Discussion
Started 28th Apr, 2020
  • Nordson MATRIX

How can computer science contribute to stop the COVID-19 pandemic?

The question of how computers can contribute to controlling the COVID-19 pandemic is being posed to experts in artificial intelligence (AI) all over the world.
AI tools can help in many different ways. They are being used to predict the spread of the coronavirus, map its genetic evolution as it transmits from human to human, speed up diagnosis, and in the development of potential treatments, while also helping policymakers cope with related issues, such as the impact on transport, food supplies and travel.
But in all these cases, AI is only effective if it has sufficient examples to learn from. As COVID-19 has taken the world into unchartered territory, the "deep learning" systems, which computers use to acquire new capabilities, don’t necessarily have the data they need to produce useful outputs.

Most recent answer

18th Jul, 2020
Mohamed Samir Boudrioua
Ronin Institute
A large datasets related to covid 19 still required and necessary for a more reliable results of AI models

All replies (22)

28th Apr, 2020
Mela G. Abdul-Haleem
University of Baghdad
The use of pattern recognition techniques can be helpful for localization the existing of the cells of the virus in the body for example Russia uses facial recognition to tackle Covid-19. City officials are using a giant network of tens of thousands of cameras - installed with facial recognition software. An interesting New York Times article last week posited that governments’ use of digital surveillance techniques for the COVID-19 response – such as the tracking of geolocation to gauge quarantine restrictions – would lead to more pervasive digital tracking in the future. On a related note, there have been reports of an increased use of facial recognition technologies as governments use digital tools to respond to the outbreak.
2 Recommendations
28th Apr, 2020
Mawadah Mohammed Sulaiman
University of Mosul
Al can helps to recognize the location of existing ceels of the virus covid 19 on the humans body by facial recognition technologies and can neural netwok also may be avoid or attempt to learn the netwok the available treatment and to avoid increesed the cells of covid_19 on the humman's boody.
1 Recommendation
28th Apr, 2020
Lahiru Laminda Abeysekara
Deakin University
The above preprint from my colleague provides many criteria on this topic.
2 Recommendations
29th Apr, 2020
Kasyap Suresh
Universiti Teknologi PETRONAS
I believe that both Machine and Deep Learning is currently a hot topic and has attracted many people to do research in this area and find numerous and interesting use-cases. Regarding COVID-19 pandemic, classification algorithms would be useful to distinguish the affected cases from unaffected ones. This applies to regions too. Another thing is you can also predict how this classified population is varying over a period of time (over this quarantine). Very large population data sets would require the usage of deep neural networks so as to train more amount of data. Additionally, AL tools can also assist in recommending the researchers regarding the appropriate medicines for the concerned person and for the right disease (when they have their vaccines in hand and wanted to know the best one for a particular person).
I also observe that cryptography will be an important area as this will help in securing authentic data about the details maintained in different websites such as affected, unaffected, susceptible areas, and so on. Maintaining a highly secure database will be an important step towards securing such valuable information as exploiting inaccurate data may easily jeopardize the psychology of the society, especially during such critical situations.
30th Apr, 2020
Aqil Assalil
Florida Atlantic University
There is an event called "Network Epidemiology Online Workshop Series - Understanding and Exploring Network Epidemiology in the Time of Coronavirus " currently going on in which they have invited individuals from a multitude of specialties on looking at unique ways of combating the COVID-19 issue. There are a ton of datasets that have already been shared. This is an excellent place to start. Don't be intimated by the Biological Aspects of the theme. Computer Science plays a major role in every area of the sciences.
1 Recommendation
1st May, 2020
Okuthe P Kogeda
University of the Free State
Computer science can develop apps that help with contact tracing, testing and warning in advance about a hotspot of the disease. All these can be achieved using AI algorithms.
2nd May, 2020
Ahmed Ismail Ebada
Nordson MATRIX
Thanks for all of your interesting answers
3rd May, 2020
Ayoub Ezzaki
Mohammed V University of Rabat
Dear Ebada
If we cant detect correctly the COVID19 virus by Computer science, we can at least stopping it from growing. One of the most interesting applications of computer science in this case is the re-programmed robots for decontamination.
As we know, the COVID19 can steak in surfaces, so a good contamination can be a great element of limiting the growing of the pandemic
6th May, 2020
Ashwani Kumar
Sant Longowal Institute of Engineering and Technology
The deep learning techniques applied on social distancing data and on CT scan images can help contain Covid-19
12th May, 2020
Olutola Olaide Fagbolu
University of Sierra Leone
Natural Language Processing Parser can help in the development of interactive chat bot that can give preventive measures, symptoms, FAQs of Covid-19, Emergency contacts for all the districts, provinces or states and general toll-free number of ministry of health, live information on cases of Covid-19 patient(s), infection rate(s) and many more
1 Recommendation
17th May, 2020
Mokhaled N. A. Al-Hamadani
Northern Technical University
As mentioned above, computer science can build many applications that could warn people from this virus!
1 Recommendation
1st Jun, 2020
Shrohan Mohapatra
University of Massachusetts Amherst
I think one can use cellular automata to design the antidote to the SARS-CoV-2!
I have worked extensively worked on cellular automata and have worked on how to convert neural nets to "learning cellular automata" as a part of my undergraduate thesis!
So with neural nets based AI techniques on learning the virus configurations, I can always construct preliminary CAs that can do the same! Perhaps, to do even better, I can use the 4-tuple definition of cellular automata, "learn" the neighbourhood of the cell of the grid and also the transition function also. To be precise and complete, I am representing a single "genome" of the virus as a single cell of the CA! This way, I can theorise the scalable parallelisation of the learning algorithm in a much-closer-to-reality fashion! This way, I would simply need to depend a large number of simpler ALUs instead of relying on several iterations of computation upon the same (perhaps more complicated and deeper) neural ALU grid! That way, I can somehow think of converting that learning CA as a "dynamical manifold" that would prove and substantiate all or most of the Markov chain based models that are currently prevalent in the literature!
To cut the long story short, I am suggesting a "computationally deterministic" dynamical model that can be scalable parallelised that can track/hunt down the genomic activity, which (at least I believe) lies at the heart of the antidote pathway design! (Although, I am a complete novice!)
Please let me know if I am astray at any point in the above suggestion!
13th Jun, 2020
Sachin Kumar
University of Jammu
With the help of technologies like IoT, AI, ML,DL ,Big Data, Blockchain etc.
15th Jun, 2020
Sourabh Shastri
University of Jammu
IoT, AI, ML, DL etc
23rd Jun, 2020
Abhijit Mitra
University of Calcutta
By developing model on infection rate and identify safe zone
23rd Jun, 2020
Harasit Kumar Paul
Bangabandhu Sheikh Mujib Medical University
Please have a look at the link below:
1 Recommendation
24th Jun, 2020
Dariusz Prokopowicz
Cardinal Stefan Wyszynski University in Warsaw
For example, ICT and Industry 4.0 are used to improve predictive analytics used to analyze the development and to develop development forecasts for complex, multifactorial processes, including predictions for the development of an epidemic and / or pandemic SARS-CoV-2 Coronavirus (causing Covid-19 disease). In this way, knowing the future, forecasted pace of development and / or expiration, you can better prepare, adapt your healthcare system, apply specific socio-economic policies to counteract negative economic effects, etc.
Best regards,
Dariusz Prokopowicz
1 Recommendation
Can you contribute to the discussion?

Similar questions and discussions

Related Publications

Preprint
Full-text available
Coronavirus, a large family of viruses, causes illness in both humans and animals. The novel coronavirus (COVID-19) came up in Wuhan in December 2019. This deadly COVID-19 pandemic has become very fast-spreading and currently present in several countries worldwide. The timely detection of patients who have COVID-19 is vitally important. To this end...
Article
Full-text available
Il y a en science quelques buzz-words — littéralement ? mots-rumeurs ? — qui font la Une avant de céder la place au mot à la mode suivant. Le deep-learning — ou en fran?ais ? apprentissage profond ? — en est un. Décryptage en profondeur pour savoir si c'est une idée creuse.
Got a technical question?
Get high-quality answers from experts.