Return to Home

Research Proposal

• May 11th, 2020
• Global Research Institute
• College of William and Mary
• chase4eck@gmail.com

Dear members of the review board,

The problem of disaster risk reduction is certainly a global one, with far-reaching consequences. In particular, Fiji has struggled in the past to defend against a myriad of epidemics. I have created a research proposal aimed to defend against future epidemics, using information from past epidemics as well as Fiji’s evolving epidemic-defense plans. My research provides a plan to efficiently intervene with an epidemic, contain it, and disover the best course of action against it. Furthermore, this plan can be used for any future epidemics, as it is a very flexbile plan with much room for change. This problem needs to be considered now. There is no more time. The next deadly virus is on the horizon, and we need to prepare, before our population is greatly diminished. As for funding, I believe business magnate Bill Gates can (and will) provide funding for this research, as explained in the paper.

-Signed: Chase Eck

Problem Statement:

There are only a handful of ways that humanity will eventually (and inevitably) come to an end, including global nuclear annihilation, climate change, and epidemic. As we develop as a race, we gain more defenses and insights on these threats. However, when it comes to epidemics, humanity is becoming more and more prone to its severe threat. The world population is at an all time high, and is continuing to grow. This allows epidemics to spread rapidly. Furthermore, our modes of transportation are advancing, allowing a virus to be transmitted globally within hours. If that doesn’t strike fear into your heart, consider the current epidemic of COVID-19: it is very likely that each of us know of someone who has passed from this virus. The silver-lining to the COVID-19 epidemic is that the virus is much less lethal compared to past viral epidemics, such as the H1N1 Swine Flu and the West African Ebola virus. When a highly-lethal epidemic inevitably occurs, the victims may outnumber the survivors. Experts wordwide continue to agree that we require more research into the future of epidemics, in order to avoid an outcome such as this one.

Some countries have an especially difficult time defending against epidemics, for a variety of economical and social reasons. For instance, Fiji has had a harsh history when it comes to epidemics, which have had significant impacts on Fiji’s economy and society as a whole. Throughout the 1900’s, Fiji has battled a myriad of measles outbreaks. The official governing body of the Oceania region, which includes many islands surrounding Fiji, stated that Fiji lost approximately 33% of its population to measles during the 1900’s (ADRC). The turning point in their story is the implementation of the measles vaccine, which arrived in 1982. Since then, this country has been relatively measles-free. Another past epidemic in Fiji was the rapid spread of the Dengue Virus Serotype-3 in 2013. Overall, the mortality rate remained around 6 deaths per 100,000 people. Though this number is not astonishing, the virus seemed to target the working class males, likely due to occupational exposure. Their economy was crippled greatly due to this particular epidemic.

In the first figure above, the ADRC depicts the mortality of the most threatening natural disasters to Fiji; epidemics make up more than 50%. However, the second figure displays how epidemics only make uo 10% of all natural disasters that occur in Fiji. This continues to prove the point that the biggest threat to society in Fiji is due to a viral epidemic.

Fiji is in a very fragile social and economic state that epidemics can easily disrupt, and it would not be the first time. The ADRC commented on the vulnerability of the Oceania region to disasters, saying “it is easily understood from these sections that [Oceania] is an extremely disaster prone region of the world in terms of human loss and suffering,” (ADRC). For instance, consider the strength of a vector-borne illness in a country where mosquitoes are rampant; the dengue virus absolutely took advantage of this in Fiji. On top of this, the country’s rapid urbanization created a much larger population density, allowing the virus to infect a dangerous amount of people in a very short time.

Epidemics have had far-reaching effects on Fiji, including social breakdown and economic conflicts. As mentioned before, the dengue fever outbreak crippled the working class, and had a large impact on their agricultural industry. In Fiji, the two industries that pulled the most weight economically are the agriculture and tourism industries. The agricultural industry produces about 11.7% of Fiji’s GDP. Consider how the COVID-19 outbreak has affected the United States’ agriculture. Since most restaurants are struggling to sell their product as usual, they require less goods from farms. This leads to farms having a mass surplus of goods, with no place to go. Some farms are even donating this surplus to various food banks. The situation in Fiji is not much different. As for the tourism industry, it essentially comes to a stand still due to epidemic-related travel restrictions.

Disaster preparedness is such a complex problem in this country due to many factors, including Fiji’s geographical location as well as Fiji’s dependence on its tourism industry. Fiji is constantly getting crippled by natural disasters, and is barely given time to recover from one before the next disaster is on the horizon. However, Fiji has greatly increased its defensive measures for pandemics. They have implemented a very successful nationwide epidemic notification system, allowing the public to respond efficiently to threats of outbreak. Response time to outbreaks is crucial in containing the virus in question, and cutting off all posibiliites for it to spread. In our current position, our country implemented the “social distancing” and “stay at home” orders to reach this goal. The UNDRR stated “No outbreaks were left undetected, the system performed well during the response period, [and] 325 alerts were generated and three large-scale outbreaks requiring intervention were successfully managed (Sheel, et al., 2019),” (UNDRR 20). This relates to Amartya Sen’s definition of human development, which considers the development of freedoms the same as the development of humanity as a whole. By creating a successful notification system, Fiji was able to develop the peoples’ freedom to knowledge, specifically about possible disasters. Another preventative measure is the “Key Messages for Disaster Risk Reduction and Resilience in Fiji: A Guide for Public Education and Awareness”, which outlines how one should prepare for disaster, how one should react to disaster, and what they should expect from disaster. It explains the specifics for each of the following disasters: drought, earthquakes, floods, pandemics, tropical cyclones, wildfires, infestations, landslides, tsunamis, and storm surges. Fiji Red Cross also lays out a plan to store rations, provide first aid, and to communicate with the community. This guide also touches on some past examples of these disasters.

Epidemics are terrifying in how they are an invisible enemy, with unknown strengths and strategies. The goal of epidemic defense is to discover these strengths, and to discover its weaknesses. For example, new research has emerged supporting the claim that warmer temperatures can slow the spread of the COVID-19. As summer approaches, this information may become very valuable. With this type of battle, we rely on the little information that we do have on the virus. In Fiji’s case, the information they had about the COVID-19 virus towards the initial outbreak was simply that the virus had not yet spread to their country– so they took action. Heavy travel restrictions were placed, preventing tourists from dragging the virus to their untouched country. Currently, Fiji has only had about 18 confirmed cases to date. This goes to show how effective simple measures such as a nationwide notification system and efficient disaster-response time can prove to be. Rather than focusing on the protection of specific regions or industries, the Fijians were able to focus on the country as a whole, making a huge impact with only a few advances. To continue this development of disaster defense systems, past and current epidemics must be studied. There are a sleuth of data science methods that are quite effective at analyzing data to arrive at an understandable conclusion. The UNDRR seems to be optimistic about Fiji’s future with disasters.

While viruses persistently evolve day-to-day, so does humanity. We continue to advance our many branches of science. Data science and computer science alike have begun to develop revolutionary techniques in which large sums of data can be analyzed to produce previously unknown conclusions. One example is the advancement artificial intelligence (AI), which can be described as teaching a computer to “think” in a certain way, similarly to humans. One simple example of AI is a neural network designed to identify what an object is on camera, such as a cat, phone, or book. Furthermore, a neural network can be designed to plot a virus’s predicted spread patterns, allowing the government to take action to block off the virus’s path. The future of epidemic research and defense relies on the advancement of our technologies.

The threat of natural disasters is a considerable one. In relation to the two figures included above, it can be seen how epidemics can make up a large percentage of this threat. As the population grows, this threat of epidemic also grows. Even political strains can play a role. If relations between two countries reach a breaking point and the thought of war is considered, biological warfare can be a very real fear. These would essentially be designer viruses, engineered to spread as quickly as possible with the highest mortality rate. To sum this up, epidemics deserve the fear that they are given. American business magnate Bill Gates has stated “The Ebola epidemic showed me that we are not ready for a serious epidemic, an epidemic that would be more infectious and would spread faster than Ebola did… The Ebola epidemic can serve as an early warning wake-up call to get ready. If we start now, we can be ready for the next epidemic,” (Bill Gates). This is our harsh reality.

Literature Review:

​ Disaster Risk Reduction (DRR) is a global development issue. Without the means to be sustainable surrounded by disaster, society would collapse. The United Nations Office for Disaster Risk Reduction, or the UNDRR “brings governments, partners and communities together [to] reduce disaster risk and losses to ensure a safer, sustainable future.” They aim to tackle the global issue of disaster. They study past epidemics to learn from, and publish a multitude of graphics to provide epidemic information to the public. One region that tends to hold their focus is the Asian/Pacific region, which includes the Republic of Fiji. When Fiji suffered from the measles and dengue-fever epidemics, the UNDRR’s response was swift and provided results. For example, they helped Fiji to disperse vaccinations nationwide, and eventually reduced the measles mortality rate in Fiji by 99% (Rubella Initiative). One article by the UNDRR about Fiji outlines the semi-recent protocol for informing the public about epidemics. Fiji was even categorized as low risk when it comes to the “inform risk index”, which describes the country’s ability to quickly respond to disaster by informing the public (UNDRR). This is a prime example of human development: Fiji has developed by creating communcation methods effectively reducing the threat of epidemic. Think about your current situation. If you did not have access to information about the COVID outbreak, would you still be social distancing? Would you be more anxious? The freedom of knowledge is a necessity, especially to fight disasters such as epidemics. Now, consider a tsunami is miraculously paving a road of destruction to William and Mary. That freedom to communication and knowledge may save your life.

​ Pre-UNDRR intervention in Fiji, outbreaks of measles and dengue fever brought Fijian society to its knees. One article about the measles outbreak begins with “In 1875 Fijians buried one-third of their population – all dead as a result of measles,” (Rubella Initiative). It took until 1982 for the measles vaccine to reach Fiji. Before that time, Fijian society struggled to develop as the measles hindered every path of development. Their tourism industry was basically non-existent, so they heavily relied on the agricultural sector. Similarly, the dengue fever epidemic also lead to this societal breakdown. The source of the problem with these two epidemics is how widely they affected working-age males. Without a healthy workforce, the majority of work came to a standstill. Without income or healthy workers, the poverty line become much more populated, with families struggling to make ends meet and the government struggling to remain operational. Another factor that made recovery from epidemic a difficult goal was the urbanization of Fiji. As seen today with COVID-19, densely populated regions are susceptible to the rapid spread of a virus. As of the moment this is written, New York has about 37,000 more cases than any other state. Other than population density, other characteristics, such as geographical location, must be considered when discussing epidemics. For example, the severity of the dengue fever epidemic in Fiji is largely due to its location in the Pacific. The region is much more susceptible to vector-borne illnesses. Fiji’s reponse to the dangerous nature of its location has been to publish a guide by the name “Key Messages for Disaster Risk Reduction And Resilience in Fiji: A Guide For Public Education & Awareness” on how one should prepare for disaster, how one should react to disaster, and what they should expect from disaster. Under the pandemic section of this guide, point 3.3 orders isolation from society. It also illustrates how the government will react, specifically how they will handle travel restrictions and the dispersal of information to the public. It is likely that Fiji will need to update and republish said guide. This complex, global problem is continuously evolving. However, here is the silver lining: so are we.

​ One of the main challenges with epidemics is incorporating the large amounts of data collected about a certain disease. How can we apply this data to be helpful to the nation? What are these numbers really telling us? Another problem is the amount of data, which is difficult to comb through and analyze with human eyes. The solution? Make a computer do it. This is one example of our technological evolution. With the use of neural networks and quatum computing, big data can be analyzed by a neural network designed to discover and report patterns. Quantum computing can be used to perform calculations on millions of gigabytes of data, which in turn can be used to develop more complex neural networks faster. This new technology can solve problems that we cannot. One article states “Quantum computing allows for quick detection, analysis, integration, and diagnosis from large scattered data sets. Quantum computers can search extensive, unsorted data sets to quickly uncover patterns. This powerful technology can also view all items in a massive database at the same time to uncover potentially important patterns,” (Moné 1). One study specifically focuses on applying these technologies to disaster response. It is “aiming at introducing the power of deep learning algorithms as the advanced computer vision approaches, to have a (near) real time disaster detection system based on UAVs data which can be effectively used in emergency response and disaster management applications” (Alidoost 12). The development of disaster reaction is becoming far more complex as our technology develops. As society as a whole develops, there the world population grows and disasters become even more lethal. Therefore, the development of our response to disasters must also grow and develop. As the population grows, so do the stakes. The more lives that are at stake, the more complex, accurate, and efficient our solutions must be. These solutions can be discovered through the use of these two newer technologies: quantum computing and neural networks.

​ Though we are evolving along with the problem of disaster preparedness, there are gaps in our evolution process. For example, these technologies that were mentioned can be used in a variety of ways to help with epidemics. The term “functional-fixedness” refers to the cognitive bias that limits a person to use an object only in the way it is traditionally used. One way that we have conquered this bias is seen in how one doctor successfully treated a COVID-19 patient using an antiserum initially synthesized for ebola. This is the type of problem-solving skills we need: thinking outside of the box. This idea hand-in-hand with quantum computing and neural networks could lead to successful treatment of patients using drugs intended for other uses. The technology can derive connections and solutions that we simply cannot see with the human eye, especially when it comes to large quantities of data. There is a plethora of drugs in the market that have unintended side effects that may be useful for treating certain diseases. We need more research into this application, as it may save many lives. There is also much to be explored with the application of these technologies to geospatial data science methods. “Regarding Big Data, quantum computing will enable organizations to sample large troves of data and optimize for all types of use cases and portfolio analyses,” (Moné 1), says one data scientist. In this case, the big data is the pool of geospatial data available to us. The main application here is to find these undiscovered patterns.

One asset that we do have in this battle against epidemic is data– Big Data. The problem is the analysis and implementation of said data. One tool that we have in our arsenal is the use of neural networks. By feeding a computer large quantities of data, we can essentially “teach” the computer to see patterns that are unable to be seen by the human eye. These neural networks are often designed to think similarly to a human brain, while being able to perform calculations that a human brain cannot. This method of pattern recognition is integral to the field of data science. Data is essentially useless; the conclusions that are come to from data is what is truly useful. This technique continues to develop for more advanced applications. It also happens work hand-in-hand with a variety of other data science methods. For example, the idea of linear regression is very applicable with neural networks. The networks can see these patterns and develop a linear-scaled model, which displays (and quantifies) the relationship between two separate variables. One data scientist states “Linear regression is one of the most simple examples of machine learning algorithms we can think of,” (Rocca 1). A neural network can be designed to take certain data points as inputs, and to find a function that accurately models the inputted data. Sometimes, this relationship between the variables is not linear. One approach to this problem could be to find the function’s derivative, and discover a linear relationship that way. Overall, these two data science methods are very complementary. Together, they can be used to answer questions that we haven’t been able to answer until now.

Linear regression can become much more complex when more inputs are involved. This is called multilinear regression. The function f(x)=ax + b (where a and b are unspecified parameters) then becomes f(x,y)=ax + ay + b. Consider the concept of big data: imagine the calculations involved in using linear regression when there are countless inputs. It would be much easier for the neural network to perform these calculations to find a linear model. Attached below is an example of a complicated, multi-linear regression model that utilizes neural networking (Rocco 1). In this model, “i” are the inputs and “p” is the output. The numbers are meant to symbolize the “optimization” of the neural network, which essentially is fitting the model better to the data, to reduce the margin of error in the output.

Another important aspect of these methods’ cooperation is the interpretability of the outputted data. “Machine Learning models are going to assist humans for some (possibly important) tasks (in health, finance, driving…) and we sometimes want to be able to understand how the results returned by the models are obtained,” says Joseph Rocca (Rocca 1). It’s one thing to make the computer solve a problem; it’s another thing to learn how the computer solved the problem. One TED-ED talk focuses on the idea of learning from machines. Titled “How to manage your time more effectively (according to machines)”, this talk discusses how to use computer science methods in your own daily life to become a more efficient person (Christian 1). As we advance our technology, we must use our technology to advance us as well.

The question “are we prepared for the next outbreak?” is an exploratory one. It aims to explore the future of data science’s application to battling epidemics. This is a worldwide problem as well as a worldwide effort. Computer scientists are developing neural networks across the globe; this has become a global and collaborative experience. This is the way it should be; we are all in this together. My hope is that one day, we will be able to learn enough from technology to see patterns where we historically could not (with the human eye). The combined power of these two data science methods is quite exciting. It is very apparent how this is only the early stages of artificial intelligence. It will continue to develop alongside us, learning from us as well as teaching us.

There is one notable gap in the literature on these topics. There are very little resources designated to teaching the unexperienced how to begin working with machine learning. If this science is to develop, it must be easily accessible to everyone, otherwise the next Einstein may end up coding the next Halo game instead of a cancer-curing neural network. This technology presents such power and ability, and we cannot take that for granted. There also needs to be a push for a wider spread of application of this technology to our everyday lives. This may create more motivation for people to pursue the root of an aritifical intelligence engineer. This is the field of the future. This is our best chance to combat unforeseen future disasters.

Research Proposal

The answer to the question “Are we prepared?” is a simple no. However, this brings up the question “How can we prepare?”. There is a severe lack of information and research into the future of epidemics, which may as well be the future of humanity. If we are not ready for the next deadly epidemic, it could be the last one. There is a lack of literature about the future of epidemics. We are so preoccupied with responding to current epidemics that we lack foresight into the next lethal epidemic. This fight needs to become less like checkers, and more like chess. It’s time to think a few steps ahead. What will be our first response to the next epidemic? Will it be to enact social distancing? Did social distancing do enough to combat COVID-19? Although there are a myriad of questions surrounding the current situation, there needs to be more focus on the future. We need more research on how to recognize future epidemics swiftly, before they can spread around the globe.

To fill this literature gap, there must be research done. First, through the use of neural networks and Big Data, we must optimize our models of epidemics in order to develop a list of an epidemic’s defining criteria. By forming this list of characteristics, it will become easier to differentiate between an outbreak and a pandemic. With this kind of disaster, time is very valuable. A faster response could mean adequate isolation of the virus. Through the use of AI and deep learning, we can improve our epidemic response time.

Included above is a figure from the New England Journal of Medicine (NEJM) that illustrates the types of studies necessary to control an epidemic (Lipsitch 1). I will begin by disecting the surveillance study. There are many sources of data that provide the information essential to survey the people. For instance, the vast population owns a smart phone, which collects tons of data on our daily lives. This data can be very useful in discovering the quantity of cases in a particular region. Furthermore, this information would be used to isolate particularly infected areas from the healthier ones. An epidemic is much easier to contain at the early stages, where only a few communities are infected. This is the basic premise of a quarantine: to contain the infection, and prevent the spread at all costs. I propose a heavy research into the warning signs of an epidemic. If the government is able to diagnose an epidemic as early as possible, defending against said virus will be exponentionally easier. This vein of research will be allocated $10,000 in order to aquire the means of data collection and data analysis as well as to finance the employees and travel costs.

The next vein of research would be focused on the environment of an infection in a household. The purpose of this study would be to investigate the undiagnosed, asymptotic, and mild cases, in separation from confirmed cases. This would further our knowledge on the timing of the spread of the virus, which means its predictability would greatly increase. This study would also lead to the decision of whether a social distancing order is necessary or not. Additionally, it would reveal whether children play a role in the mass transmission of the virus, which would lead to the closure of schools. The budget for the household study will be $5,000, for similar reasons as the surveillance study.

The next study would be focused on communities as a whole. The strategy here would be to combine a variety of surveillance studies in a single community, as well as performing singular case studies. The prospective goal is to quantify the burden of the infection on a household as well as on a community. This study will also aim to increase the accuracy of a work-in-progress epidemic curve for the virus in question. By considering the hospitilizations and deaths of a singular community at a time, the virus can become much better understood. The information gathered here can be applied to one larger community: the nation. This vein of study will also receive a budget of $5,000 in order to continue the analysis of previously collected data, as well as another $10,000 to conduct multiple case studies.

By conducting these case studies, we will be able to characterize the outcomes of the virus and its infectivity. We will investigate the history of a single person at a time, to find possible sources of infections. Travel history plays a large role in this, as well as the person’s occupation and day-to-day life. By looking at the people they have come into contact with, one can assess where the virus may have been transmitted to them. Then, by looking into the people they have come in contact with and testing them, a conclusion may arise. Is the virus airborne or vector-borne? This study will answer that question and many more.

Once these studies are conducted, the data and the conclusions will be compiled into one study. The data will then be used to discuss the necessary actions, which may include (but are not limited to) quarantining a specific region, enacting a stay at home order, proposing social distancing, placing travel restrictions, and making testing sites available to either the entire nation or to particular areas. This study will receive a $10,000 budget, to work alongside partner institutions and to communicate with the government. Another $2,000 will be allocated to converse with the World Health Organization (WHO), basically trading any knowledge or information on the virus in question. Overall, the budget will come to about $42,000. This is not an astonishing price, considering it is being substituted for the price of thousands (possibly hundreds of thousands) of people. One very realistic source of investment would be Bill Gates. As mentioned previously, Gates is passionate about the future of epidemic research, and would agree with the claim that we are exceptionally unprepared for the next deadly viral epidemic.

This research plan is the most efficient plan for the containment of a virus. While other plans may have designed a step-by-step process, I have purposely arranged my plan to create multiple simultaneous studies. Time is unarguably the most important resource when it comes to battling an epidemic. By enacting these studies at the same time, data will come in at a rapid pace, allowing decisions to be made as efficiently as possible. Not to mention, this plan is cost effective, by using a singular community as a representation of the country as a whole. The cost to study the entire nation is unconceivable, as well as the labor that would be required. Instead, I will focus on the smaller scale. There may be concerns with the timing of the studies. For example, the final step where a decision on action is made can only occur once the other studies have been conducted. Realistically, these studies will continue as long as the virus is a problem. Once the studies have collected enough data, a decision can be made. However, more information will persistenly arrive, allowing us to make new decisions, such as lightening travel restrictions or social distancing orders. This is not simply a plan for the beginning of an epidemic; it is a plan for the entire course of a virus. If this study is overall successful, I would then propose a plan to study our reactions, and decide what went wrong, and where. This leaves room for improvement, which means this plan can be used for any future epidemics. It will continue to evolve and include new technologies as they come available. Another strength of this plan is the sheer flexibility of it. If one study is not producing the conclusions that are expected, it can be revised to fit the virus as needed. Furthermore, if the selected region is not producing results as hoped, a new region may easily be selected. One hope that is carried by this research plan is that the World Health Organization will work alongside this project, providing whatever insights they may hold on the virus’s origin, infectivity, lethality, severity, and transmission. One more strength of this plan is how it will help to predict more “waves” of the virus. Currently, there are many questions about the next wave of COVID-19. We only know that this is a very probable possibility because of how it has acted in other countries. This is the same mentality that will be used for my research plan; collect data from wherever possible, and come to logical conclusions based off of it. This will certainly be a cooperative and communitive research plan. We must pull together and work together to fight epidemics.

At the root of this human development problem of disaster preparedness is what matters most: human lives at stake. Another harm of this problem is the threat to economies and societies. Fiji knows this problem all-too-well, as they have faced these threats and have developed means to negate them. This is also a very current harm as well: the U.S.’s economy has undoubtedly taken quite a hit from COVID-19. Many countries, including the U.S., have even implemented economy-stimulating packages, by giving money unemployed citizens. One final harm of this problem is how present it is. This COVID outbreak is only the first; the government expects more to come, even considering the fall a possibility to be our next wave of cases. These diseases are able to spread horrifyingly fast. They can spread to all corners of the globe in days, thanks to our modes of travel. Disaster preparedness is inherently global, and there must be a strong global presence to combat it. One example of this is the World Heath Organization. We also must learn from past experiences. Writer and philosopher George Santayan once prophesized “Those who do not learn history are doomed to repeat it.”

Sources

ADRC. “Characteristics of Disasters in Oceania.” ADRC Asia, 2002, Characteristics of Disasters in Oceania

UNDRR, ADPC. “Disaster Risk Reduction in the Republic of Fiji.” UNDRR, July 2019, Disaster Risk Reduction in the Republic of Fiji

Save the Children’s Resource Centre. “Key Messages for Disaster Risk Reduction And Resilience in Fiji: A Guide For Public Education & Awareness.” UNISDR, Humanitarian Aid and Civil Protections, 2016 https://resourcecentre.savethechildren.net/node/12396/pdf/key-messages_booklet_drr_fiji_2016.pdf Key Messages for Disaster Risk Reduction And Resilience in Fiji: A Guide For Public Education & Awareness

Rubella Initiative. “Fiji and Measles: from Devastation to Elimination.” Measles & Rubella Initiative, American Red Cross, 16 Jan. 2017, measlesrubellainitiative.org/fiji-and-measles-from-devastation-to-elimination/.Fiji and Measles: from Devastation to Elimination

Getahun, Aneley, et al. “Dengue in Fiji: Epidemiology of the 2014 DENV-3 Outbreak.” World Health Organization, World Health Organization, Apr. 2019, ojs.wpro.who.int/ojs/index.php/wpsar/article/view/652/921. Dengue in Fiji: Epidemiology of the 2014 DENV-3 Outbreak

Alidoost, Fatemeh & Arefi, Hossein. (2018). Application of Deep Learning for Emergency Response and Disaster Management. https://www.researchgate.net/publication/323187472_Application_of_Deep_Learning_for_Emergency_Response_and_Disaster_Management

UNDRR. “UNDRR Home.” UNDRR, 2020, www.undrr.org/.

Kommenda, Niko, et al. “Coronavirus Map of the US: Latest Cases State by State.” The Guardian, Guardian News and Media, 2020, www.theguardian.com/world/ng-interactive/2020/mar/27/coronavirus-map-of-the-us-latest-cases-state-by-state.

Routh, Jennifer. “NIH Clinical Trial of Remdesivir to Treat COVID-19 Begins.” National Institutes of Health, U.S. Department of Health and Human Services, 25 Feb. 2020, www.nih.gov/news-events/news-releases/nih-clinical-trial-remdesivir-treat-covid-19-begins.

Moné, Lesa. “The Era of Quantum Computing and Big Data Analytics.” Enterprise Architecture Management, LeanIX GmbH, 18 Jan. 2019, www.leanix.net/en/blog/quantum-computing-and-big-data-analytics.

Gill, Navdeeo Singh. “Artificial Neural Network Applications and Algorithms.” XenonStack, XenonStack, 24 Mar. 2020, www.xenonstack.com/blog/artificial-neural-network-applications/.

Rocca, Joseph. “A Gentle Journey from Linear Regression to Neural Networks.” Medium, Towards Data Science, 13 July 2019, towardsdatascience.com/a-gentle-journey-from-linear-regression-to-neural-networks-68881590760e

Christian, Brian. (2018, January 2). Brian Christian: How to manage your time more effectively (according to machines) [Video file]. Retrieved from https://www.youtube.com/watch?v=iDbdXTMnOmE&t=3s

Lipsitch, Marc, et al. “Defining the Epidemiology of Covid-19 - Studies Needed: NEJM.” New England Journal of Medicine, 7 May 2020, www.nejm.org/doi/full/10.1056/NEJMp2002125.