SlideShare ist ein Scribd-Unternehmen logo
1 von 73
Potential impact of COVID-19 on the adoption of
healthcare, smart homes, and Hospital
Dr. R. Periyasamy M.Tech (IITM) & PhD (IITD)
Assistant Professor
Department of Instrumentation & Control
Engineering,
National Institute of Technology, Tiruchirappalli,
Trichy-620015
periyasamyr@nitt.edu
3/4/2023 1
CHECKOUT
THE LATESTGLOBAL SITUATION
2
* Data are incomplete for the current week. Cases depicted by bars; deaths depicted by line
WHO
Coronavirus
Disease (COVID-19)
Dashboard
Current global situation
Casesreported toWHO asof28 February2021
• > 113 million cases • > 2.5 million deaths
3/4/2023 2
THE COVID-19 PANDEMIC
Stage 1
An unknown virus
emerges
3
Stage 2
A pandemic
unfolds
Stage 3
The pandemic
accelerates
Stage 4
A multi-faceted
pandemic
Overview of the COVID-19 pandemic
A high-level overview of emerging issues
As the COVID-19 pandemic evolves, several distinct questions and challenges arise...
Stage 5
Medical counter
measures
3/4/2023
AN UNKNOWN VIRUS EMERGES
Stage 1
An unknown virus emerges
An unusual cluster of severe
pneumonia cases is identifiedin China
raisingquestions about a possiblenew
disease (December 2019)
Source:WHO 21 January 2020
• Some cases are linked to a sea food market, in
Wuhan, Hubei province, China
• Some patients die, especially older people and
those with other medical conditions
• The new disease is caused by a novel coronavirus,
a family of viruses known to infect animals &
humans
• The infection causes respiratory disease ranging
from mild to severe disease
Following advice from the IHR Emergency
Committee for COVID-19, on 30 January 2020 –
with around 7700 confirmed cases in China and
82 cases outside of China – WHO declares the
outbreak to be a Public Health Emergency of
InternationalConcern.
At that time, no death relatedto COVID-19 is
recordedoutside China
4
3/4/2023
AN UNKNOWN VIRUS EMERGES
Stage 1
5
Initial response to the virus
31st Dec 2019: Cluster of pneumoniadetectedin Wuhan
1st Jan 2020: WHO activates Incident Management T
eam
5 Jan: WHO issues firstDisease OutbreakNews
23 Jan: First IHR Emergency Committee meeting
23 Jan: Restrictions in Wuhan,all transportin & out of Wuhansuspended
30 Jan: WHO declares Public Health Emergency of InternationalConcern
4 Feb: Strategic Preparedness & Response Plan issued
11 Mar: WHO describes COVID-19as a pandemic
3/4/2023
AN UNKNOWN VIRUS EMERGES
Stage 1
Research for diagnostics,vaccinesand therapeuticsbegan immediately
• After the West Africa Ebola outbreak in
2014-2016, the World Health Organization
(WHO) adopted a plan for research and
development (R&D) – this is known as the
R&D Blueprint
• The R&D Blueprint is a global strategy to
enable rapid activation of research during
epidemics and fast-track development of
diagnostics, vaccines and medicines.
• WHO convened the first global COVID-19
Research and Innovation Forum in Geneva
on 11-12 February 2020.
6
3/4/2023
A PANDEMIC UNFOLDS
Stage 2
A pandemic unfolds
7
By 12 March 2020, there
were over 120,000 cases
and over 4,600 deaths
3/4/2023
A PANDEMIC UNFOLDS
Stage 2
In many countries, spread of COVID-19 leads to community transmission
• ‘Flatteningthe curve’ is importantas in everycountry,there are limited numbersof
hospitals, nurses and doctors
• The capacity of the health system can be exceeded if toomanypeopleseek healthcareat
the same time
• Testing,isolatingpositivecases,
contact tracing and PHSM are
important to flattening the curve
• Some countries manage to stop
transmission with control
measures
• Many countries close schools,
shops, workplaces, bars,
restaurants as well as borders
and ask people to stay home to
limit the spread of the virus
8
3/4/2023
A PANDEMIC UNFOLDS
Stage 2
Implementation of Public Health & Social Measures
Personal protective
measures
 Hand hygiene
 Respiratory
etiquette
 Face masks
Travel-related
measures
 Travel advices
 Travel restrictions
 Border closure
 Entry and exit
screenings
Social distancing measures
 Contact tracing
Isolation of sick
individuals
 Quarantine of exposed
individuals
School measures /
closures
Workplace measures /
closures
 Avoiding crowding
Environmental measures
 Surface and object
cleaning
 Increased ventilation
WHAT HOW
9
3/4/2023
A PANDEMIC UNFOLDS
Stage 2
Health systems are under pressure even in
wealthy countries
• Hospitals and health workersfacerising demand to attend to a
growing number of COVID-19 patients
• Materials are in short supply:
 Personal protective equipment
 Oxygen and ventilators
 COVID-19 diagnostic tests
š Globally aggregated weekly surveillance data based on cases notifiedto WHO
https://www.who.int/fr/news/item/17-09-2020-keep-health-workers-safe-to-keep-patients-safe-who
https://apps.who.int/iris/handle/10665/336265
Photo: WHO
10
• Health workersare affected,of all detailed casereportssubmitted to WHO by October2020,
14% of the cases are health workers. Capacity building and access to adequate personal
protective equipment & measureslead tothe decreaseof this percentage.š
• Usual health care is cancelled or postponed with a major impact on other endemic or
chronic diseases as well as on preventive activities such as routine immunization
3/4/2023
THE PANDEMIC ACCELERATES
Stage 3
The pandemic accelerates
Number of newconfirmed COVID-19 cases bydatereportedtoWHO andregion
The epicentre moves from
Europe to the Americas
By 1 July 2020, there were over
10.3 million cases and over
503,000 deaths in 215 countries
or areas and two cruise ships
Source: WHO
11
3/4/2023
THE PANDEMIC ACCELERATES
Stage 3
Beyond the health crisis: impact on
all of society
• National restrictions have a huge impact on businesses
and individuals lose jobs
• The travel sector is greatly affected by international
movement restrictions
• Pressure mounts to re-open societies, including schools to
minimize social and economic damage
InsideChicagoO’HareInternationalAirport,UnitedStatesofAmerica
Countries start re-opening societies
The ‘first wave’ passes in countries first affected which
see cases declining
Some country borders re-open and restrictions are
eased, in particular during holidays in the northern
hemisphere
Source: www.weforum.org/agenda/2020/06/imf-lockdown-recession-covid19-coronavirus-economics-recession/
12
3/4/2023
THE PANDEMIC ACCELERATES
Stage 3
COVID-19 spreads more easily in certain
settings
• Certain situations and activities (such as singing,
exercising, shouting) are identified to be at higher risk for
COVID-19 transmission:
 Crowded places
 Close-contact settings
 Confined and
enclosed spaces with
poor ventilation
13
3/4/2023
A MULTIFACETED PANDEMIC
Stage 4
A multifaceted pandemic
Source: WHO 01 November 2020
There is sustained
transmission in the US
and India, a new
increase of cases in
Europe (2nd wave); while
other countries remain
COVID-19 free (e.g. New
Zealand)
By 01 November, there
are nearly 46 million
cases and over 1.19
million deaths
Source:WHO
14
3/4/2023
A MULTIFACETED PANDEMIC
Stage 4
Global partnership
Source: WHO 06 October 2020
• Access to COVID-19 Tools (ACT) Accelerator is a global
collaboration end to end process, to accelerate
development, production, and access to COVID-19
vaccines, therapeutics and diagnostics
 Vaccines in development as of 1st November 2020:
• 154 in preclinical evaluation
• 44 in clinical evaluation
• 10 in phase III trials
 Dexamethasone has been confirmed as a useful
therapeutic treatment for severe cases
 An antigen-based rapid diagnostic test has been
approved
• Information on vaccines
• More information on the ACT Accelerator
2 billion
doses
globallyby
endof2021
245 million
therapeutic
coursesinlow
andmiddle-
incomecountries
bymid-2021
500 million
testsinlowand
middle-income
countries
bymid-2021
Health SystemsConnector
Strengtheninghealthsystemstomakesureessential
COVID-19tools reachthepeople whoneedthem
15
3/4/2023
MEDICAL COUNTER MEASURES
Stage 5
Medical counter measures available
Source:WHO
16
The increase of cases in
Europe and the USA (2nd
wave) continues;
The first COVID-19
vaccines are rolled out;
There is growing concern
about emerging variants
As of January 3rd, more
than 83 million cases and
over 1.8 million deaths
Source:WHO
3/4/2023
MEDICAL COUNTER MEASURES
• As of 2nd March 2021, there are 76 COVID-19 candidate vaccines in clinical development of
which 12 are in Phase III and 4 in Phase IV trials
• There are another 182 candidate vaccines in preclinical development
• More than 90% of all top candidate vaccines will be delivered through intra-muscular injection
• Most are designed for a two-doseschedule
Stage 5
COVID-19 vaccine accelerated development
Source: 2nd March 2021
https://www.who.int/publications/m/item/draft-landscape-of-covid-19-candidate-vaccines
17
3/4/2023
MEDICAL COUNTER MEASURES
Stage 5
COVID-19 vaccine development
As of 3rd March, more than 265 million vaccine doses have been administered:
 Different vaccines (3 platforms) have been administered (Pfizer, Moderna, Oxford/AZ, SII,
Gamaleya, Sinopharm, Sinovac, Bharat Biotech)
From Bloomberg COVID-19 vaccines tracker on Global Distribution (28th Feb2021)
35%
30%
20%
17% 15% 13% 10% 10%
% of population given at least 1 dose
52%
Israel UAE U.K. Bahrain Chile U.S.
https://www.bloomberg.com/graphics/covid-vaccine-tracker-global-distribution/
https://ourworldindata.org/
Serbia Malta Morocco
18
3/4/2023
MEDICAL COUNTER MEASURES
Stage 5
New emerging SARS-CoV-2 variants and their implications
• New SARS-CoV-2 variants:
 Sept. 2020, a variant emerged in Denmark related to mink farming
 Variant detected in the United Kingdom in December 2020
 Variant detected in South Africa in December 2020
 9th January 2021, variant detected in Japan among persons coming
back from Brazil
• All these variants involve genetic mutations coding for the
spike protein
• The spike protein of SARS-CoV-2 is targeted by most vaccines currently
approved or in development; mutations of the spike protein are closely
monitored
• The mode of transmission of the virus variantshas not changed
• The same preventive measures continue to be effective and should continue to be implemented¹
š https://www.who.int/publications/i/item/considerations-in-adjusting-public-health-and-social-measures-in-the-context-of-covid-19-interim-guidance
19
3/4/2023
MEDICAL COUNTER MEASURES
• Baseline analysis by the World
Bank Group estimated that
COVID-19 could push an
additional 88 million people
into extreme poverty in 2020.
In the worst case scenario, it
could be 115 million people
• The largest share of the ‘new
poor’ are living in South Asia
and Sub-Saharan Africa
Stage 5
Extreme poverty is predictedto increasesharply
Sources: Lakner et al. (2020) (updated), PovcalNet, Global Economic Prospects
Note: Extreme poverty is measured as the number of people living on less than $1.90 per day.
Figure. Forecastof number of people living in extreme poverty (From WoldBank Blogs)
20
3/4/2023
COVID 19-
Diagnostic method
Imaging Modalities - Chest X-Ray and Computer
Tomography
RT-PCR test
3/4/2023 21
Challenges in Conventional Methods
Imaging Modalities
• It’s a complex diagnostic technique
• Frequent exposure to radiation is harmful
to the body
• Not applicable for children, pregnant
women, mentally challenged people
• Images of the lungs are hidden by the rib
cage
• Its costly diagnosing technique
• Expertise is needed for this technique
• Direct contact with patients
• It’s risky for technicians
RTPCR test
• False positive results
• False negative results
• Different steps
• Needing different lab tools
• Direct contact with patients
• It’s risky for technicians
3/4/2023 22
Emerging of Auscultation Technique
Respiratory sounds
Vibration
Voice
Lung sounds
Heart sounds
Bowel sound
Breathing
Cough Digital Stethoscope
Diagnostic tools for
different diseases
Early
detection and
inexpensive
solutions
Technological
researchers and
medical scientists
3/4/2023 23
Block Diagram
3/4/2023 24
1. Data Acquisition
 COUGHVID
 COVID-19 sounds
crowdsourced
dataset
 COVID-19 sounds app
 Corona voice detect App
3/4/2023 25
COVID-19 sounds crowdsourced dataset
• Approved by the Ethics Committee of the Department of Computer Science
and Technology at the University of Cambridge
• partly funded by the European Research Council through Project EAR
#833296
• enable machine learning model training and evaluation tens of thousands
of participants
• easy-to-use for researchers to facilitate healthcare model development
• 53,449 audio samples (over 552 hours) from 36,116 participants
• 62% are male, 36% are female
• one year from April 2020 to April 2021
3/4/2023 26
Normalization
Normalized to certain level so expected
amplitude of signal is not affected from data
acquition
3/4/2023 27
2. Dataset Preparation
Data Augmentation
i) Stretching Time (ST): Increase or reduce the sample sound signal (to unchanged
running
pitch). Based on the four factors {0.80, 0.94, 1.06, and 1.24} the duration is stretched.
ii). Shift Pitch1 (SP1): Sound/audio samples can be increased or decreased (to
unchanged
running pitch), and every sample can be shifted differently by four values (-1,-2,-2,-1).
iii). Shift Pitch2 (SP2): We wanted to build a second augmentation package because our
initial tests showed that pitch shifting was an especially beneficial increase. Every
sample was pitch moved by four higher values (in different sizes and shapes) this time
(-2.5,-3.5, 3.5, and 2.5).
iv). Compression of Range Dynamically (CRD): We have compressed these 4 parameters
online, one taken from the
3/4/2023 28
3. Data Pre-processing: Signal Denoising
 Involves removal of noise like external artifacts from original signal
3/4/2023 29
Signal
Pre-processing
Linear Filtering
Blind Source
Separation
Non Linear filtering
Adaptive filtering
Techniques
Wavelet
based
denoising
Modulation
filtering
Independent
Component
analysis
Linear filtering
 Butterworth FIR filter
 Butterworth IIR filter
 Savitzky Golay Filter
 Smoothing filter
 Moving Average filter
 Gaussian Filter
 Median Filter
 Rectangular window FIR filter
Adaptive filtering techniques
 Least Mean Square Algorithm
 Recursive Least Square Algorithm
 Adaptive Line Enhancement
 Adaptive Noise Cancellation
 Empirical Mode Decomposition
 Ensemble Empirical Mode
Decomposition
 Variation Mode Decomposition
3/4/2023 30
Non-Linear filtering
Wavelet-based Denoising- Heuristic
Threshold Approach
1. Continuous Wavelet Transform
2. Discrete Wavelet Transform
Input time
series
Time to frequency
Domain conversion
3/4/2023 31
Fourier
Transform
Short Time
Fourier
Transform
Wavelet
Transform
• Windowing
• Maps signals
into two
dimension
space
• Hanning window
• Hamming window
• Haar window
• Daubechies window
• Symlets window
• Multiple windows
• Allows coarse to fine
multiresolution
predictive of signals
Modulation
Filtering
 Spectro-
Temporal
Separation
 Frequency
separation
Spectrogram
ICA
Convolution
extension of
Fast ICA
3/4/2023 32
Independent
Component
Analysis
Blind Source
Separation
Basic BSS
Sequential BSS
Non-Negative
Matrix
Factorization
BSS
Periodic Source
Separation
Convolutive
BSS
Denoising Evaluation metrics
 Signal to Noise Ratio
 Root Mean Square error
 Correlation Coefficient
 Normalized Root Mean Square
 Normalized max amplitude error
 Percentage distortion
3/4/2023 33
4. Signal Analysis
To convert raw data to some type of parametric representation
called features
• Statistical analysis
• Discrete Fourier transform analysis
• Frequency Domain analysis
• Time-frequency analysis
• MFCC
• Wavelet and Hilbert Huang Transform
• Autoregressive Modelling
3/4/2023 34
5. Feature Extraction
3/4/2023 35
Feature
Extraction
Time-domain
Time
frequency
domain
Frequency
domain
Statistical
features
Spectral
features
Time Domain Features
• Timing Intensity
• Zero crossing rate
• Transition ratio
• Power ratio
• Spontaneous energy
3/4/2023 36
Frequency Domain Features
• Frequency ratio-fmin/fmax
• Average instantaneous frequency
• Exchange time of instantaneous
frequency
• Maximum frequency
• Minimum frequency
• Peak frequency
• Median frequency
• Mean frequency
3/4/2023 37
Statistical Features
• Mean
• Variance
• Standard Deviation
• Skewness
• Kurtosis
• Shannon Entropy
• Energy
• Minimum and Maximum energy
• Entropy-based features
• Mean Crossing Irregularity
3/4/2023 38
Spectral features
 Spectral Centroid
 Spectral Decrease
 Spectral flatness
 Spectral slope
 Spectral spread
 Spectral crest
 Spectral entropy
 Spectral flux
 Spectral roll off
 Power spectral density
3/4/2023 39
Time- Frequency Domain Features
 Mel Frequency cepstral coefficients
 Discrete wavelet transform
 Short-time Fourier Transform
 Empirical Mode decomposition
technique
 Ensemble Empirical Mode
Decomposition Technique
 Variational Mode Decomposition
3/4/2023 40
Feature Selection
 Student t test
 Mann Whitney U test
 MANOVA test
 Perceptual Linear Predictions
 ROC analysis of individual features
• used to evaluate machine learning
models
• additional tool to evaluate most
relevant features
• highest discrimination capabilities
Statistical
Package for
Social Sciences
software-
MedCalc
software
3/4/2023 41
6. Classifiers
3/4/2023 42
Classifiers
Machine
learning
Technique
Deep learning
What is Machine learning?
An ML algorithm, which is a part of AI, uses an
assortment of accurate, probabilistic, and
upgraded techniques that empower computers to
pick up from the past point of reference and
perceive hard-to-perceive patterns from massive,
noisy, or complex datasets.
3/4/2023 43
Machine learning algorithms
4 types:
•Supervised and
•Unsupervised Learning
•Semi-supervised Learning
•Reinforcement Learning
Top 10 commonly used Machine Learning (ML)
Algorithms
•Linear regression
•Logistic regression
•Decision tree
•SVM algorithm
•Naive Bayes algorithm
•KNN algorithm
•K-means
•Random forest algorithm
•Dimensionality reduction algorithms
•Gradient boosting algorithm and AdaBoosting algorithm
3/4/2023 44
1. Linear Regression
3/4/2023 45
2. Logistic Regression
3. Decision tree
3/4/2023 46
4.SVM algorithm
5. NaĂŻve Bayes algorithm
3/4/2023 47
6. KNN algorithm
7. K-Means
3/4/2023 48
8. Random Forest algorithm
9. Dimensionality
Reduction
Algorithm
3/4/2023 49
9. Gradient and
Adaboosting
Algorithm
What is Deep Learning?
Deep learning has gained massive popularity in scientific computing, and its algorithms are widely used by
industries that solve complex problems. All deep learning algorithms use different types of neural networks
to perform specific tasks.
Deep learning uses artificial neural networks to perform sophisticated computations on large amounts of
data. It is a type of machine learning that works based on the structure and function of the human brain.
Deep learning algorithms train machines by learning from examples. Industries such as health care,
eCommerce, entertainment, and advertising commonly use deep learning.
3/4/2023 50
Types of algorithms used in Deep Learning
1.Convolutional Neural Networks (CNNs)
2.Long Short Term Memory Networks (LSTMs)
3.Recurrent Neural Networks (RNNs)
4.Generative Adversarial Networks (GANs)
5.Radial Basis Function Networks (RBFNs)
6.Multilayer Perceptrons (MLPs)
7.Self Organizing Maps (SOMs)
8.Deep Belief Networks (DBNs)
9.Restricted Boltzmann Machines( RBMs)
10.Autoencoders
3/4/2023 51
Classifier Performance Metrics
 Sensitivity
 Specificity
 Accuracy
 Confusion matrix
 AUC/ROC
 Precision
 Recall
 F1 Score
 Kappa
 Mathews Correlation Coefficient
 Cross validation
 Leave one out cross validation
scheme
 10 fold cross-validation- 10
subsets
 9 train models, 1 test model
 5 fold cross-validation 5 subsets
 4 train models, 1 test model
3/4/2023 52
Institutional Ethical Board
3/4/2023 53
Ethical Committee- Procedure
3/4/2023 54
3/4/2023 55
IEC checklist
1. Protocol discussed internally in the concerned department and obtained HOD’s permission?
2. Sources of funding mentioned
3. Adequate literature review with justification for the study mentioned
4. Detailed description of methodology (Study design, number of groups, sample size, etc)
5. No mirror statement in Inclusion/Exclusion criteria
6. The Sample size calculated and mentioned
7. Consent form part
8. Validated questionnaires both in Tamil and English attached
9. Signature of all investigators (Principal & Co-investigator) and Head of the corresponding
department obtained with date
10. Ethical issues explained in detail with a level of risk
3/4/2023 56
Covid-19 shock
COVID-19 impact on IoT Research and Development
57
Smart Stethoscope: Intelligent Respiratory Disease
Prediction System
3/4/2023 58
Smart Homes
New features and New
Sensors
New home energy
management solution
New features to Assist xFH
59
COVID-19 Timeline
60
61
62
63
Smart Buildings
64
65
66
67
The severity of the disease- varies from mild or asymptomatic to critical
patients are usually attended to on this basis.
severely ill are hospitalized as they may require external ventilation and
intensive care,
while those with milder symptoms are made to remain at home, provided
their condition does not worsen.
These measures prevent healthcare systems from being overloaded.
In this age of pervasive technology, the progress in wearable technology,
IoT, and telemedicine, make remote monitoring of patients to check if
their symptoms worsen, possible.
This can help in carrying out the strategy as mentioned above of
prioritizing healthcare resources and hospital beds for those who really
need them
This kind of monitoring is important for vulnerable groups, i.e those aged
above 60 and/or with pre-existing health issues like cardiovascular or
respiratory disorders.
Also, patients with Non-COVID-19 and Nonemergency medical problems
can be monitored remotely, which reduces the chances of cross-infection
68
3/4/2023 69
Healthcare
Abbott Laboratories, Philips Healthcare, Life Watch, GE Healthcare, Omron Healthcare,
Siemens Healthcare and Honeywell International Inc. etc
3/4/2023 70
Resources
• E-health and wellbeing monitoring using smart healthcare devices: An empirical
investigation
3/4/2023 71
WHO Coronavirus Disease (COVID-19) Dashboard
https://covid19.who.int/
R&D Blueprint and COVID-19
https://www.who.int/teams/blueprint/covid-19
Global research and innovation forum to mobilize international action in response to the novel coronavirus (2019-nCoV) emergency
https://www.who.int/news-room/events/detail/2020/02/11/default-calendar/global-research-and-innovation-forum-to-mobilize-
international-action-in-response-to-the-novel-coronavirus-(2019-ncov)-emergency
Considerations for implementing and adjusting public health and social measures in the context of COVID-19
https://www.who.int/publications/i/item/considerations-in-adjusting-public-health-and-social-measures-in-the-context-of-covid-19-
interim-guidance
Non-pharmaceutical public health measures for mitigating the risk and impact of epidemic and pandemic influenza
https://apps.who.int/iris/bitstream/handle/10665/329438/9789241516839-eng.pdf?ua=1
Keep health workers safe to keep patients safe: WHO
https://www.who.int/news/item/17-09-2020-keep-health-workers-safe-to-keep-patients-safe-who?v=4
Prevention, identification and management of health worker infection in the context of COVID-19: interim guidance, 30 October 2020
https://apps.who.int/iris/handle/10665/336265
IMF: New predictions suggest a deeper recession and a slower recovery
https://www.weforum.org/agenda/2020/06/imf-lockdown-recession-covid19-coronavirus-economics-recession/
72
Resources
3/4/2023
Resources (2)
73
Three factors help you make safer choices during COVID-19
https://www.who.int/teams/risk-communication/covid-19-transmission
Infodemic management
https://www.who.int/teams/risk-communication/infodemic-management
COVID-19 vaccines
https://www.who.int/emergencies/diseases/novel-coronavirus-2019/covid-19-vaccines
Fair allocation mechanism for COVID-19 vaccines through the COVAX Facility
https://www.who.int/publications/m/item/fair-allocation-mechanism-for-covid-19-vaccines-through-the-covax-facility
Draft landscape and tracker of COVID-19 candidate vaccines
https://www.who.int/publications/m/item/draft-landscape-of-covid-19-candidate-vaccines
Bloomberg
https://www.bloomberg.com/graphics/covid-vaccine-tracker-global-distribution/
Our World in Data
https://ourworldindata.org/
World Bank
https://blogs.worldbank.org/voices/2020-year-review-impact-covid-19-12-charts
The World Health Organization (WHO) is not responsible for the accuracy of information provided by external sites.
The mention of specific companies does not imply that they are endorsed by WHO.
3/4/2023

Weitere ähnliche Inhalte

Ähnlich wie update51_pandemic_overview_where_are_we_now (1).pptx

Scopus Indexed Journal- AIP Conference Proceedings May 2023.pdf
Scopus Indexed Journal- AIP Conference Proceedings May 2023.pdfScopus Indexed Journal- AIP Conference Proceedings May 2023.pdf
Scopus Indexed Journal- AIP Conference Proceedings May 2023.pdf
Pugalendhi R
 
Covid-19: risk assessment and mitigation measures in healthcare and non healt...
Covid-19: risk assessment and mitigation measures in healthcare and non healt...Covid-19: risk assessment and mitigation measures in healthcare and non healt...
Covid-19: risk assessment and mitigation measures in healthcare and non healt...
Ahmed Hasham
 
COVID-19: Knowledge Base, Attitudes and Practices among Practising Journalist...
COVID-19: Knowledge Base, Attitudes and Practices among Practising Journalist...COVID-19: Knowledge Base, Attitudes and Practices among Practising Journalist...
COVID-19: Knowledge Base, Attitudes and Practices among Practising Journalist...
Premier Publishers
 
COVID-19 pandemic in Nigeria: Misconception among individuals, impact on anim...
COVID-19 pandemic in Nigeria: Misconception among individuals, impact on anim...COVID-19 pandemic in Nigeria: Misconception among individuals, impact on anim...
COVID-19 pandemic in Nigeria: Misconception among individuals, impact on anim...
BRNSSPublicationHubI
 
Comparing the Coronavirus pandemic in New Zealand and Iraq: A Preventive Medi...
Comparing the Coronavirus pandemic in New Zealand and Iraq: A Preventive Medi...Comparing the Coronavirus pandemic in New Zealand and Iraq: A Preventive Medi...
Comparing the Coronavirus pandemic in New Zealand and Iraq: A Preventive Medi...
Vedica Sethi
 

Ähnlich wie update51_pandemic_overview_where_are_we_now (1).pptx (20)

Scopus Indexed Journal- AIP Conference Proceedings May 2023.pdf
Scopus Indexed Journal- AIP Conference Proceedings May 2023.pdfScopus Indexed Journal- AIP Conference Proceedings May 2023.pdf
Scopus Indexed Journal- AIP Conference Proceedings May 2023.pdf
 
Main
MainMain
Main
 
COVID-19
COVID-19COVID-19
COVID-19
 
Covid 19 emergencia Dr. Freddy Flores Malpartida
Covid 19 emergencia Dr. Freddy Flores MalpartidaCovid 19 emergencia Dr. Freddy Flores Malpartida
Covid 19 emergencia Dr. Freddy Flores Malpartida
 
All you need to know about COVID-19 - Situational Update
All you need to know about COVID-19 - Situational UpdateAll you need to know about COVID-19 - Situational Update
All you need to know about COVID-19 - Situational Update
 
Yale-Tulane-Sacred Heart- ESF-8 Special Global Report - COVID-19 4-27-20
Yale-Tulane-Sacred Heart- ESF-8 Special  Global Report - COVID-19 4-27-20 Yale-Tulane-Sacred Heart- ESF-8 Special  Global Report - COVID-19 4-27-20
Yale-Tulane-Sacred Heart- ESF-8 Special Global Report - COVID-19 4-27-20
 
Covid-19: risk assessment and mitigation measures in healthcare and non healt...
Covid-19: risk assessment and mitigation measures in healthcare and non healt...Covid-19: risk assessment and mitigation measures in healthcare and non healt...
Covid-19: risk assessment and mitigation measures in healthcare and non healt...
 
Disaster management social science class 9
Disaster management social science class 9 Disaster management social science class 9
Disaster management social science class 9
 
Abstract congress covid 19.docx30
Abstract congress covid 19.docx30Abstract congress covid 19.docx30
Abstract congress covid 19.docx30
 
Coronavirus Pandemic
Coronavirus PandemicCoronavirus Pandemic
Coronavirus Pandemic
 
Ipc draft
Ipc draftIpc draft
Ipc draft
 
COVID-19: Knowledge Base, Attitudes and Practices among Practising Journalist...
COVID-19: Knowledge Base, Attitudes and Practices among Practising Journalist...COVID-19: Knowledge Base, Attitudes and Practices among Practising Journalist...
COVID-19: Knowledge Base, Attitudes and Practices among Practising Journalist...
 
COVID-19 pandemic in Nigeria: Misconception among individuals, impact on anim...
COVID-19 pandemic in Nigeria: Misconception among individuals, impact on anim...COVID-19 pandemic in Nigeria: Misconception among individuals, impact on anim...
COVID-19 pandemic in Nigeria: Misconception among individuals, impact on anim...
 
Comparing the Coronavirus pandemic in New Zealand and Iraq: A Preventive Medi...
Comparing the Coronavirus pandemic in New Zealand and Iraq: A Preventive Medi...Comparing the Coronavirus pandemic in New Zealand and Iraq: A Preventive Medi...
Comparing the Coronavirus pandemic in New Zealand and Iraq: A Preventive Medi...
 
Assessment of awareness, knowledge, readiness, prevalence and determinants o...
Assessment of awareness,  knowledge, readiness, prevalence and determinants o...Assessment of awareness,  knowledge, readiness, prevalence and determinants o...
Assessment of awareness, knowledge, readiness, prevalence and determinants o...
 
IRJET - Technology and COVID - 19
IRJET -  	  Technology and COVID - 19IRJET -  	  Technology and COVID - 19
IRJET - Technology and COVID - 19
 
5484101.pdf
5484101.pdf5484101.pdf
5484101.pdf
 
200th publication jfmpc- 4th name
200th publication  jfmpc- 4th name200th publication  jfmpc- 4th name
200th publication jfmpc- 4th name
 
Novel coronavirus- A comprehensive review
 Novel coronavirus- A comprehensive review Novel coronavirus- A comprehensive review
Novel coronavirus- A comprehensive review
 
58th Publication -JFMPC- 4th Name.pdf
58th Publication -JFMPC- 4th Name.pdf58th Publication -JFMPC- 4th Name.pdf
58th Publication -JFMPC- 4th Name.pdf
 

KĂźrzlich hochgeladen

Salient Features of India constitution especially power and functions
Salient Features of India constitution especially power and functionsSalient Features of India constitution especially power and functions
Salient Features of India constitution especially power and functions
KarakKing
 
Spellings Wk 3 English CAPS CARES Please Practise
Spellings Wk 3 English CAPS CARES Please PractiseSpellings Wk 3 English CAPS CARES Please Practise
Spellings Wk 3 English CAPS CARES Please Practise
AnaAcapella
 
The basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxThe basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptx
heathfieldcps1
 

KĂźrzlich hochgeladen (20)

Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024
 
Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)
 
Salient Features of India constitution especially power and functions
Salient Features of India constitution especially power and functionsSalient Features of India constitution especially power and functions
Salient Features of India constitution especially power and functions
 
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Kodo Millet  PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...Kodo Millet  PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
 
Spellings Wk 3 English CAPS CARES Please Practise
Spellings Wk 3 English CAPS CARES Please PractiseSpellings Wk 3 English CAPS CARES Please Practise
Spellings Wk 3 English CAPS CARES Please Practise
 
FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024FSB Advising Checklist - Orientation 2024
FSB Advising Checklist - Orientation 2024
 
SOC 101 Demonstration of Learning Presentation
SOC 101 Demonstration of Learning PresentationSOC 101 Demonstration of Learning Presentation
SOC 101 Demonstration of Learning Presentation
 
Introduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsIntroduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The Basics
 
How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17
 
Unit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptxUnit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptx
 
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...
Beyond_Borders_Understanding_Anime_and_Manga_Fandom_A_Comprehensive_Audience_...
 
Understanding Accommodations and Modifications
Understanding  Accommodations and ModificationsUnderstanding  Accommodations and Modifications
Understanding Accommodations and Modifications
 
Google Gemini An AI Revolution in Education.pptx
Google Gemini An AI Revolution in Education.pptxGoogle Gemini An AI Revolution in Education.pptx
Google Gemini An AI Revolution in Education.pptx
 
On National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan FellowsOn National Teacher Day, meet the 2024-25 Kenan Fellows
On National Teacher Day, meet the 2024-25 Kenan Fellows
 
How to setup Pycharm environment for Odoo 17.pptx
How to setup Pycharm environment for Odoo 17.pptxHow to setup Pycharm environment for Odoo 17.pptx
How to setup Pycharm environment for Odoo 17.pptx
 
The basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxThe basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptx
 
This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.
 
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
 
Towards a code of practice for AI in AT.pptx
Towards a code of practice for AI in AT.pptxTowards a code of practice for AI in AT.pptx
Towards a code of practice for AI in AT.pptx
 
Micro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdfMicro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdf
 

update51_pandemic_overview_where_are_we_now (1).pptx

  • 1. Potential impact of COVID-19 on the adoption of healthcare, smart homes, and Hospital Dr. R. Periyasamy M.Tech (IITM) & PhD (IITD) Assistant Professor Department of Instrumentation & Control Engineering, National Institute of Technology, Tiruchirappalli, Trichy-620015 periyasamyr@nitt.edu 3/4/2023 1
  • 2. CHECKOUT THE LATESTGLOBAL SITUATION 2 * Data are incomplete for the current week. Cases depicted by bars; deaths depicted by line WHO Coronavirus Disease (COVID-19) Dashboard Current global situation Casesreported toWHO asof28 February2021 • > 113 million cases • > 2.5 million deaths 3/4/2023 2
  • 3. THE COVID-19 PANDEMIC Stage 1 An unknown virus emerges 3 Stage 2 A pandemic unfolds Stage 3 The pandemic accelerates Stage 4 A multi-faceted pandemic Overview of the COVID-19 pandemic A high-level overview of emerging issues As the COVID-19 pandemic evolves, several distinct questions and challenges arise... Stage 5 Medical counter measures 3/4/2023
  • 4. AN UNKNOWN VIRUS EMERGES Stage 1 An unknown virus emerges An unusual cluster of severe pneumonia cases is identifiedin China raisingquestions about a possiblenew disease (December 2019) Source:WHO 21 January 2020 • Some cases are linked to a sea food market, in Wuhan, Hubei province, China • Some patients die, especially older people and those with other medical conditions • The new disease is caused by a novel coronavirus, a family of viruses known to infect animals & humans • The infection causes respiratory disease ranging from mild to severe disease Following advice from the IHR Emergency Committee for COVID-19, on 30 January 2020 – with around 7700 confirmed cases in China and 82 cases outside of China – WHO declares the outbreak to be a Public Health Emergency of InternationalConcern. At that time, no death relatedto COVID-19 is recordedoutside China 4 3/4/2023
  • 5. AN UNKNOWN VIRUS EMERGES Stage 1 5 Initial response to the virus 31st Dec 2019: Cluster of pneumoniadetectedin Wuhan 1st Jan 2020: WHO activates Incident Management T eam 5 Jan: WHO issues firstDisease OutbreakNews 23 Jan: First IHR Emergency Committee meeting 23 Jan: Restrictions in Wuhan,all transportin & out of Wuhansuspended 30 Jan: WHO declares Public Health Emergency of InternationalConcern 4 Feb: Strategic Preparedness & Response Plan issued 11 Mar: WHO describes COVID-19as a pandemic 3/4/2023
  • 6. AN UNKNOWN VIRUS EMERGES Stage 1 Research for diagnostics,vaccinesand therapeuticsbegan immediately • After the West Africa Ebola outbreak in 2014-2016, the World Health Organization (WHO) adopted a plan for research and development (R&D) – this is known as the R&D Blueprint • The R&D Blueprint is a global strategy to enable rapid activation of research during epidemics and fast-track development of diagnostics, vaccines and medicines. • WHO convened the first global COVID-19 Research and Innovation Forum in Geneva on 11-12 February 2020. 6 3/4/2023
  • 7. A PANDEMIC UNFOLDS Stage 2 A pandemic unfolds 7 By 12 March 2020, there were over 120,000 cases and over 4,600 deaths 3/4/2023
  • 8. A PANDEMIC UNFOLDS Stage 2 In many countries, spread of COVID-19 leads to community transmission • ‘Flatteningthe curve’ is importantas in everycountry,there are limited numbersof hospitals, nurses and doctors • The capacity of the health system can be exceeded if toomanypeopleseek healthcareat the same time • Testing,isolatingpositivecases, contact tracing and PHSM are important to flattening the curve • Some countries manage to stop transmission with control measures • Many countries close schools, shops, workplaces, bars, restaurants as well as borders and ask people to stay home to limit the spread of the virus 8 3/4/2023
  • 9. A PANDEMIC UNFOLDS Stage 2 Implementation of Public Health & Social Measures Personal protective measures  Hand hygiene  Respiratory etiquette  Face masks Travel-related measures  Travel advices  Travel restrictions  Border closure  Entry and exit screenings Social distancing measures  Contact tracing Isolation of sick individuals  Quarantine of exposed individuals School measures / closures Workplace measures / closures  Avoiding crowding Environmental measures  Surface and object cleaning  Increased ventilation WHAT HOW 9 3/4/2023
  • 10. A PANDEMIC UNFOLDS Stage 2 Health systems are under pressure even in wealthy countries • Hospitals and health workersfacerising demand to attend to a growing number of COVID-19 patients • Materials are in short supply:  Personal protective equipment  Oxygen and ventilators  COVID-19 diagnostic tests š Globally aggregated weekly surveillance data based on cases notifiedto WHO https://www.who.int/fr/news/item/17-09-2020-keep-health-workers-safe-to-keep-patients-safe-who https://apps.who.int/iris/handle/10665/336265 Photo: WHO 10 • Health workersare affected,of all detailed casereportssubmitted to WHO by October2020, 14% of the cases are health workers. Capacity building and access to adequate personal protective equipment & measureslead tothe decreaseof this percentage.š • Usual health care is cancelled or postponed with a major impact on other endemic or chronic diseases as well as on preventive activities such as routine immunization 3/4/2023
  • 11. THE PANDEMIC ACCELERATES Stage 3 The pandemic accelerates Number of newconfirmed COVID-19 cases bydatereportedtoWHO andregion The epicentre moves from Europe to the Americas By 1 July 2020, there were over 10.3 million cases and over 503,000 deaths in 215 countries or areas and two cruise ships Source: WHO 11 3/4/2023
  • 12. THE PANDEMIC ACCELERATES Stage 3 Beyond the health crisis: impact on all of society • National restrictions have a huge impact on businesses and individuals lose jobs • The travel sector is greatly affected by international movement restrictions • Pressure mounts to re-open societies, including schools to minimize social and economic damage InsideChicagoO’HareInternationalAirport,UnitedStatesofAmerica Countries start re-opening societies The ‘first wave’ passes in countries first affected which see cases declining Some country borders re-open and restrictions are eased, in particular during holidays in the northern hemisphere Source: www.weforum.org/agenda/2020/06/imf-lockdown-recession-covid19-coronavirus-economics-recession/ 12 3/4/2023
  • 13. THE PANDEMIC ACCELERATES Stage 3 COVID-19 spreads more easily in certain settings • Certain situations and activities (such as singing, exercising, shouting) are identified to be at higher risk for COVID-19 transmission:  Crowded places  Close-contact settings  Confined and enclosed spaces with poor ventilation 13 3/4/2023
  • 14. A MULTIFACETED PANDEMIC Stage 4 A multifaceted pandemic Source: WHO 01 November 2020 There is sustained transmission in the US and India, a new increase of cases in Europe (2nd wave); while other countries remain COVID-19 free (e.g. New Zealand) By 01 November, there are nearly 46 million cases and over 1.19 million deaths Source:WHO 14 3/4/2023
  • 15. A MULTIFACETED PANDEMIC Stage 4 Global partnership Source: WHO 06 October 2020 • Access to COVID-19 Tools (ACT) Accelerator is a global collaboration end to end process, to accelerate development, production, and access to COVID-19 vaccines, therapeutics and diagnostics  Vaccines in development as of 1st November 2020: • 154 in preclinical evaluation • 44 in clinical evaluation • 10 in phase III trials  Dexamethasone has been confirmed as a useful therapeutic treatment for severe cases  An antigen-based rapid diagnostic test has been approved • Information on vaccines • More information on the ACT Accelerator 2 billion doses globallyby endof2021 245 million therapeutic coursesinlow andmiddle- incomecountries bymid-2021 500 million testsinlowand middle-income countries bymid-2021 Health SystemsConnector Strengtheninghealthsystemstomakesureessential COVID-19tools reachthepeople whoneedthem 15 3/4/2023
  • 16. MEDICAL COUNTER MEASURES Stage 5 Medical counter measures available Source:WHO 16 The increase of cases in Europe and the USA (2nd wave) continues; The first COVID-19 vaccines are rolled out; There is growing concern about emerging variants As of January 3rd, more than 83 million cases and over 1.8 million deaths Source:WHO 3/4/2023
  • 17. MEDICAL COUNTER MEASURES • As of 2nd March 2021, there are 76 COVID-19 candidate vaccines in clinical development of which 12 are in Phase III and 4 in Phase IV trials • There are another 182 candidate vaccines in preclinical development • More than 90% of all top candidate vaccines will be delivered through intra-muscular injection • Most are designed for a two-doseschedule Stage 5 COVID-19 vaccine accelerated development Source: 2nd March 2021 https://www.who.int/publications/m/item/draft-landscape-of-covid-19-candidate-vaccines 17 3/4/2023
  • 18. MEDICAL COUNTER MEASURES Stage 5 COVID-19 vaccine development As of 3rd March, more than 265 million vaccine doses have been administered:  Different vaccines (3 platforms) have been administered (Pfizer, Moderna, Oxford/AZ, SII, Gamaleya, Sinopharm, Sinovac, Bharat Biotech) From Bloomberg COVID-19 vaccines tracker on Global Distribution (28th Feb2021) 35% 30% 20% 17% 15% 13% 10% 10% % of population given at least 1 dose 52% Israel UAE U.K. Bahrain Chile U.S. https://www.bloomberg.com/graphics/covid-vaccine-tracker-global-distribution/ https://ourworldindata.org/ Serbia Malta Morocco 18 3/4/2023
  • 19. MEDICAL COUNTER MEASURES Stage 5 New emerging SARS-CoV-2 variants and their implications • New SARS-CoV-2 variants:  Sept. 2020, a variant emerged in Denmark related to mink farming  Variant detected in the United Kingdom in December 2020  Variant detected in South Africa in December 2020  9th January 2021, variant detected in Japan among persons coming back from Brazil • All these variants involve genetic mutations coding for the spike protein • The spike protein of SARS-CoV-2 is targeted by most vaccines currently approved or in development; mutations of the spike protein are closely monitored • The mode of transmission of the virus variantshas not changed • The same preventive measures continue to be effective and should continue to be implementedš š https://www.who.int/publications/i/item/considerations-in-adjusting-public-health-and-social-measures-in-the-context-of-covid-19-interim-guidance 19 3/4/2023
  • 20. MEDICAL COUNTER MEASURES • Baseline analysis by the World Bank Group estimated that COVID-19 could push an additional 88 million people into extreme poverty in 2020. In the worst case scenario, it could be 115 million people • The largest share of the ‘new poor’ are living in South Asia and Sub-Saharan Africa Stage 5 Extreme poverty is predictedto increasesharply Sources: Lakner et al. (2020) (updated), PovcalNet, Global Economic Prospects Note: Extreme poverty is measured as the number of people living on less than $1.90 per day. Figure. Forecastof number of people living in extreme poverty (From WoldBank Blogs) 20 3/4/2023
  • 21. COVID 19- Diagnostic method Imaging Modalities - Chest X-Ray and Computer Tomography RT-PCR test 3/4/2023 21
  • 22. Challenges in Conventional Methods Imaging Modalities • It’s a complex diagnostic technique • Frequent exposure to radiation is harmful to the body • Not applicable for children, pregnant women, mentally challenged people • Images of the lungs are hidden by the rib cage • Its costly diagnosing technique • Expertise is needed for this technique • Direct contact with patients • It’s risky for technicians RTPCR test • False positive results • False negative results • Different steps • Needing different lab tools • Direct contact with patients • It’s risky for technicians 3/4/2023 22
  • 23. Emerging of Auscultation Technique Respiratory sounds Vibration Voice Lung sounds Heart sounds Bowel sound Breathing Cough Digital Stethoscope Diagnostic tools for different diseases Early detection and inexpensive solutions Technological researchers and medical scientists 3/4/2023 23
  • 25. 1. Data Acquisition  COUGHVID  COVID-19 sounds crowdsourced dataset  COVID-19 sounds app  Corona voice detect App 3/4/2023 25
  • 26. COVID-19 sounds crowdsourced dataset • Approved by the Ethics Committee of the Department of Computer Science and Technology at the University of Cambridge • partly funded by the European Research Council through Project EAR #833296 • enable machine learning model training and evaluation tens of thousands of participants • easy-to-use for researchers to facilitate healthcare model development • 53,449 audio samples (over 552 hours) from 36,116 participants • 62% are male, 36% are female • one year from April 2020 to April 2021 3/4/2023 26
  • 27. Normalization Normalized to certain level so expected amplitude of signal is not affected from data acquition 3/4/2023 27
  • 28. 2. Dataset Preparation Data Augmentation i) Stretching Time (ST): Increase or reduce the sample sound signal (to unchanged running pitch). Based on the four factors {0.80, 0.94, 1.06, and 1.24} the duration is stretched. ii). Shift Pitch1 (SP1): Sound/audio samples can be increased or decreased (to unchanged running pitch), and every sample can be shifted differently by four values (-1,-2,-2,-1). iii). Shift Pitch2 (SP2): We wanted to build a second augmentation package because our initial tests showed that pitch shifting was an especially beneficial increase. Every sample was pitch moved by four higher values (in different sizes and shapes) this time (-2.5,-3.5, 3.5, and 2.5). iv). Compression of Range Dynamically (CRD): We have compressed these 4 parameters online, one taken from the 3/4/2023 28
  • 29. 3. Data Pre-processing: Signal Denoising  Involves removal of noise like external artifacts from original signal 3/4/2023 29 Signal Pre-processing Linear Filtering Blind Source Separation Non Linear filtering Adaptive filtering Techniques Wavelet based denoising Modulation filtering Independent Component analysis
  • 30. Linear filtering  Butterworth FIR filter  Butterworth IIR filter  Savitzky Golay Filter  Smoothing filter  Moving Average filter  Gaussian Filter  Median Filter  Rectangular window FIR filter Adaptive filtering techniques  Least Mean Square Algorithm  Recursive Least Square Algorithm  Adaptive Line Enhancement  Adaptive Noise Cancellation  Empirical Mode Decomposition  Ensemble Empirical Mode Decomposition  Variation Mode Decomposition 3/4/2023 30 Non-Linear filtering
  • 31. Wavelet-based Denoising- Heuristic Threshold Approach 1. Continuous Wavelet Transform 2. Discrete Wavelet Transform Input time series Time to frequency Domain conversion 3/4/2023 31 Fourier Transform Short Time Fourier Transform Wavelet Transform • Windowing • Maps signals into two dimension space • Hanning window • Hamming window • Haar window • Daubechies window • Symlets window • Multiple windows • Allows coarse to fine multiresolution predictive of signals
  • 32. Modulation Filtering  Spectro- Temporal Separation  Frequency separation Spectrogram ICA Convolution extension of Fast ICA 3/4/2023 32 Independent Component Analysis Blind Source Separation Basic BSS Sequential BSS Non-Negative Matrix Factorization BSS Periodic Source Separation Convolutive BSS
  • 33. Denoising Evaluation metrics  Signal to Noise Ratio  Root Mean Square error  Correlation Coefficient  Normalized Root Mean Square  Normalized max amplitude error  Percentage distortion 3/4/2023 33
  • 34. 4. Signal Analysis To convert raw data to some type of parametric representation called features • Statistical analysis • Discrete Fourier transform analysis • Frequency Domain analysis • Time-frequency analysis • MFCC • Wavelet and Hilbert Huang Transform • Autoregressive Modelling 3/4/2023 34
  • 35. 5. Feature Extraction 3/4/2023 35 Feature Extraction Time-domain Time frequency domain Frequency domain Statistical features Spectral features
  • 36. Time Domain Features • Timing Intensity • Zero crossing rate • Transition ratio • Power ratio • Spontaneous energy 3/4/2023 36
  • 37. Frequency Domain Features • Frequency ratio-fmin/fmax • Average instantaneous frequency • Exchange time of instantaneous frequency • Maximum frequency • Minimum frequency • Peak frequency • Median frequency • Mean frequency 3/4/2023 37
  • 38. Statistical Features • Mean • Variance • Standard Deviation • Skewness • Kurtosis • Shannon Entropy • Energy • Minimum and Maximum energy • Entropy-based features • Mean Crossing Irregularity 3/4/2023 38
  • 39. Spectral features  Spectral Centroid  Spectral Decrease  Spectral flatness  Spectral slope  Spectral spread  Spectral crest  Spectral entropy  Spectral flux  Spectral roll off  Power spectral density 3/4/2023 39
  • 40. Time- Frequency Domain Features  Mel Frequency cepstral coefficients  Discrete wavelet transform  Short-time Fourier Transform  Empirical Mode decomposition technique  Ensemble Empirical Mode Decomposition Technique  Variational Mode Decomposition 3/4/2023 40
  • 41. Feature Selection  Student t test  Mann Whitney U test  MANOVA test  Perceptual Linear Predictions  ROC analysis of individual features • used to evaluate machine learning models • additional tool to evaluate most relevant features • highest discrimination capabilities Statistical Package for Social Sciences software- MedCalc software 3/4/2023 41
  • 43. What is Machine learning? An ML algorithm, which is a part of AI, uses an assortment of accurate, probabilistic, and upgraded techniques that empower computers to pick up from the past point of reference and perceive hard-to-perceive patterns from massive, noisy, or complex datasets. 3/4/2023 43
  • 44. Machine learning algorithms 4 types: •Supervised and •Unsupervised Learning •Semi-supervised Learning •Reinforcement Learning Top 10 commonly used Machine Learning (ML) Algorithms •Linear regression •Logistic regression •Decision tree •SVM algorithm •Naive Bayes algorithm •KNN algorithm •K-means •Random forest algorithm •Dimensionality reduction algorithms •Gradient boosting algorithm and AdaBoosting algorithm 3/4/2023 44
  • 45. 1. Linear Regression 3/4/2023 45 2. Logistic Regression
  • 46. 3. Decision tree 3/4/2023 46 4.SVM algorithm
  • 47. 5. NaĂŻve Bayes algorithm 3/4/2023 47 6. KNN algorithm
  • 48. 7. K-Means 3/4/2023 48 8. Random Forest algorithm
  • 49. 9. Dimensionality Reduction Algorithm 3/4/2023 49 9. Gradient and Adaboosting Algorithm
  • 50. What is Deep Learning? Deep learning has gained massive popularity in scientific computing, and its algorithms are widely used by industries that solve complex problems. All deep learning algorithms use different types of neural networks to perform specific tasks. Deep learning uses artificial neural networks to perform sophisticated computations on large amounts of data. It is a type of machine learning that works based on the structure and function of the human brain. Deep learning algorithms train machines by learning from examples. Industries such as health care, eCommerce, entertainment, and advertising commonly use deep learning. 3/4/2023 50
  • 51. Types of algorithms used in Deep Learning 1.Convolutional Neural Networks (CNNs) 2.Long Short Term Memory Networks (LSTMs) 3.Recurrent Neural Networks (RNNs) 4.Generative Adversarial Networks (GANs) 5.Radial Basis Function Networks (RBFNs) 6.Multilayer Perceptrons (MLPs) 7.Self Organizing Maps (SOMs) 8.Deep Belief Networks (DBNs) 9.Restricted Boltzmann Machines( RBMs) 10.Autoencoders 3/4/2023 51
  • 52. Classifier Performance Metrics  Sensitivity  Specificity  Accuracy  Confusion matrix  AUC/ROC  Precision  Recall  F1 Score  Kappa  Mathews Correlation Coefficient  Cross validation  Leave one out cross validation scheme  10 fold cross-validation- 10 subsets  9 train models, 1 test model  5 fold cross-validation 5 subsets  4 train models, 1 test model 3/4/2023 52
  • 56. IEC checklist 1. Protocol discussed internally in the concerned department and obtained HOD’s permission? 2. Sources of funding mentioned 3. Adequate literature review with justification for the study mentioned 4. Detailed description of methodology (Study design, number of groups, sample size, etc) 5. No mirror statement in Inclusion/Exclusion criteria 6. The Sample size calculated and mentioned 7. Consent form part 8. Validated questionnaires both in Tamil and English attached 9. Signature of all investigators (Principal & Co-investigator) and Head of the corresponding department obtained with date 10. Ethical issues explained in detail with a level of risk 3/4/2023 56
  • 57. Covid-19 shock COVID-19 impact on IoT Research and Development 57
  • 58. Smart Stethoscope: Intelligent Respiratory Disease Prediction System 3/4/2023 58
  • 59. Smart Homes New features and New Sensors New home energy management solution New features to Assist xFH 59
  • 61. 61
  • 62. 62
  • 63. 63
  • 65. 65
  • 66. 66
  • 67. 67
  • 68. The severity of the disease- varies from mild or asymptomatic to critical patients are usually attended to on this basis. severely ill are hospitalized as they may require external ventilation and intensive care, while those with milder symptoms are made to remain at home, provided their condition does not worsen. These measures prevent healthcare systems from being overloaded. In this age of pervasive technology, the progress in wearable technology, IoT, and telemedicine, make remote monitoring of patients to check if their symptoms worsen, possible. This can help in carrying out the strategy as mentioned above of prioritizing healthcare resources and hospital beds for those who really need them This kind of monitoring is important for vulnerable groups, i.e those aged above 60 and/or with pre-existing health issues like cardiovascular or respiratory disorders. Also, patients with Non-COVID-19 and Nonemergency medical problems can be monitored remotely, which reduces the chances of cross-infection 68
  • 70. Healthcare Abbott Laboratories, Philips Healthcare, Life Watch, GE Healthcare, Omron Healthcare, Siemens Healthcare and Honeywell International Inc. etc 3/4/2023 70
  • 71. Resources • E-health and wellbeing monitoring using smart healthcare devices: An empirical investigation 3/4/2023 71
  • 72. WHO Coronavirus Disease (COVID-19) Dashboard https://covid19.who.int/ R&D Blueprint and COVID-19 https://www.who.int/teams/blueprint/covid-19 Global research and innovation forum to mobilize international action in response to the novel coronavirus (2019-nCoV) emergency https://www.who.int/news-room/events/detail/2020/02/11/default-calendar/global-research-and-innovation-forum-to-mobilize- international-action-in-response-to-the-novel-coronavirus-(2019-ncov)-emergency Considerations for implementing and adjusting public health and social measures in the context of COVID-19 https://www.who.int/publications/i/item/considerations-in-adjusting-public-health-and-social-measures-in-the-context-of-covid-19- interim-guidance Non-pharmaceutical public health measures for mitigating the risk and impact of epidemic and pandemic influenza https://apps.who.int/iris/bitstream/handle/10665/329438/9789241516839-eng.pdf?ua=1 Keep health workers safe to keep patients safe: WHO https://www.who.int/news/item/17-09-2020-keep-health-workers-safe-to-keep-patients-safe-who?v=4 Prevention, identification and management of health worker infection in the context of COVID-19: interim guidance, 30 October 2020 https://apps.who.int/iris/handle/10665/336265 IMF: New predictions suggest a deeper recession and a slower recovery https://www.weforum.org/agenda/2020/06/imf-lockdown-recession-covid19-coronavirus-economics-recession/ 72 Resources 3/4/2023
  • 73. Resources (2) 73 Three factors help you make safer choices during COVID-19 https://www.who.int/teams/risk-communication/covid-19-transmission Infodemic management https://www.who.int/teams/risk-communication/infodemic-management COVID-19 vaccines https://www.who.int/emergencies/diseases/novel-coronavirus-2019/covid-19-vaccines Fair allocation mechanism for COVID-19 vaccines through the COVAX Facility https://www.who.int/publications/m/item/fair-allocation-mechanism-for-covid-19-vaccines-through-the-covax-facility Draft landscape and tracker of COVID-19 candidate vaccines https://www.who.int/publications/m/item/draft-landscape-of-covid-19-candidate-vaccines Bloomberg https://www.bloomberg.com/graphics/covid-vaccine-tracker-global-distribution/ Our World in Data https://ourworldindata.org/ World Bank https://blogs.worldbank.org/voices/2020-year-review-impact-covid-19-12-charts The World Health Organization (WHO) is not responsible for the accuracy of information provided by external sites. The mention of specific companies does not imply that they are endorsed by WHO. 3/4/2023