Tag Archives: ‘predict

Coronavirus leaves Olympic athletes with no way to predict whether Games will go on

The countdown clock for the 2020 Summer Games officially sits at 143 days, and Canada’s top athletes are making the final push toward realizing their personal dreams of Olympic glory.

Already under immense pressure — the Olympics only come every four years and, for many, they are a once-in-a-lifetime opportunity — these young men and women face another massive obstacle on the rocky road to Tokyo.

The coronavirus has already forced Canadian athletes — in sports such as track and field, water polo, and table tennis — to scuttle training camps and bow out of major competitions.

In the bigger picture, the athletes have no idea if the Tokyo Games themselves might be postponed or cancelled altogether. The opening ceremony is scheduled for July 24.

“The support teams — the coaches and the families — can help by redirecting them to focus on the here and now,” says Dr. Tricia Orzeck, a licensed psychologist with a specialty in sports.

“One day at a time. They can’t control what decision is made with Tokyo, so really they just need to just keep focusing on what they’re doing now.”

Rising threat

One of Canada’s brightest stars, Andre De Grasse, is shooting for gold in the 100, 200 and 4×100-metre relay. He won silver and bronze at the 2016 Summer Games in Rio de Janeiro, and he badly wants to upgrade.

His phone is constantly bombarded with news about coronavirus. 

One of the fastest men on the planet, De Grasse can’t outrun the constant talk about the rising threat.

“It is scary, but I just try not to think about it,” De Grasse told Radio-Canada Sports.

“I kind of have to continue to keep focusing on my sport and hoping that by the time the Olympics come around everything is cleared, everything is ready to go, and everyone is going to have a great time at the Olympics.

“So we’ll see.” 

Preparing for potential calamity is nothing new for the International Olympic Committee. Fears of the H1N1 pandemic hung over the 2010 Winter Games in Vancouver. The threat of the Zika virus caused some athletes to bow out of the 2016 Summer Games in Rio.

Two years later in Pyeongchang, South Korea, the main issue was Norovirus.

“The Canadian Olympic Committee and the IOC ­—  and indeed all countries — always prepare for this kind of eventuality,” Dr. Bob McCormack, the Canadian Olympic Committee’s chief medical officer since 2004, told CBC News Network.

“Like any big Games, you plan for the worst and hope for the best. And the same thing really applies this time.”

WATCH | COC’s chief medical officer on impact COVID-19 might have on Canadian athletes:

Dr. Bob McCormack speaks to CBC on the concern the virus might have on Canadian athletes and the Tokyo Olympics. 7:32

Death toll sits around 3,000

The global death toll from COVID-19 sits around 3,000, with roughly 2,900 of those fatalities occurring in mainland China. The virus has spread to more than 60 countries with more than 100 deaths. On Sunday, health officials announced four new cases in Ontario, bringing the number of confirmed cases in Canada to 24.

Former IOC vice-president Dick Pound, of Montreal, warned last week that June is the likely the cut-off to decide whether the Games will be cancelled.

The Olympics in 1916, 1940 and 1944 were cancelled due to war.

“This is the new war, and you have to face it,” Pound told The Associated Press. “In and around there, folks are going to have to say: ‘Is this under sufficient control that we can be confident of going to Tokyo or not?'”

Tokyo organizers acted swiftly to assure people that cancellation is not on the table. But the spread of coronavirus is escalating and the situation is fluid.

“At this point, the plan is to plan that the Games will be on,” McCormack said. “This is a different virus. And it certainly is a concern. The biggest concern is that we don’t just know the details. We don’t know the trajectory it’s going to take. We don’t know if it’s going to come under control or not.”

The COC issued a statement late last week that said: “As of now, and based on all scientific information available, our plans remain unchanged, all while being alert that we must always consider important and necessary public-health precautions as they arise … COVID-19 is a fast-evolving situation globally, and we will update or revise our Games planning as necessary.”

Canadian breach volleyball star Brandie Wilkerson, pictured competing at the 2019 FIVB Tokyo Open, isn’t ready to push the panic button just yet. (Toshifumi Kitamura/AFP via Getty Images)

Canadian athletes left to train

In the meantime, the athletes are left to train as if the Games will happen, with no way of predicting whether they actually will.

Orzeck advises would-be Canadian Olympians to concentrate on the tasks in front of them.

“Focus on doing the best that you can in the training in your World Cups and the training camps that are all coming up,” says Orzeck, former chair of the sports psychology section of the Canadian Psychology Association. 

“Things are happening very quickly for these athletes that compete in the summer, so it’s really gearing up for the majority of my athletes I’m working with.

“Every day to try to do the best the best that you can be the top of your sport, but also just the top for yourself.”

Canadian beach volleyball star Brandie Wilkerson is trying to adhere to that wisdom.

“There’s always a lot of news, a lot of different ideas and things that show up before an Olympic Games that cause a lot of attention,” she told CBC Sports.

“So while I always want make sure we are all safe and healthy, I think I’m just looking to just kind of wait and see and trust in the process of containing these things and regulating it — and then kind of make a judgment from there and not be so [hasty] to panic.”

Let’s block ads! (Why?)

CBC | Sports News

AI could better predict climate change impacts, some experts believe

All signs point toward a future affected by climate change. 

From higher temperatures to droughts and more extreme weather, experts are searching for ways to sustain our growing population, as well as our planet. 

Some analysts say machine learning and artificial intelligence (AI) offer promising strategies to respond to the affects of climate change. 

AI can work faster than a human being, can forecast further into the future, has a low error rate and has 24/7 availability.

This allows it to better predict extreme weather, flooding, natural disasters and other destruction linked to climate change.

And that’s why, in late June, University of Waterloo partnered with Microsoft AI for Earth.

Launched in 2017, AI for Earth is a program that issues grants to projects using AI to address climate change challenges.

The project, which focuses on finding solutions in four specific areas —  agriculture, water, biodiversity and climate change —  is dedicating $ 50 million US to solving problems caused by the shifting climate. 

A woman is shown tending to crops in 2015 in North Phyongan province, North Korea. AI has the potential to improve sustainable and data-driven farming. (Jacky Chen/Reuters)

Since 2017, it has expanded across the world, giving grants to more than 250 applicants in 66 countries.

Lucas Joppa, chief environmental officer at Microsoft and founder of AI for Earth, said the project is helping to create a digital transformation of environmental sustainability.

Grantees use AI technologies to process machine learning algorithms, which, through code, can create future risk models and predictions of challenges caused by climate change disruptions. The AI uses combinations of historical data, simulations and real-time satellite observations to track patterns much faster than a human being.

This technology can better predict future events, including potentially forecasting the location of the next wildfire or using past data to improve food production through weather tracking and soil information.

Predictions like these could help prevent disasters, create safer environments and warn people of impending dangers.

Fear of AI 

With the increase of AI comes an increase of fear in some quarters.

Christopher Fletcher, associate professor at the University of Waterloo and grantee of the AI for Earth program, said the concept of machines taking over the job market or gaining superior intelligence are common misconceptions of the large scale development of AI.

“I think most people think about AI as being a machine somehow replacing something that a human being does,” Fletcher said. “In my project, it’s slightly different because I have a machine that is able to kind of learn but it’s not replacing a human. It’s actually replacing a more complicated computer model.”

Fletcher’s project — which aims to predict future climate forecasts more accurately through the use of AI — isn’t the only one.  

A woman looks out at the Atlantic coastline on the Herring Cove Provincial Park trail in Halifax, 2016. These communities face one of the biggest risks from climate change in Canada. (Darren Calabrese/The Canadian Press)

There are other commercially available projects that focus on anything from creating sustainable, data-driven farming, to analyzing blood from mosquitoes to stay ahead of diseases.

These are created to help people tackle climate change challenges, although one analyst fears AI could have the impact of letting people get away with consuming too much and failing to change their behaviour.

“Although [AI] could be helpful for tracking things like over fishing or pollution, it takes people off the hook,” said Kerry Bowmen, a bioethicist and conservationist. 

“Solving challenges like these doesn’t make people change. This brings an issue of intergenerational ethics — we have a responsibility to future generations. We need more long-term solutions.” 

Let’s block ads! (Why?)

CBC | World News

MIT Uses AI to Predict Breast Cancer Up to 5 Years in Advance

This site may earn affiliate commissions from the links on this page. Terms of use.

Modern artificial intelligence employs complex algorithms to do all sorts of tasks in an instant, such as figuring out how a customer feels based on their review or identifying specific characteristics of an image. However, AI’s brightest moments come from the creative ways we employ these algorithms. People have used AI to generate new sports, turn doodles into realistic landscapes, and now MIT has found a way to detect breast cancer up to five years in advance using a deep-learning image classification model.

MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and Massachusetts General Hospital (MGH) used mammograms and known outcomes from over 60,000 patients to train their new model on the tiniest visual details the human eye can easily miss. Well-trained doctors don’t miss these predictive patterns just because they can appear too small to notice, but because more subtle patterns simply don’t attract enough attention. An image classification model that can file through the minutia across thousands of scans can make quick work of this daunting task.

The team’s model identified a woman at high risk of breast cancer four years (left) before it developed (right). Credit: MIT

MIT Professor (and breast cancer survivor) Regina Barzilay explains how this new model can change treatment plans for the better:

Rather than taking a one-size-fits-all approach, we can personalize screening around a woman’s risk of developing cancer. For example, a doctor might recommend that one group of women get a mammogram every other year, while another higher-risk group might get supplemental MRI screening.

When doctors can order mammograms based on patient need, they can avoid unnecessary exposure to radiation and costs of potentially unnecessary scans. While existing models can accurately identify 18 percent of patients in the high-risk category, this new model boosts that number up to 31 percent. Its success leans heavily on the team’s approach to its development. For the first time, a breast cancer prevention model focuses on individual women. It also takes racial diversity into account, where past models primarily focused on Caucasian populations. This not only helps to further accuracy but reduce the notably higher rate of breast cancer deaths in African American women.

As MIT and MGH have demonstrated, well-trained image classification models can help doctors save lives. Although no AI yields perfect results, image classification algorithms have matured and become reliable in many different applications—especially in specific models like this one. You need little more than a good idea, relevant data, and a bit of time to create a successful image recognition model. Services like Clarifai, Microsoft Azure, IBM Watson, Vize and others provide free custom model training platforms that require no programming knowledge to set up. With these algorithms freely available for everyone to use, we all have the necessary resources to train AI to solve problems and help others. It takes time and care to safely integrate a successful experiment into the practices of diagnostic medicine; this approach will likely see many revisions as it expands outside of a single hospital. But the early results are promising.

Now read:

Let’s block ads! (Why?)

ExtremeTechExtreme – ExtremeTech

Engineers Are Using AI to Predict How New, Unknown Materials Will Perform

This site may earn affiliate commissions from the links on this page. Terms of use.

Materials engineering is critical to the modern world in ways we almost never stop to think about. Understanding how solid structures behave at the nanoscale level is critical to modern advances in many fields, including semiconductors.

Researchers working at MIT and in Russia and Singapore are using AI to predict how strain will impact material performance and to explore which types of strain will create which effects. Some of you may be familiar with the term “strained silicon,” which refers to the process of stretching a layer of silicon over a substrate of silicon-germanium. Strained silicon, which was introduced in modern microprocessor manufacturing during the P4 era, improves overall CPU performance compared with non-strained silicon. But, as the MIT author notes, finding the exact degree and type of strain to use is exceedingly difficult.

Strain can be applied in any of six different ways (in three different dimensions, each one of which can produce strain in-and-out or sideways), and with nearly infinite gradations of degree, so the full range of possibilities is impractical to explore simply by trial and error. “It quickly grows to 100 million calculations if we want to map out the entire elastic strain space,” Li says.

The Wikipedia page for strained silicon itself indirectly hints at the complexity of these changes. It notes that while initial strained silicon work took the form I just described, later improvements to the technique involve additional complex processing steps. Finding the precise tools to further improve the overall performance of these materials is clearly a slow, painstaking process. This is also part of why the development time for new features and capabilities in semiconductor manufacturing (or, say, battery capacity improvements) tends to be as long and slow as it is. Many of the improvements we discuss when we talk about batteries or improved semiconductor technology are fundamentally material engineering improvements.

Strained silicon

Strained silicon. Image by Wikipedia

According to the research team, their neural network model for predicting strain was highly accurate. The team focused on diamond, which has a number of positive traits that would make it an excellent semiconductor if some of its negatives could be ameliorated. There’s also the potential for introducing higher amounts of strain in products that already use the approach, potentially transforming the base material in the process.

Whereas this study focused specifically on the effects of strain on the materials’ bandgap, “the method is generalizable” to other aspects, which affect not only electronic properties but also other properties such as photonic and magnetic behavior, Li says. From the 1 percent strain now being used in commercial chips, many new applications open up now that this team has shown that strains of nearly 10 percent are possible without fracturing. “When you get to more than 7 percent strain, you really change a lot in the material,” he says.

“This new method could potentially lead to the design of unprecedented material properties,” Li says. “But much further work will be needed to figure out how to impose the strain and how to scale up the process to do it on 100 million transistors on a chip [and ensure that] none of them can fail.”

The most interesting thing about approaches like this is whether or not they can scale to the point of becoming fundamentally new approaches to the way we perform materials research. In theory, an AI-powered research engine could tear through material permutations that would take a dedicated research team weeks or months to test. But ensuring that our models can properly anticipate how materials would deform under various conditions is challenging — the data set to “train” the AI would seem to be formidable, in the best of scenarios.

Still, even a model that could pare down the list of ideas to investigate from hundreds of millions to thousands would be a major breakthrough. There could come a time when the use of AI resources like this isn’t just expected but has become a functional requirement of continuing scientific advance.

Now Read:

Let’s block ads! (Why?)

ExtremeTechExtreme – ExtremeTech

Google Neural Network Can Predict Your Health Status From Your Retina

This site may earn affiliate commissions from the links on this page. Terms of use.

Machine learning can be used to recognize faces, drive cars, and even spot exoplanets, but now Google is teaching its computers to do something even more unexpected. Researchers at Google have developed a way to predict a person’s blood pressure, age, and smoking status from an image of their retina, according to Scientific American. This data may even be enough to determine when someone is at high risk of a heart attack.

Google’s research used a convolutional neural network, the same biologically inspired system used to identify objects in photos. However, these networks can do plenty of other things if you just train them on different data sets. Convolutional neural networks are able to analyze an overall image more like the human brain, without splitting it up into pieces. These networks can actually understand the content of an image, and they’re getting very good at it.

Google’s research arm had the idea to apply neural network design to biological problems, but it didn’t start with the retina. In a past study, Google created a tool called DeepVariant that could scan a DNA sequence to find small mutations that would be missed by other methods. Outside of Google, researchers from the Allen Institute for Cell Science in Seattle are using convolutional neural networks to automatically identify cellular organelles in 3D images from microscopes. The components are colored by the computer, which eliminates the need to stain cells.

Deep neural networks have at least one hidden layer, and often hundreds. That makes them expensive to emulate on traditional hardware.

To develop its retina-scanning neural network, Google needed a lot of data. It used retinal images from 284,335 patients to set up the network. Later, it validated the network’s deep learning abilities using two different data sets of 12,026 and 999 patients. This was an important step as it showed that Google’s model could accurately predict health metrics. Just from retinal images, the model can determine age within about 3 years, gender (97 percent accuracy), smoking status (71 percent accuracy), blood pressure (within 11.23mmHg), and how likely it is that someone will have an “adverse cardiac event.” The model was able to predict that last one with 70 percent accuracy. It’s not a sure thing, but that’s pretty accurate when you consider it’s just looking at blood vessels in the eye.

The study is still just in preprint right now and has not been peer reviewed. Other researchers will need to go over the models and validate the results before we’ll know the impact, but it could be a boon to medicine. Even if it’s not 100 percent accurate, a retina scan is a simple, noninvasive procedure that could provide more data to doctors.

Let’s block ads! (Why?)

ExtremeTechExtreme – ExtremeTech

Researchers predict 'vaccine scares' using Google and Twitter trends

What do Google searches and tweets tell us about disease outbreaks? As it turns out, analyzing search and tweet trends could give warning signs for when a disease outbreak may happen due to reduced vaccinations.

An international team of researchers analyzed searches and tweets related to measles and the measles-mumps-rubella vaccine using artificial intelligence and a mathematical model, and detected warning signs of a “tipping point” two years before the Disneyland outbreak happened.

In early 2015, there was a measles outbreak that was traced to Disneyland in California. Many of the people who fell ill in Disneyland were not immunized — some too young for the vaccine and others had personal reasons for refusing shots. The outbreak was declared months later in the spring.

Chris Bauch, one of the researchers and a professor of applied mathematics at University of Waterloo, told CBC News the “tipping point” is where there begins to be “enormous decline” in vaccinations due to fear of “vaccine risk.”

Bauch said while there were warning signs for California that showed it was approaching a tipping point, it didn’t actually cross over.

“You had this outbreak which seems to have made people more scared of the disease again and that pushed the population back away from the tipping point.”

The study was conducted in collaboration with researchers from Dartmouth College in the United States and École polytechnique fédérale de Lausanne in Switzerland. It was recently published in the Proceedings of the National Academy of Sciences.

What warning signs look like

As to what those warning signs look like in real life, outside of the data, Bauch said there tends to be a lot of “variability” and “change in the population’s opinion in pro or against vaccines.”

Bauch is hoping his team’s work can be used for public health units and other organizations to focus their resources on educational campaigns on vaccines, to ensure the rates don’t go low enough to set off a disease outbreak.

He made an analogy using people who are at higher risk for heart disease due to smoking, where physicians could target those patients and advise them to stop smoking.

“In the same way, we hope to target populations where they’re showing a lot of variability,” Bauch said. “And we can therefore say, well if we don’t do something here, the population might have a vaccine scare, an outbreak, so we should try to do something to stop that.”

For now, his research team will work on expanding the research to analyze trends in searches and tweets that are in languages other than English.

Let’s block ads! (Why?)

CBC | Health News