SlideShare a Scribd company logo
1 of 17
Download to read offline
Signal System Overview [WIP]
Contagion Spread Detection and Containment
Mapping v1.2
Authors: @Sachin Dev Duggal, @Dr Siddhartha Ghosh,
Contributors: @Rohan Patel @Saurabh Dhoot @Dr Sharon Jheeta
@Rushen Patel @Chandan Kumar
builder.ai
© April 2020 Engineer.ai Global Limited.
Except as otherwise noted, this work is licensed under under a
Creative Commons Attribution-NonCommercial-ShareAlike 4.0
International License.
© engineer.ai 2020
Problem - Preamble
Viruses / contagions spread an order of magnitude faster than the rate of testing. The contagion follows the path of a
social network whereas testing patterns are quasi linear in their approach.
Key is to reduce the potential of reaching terminal spread velocity and reducing the affected population.
© engineer.ai 2020
Problem - Preamble
- Contagions, like Covid-19 can spread incredibly quickly as they survive on surfaces or transmit over airborne human
contact. The rate at which they spread makes testing almost impossible and containment incredibly expensive.
- Until a vaccination is ready; isolation (containment) and digital passports are only ways to reduce terminal spread velocity
and economic fall out.
- Most affected in any such pandemics are the elderly and the impoverished; they do not have access to smartphones; but
by in large all have access to a feature phone. Therefore the contagion has disproportionately more impact to these people.
- The contagion has a number of spread vectors
- A diagnosed person has an incubation period that gets longer closer to R0 (first instance).
- A diagnosed person may have touched a surface that will stay “live” for upto X Days.
- Multiple diagnosed persons may have been in the same area thereby causing a compounding impact.
- A diagnosed person who travels will likely have spread to a larger person via the air conditioning systems of a flight.
- Alternative: a diagnosed person who has travelled previously and was mobile is likely to have infected significant
numbers in confined spaces
© engineer.ai 2020
Problem
- Build an effective and dynamic contact tracing solution that continuously shows a real-time view of most at risk and
provides a navigational direction to health authorities on how to break the spread down such that you have contained
communities.
- The solution has to be low tech as the most impact is usually on those without internet connected smartphones; ie elderly
or impoverished who have features phone.
- Development Market Smartphone penetration hovers at 60-70% for the elderly and 45-55% for the underprivileged.
- Emerging Market Smartphone penetration hover at 25-30% overall. **
- For the solution to work you need >90/95% coverage of a population at a given time; and a stratified testing model that
continuously re-evaluates the network and ensures that a real-time view of risk is shown.
- When you have a vaccine, you need to be able to the shortest path to stopping spreading and optimizing for the least
deaths which is not the same as a linear roll out of a vaccination especially when at the start the vaccination quantities
will be less.
** Source: https://www.finder.com/uk/mobile-internet-statistics
© engineer.ai 2020
Smartphones and Apps only won’t work - must be hybrid
- Because of their very low coverage they don’t have the ability to model analogous to population. In very specific forward
cities they can have a strong impact only if >90% download - but holistically on a global basis, a smartphone only strategy
won’t work.
- Without a model that can dynamically adjust the radius to create a “catchment” area they will create large false positives
or false negatives.
© engineer.ai 2020
Signal - Highlights Overview
1. Use the triangulation data available from all cell phone towers to be
able to pinpoint all devices (ie people).
a. The phone numbers would all be one way hashed so there is no
way to track a single individual.
2. Create an accurate backtrace using prior locations across cell towers -
this will be created on a spatiotemporal signal network graph
3. Superimpose this with health condition tags (ie did the person have a
lung condition.
a. Set a dynamic radius (s0) at each point of the backtrace to create
a catchment zone.
b. This will show who could be infected and who is most at risk.
i. i.e using the phone hash and medical tags (and their
severity).
4. The graph is a “living” structure that is effectively mapped in real time
as people move about and get diagnosed (true positives and true
negatives).
a. Effective reduction of area is key whether it's via testing or via
decay system (where if someone and their community have
shown no positive test results for a given period the whole
branch becomes clean).
5. The system can also identify which communities to test and the result
is then used to clear out entire branches of the graph until they have a
new node (person) entering them.
6. Vaccine Delivery needs to be done in a way to reduce the amount of
vaccine needed splinter the graph thereby making this a non spreading
localised problem which can then fall into a second wave of treatment.
© engineer.ai 2020
Signal - Three phases of the pandemic
1. Isolation
a. Reduce the amplitude of the spread (ie reduce the peak).
2. Allow limited back to work - Prevent economic free-fall or further damage
a. Create a dynamic digital passport for antibody testing and pseudo green light
b. Create a path to dynamically test (stratified testing).
3. Vaccination Deployment
a. With limited resources what’s the most optimized way to deploy to break universe of population into smaller and
smaller communities and track when communities fuse together.
© engineer.ai 2020
Signal - Highlights Overview
Path of an individual using
cell tower data
People they interact with
Dynamic Radius is the
catchment zone
When and where this
person got infected
Tertiary effected (not the
person diagnosed, not the
person they met but others
who crossed over)
Intensity of other contagion
carriers increases the radius
T=0 is when the person is
diagnosed
© engineer.ai 2020
Signal - 4D Spatial - Time Box
Contagions have a 4D infection spread
The 3d is the spatial plane and the 4d dimension is a time duration since an infected person visited the site.
The horizontal
radius is the
normal
geo-plane (ie the
spatial distance)
In this time box if
anyone crosses the
“spread radius”
they get tagged as
potentially infected.
Any given location needs
to have a t+4 days time
horizon as C19 has a time
box of 4 days on some
materials.
© engineer.ai 2020
Signal - Approach Overview
1. Use cell phone tower data.
2. Triangulate all devices using signal strength and
fixed nature of towers.
3. Superimpose this with account data for phone
numbers to infer mandatory spread.
4. Link the master universe of nodes based on
historical interaction to create a propagation
network (PN). This PN is dynamic and evolves
backward in time from the point a node has been
diagnosed to be infected
5. Adjust interactions on the network based on
intensity and other carriers (to establish who all
could be infected)
6. Fuse hashed node identifier with medical tags
basis EMR (electronic medical records) (again
only tagged not identifiable) (pre existing tags
that are medically designated with a weight)
1. Ie Node Hash has 3 Sev 1 conditions, 2 Sev
2 Conditions etc
7. Identify high risk nodes who have attributable
medical conditions on the PN and test
8. Stratified testing of those most likely; use
sensitivity and specificity to re-calibrate master
propagation network
9. Establish a vaccination strategy based on
understanding the characteristics of the PN with
an aim to reduce the size and the connectedness
of the network
© engineer.ai 2020
Signal uses a 5 point process
1. Person Triangulation & historical movement
a. Data from cell towers will tell you the movement off all people in a given geography (spatial plane).
b. You backtrace from when a person is positively diagnosed to see their reverse journey for a given period of time (the
contagion incubation period).
i. You do this for all people.
c. This will create a spatiotemporal signal network graph (SSNG)
d. One way hash of all numbers.
2. Propagation Network - with a dynamic radius (“spread) across the backtrace
e. The spread (s0) of a contagion (at a time t and location a) over the network should take into account the following: r
= radius of interaction of a node; p = potency of contagion; c = intensity of carriers; d = max time to dissipate on any
surface and i = saturation of nodes at a given t + d.
i. Signal DR will take into account the forward looking surface life time as well ie if a known contained person was
in a particular location then anyone coming in that location for 4 days would run the risk of being infected.
f. The dynamic radius tell you who additionally to add from (1) to the SSNG (you are effectively adding more nodes to
the network basis their inclusion in the radius).
© engineer.ai 2020
Signal uses a 5 point process cont’d
3. High Risk Identification
a. Use medical tags and severity to add attributes to hashed phone numbers so that you can map out those most
critically at risk. The most at risk get flagged quicker for testing.
4. Pruning and Spread Velocity Decreasing ---> Smarter testing to optimize lower test availability
a. Use stratified testing algorithm to define which are the parts of the graph to test.
b. Use implicit decay in contagions behavior to eliminate branches from testing. These become green branches that
unless they have a new person coming into them or a positive test remain green.
c. Create a vaccination path that aims to break the SSNG into smaller communities dividing the spread rather than
trying to do entire population at once. Optimize for the fastest path to vaccinate where ultimate death toll is minimal.
(This of this as a traffic navigation problem).
5. Interim Digital Passport
a. Whilst there is no fully rolled our vaccine or vaccine is still being rolled out digital certify people back into the
economy by seeing how they move across the spatial plane of the SSNG.
b. Use self test and clinical testing to create reinforced feedback into the network (including back trace - i.e if someone
is clear then the back trace for 14 days for that person is also clear).
© engineer.ai 2020
Holistic Visualization
Create a time vector (y-axis) and use a network structure for representation.
a. Moving vertically shows time backwards (ie days from the diagnosis)
b. Color coded interactions for who they met.
c. Show X plane as the map of the region so you can also see the locales visited.
© engineer.ai 2020
Holistic Visualization
Create a time vector (y-axis) and use a network
structure for representation.
a. Moving vertically shows time backwards (ie
days from the diagnosis)
b. Color coded interactions for who they met.
c. Show X plane as the map of the region so you
can also see the locales visited.
© engineer.ai 2020
Holistic Visualization
Create a flat heat map using icons on the
node diagram to show time from diagnosis
(t=0=date of being positively diagnosed).
Color code regions of high positive diagnosis and
their paths (ie if 5 people 5 days ago were in a
particular place)
Show the network interaction
(person a met person b)
© engineer.ai 2020
Holistic Visualization
Creating communities that become bigger/smaller (engulf or get divided)
basis the movement of infected people in between them.
Each “bubble” is a community that is continuously expanding or contracting.
© engineer.ai 2020
Detailed Framework Paper & References
Please see the detailed paper here - as we are working on this in real time we have asked for
verified email addresses to access this so that we can get updated content notified.
Visit this site: https://docsend.com/view/862npsj
1. Spatiotemporal Signal Visualizations
1. https://www.mdpi.com/2220-9964/7/9/371/htm
2. Triangulation/trilateration:
1. https://www.101computing.net/cell-phone-trilateration-algorithm/
2. https://searchengineland.com/cell-phone-triangulation-accuracy-is-all-over-the-map-14790
3. Epidemiology / Epidemiology contact tracing / social network spread
1. http://escholarship.umassmed.edu/cgi/viewcontent.cgi?article=2155&context=qhs_pp
2. https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0095133
3. https://academic.oup.com/aje/article/162/10/1024/65086
4. https://arxiv.org/pdf/1403.1011.pdf
5. http://biocircuits.ucsd.edu/lev/papers/contact_tracing1.pdf
4. Examples of visualisations:
1. https://cdv.dei.uc.pt/visualizing-urban-mobility/
2. https://www.fastcompany.com/3023416/outbreak-watch-how-quickly-an-epidemic-would-spread-across-the-world
3. https://www.wired.com/2015/04/see-diseases-spread-mesmerizing-graphics/

More Related Content

What's hot

A secure routing process to simultaneously defend against false report and wo...
A secure routing process to simultaneously defend against false report and wo...A secure routing process to simultaneously defend against false report and wo...
A secure routing process to simultaneously defend against false report and wo...ieijjournal
 
LIGHT AND SECURE COMMUNICATION ALGORITHM FOR COGNITIVE RADIO NETWORK BY USING...
LIGHT AND SECURE COMMUNICATION ALGORITHM FOR COGNITIVE RADIO NETWORK BY USING...LIGHT AND SECURE COMMUNICATION ALGORITHM FOR COGNITIVE RADIO NETWORK BY USING...
LIGHT AND SECURE COMMUNICATION ALGORITHM FOR COGNITIVE RADIO NETWORK BY USING...Raja Larik
 
Integrated Security and Attack Detection Scheme for Wireless Sensor Networks
Integrated Security and Attack Detection Scheme for Wireless Sensor NetworksIntegrated Security and Attack Detection Scheme for Wireless Sensor Networks
Integrated Security and Attack Detection Scheme for Wireless Sensor NetworksEditor IJMTER
 
Modeling & automated containment of worms(synopsis)
Modeling & automated containment of worms(synopsis)Modeling & automated containment of worms(synopsis)
Modeling & automated containment of worms(synopsis)Mumbai Academisc
 
An epidemiological model of virus spread and cleanup
An epidemiological model of virus spread and cleanupAn epidemiological model of virus spread and cleanup
An epidemiological model of virus spread and cleanupUltraUploader
 
The mimetic virus A vector for cyberterrorism
The mimetic virus A vector for cyberterrorismThe mimetic virus A vector for cyberterrorism
The mimetic virus A vector for cyberterrorismNicholas Ayres
 
The comparison of immunization
The comparison of immunizationThe comparison of immunization
The comparison of immunizationIJCNCJournal
 
Secure and Reliable Data Routing in Wireless Sensor Network
Secure and Reliable Data Routing in Wireless Sensor NetworkSecure and Reliable Data Routing in Wireless Sensor Network
Secure and Reliable Data Routing in Wireless Sensor Networkdbpublications
 
Securing WSN communication using Enhanced Adaptive Acknowledgement Protocol
Securing WSN communication using Enhanced Adaptive Acknowledgement ProtocolSecuring WSN communication using Enhanced Adaptive Acknowledgement Protocol
Securing WSN communication using Enhanced Adaptive Acknowledgement ProtocolIJMTST Journal
 
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)IJERD Editor
 
Tqds time stamped quantum digital signature to defend
Tqds time stamped quantum digital signature to defendTqds time stamped quantum digital signature to defend
Tqds time stamped quantum digital signature to defendeSAT Publishing House
 
Delta sm analysis quintile analysis_march-may 2012
Delta sm analysis quintile analysis_march-may 2012Delta sm analysis quintile analysis_march-may 2012
Delta sm analysis quintile analysis_march-may 2012BrettJossSimulmedia
 
Modeling and automated containment of worms (synopsis)
Modeling and automated containment of worms (synopsis)Modeling and automated containment of worms (synopsis)
Modeling and automated containment of worms (synopsis)Mumbai Academisc
 
Hop by hop message authentication chapter 1
Hop by hop message authentication chapter 1Hop by hop message authentication chapter 1
Hop by hop message authentication chapter 1Selva Raj
 
CONTRADICTION COMMUNICATION RANGE OF SENSOR NETWORKS
CONTRADICTION COMMUNICATION RANGE OF SENSOR NETWORKSCONTRADICTION COMMUNICATION RANGE OF SENSOR NETWORKS
CONTRADICTION COMMUNICATION RANGE OF SENSOR NETWORKSpharmaindexing
 
Detection and Prevention of Attacks in Wireless Sensor Networks: A Survey
Detection and Prevention of Attacks in Wireless Sensor Networks: A SurveyDetection and Prevention of Attacks in Wireless Sensor Networks: A Survey
Detection and Prevention of Attacks in Wireless Sensor Networks: A Surveydbpublications
 

What's hot (17)

A secure routing process to simultaneously defend against false report and wo...
A secure routing process to simultaneously defend against false report and wo...A secure routing process to simultaneously defend against false report and wo...
A secure routing process to simultaneously defend against false report and wo...
 
LIGHT AND SECURE COMMUNICATION ALGORITHM FOR COGNITIVE RADIO NETWORK BY USING...
LIGHT AND SECURE COMMUNICATION ALGORITHM FOR COGNITIVE RADIO NETWORK BY USING...LIGHT AND SECURE COMMUNICATION ALGORITHM FOR COGNITIVE RADIO NETWORK BY USING...
LIGHT AND SECURE COMMUNICATION ALGORITHM FOR COGNITIVE RADIO NETWORK BY USING...
 
Integrated Security and Attack Detection Scheme for Wireless Sensor Networks
Integrated Security and Attack Detection Scheme for Wireless Sensor NetworksIntegrated Security and Attack Detection Scheme for Wireless Sensor Networks
Integrated Security and Attack Detection Scheme for Wireless Sensor Networks
 
Modeling & automated containment of worms(synopsis)
Modeling & automated containment of worms(synopsis)Modeling & automated containment of worms(synopsis)
Modeling & automated containment of worms(synopsis)
 
An epidemiological model of virus spread and cleanup
An epidemiological model of virus spread and cleanupAn epidemiological model of virus spread and cleanup
An epidemiological model of virus spread and cleanup
 
50120140506007 2
50120140506007 250120140506007 2
50120140506007 2
 
The mimetic virus A vector for cyberterrorism
The mimetic virus A vector for cyberterrorismThe mimetic virus A vector for cyberterrorism
The mimetic virus A vector for cyberterrorism
 
The comparison of immunization
The comparison of immunizationThe comparison of immunization
The comparison of immunization
 
Secure and Reliable Data Routing in Wireless Sensor Network
Secure and Reliable Data Routing in Wireless Sensor NetworkSecure and Reliable Data Routing in Wireless Sensor Network
Secure and Reliable Data Routing in Wireless Sensor Network
 
Securing WSN communication using Enhanced Adaptive Acknowledgement Protocol
Securing WSN communication using Enhanced Adaptive Acknowledgement ProtocolSecuring WSN communication using Enhanced Adaptive Acknowledgement Protocol
Securing WSN communication using Enhanced Adaptive Acknowledgement Protocol
 
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)
 
Tqds time stamped quantum digital signature to defend
Tqds time stamped quantum digital signature to defendTqds time stamped quantum digital signature to defend
Tqds time stamped quantum digital signature to defend
 
Delta sm analysis quintile analysis_march-may 2012
Delta sm analysis quintile analysis_march-may 2012Delta sm analysis quintile analysis_march-may 2012
Delta sm analysis quintile analysis_march-may 2012
 
Modeling and automated containment of worms (synopsis)
Modeling and automated containment of worms (synopsis)Modeling and automated containment of worms (synopsis)
Modeling and automated containment of worms (synopsis)
 
Hop by hop message authentication chapter 1
Hop by hop message authentication chapter 1Hop by hop message authentication chapter 1
Hop by hop message authentication chapter 1
 
CONTRADICTION COMMUNICATION RANGE OF SENSOR NETWORKS
CONTRADICTION COMMUNICATION RANGE OF SENSOR NETWORKSCONTRADICTION COMMUNICATION RANGE OF SENSOR NETWORKS
CONTRADICTION COMMUNICATION RANGE OF SENSOR NETWORKS
 
Detection and Prevention of Attacks in Wireless Sensor Networks: A Survey
Detection and Prevention of Attacks in Wireless Sensor Networks: A SurveyDetection and Prevention of Attacks in Wireless Sensor Networks: A Survey
Detection and Prevention of Attacks in Wireless Sensor Networks: A Survey
 

Similar to Covid-19 Spread Detection, Containment Mapping & Vaccine Delivery Framework

Spatio-temporal Monitoring of Health Epidemics in Real-Time-Some Considerations
Spatio-temporal Monitoring of Health Epidemics  in Real-Time-Some ConsiderationsSpatio-temporal Monitoring of Health Epidemics  in Real-Time-Some Considerations
Spatio-temporal Monitoring of Health Epidemics in Real-Time-Some Considerationssanjay_rana
 
A Survey on Person Detection for Social Distancing and Safety Violation Alert...
A Survey on Person Detection for Social Distancing and Safety Violation Alert...A Survey on Person Detection for Social Distancing and Safety Violation Alert...
A Survey on Person Detection for Social Distancing and Safety Violation Alert...IRJET Journal
 
Deep Learning Approaches for Diagnosis and Treatment of COVID-19
Deep Learning Approaches for Diagnosis and Treatment of COVID-19Deep Learning Approaches for Diagnosis and Treatment of COVID-19
Deep Learning Approaches for Diagnosis and Treatment of COVID-19IRJET Journal
 
Monitoring Pandemic Precautionary Protocols using Real-time Surveillance and ...
Monitoring Pandemic Precautionary Protocols using Real-time Surveillance and ...Monitoring Pandemic Precautionary Protocols using Real-time Surveillance and ...
Monitoring Pandemic Precautionary Protocols using Real-time Surveillance and ...darsh228313
 
NEW CORONA VIRUS DISEASE 2022: SOCIAL DISTANCING IS AN EFFECTIVE MEASURE (COV...
NEW CORONA VIRUS DISEASE 2022: SOCIAL DISTANCING IS AN EFFECTIVE MEASURE (COV...NEW CORONA VIRUS DISEASE 2022: SOCIAL DISTANCING IS AN EFFECTIVE MEASURE (COV...
NEW CORONA VIRUS DISEASE 2022: SOCIAL DISTANCING IS AN EFFECTIVE MEASURE (COV...IRJET Journal
 
IRJET- Fake News Detection and Rumour Source Identification
IRJET- Fake News Detection and Rumour Source IdentificationIRJET- Fake News Detection and Rumour Source Identification
IRJET- Fake News Detection and Rumour Source IdentificationIRJET Journal
 
Location tracking and_allerting_apparatus_and_method
Location tracking and_allerting_apparatus_and_methodLocation tracking and_allerting_apparatus_and_method
Location tracking and_allerting_apparatus_and_methodAditya Potharaju
 
Telemedicine in Clinical Research
Telemedicine in Clinical ResearchTelemedicine in Clinical Research
Telemedicine in Clinical ResearchClinosolIndia
 
COVID-19 FACE MASK DETECTION
COVID-19 FACE MASK DETECTIONCOVID-19 FACE MASK DETECTION
COVID-19 FACE MASK DETECTIONIRJET Journal
 
A CLOUD-BASED PROTOTYPE IMPLEMENTATION OF A DISEASE OUTBREAK NOTIFICATION SYS...
A CLOUD-BASED PROTOTYPE IMPLEMENTATION OF A DISEASE OUTBREAK NOTIFICATION SYS...A CLOUD-BASED PROTOTYPE IMPLEMENTATION OF A DISEASE OUTBREAK NOTIFICATION SYS...
A CLOUD-BASED PROTOTYPE IMPLEMENTATION OF A DISEASE OUTBREAK NOTIFICATION SYS...IJCSEA Journal
 
ENHANCED GREEN FIREWALL FOR EFFICIENT DETECTION AND PREVENTION OF MOBILE INTR...
ENHANCED GREEN FIREWALL FOR EFFICIENT DETECTION AND PREVENTION OF MOBILE INTR...ENHANCED GREEN FIREWALL FOR EFFICIENT DETECTION AND PREVENTION OF MOBILE INTR...
ENHANCED GREEN FIREWALL FOR EFFICIENT DETECTION AND PREVENTION OF MOBILE INTR...ijistjournal
 
A Cloud-Based Prototype Implementation of a Disease Outbreak Notification System
A Cloud-Based Prototype Implementation of a Disease Outbreak Notification SystemA Cloud-Based Prototype Implementation of a Disease Outbreak Notification System
A Cloud-Based Prototype Implementation of a Disease Outbreak Notification SystemIJCSEA Journal
 
Comprehensive study: machine learning approaches for COVID-19 diagnosis
Comprehensive study: machine learning approaches for COVID-19 diagnosis Comprehensive study: machine learning approaches for COVID-19 diagnosis
Comprehensive study: machine learning approaches for COVID-19 diagnosis IJECEIAES
 
COVID RESEARCH.docx
COVID RESEARCH.docxCOVID RESEARCH.docx
COVID RESEARCH.docxSaudBilal3
 
An intelligent approach for detection of covid by analysing Xray and CT scan ...
An intelligent approach for detection of covid by analysing Xray and CT scan ...An intelligent approach for detection of covid by analysing Xray and CT scan ...
An intelligent approach for detection of covid by analysing Xray and CT scan ...IRJET Journal
 
Detection of Replica Nodes in Wireless Sensor Network: A Survey
Detection of Replica Nodes in Wireless Sensor Network: A SurveyDetection of Replica Nodes in Wireless Sensor Network: A Survey
Detection of Replica Nodes in Wireless Sensor Network: A SurveyIOSR Journals
 
Defending Reactive Jammers in WSN using a Trigger Identification Service.
Defending Reactive Jammers in WSN using a Trigger Identification Service.Defending Reactive Jammers in WSN using a Trigger Identification Service.
Defending Reactive Jammers in WSN using a Trigger Identification Service.ijsrd.com
 
Plant Leaf Diseases Identification in Deep Learning
Plant Leaf Diseases Identification in Deep LearningPlant Leaf Diseases Identification in Deep Learning
Plant Leaf Diseases Identification in Deep LearningCSEIJJournal
 

Similar to Covid-19 Spread Detection, Containment Mapping & Vaccine Delivery Framework (20)

Spatio-temporal Monitoring of Health Epidemics in Real-Time-Some Considerations
Spatio-temporal Monitoring of Health Epidemics  in Real-Time-Some ConsiderationsSpatio-temporal Monitoring of Health Epidemics  in Real-Time-Some Considerations
Spatio-temporal Monitoring of Health Epidemics in Real-Time-Some Considerations
 
A Survey on Person Detection for Social Distancing and Safety Violation Alert...
A Survey on Person Detection for Social Distancing and Safety Violation Alert...A Survey on Person Detection for Social Distancing and Safety Violation Alert...
A Survey on Person Detection for Social Distancing and Safety Violation Alert...
 
Deep Learning Approaches for Diagnosis and Treatment of COVID-19
Deep Learning Approaches for Diagnosis and Treatment of COVID-19Deep Learning Approaches for Diagnosis and Treatment of COVID-19
Deep Learning Approaches for Diagnosis and Treatment of COVID-19
 
Monitoring Pandemic Precautionary Protocols using Real-time Surveillance and ...
Monitoring Pandemic Precautionary Protocols using Real-time Surveillance and ...Monitoring Pandemic Precautionary Protocols using Real-time Surveillance and ...
Monitoring Pandemic Precautionary Protocols using Real-time Surveillance and ...
 
NEW CORONA VIRUS DISEASE 2022: SOCIAL DISTANCING IS AN EFFECTIVE MEASURE (COV...
NEW CORONA VIRUS DISEASE 2022: SOCIAL DISTANCING IS AN EFFECTIVE MEASURE (COV...NEW CORONA VIRUS DISEASE 2022: SOCIAL DISTANCING IS AN EFFECTIVE MEASURE (COV...
NEW CORONA VIRUS DISEASE 2022: SOCIAL DISTANCING IS AN EFFECTIVE MEASURE (COV...
 
IRJET- Fake News Detection and Rumour Source Identification
IRJET- Fake News Detection and Rumour Source IdentificationIRJET- Fake News Detection and Rumour Source Identification
IRJET- Fake News Detection and Rumour Source Identification
 
Location tracking and_allerting_apparatus_and_method
Location tracking and_allerting_apparatus_and_methodLocation tracking and_allerting_apparatus_and_method
Location tracking and_allerting_apparatus_and_method
 
Telemedicine in Clinical Research
Telemedicine in Clinical ResearchTelemedicine in Clinical Research
Telemedicine in Clinical Research
 
COVID-19 FACE MASK DETECTION
COVID-19 FACE MASK DETECTIONCOVID-19 FACE MASK DETECTION
COVID-19 FACE MASK DETECTION
 
A CLOUD-BASED PROTOTYPE IMPLEMENTATION OF A DISEASE OUTBREAK NOTIFICATION SYS...
A CLOUD-BASED PROTOTYPE IMPLEMENTATION OF A DISEASE OUTBREAK NOTIFICATION SYS...A CLOUD-BASED PROTOTYPE IMPLEMENTATION OF A DISEASE OUTBREAK NOTIFICATION SYS...
A CLOUD-BASED PROTOTYPE IMPLEMENTATION OF A DISEASE OUTBREAK NOTIFICATION SYS...
 
ENHANCED GREEN FIREWALL FOR EFFICIENT DETECTION AND PREVENTION OF MOBILE INTR...
ENHANCED GREEN FIREWALL FOR EFFICIENT DETECTION AND PREVENTION OF MOBILE INTR...ENHANCED GREEN FIREWALL FOR EFFICIENT DETECTION AND PREVENTION OF MOBILE INTR...
ENHANCED GREEN FIREWALL FOR EFFICIENT DETECTION AND PREVENTION OF MOBILE INTR...
 
A Cloud-Based Prototype Implementation of a Disease Outbreak Notification System
A Cloud-Based Prototype Implementation of a Disease Outbreak Notification SystemA Cloud-Based Prototype Implementation of a Disease Outbreak Notification System
A Cloud-Based Prototype Implementation of a Disease Outbreak Notification System
 
Comprehensive study: machine learning approaches for COVID-19 diagnosis
Comprehensive study: machine learning approaches for COVID-19 diagnosis Comprehensive study: machine learning approaches for COVID-19 diagnosis
Comprehensive study: machine learning approaches for COVID-19 diagnosis
 
COVID RESEARCH.docx
COVID RESEARCH.docxCOVID RESEARCH.docx
COVID RESEARCH.docx
 
An intelligent approach for detection of covid by analysing Xray and CT scan ...
An intelligent approach for detection of covid by analysing Xray and CT scan ...An intelligent approach for detection of covid by analysing Xray and CT scan ...
An intelligent approach for detection of covid by analysing Xray and CT scan ...
 
Detection of Replica Nodes in Wireless Sensor Network: A Survey
Detection of Replica Nodes in Wireless Sensor Network: A SurveyDetection of Replica Nodes in Wireless Sensor Network: A Survey
Detection of Replica Nodes in Wireless Sensor Network: A Survey
 
P017129296
P017129296P017129296
P017129296
 
Defending Reactive Jammers in WSN using a Trigger Identification Service.
Defending Reactive Jammers in WSN using a Trigger Identification Service.Defending Reactive Jammers in WSN using a Trigger Identification Service.
Defending Reactive Jammers in WSN using a Trigger Identification Service.
 
C0511318
C0511318C0511318
C0511318
 
Plant Leaf Diseases Identification in Deep Learning
Plant Leaf Diseases Identification in Deep LearningPlant Leaf Diseases Identification in Deep Learning
Plant Leaf Diseases Identification in Deep Learning
 

Recently uploaded

Call Girls In ludhiana For Fun 9053900678 By ludhiana Call Girls For Pick...
Call Girls In  ludhiana  For Fun 9053900678 By  ludhiana  Call Girls For Pick...Call Girls In  ludhiana  For Fun 9053900678 By  ludhiana  Call Girls For Pick...
Call Girls In ludhiana For Fun 9053900678 By ludhiana Call Girls For Pick...Russian Call Girls in Ludhiana
 
VIP Call Girl Sector 32 Noida Just Book Me 9711199171
VIP Call Girl Sector 32 Noida Just Book Me 9711199171VIP Call Girl Sector 32 Noida Just Book Me 9711199171
VIP Call Girl Sector 32 Noida Just Book Me 9711199171Call Girls Service Gurgaon
 
Call Girls Service Chandigarh Gori WhatsApp ❤7710465962 VIP Call Girls Chandi...
Call Girls Service Chandigarh Gori WhatsApp ❤7710465962 VIP Call Girls Chandi...Call Girls Service Chandigarh Gori WhatsApp ❤7710465962 VIP Call Girls Chandi...
Call Girls Service Chandigarh Gori WhatsApp ❤7710465962 VIP Call Girls Chandi...Niamh verma
 
Call Girls Thane Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Thane Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Thane Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Thane Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
 
Russian Escorts Aishbagh Road * 9548273370 Naughty Call Girls Service in Lucknow
Russian Escorts Aishbagh Road * 9548273370 Naughty Call Girls Service in LucknowRussian Escorts Aishbagh Road * 9548273370 Naughty Call Girls Service in Lucknow
Russian Escorts Aishbagh Road * 9548273370 Naughty Call Girls Service in Lucknowgragteena
 
Local Housewife and effective ☎️ 8250192130 🍉🍓 Sexy Girls VIP Call Girls Chan...
Local Housewife and effective ☎️ 8250192130 🍉🍓 Sexy Girls VIP Call Girls Chan...Local Housewife and effective ☎️ 8250192130 🍉🍓 Sexy Girls VIP Call Girls Chan...
Local Housewife and effective ☎️ 8250192130 🍉🍓 Sexy Girls VIP Call Girls Chan...Russian Call Girls Amritsar
 
❤️♀️@ Jaipur Call Girls ❤️♀️@ Jaispreet Call Girl Services in Jaipur QRYPCF ...
❤️♀️@ Jaipur Call Girls ❤️♀️@ Jaispreet Call Girl Services in Jaipur QRYPCF  ...❤️♀️@ Jaipur Call Girls ❤️♀️@ Jaispreet Call Girl Services in Jaipur QRYPCF  ...
❤️♀️@ Jaipur Call Girls ❤️♀️@ Jaispreet Call Girl Services in Jaipur QRYPCF ...Gfnyt.com
 
Chandigarh Call Girls 👙 7001035870 👙 Genuine WhatsApp Number for Real Meet
Chandigarh Call Girls 👙 7001035870 👙 Genuine WhatsApp Number for Real MeetChandigarh Call Girls 👙 7001035870 👙 Genuine WhatsApp Number for Real Meet
Chandigarh Call Girls 👙 7001035870 👙 Genuine WhatsApp Number for Real Meetpriyashah722354
 
Call Girls Hyderabad Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Hyderabad Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Hyderabad Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Hyderabad Just Call 9907093804 Top Class Call Girl Service AvailableDipal Arora
 
💚😋Mumbai Escort Service Call Girls, ₹5000 To 25K With AC💚😋
💚😋Mumbai Escort Service Call Girls, ₹5000 To 25K With AC💚😋💚😋Mumbai Escort Service Call Girls, ₹5000 To 25K With AC💚😋
💚😋Mumbai Escort Service Call Girls, ₹5000 To 25K With AC💚😋Sheetaleventcompany
 
Call Now ☎ 9999965857 !! Call Girls in Hauz Khas Escort Service Delhi N.C.R.
Call Now ☎ 9999965857 !! Call Girls in Hauz Khas Escort Service Delhi N.C.R.Call Now ☎ 9999965857 !! Call Girls in Hauz Khas Escort Service Delhi N.C.R.
Call Now ☎ 9999965857 !! Call Girls in Hauz Khas Escort Service Delhi N.C.R.ktanvi103
 
Ozhukarai Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Ozhukarai Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real MeetOzhukarai Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Ozhukarai Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real MeetCall Girls Service
 
Bangalore call girl 👯‍♀️@ Simran Independent Call Girls in Bangalore GIUXUZ...
Bangalore call girl  👯‍♀️@ Simran Independent Call Girls in Bangalore  GIUXUZ...Bangalore call girl  👯‍♀️@ Simran Independent Call Girls in Bangalore  GIUXUZ...
Bangalore call girl 👯‍♀️@ Simran Independent Call Girls in Bangalore GIUXUZ...Gfnyt
 
Hot Call Girl In Chandigarh 👅🥵 9053'900678 Call Girls Service In Chandigarh
Hot  Call Girl In Chandigarh 👅🥵 9053'900678 Call Girls Service In ChandigarhHot  Call Girl In Chandigarh 👅🥵 9053'900678 Call Girls Service In Chandigarh
Hot Call Girl In Chandigarh 👅🥵 9053'900678 Call Girls Service In ChandigarhVip call girls In Chandigarh
 
❤️♀️@ Jaipur Call Girl Agency ❤️♀️@ Manjeet Russian Call Girls Service in Jai...
❤️♀️@ Jaipur Call Girl Agency ❤️♀️@ Manjeet Russian Call Girls Service in Jai...❤️♀️@ Jaipur Call Girl Agency ❤️♀️@ Manjeet Russian Call Girls Service in Jai...
❤️♀️@ Jaipur Call Girl Agency ❤️♀️@ Manjeet Russian Call Girls Service in Jai...Gfnyt.com
 
VIP Call Girl Sector 25 Gurgaon Just Call Me 9899900591
VIP Call Girl Sector 25 Gurgaon Just Call Me 9899900591VIP Call Girl Sector 25 Gurgaon Just Call Me 9899900591
VIP Call Girl Sector 25 Gurgaon Just Call Me 9899900591adityaroy0215
 
Nanded Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Nanded Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real MeetNanded Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Nanded Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real MeetCall Girls Service
 
Vip sexy Call Girls Service In Sector 137,9999965857 Young Female Escorts Ser...
Vip sexy Call Girls Service In Sector 137,9999965857 Young Female Escorts Ser...Vip sexy Call Girls Service In Sector 137,9999965857 Young Female Escorts Ser...
Vip sexy Call Girls Service In Sector 137,9999965857 Young Female Escorts Ser...Call Girls Noida
 
VIP Call Girl Sector 88 Gurgaon Delhi Just Call Me 9899900591
VIP Call Girl Sector 88 Gurgaon Delhi Just Call Me 9899900591VIP Call Girl Sector 88 Gurgaon Delhi Just Call Me 9899900591
VIP Call Girl Sector 88 Gurgaon Delhi Just Call Me 9899900591adityaroy0215
 
VIP Kolkata Call Girl New Town 👉 8250192130 Available With Room
VIP Kolkata Call Girl New Town 👉 8250192130  Available With RoomVIP Kolkata Call Girl New Town 👉 8250192130  Available With Room
VIP Kolkata Call Girl New Town 👉 8250192130 Available With Roomdivyansh0kumar0
 

Recently uploaded (20)

Call Girls In ludhiana For Fun 9053900678 By ludhiana Call Girls For Pick...
Call Girls In  ludhiana  For Fun 9053900678 By  ludhiana  Call Girls For Pick...Call Girls In  ludhiana  For Fun 9053900678 By  ludhiana  Call Girls For Pick...
Call Girls In ludhiana For Fun 9053900678 By ludhiana Call Girls For Pick...
 
VIP Call Girl Sector 32 Noida Just Book Me 9711199171
VIP Call Girl Sector 32 Noida Just Book Me 9711199171VIP Call Girl Sector 32 Noida Just Book Me 9711199171
VIP Call Girl Sector 32 Noida Just Book Me 9711199171
 
Call Girls Service Chandigarh Gori WhatsApp ❤7710465962 VIP Call Girls Chandi...
Call Girls Service Chandigarh Gori WhatsApp ❤7710465962 VIP Call Girls Chandi...Call Girls Service Chandigarh Gori WhatsApp ❤7710465962 VIP Call Girls Chandi...
Call Girls Service Chandigarh Gori WhatsApp ❤7710465962 VIP Call Girls Chandi...
 
Call Girls Thane Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Thane Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Thane Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Thane Just Call 9907093804 Top Class Call Girl Service Available
 
Russian Escorts Aishbagh Road * 9548273370 Naughty Call Girls Service in Lucknow
Russian Escorts Aishbagh Road * 9548273370 Naughty Call Girls Service in LucknowRussian Escorts Aishbagh Road * 9548273370 Naughty Call Girls Service in Lucknow
Russian Escorts Aishbagh Road * 9548273370 Naughty Call Girls Service in Lucknow
 
Local Housewife and effective ☎️ 8250192130 🍉🍓 Sexy Girls VIP Call Girls Chan...
Local Housewife and effective ☎️ 8250192130 🍉🍓 Sexy Girls VIP Call Girls Chan...Local Housewife and effective ☎️ 8250192130 🍉🍓 Sexy Girls VIP Call Girls Chan...
Local Housewife and effective ☎️ 8250192130 🍉🍓 Sexy Girls VIP Call Girls Chan...
 
❤️♀️@ Jaipur Call Girls ❤️♀️@ Jaispreet Call Girl Services in Jaipur QRYPCF ...
❤️♀️@ Jaipur Call Girls ❤️♀️@ Jaispreet Call Girl Services in Jaipur QRYPCF  ...❤️♀️@ Jaipur Call Girls ❤️♀️@ Jaispreet Call Girl Services in Jaipur QRYPCF  ...
❤️♀️@ Jaipur Call Girls ❤️♀️@ Jaispreet Call Girl Services in Jaipur QRYPCF ...
 
Chandigarh Call Girls 👙 7001035870 👙 Genuine WhatsApp Number for Real Meet
Chandigarh Call Girls 👙 7001035870 👙 Genuine WhatsApp Number for Real MeetChandigarh Call Girls 👙 7001035870 👙 Genuine WhatsApp Number for Real Meet
Chandigarh Call Girls 👙 7001035870 👙 Genuine WhatsApp Number for Real Meet
 
Call Girls Hyderabad Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Hyderabad Just Call 9907093804 Top Class Call Girl Service AvailableCall Girls Hyderabad Just Call 9907093804 Top Class Call Girl Service Available
Call Girls Hyderabad Just Call 9907093804 Top Class Call Girl Service Available
 
💚😋Mumbai Escort Service Call Girls, ₹5000 To 25K With AC💚😋
💚😋Mumbai Escort Service Call Girls, ₹5000 To 25K With AC💚😋💚😋Mumbai Escort Service Call Girls, ₹5000 To 25K With AC💚😋
💚😋Mumbai Escort Service Call Girls, ₹5000 To 25K With AC💚😋
 
Call Now ☎ 9999965857 !! Call Girls in Hauz Khas Escort Service Delhi N.C.R.
Call Now ☎ 9999965857 !! Call Girls in Hauz Khas Escort Service Delhi N.C.R.Call Now ☎ 9999965857 !! Call Girls in Hauz Khas Escort Service Delhi N.C.R.
Call Now ☎ 9999965857 !! Call Girls in Hauz Khas Escort Service Delhi N.C.R.
 
Ozhukarai Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Ozhukarai Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real MeetOzhukarai Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Ozhukarai Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
 
Bangalore call girl 👯‍♀️@ Simran Independent Call Girls in Bangalore GIUXUZ...
Bangalore call girl  👯‍♀️@ Simran Independent Call Girls in Bangalore  GIUXUZ...Bangalore call girl  👯‍♀️@ Simran Independent Call Girls in Bangalore  GIUXUZ...
Bangalore call girl 👯‍♀️@ Simran Independent Call Girls in Bangalore GIUXUZ...
 
Hot Call Girl In Chandigarh 👅🥵 9053'900678 Call Girls Service In Chandigarh
Hot  Call Girl In Chandigarh 👅🥵 9053'900678 Call Girls Service In ChandigarhHot  Call Girl In Chandigarh 👅🥵 9053'900678 Call Girls Service In Chandigarh
Hot Call Girl In Chandigarh 👅🥵 9053'900678 Call Girls Service In Chandigarh
 
❤️♀️@ Jaipur Call Girl Agency ❤️♀️@ Manjeet Russian Call Girls Service in Jai...
❤️♀️@ Jaipur Call Girl Agency ❤️♀️@ Manjeet Russian Call Girls Service in Jai...❤️♀️@ Jaipur Call Girl Agency ❤️♀️@ Manjeet Russian Call Girls Service in Jai...
❤️♀️@ Jaipur Call Girl Agency ❤️♀️@ Manjeet Russian Call Girls Service in Jai...
 
VIP Call Girl Sector 25 Gurgaon Just Call Me 9899900591
VIP Call Girl Sector 25 Gurgaon Just Call Me 9899900591VIP Call Girl Sector 25 Gurgaon Just Call Me 9899900591
VIP Call Girl Sector 25 Gurgaon Just Call Me 9899900591
 
Nanded Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Nanded Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real MeetNanded Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
Nanded Call Girls 👙 6297143586 👙 Genuine WhatsApp Number for Real Meet
 
Vip sexy Call Girls Service In Sector 137,9999965857 Young Female Escorts Ser...
Vip sexy Call Girls Service In Sector 137,9999965857 Young Female Escorts Ser...Vip sexy Call Girls Service In Sector 137,9999965857 Young Female Escorts Ser...
Vip sexy Call Girls Service In Sector 137,9999965857 Young Female Escorts Ser...
 
VIP Call Girl Sector 88 Gurgaon Delhi Just Call Me 9899900591
VIP Call Girl Sector 88 Gurgaon Delhi Just Call Me 9899900591VIP Call Girl Sector 88 Gurgaon Delhi Just Call Me 9899900591
VIP Call Girl Sector 88 Gurgaon Delhi Just Call Me 9899900591
 
VIP Kolkata Call Girl New Town 👉 8250192130 Available With Room
VIP Kolkata Call Girl New Town 👉 8250192130  Available With RoomVIP Kolkata Call Girl New Town 👉 8250192130  Available With Room
VIP Kolkata Call Girl New Town 👉 8250192130 Available With Room
 

Covid-19 Spread Detection, Containment Mapping & Vaccine Delivery Framework

  • 1. Signal System Overview [WIP] Contagion Spread Detection and Containment Mapping v1.2 Authors: @Sachin Dev Duggal, @Dr Siddhartha Ghosh, Contributors: @Rohan Patel @Saurabh Dhoot @Dr Sharon Jheeta @Rushen Patel @Chandan Kumar builder.ai © April 2020 Engineer.ai Global Limited. Except as otherwise noted, this work is licensed under under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
  • 2. © engineer.ai 2020 Problem - Preamble Viruses / contagions spread an order of magnitude faster than the rate of testing. The contagion follows the path of a social network whereas testing patterns are quasi linear in their approach. Key is to reduce the potential of reaching terminal spread velocity and reducing the affected population.
  • 3. © engineer.ai 2020 Problem - Preamble - Contagions, like Covid-19 can spread incredibly quickly as they survive on surfaces or transmit over airborne human contact. The rate at which they spread makes testing almost impossible and containment incredibly expensive. - Until a vaccination is ready; isolation (containment) and digital passports are only ways to reduce terminal spread velocity and economic fall out. - Most affected in any such pandemics are the elderly and the impoverished; they do not have access to smartphones; but by in large all have access to a feature phone. Therefore the contagion has disproportionately more impact to these people. - The contagion has a number of spread vectors - A diagnosed person has an incubation period that gets longer closer to R0 (first instance). - A diagnosed person may have touched a surface that will stay “live” for upto X Days. - Multiple diagnosed persons may have been in the same area thereby causing a compounding impact. - A diagnosed person who travels will likely have spread to a larger person via the air conditioning systems of a flight. - Alternative: a diagnosed person who has travelled previously and was mobile is likely to have infected significant numbers in confined spaces
  • 4. © engineer.ai 2020 Problem - Build an effective and dynamic contact tracing solution that continuously shows a real-time view of most at risk and provides a navigational direction to health authorities on how to break the spread down such that you have contained communities. - The solution has to be low tech as the most impact is usually on those without internet connected smartphones; ie elderly or impoverished who have features phone. - Development Market Smartphone penetration hovers at 60-70% for the elderly and 45-55% for the underprivileged. - Emerging Market Smartphone penetration hover at 25-30% overall. ** - For the solution to work you need >90/95% coverage of a population at a given time; and a stratified testing model that continuously re-evaluates the network and ensures that a real-time view of risk is shown. - When you have a vaccine, you need to be able to the shortest path to stopping spreading and optimizing for the least deaths which is not the same as a linear roll out of a vaccination especially when at the start the vaccination quantities will be less. ** Source: https://www.finder.com/uk/mobile-internet-statistics
  • 5. © engineer.ai 2020 Smartphones and Apps only won’t work - must be hybrid - Because of their very low coverage they don’t have the ability to model analogous to population. In very specific forward cities they can have a strong impact only if >90% download - but holistically on a global basis, a smartphone only strategy won’t work. - Without a model that can dynamically adjust the radius to create a “catchment” area they will create large false positives or false negatives.
  • 6. © engineer.ai 2020 Signal - Highlights Overview 1. Use the triangulation data available from all cell phone towers to be able to pinpoint all devices (ie people). a. The phone numbers would all be one way hashed so there is no way to track a single individual. 2. Create an accurate backtrace using prior locations across cell towers - this will be created on a spatiotemporal signal network graph 3. Superimpose this with health condition tags (ie did the person have a lung condition. a. Set a dynamic radius (s0) at each point of the backtrace to create a catchment zone. b. This will show who could be infected and who is most at risk. i. i.e using the phone hash and medical tags (and their severity). 4. The graph is a “living” structure that is effectively mapped in real time as people move about and get diagnosed (true positives and true negatives). a. Effective reduction of area is key whether it's via testing or via decay system (where if someone and their community have shown no positive test results for a given period the whole branch becomes clean). 5. The system can also identify which communities to test and the result is then used to clear out entire branches of the graph until they have a new node (person) entering them. 6. Vaccine Delivery needs to be done in a way to reduce the amount of vaccine needed splinter the graph thereby making this a non spreading localised problem which can then fall into a second wave of treatment.
  • 7. © engineer.ai 2020 Signal - Three phases of the pandemic 1. Isolation a. Reduce the amplitude of the spread (ie reduce the peak). 2. Allow limited back to work - Prevent economic free-fall or further damage a. Create a dynamic digital passport for antibody testing and pseudo green light b. Create a path to dynamically test (stratified testing). 3. Vaccination Deployment a. With limited resources what’s the most optimized way to deploy to break universe of population into smaller and smaller communities and track when communities fuse together.
  • 8. © engineer.ai 2020 Signal - Highlights Overview Path of an individual using cell tower data People they interact with Dynamic Radius is the catchment zone When and where this person got infected Tertiary effected (not the person diagnosed, not the person they met but others who crossed over) Intensity of other contagion carriers increases the radius T=0 is when the person is diagnosed
  • 9. © engineer.ai 2020 Signal - 4D Spatial - Time Box Contagions have a 4D infection spread The 3d is the spatial plane and the 4d dimension is a time duration since an infected person visited the site. The horizontal radius is the normal geo-plane (ie the spatial distance) In this time box if anyone crosses the “spread radius” they get tagged as potentially infected. Any given location needs to have a t+4 days time horizon as C19 has a time box of 4 days on some materials.
  • 10. © engineer.ai 2020 Signal - Approach Overview 1. Use cell phone tower data. 2. Triangulate all devices using signal strength and fixed nature of towers. 3. Superimpose this with account data for phone numbers to infer mandatory spread. 4. Link the master universe of nodes based on historical interaction to create a propagation network (PN). This PN is dynamic and evolves backward in time from the point a node has been diagnosed to be infected 5. Adjust interactions on the network based on intensity and other carriers (to establish who all could be infected) 6. Fuse hashed node identifier with medical tags basis EMR (electronic medical records) (again only tagged not identifiable) (pre existing tags that are medically designated with a weight) 1. Ie Node Hash has 3 Sev 1 conditions, 2 Sev 2 Conditions etc 7. Identify high risk nodes who have attributable medical conditions on the PN and test 8. Stratified testing of those most likely; use sensitivity and specificity to re-calibrate master propagation network 9. Establish a vaccination strategy based on understanding the characteristics of the PN with an aim to reduce the size and the connectedness of the network
  • 11. © engineer.ai 2020 Signal uses a 5 point process 1. Person Triangulation & historical movement a. Data from cell towers will tell you the movement off all people in a given geography (spatial plane). b. You backtrace from when a person is positively diagnosed to see their reverse journey for a given period of time (the contagion incubation period). i. You do this for all people. c. This will create a spatiotemporal signal network graph (SSNG) d. One way hash of all numbers. 2. Propagation Network - with a dynamic radius (“spread) across the backtrace e. The spread (s0) of a contagion (at a time t and location a) over the network should take into account the following: r = radius of interaction of a node; p = potency of contagion; c = intensity of carriers; d = max time to dissipate on any surface and i = saturation of nodes at a given t + d. i. Signal DR will take into account the forward looking surface life time as well ie if a known contained person was in a particular location then anyone coming in that location for 4 days would run the risk of being infected. f. The dynamic radius tell you who additionally to add from (1) to the SSNG (you are effectively adding more nodes to the network basis their inclusion in the radius).
  • 12. © engineer.ai 2020 Signal uses a 5 point process cont’d 3. High Risk Identification a. Use medical tags and severity to add attributes to hashed phone numbers so that you can map out those most critically at risk. The most at risk get flagged quicker for testing. 4. Pruning and Spread Velocity Decreasing ---> Smarter testing to optimize lower test availability a. Use stratified testing algorithm to define which are the parts of the graph to test. b. Use implicit decay in contagions behavior to eliminate branches from testing. These become green branches that unless they have a new person coming into them or a positive test remain green. c. Create a vaccination path that aims to break the SSNG into smaller communities dividing the spread rather than trying to do entire population at once. Optimize for the fastest path to vaccinate where ultimate death toll is minimal. (This of this as a traffic navigation problem). 5. Interim Digital Passport a. Whilst there is no fully rolled our vaccine or vaccine is still being rolled out digital certify people back into the economy by seeing how they move across the spatial plane of the SSNG. b. Use self test and clinical testing to create reinforced feedback into the network (including back trace - i.e if someone is clear then the back trace for 14 days for that person is also clear).
  • 13. © engineer.ai 2020 Holistic Visualization Create a time vector (y-axis) and use a network structure for representation. a. Moving vertically shows time backwards (ie days from the diagnosis) b. Color coded interactions for who they met. c. Show X plane as the map of the region so you can also see the locales visited.
  • 14. © engineer.ai 2020 Holistic Visualization Create a time vector (y-axis) and use a network structure for representation. a. Moving vertically shows time backwards (ie days from the diagnosis) b. Color coded interactions for who they met. c. Show X plane as the map of the region so you can also see the locales visited.
  • 15. © engineer.ai 2020 Holistic Visualization Create a flat heat map using icons on the node diagram to show time from diagnosis (t=0=date of being positively diagnosed). Color code regions of high positive diagnosis and their paths (ie if 5 people 5 days ago were in a particular place) Show the network interaction (person a met person b)
  • 16. © engineer.ai 2020 Holistic Visualization Creating communities that become bigger/smaller (engulf or get divided) basis the movement of infected people in between them. Each “bubble” is a community that is continuously expanding or contracting.
  • 17. © engineer.ai 2020 Detailed Framework Paper & References Please see the detailed paper here - as we are working on this in real time we have asked for verified email addresses to access this so that we can get updated content notified. Visit this site: https://docsend.com/view/862npsj 1. Spatiotemporal Signal Visualizations 1. https://www.mdpi.com/2220-9964/7/9/371/htm 2. Triangulation/trilateration: 1. https://www.101computing.net/cell-phone-trilateration-algorithm/ 2. https://searchengineland.com/cell-phone-triangulation-accuracy-is-all-over-the-map-14790 3. Epidemiology / Epidemiology contact tracing / social network spread 1. http://escholarship.umassmed.edu/cgi/viewcontent.cgi?article=2155&context=qhs_pp 2. https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0095133 3. https://academic.oup.com/aje/article/162/10/1024/65086 4. https://arxiv.org/pdf/1403.1011.pdf 5. http://biocircuits.ucsd.edu/lev/papers/contact_tracing1.pdf 4. Examples of visualisations: 1. https://cdv.dei.uc.pt/visualizing-urban-mobility/ 2. https://www.fastcompany.com/3023416/outbreak-watch-how-quickly-an-epidemic-would-spread-across-the-world 3. https://www.wired.com/2015/04/see-diseases-spread-mesmerizing-graphics/