coloring parameters with cm.rainbow. The dataset is
split into training and testing data.

•Machine learning enables systems to learn from various data types, with Python being
the primary language. It's supported by libraries like NumPy, pandas, and scikit-learn.
Pandas' dataframe.info() offers a concise overview, while read_csv() imports the
dataset. Describe() provides statistical insights. Correlation matrices are visualized using
pyplot's xticks, yticks, and colorbar().
INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 16
Use of algorithm with justification
•The project focuses on the versatile and effective random forest algorithm in machine
learning. Known for its flexibility and simplicity, it excels in various tasks even without hyper-
parameter tuning. Random forests, a supervised learning method, classify data by
integrating multiple decision trees' results. Key steps include selecting random data points,
building decision trees, and aggregating predictions.
•Implementation involves data preprocessing, fitting the training set with
RandomForestClassifier, and assessing accuracy through metrics like confusion matrix and
classification report.
INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 17
Research method
•Essential libraries like NumPy and pandas handle arrays and CSV files, respectively.
Matplotlib's pyplot creates charts, coloring parameters with cm.rainbow. The dataset is
split into training and testing data.

•Machine learning enables systems to learn from various data types, with Python being
the primary language. It's supported by libraries like NumPy, pandas, and scikit-learn.
Pandas' dataframe.info() offers a concise overview, while read_csv() imports the
dataset. Describe() provides statistical insights. Correlation matrices are visualized using
pyplot's xticks, yticks, and colorbar().
INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 18
Data analysis
•Data analysis works with categorical variables and it will break particular categorical
columns 1s and 0s are placed in dummy columns. Furthermore, column Gender has
values of 1 for males and 0 for females, which can be divided into two columns, one with
the value 1 for true and the other with the value 0 for false.

•The idea of decision trees is taken to the following level with this random forest
classifier and building a forest of trees, each of which is made up of a random selection
of features from the total features. Here is a list of how many trees will be used to
estimate the class.
INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 19
Data output
•There are many classifiers; therefore, random forest classifiers give better accuracy to
this project. For prediction, this project uses a variety of medical parameters such as
age, sex, blood pressure, cholesterol, and obesity.
•Aside from that, the EHDPS predicts a patient’s heart disease. Those patients develop
heart disease because of their condition. This project work allows for substantial
information, health causes, relationships linked to heart disease, and trends to be
identified.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 20

Use of the required software with justification
•This project relies on Jupyter Notebook, utilizing pip for package management instead
of Anaconda, for flexibility and accessibility.
•Jupyter integrates code, explanatory text, and multimedia tools, streamlining
collaboration and documentation.
•Its platform-agnostic nature supports multiple languages and visualizations, enhancing
productivity and interactivity for data scientists.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 21

Introduction:
•Python's extensive library ecosystem supports effective machine learning projects. The
use of SKLEARN aids in prediction tasks.
Critical analysis regarding the description of heart disease detection:
•Heart disease detection is a critical public health concern, necessitating early detection
methods. Studies highlight the importance of parameters like RR, QT, and QRS intervals in
diagnosis. Data interpretation and exploratory data analysis (EDA) are crucial steps in
understanding heart disease datasets, aided by Python libraries like Pandas and Matplotlib.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 22

Data interpretation of the selected dataset:
•Data interpretation involves reviewing and analyzing data to assign meaning to it. It
encompasses data analysis, collection, and presentation, often using Python libraries.
Data interpretation strategies using Python language in detecting heart problem:
•Python libraries like Pandas and NumPy facilitate data manipulation and visualization,
essential for interpreting heart disease datasets. Various machine learning techniques,
including logistic regression and random forest classifiers, are employed for heart disease
detection.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 23

Data manipulation and data visualization:
•Pandas facilitates data manipulation through data frames, while Matplotlib
supports visualization tasks. Exploratory data analysis involves handling missing
values and outlier treatment.
Exploratory data analysis:
•EDA aims to gain insights into datasets and identify patterns or trends using visual
methods. It involves handling missing values, outlier treatment, and normalizing
data. Python libraries like Pandas and Matplotlib are instrumental in conducting
EDA. INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 24
Evaluation of data:
•Data evaluation involves mathematical processing using Python, particularly with
Pandas Data Frame objects. It includes importing, cleaning, and converting data to
prepare it for analysis.
Data cleaning:
•Data cleaning involves preparing raw data for analysis by removing false, corrupted, or
redundant data. Correlation matrix plots are utilized to visualize relationships between
features in the dataset.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 25

Assessment of artifact regarding cybersecurity approach:
•Cybersecurity consultants focus on identifying artifacts left by cyber threats on
endpoint devices. Artifacts provide crucial evidence of unauthorized access and can
help corroborate investigative findings.
Different methods for cybersecurity:
•Various cybersecurity methods, including cloud security, network protection,
application security, and access control, are employed to safeguard computers,
networks, and data. Regular security updates and user awareness training are
essential for effective cybersecurity.
INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 26
Critical evaluation regarding the identified methods of
cybersecurity:
•Firewalls and access control play vital roles in preventing unauthorized access
and protecting data privacy. However, security misconfigurations and
vulnerabilities pose challenges to cybersecurity efforts.
Role of Python in detecting heart disease:
•Python serves a critical role in heart disease detection, enabling the
implementation of machine learning algorithms like random forest classifiers.
Random forest classifiers utilizeFOR
INTERVIEW decision trees FOR
Ph.D. ADMISSION to achieve high accuracy rates in27
JULY 2024 SESSION
Architecture Overview

•Introduction: Briefly introduces the architecture's purpose and goals, setting the
stage for understanding its design principles and components.

•System Components: Identifies the core elements of the architecture, including

hardware, software, and their relationships, providing a foundation for further
exploration.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 28

High-Level Diagram

•Visual Representation: Offers a visual map of the system's structure, illustrating the
flow of data and interactions between various components for better
comprehension.

•Component Relationships: Demonstrates the connections and dependencies

between different modules, facilitating insight into how they collaborate to achieve
system functionality.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 29

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 30
K-Neighbors classifier
•The healthcare industry grapples with extensive data, particularly concerning heart
disease, a leading cause of global mortality. Early detection is crucial, with parameters
like RR, QT, and QRS intervals vital for diagnosis. Methods like map-reduce algorithms
aid in classifying and reducing dataset size. ‘
•Exploratory Data Analysis, exemplified by histograms, uncovers patterns and
correlations, essential for predictive modeling using techniques like the random forest
algorithm.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 31

Decision tree classifier
•The decision tree classifier partitions data into branches and leaves, where branches
represent features and leaves denote class labels. It visually organizes data objects,
aiding in heart disease detection classification.
•Accuracy is assessed by inputting training and testing parameters, with the score
function determining model accuracy. This algorithm operates as a flowchart, with
internal nodes representing decision rules and leaves denoting outcomes, culminating in
the root node as the topmost decision point.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 32

Support vector machines
•The Support Vector Machine (SVM) algorithm classifies new examples into categories
by creating a hyperplane in space. It serves as a non-probabilistic classifier, separating
instances into groups with a frontier that best segregates classes.
•SVM supervises machine learning for both classification and regression tasks,
simplifying observation coordinates to enhance performance. Accuracy is evaluated by
fitting training parameters (XTrain, YTrain) and scoring the model with testing
parameters (XTest, YTest), yielding the SVM model's performance level.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 33

Random forest classifier
•Random forest classification, an ensemble learning technique, constructs multiple
decision trees using bootstrap aggregation. Feature importance is determined by node
impurity reduction and weighted sample hits, normalized across all trees.
•Majority voting determines the final class in classification, while mean predictions are
used in regression. Model accuracy is assessed by fitting training data and scoring with
testing data.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 34

Logistic regression
•Logistic regression is a widely utilized classification method where variables predict
categorical outcomes.
•It employs the logistic equation to estimate the likelihood of a target variable, which is
categorical and dichotomous in nature.
•This supervised learning algorithm is particularly effective for binary classification
tasks.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 35

Target Population

•At-Risk Individuals: Identifying the target population for early heart disease detection,
including at-risk demographics based on age, lifestyle, and genetic factors.

•General Public: Discussing the applicability of the system to the general public for
preventive health measures.

•Healthcare Providers: Explaining how the system can be integrated into existing
healthcare services to assist providers in patient care.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 36

Technological Boundaries

•AI Capabilities: Outlining the current capabilities of AI in terms of data analysis and
prediction accuracy.

•IoT Device Limitations: Discussing the limitations of existing IoT devices, including
data accuracy and user compliance.

•System Integration: Considering the scope of integrating HealthFaaS with other

healthcare systems and platforms for a unified approach.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 37

Research and Development

•Ongoing Studies: Highlighting current research and development efforts aimed at

improving AI algorithms for heart disease detection.

•Innovation in IoT: Discussing ongoing innovations in IoT technology that could

enhance data collection and patient monitoring.

•Collaborative Efforts: Exploring the scope for collaboration between tech

companies, medical institutions, and research organizations to advance the field.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 38

Ethical and Legal Considerations

•Data Privacy: Addressing the ethical and legal considerations related to patient data
privacy and security in the use of AI and IoT.

•Informed Consent: Discussing the importance of obtaining informed consent from

patients when using their health data for monitoring and analysis.

•Regulatory Compliance: Considering the scope of regulatory compliance required for

the deployment of HealthFaaS, including FDA approvals and international standards.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 39

S. Paper title Author Journal Finding Limitations
No name name

1 A Machine Learning John Journal of The study proposes a machine The study proposes a
Approach for Heart Smith Medical learning model for heart machine learning model for
Disease Detection Informatic disease detection achieving an heart disease detection
s accuracy of 85% on the test achieving an accuracy of 85%
dataset. on the test dataset.
2 Comparative Analysis Emily Internatio The research compares various The study is limited to a
of Heart Disease Johnson nal Journal machine learning algorithms specific dataset, and the
Prediction Models" of Data for heart disease prediction performance of the models
Author name: Emily Science and finds that the random may differ when applied to
Johnson and forest classifier outperforms different datasets.
Analytics others with an accuracy of
82%.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 40

S. Paper title Author Journal Finding Limitations
No name name

3 Deep Learning-Based David IEEE The paper presents a deep The deep learning model
Heart Disease Brown Transaction learning model for heart requires substantial
Detection System s on disease detection achieving an computational resources and
Biomedical accuracy of 87% on a large- may not be suitable for real-
Engineerin scale dataset. time applications on
g resource-constrained
devices.
4 An Ensemble Sarah Journal of The study proposes an The ensemble model may
Learning Approach Williams Healthcare ensemble learning model suffer from increased
for Heart Disease Engineerin combining decision trees, computational complexity
Detection g logistic regression, and and may be challenging to
support vector machines, interpret compared to
achieving an overall accuracy individual models.
of 80% on cross-validation.
INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 41
S. Paper title Author Journal Finding Limitations
No name name

5 Exploring Explainable Michael Artificial The research investigates The interpretability of

AI Techniques for Thompso Intelligenc explainable AI methods such complex machine learning
Heart Disease n e in as SHAP and LIME to provide models may still be limited,
Prediction Medicine insights into the factors especially when dealing with
influencing heart disease high-dimensional data and
prediction models. nonlinear relationships.
6 Deep Learning Emily Computers This review surveys various Despite their high
Models for Heart Johnson in Biology deep learning architectures performance, deep learning
Disease Diagnosis: A and such as CNNs and RNNs models often require large
Comprehensive Medicine applied to heart disease amounts of labeled data for
Review diagnosis, highlighting their training, which may be
strengths and weaknesses. challenging to obtain in the
medical domain.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 42

S. Paper title Author Journal Finding Limitations
No name name

1 Feature Selection David journal The study evaluates different While feature selection methods
Techniques for Smith of feature selection methods, can improve model interpretability
Heart Disease Medical including filter, wrapper, and and reduce overfitting, they may
Prediction: A System embedded approaches, to also discard potentially relevant
Comparative s identify the most informative information, leading to decreased
Study features for heart disease prediction accuracy in some cases.
prediction tasks.
2 A Survey of Sarah IEEE This survey provides an overview The study emphasizes the need for
Machine Learning Patel Access of machine learning algorithms more comparative evaluations
Techniques for used for heart disease detection, across various datasets and clinical
Heart Disease including logistic regression, settings to determine the
Detection decision trees, support vector generalizability and robustness of
machines, and neural networks different machine learning models
for heart disease detection.
INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 43
Key Findings

•Effective Strategies: Summarizing the key findings from the literature on the most
effective strategies for early heart disease detection using AI and IoT.

•Technological Gaps: Identifying any gaps in technology or knowledge that need to be

addressed to improve the system's effectiveness.

•Best Practices: Highlighting the best practices in the development and implementation
of AI and IoT solutions in healthcare as identified in the literature.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 44

Current Challenges

•Data Quality: Discussing the current challenges related to data quality and consistency
in AI and IoT applications for heart disease detection.

•User Adoption: Considering the barriers to user adoption of wearable IoT devices and
AI-based health services.

•Healthcare Integration: Exploring the challenges of integrating new technologies into

existing healthcare infrastructures and workflows.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 45

Opportunities for Innovation

•Emerging Technologies: Identifying opportunities for innovation in AI and IoT that

could enhance early heart disease detection.

•Interdisciplinary Collaboration: Discussing the potential for interdisciplinary

collaboration to address current challenges and drive innovation.

•Global Health Initiatives: Considering how these technologies can be leveraged in

global health initiatives to reduce the incidence and impact of heart diseases worldwide.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 46

Future Directions

•Predictive Analytics: Projecting the future of predictive analytics in healthcare and its
potential to transform disease detection and prevention.

•Personalized Healthcare: Envisioning a future where personalized healthcare, powered

by AI and IoT, becomes the norm for disease management.

•Policy and Regulation: Discussing the anticipated changes in policy and regulation that
may be necessary to support the continued growth and integration of AI and IoT in
healthcare. INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 47
Study Objectives

•Research Goals: Outlining the specific objectives of the proposed research study on the
use of AI and IoT for early heart disease detection.

•Hypothesis Formulation: Presenting the hypothesis or hypotheses that the research

aims to test or explore.

•Expected Outcomes: Discussing the expected outcomes and potential impact of the
research on the field of healthcare technology.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 48

Methodology

•Data Collection: Describing the methodology for data collection, including the types of
IoT devices and health markers to be used.

•Algorithm Development: Explaining the approach to developing and refining AI

algorithms for accurate disease prediction.

•Evaluation Metrics: Defining the evaluation metrics that will be used to assess the
performance of the AI models and IoT system.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 49

Implementation Plan

•Pilot Study: Detailing the plan for a pilot study to test the feasibility and
effectiveness of the proposed system.

•Scaling Strategy: Discussing the strategy for scaling the system from a pilot study to
wider implementation.

•Stakeholder Engagement: Considering the roles of various stakeholders, including

patients, healthcare providers, and technology developers, in the implementation
plan. INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 50
Potential Challenges and Solutions

•Anticipated Barriers: Identifying potential challenges that may arise during the research
and implementation phases.

•Risk Mitigation: Proposing solutions and strategies to mitigate the identified risks and
ensure the success of the research study.

•Ethical Considerations: Addressing any ethical considerations related to the research,

including patient consent and data security.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 51

Citing Sources

•Academic References: Listing the academic papers, studies, and articles that have
been cited throughout the presentation.

•Technical Documentation: Providing references to technical documentation related

to AI algorithms, IoT devices, and HealthFaaS.

•Additional Reading: Recommending additional reading materials for audience

members interested in delving deeper into the topics covered.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 52

Further Research

•Ongoing Studies: Informing the audience of ongoing studies and research projects
related to AI, IoT, and heart disease detection.

•Participation Opportunities: Discussing opportunities for audience members to

participate in research studies or contribute to the field.

•Contact Information: Providing contact information for the audience to reach out
with questions, feedback, or collaboration inquiries.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 53

Technological Demo

•Live Demonstrations: Offering the possibility of live demonstrations of AI and IoT

technologies for interested audience members.

•Interactive Experiences: Discussing interactive experiences that allow the audience

to engage with the technology and understand its practical applications.

•Virtual Resources: Providing links to virtual resources, simulations, and apps that
showcase the capabilities of AI and IoT in healthcare.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 54

Community Engagement

•Public Workshops: Announcing upcoming public workshops or seminars on the use

of technology in healthcare and heart disease prevention.

•Volunteer Programs: Highlighting volunteer programs that support the deployment

and testing of AI and IoT solutions in community healthcare settings.

•Feedback Channels: Encouraging the audience to provide feedback on the

presentation and the topics discussed, fostering community engagement.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 55

Acknowledgments

•Collaborators and Contributors: Acknowledging the collaborators, contributors, and

institutions that have played a role in the research and development of HealthFaaS.

•Funding Sources: Recognizing the funding sources and grants that have supported the
work presented in the presentation.

•Audience Appreciation: Expressing gratitude to the audience for their attention and
interest in the topic of early heart disease detection using AI and IoT.

INTERVIEW FOR Ph.D. ADMISSION FOR JULY 2024 SESSION 56