A team of U of T Engineering researchers, led by Professor Timothy Chan (MIE), is leveraging machine learning to optimize the macronutrient content of pooled human donor milk recipes.  

The researchers introduce their data-driven optimization model in a new paper published in Manufacturing & Service Operations Management. 

Chan and his team worked with Mount Sinai Hospital’s Rogers Hixon Ontario Human Milk Bank — which provides donor milk to preterm and sick babies who are hospitalized across Ontario — as well as Professor Debbie O’Connor (Temerty Faculty of Medicine, Nutritional Sciences). 

“For a variety of reasons, many hospitalized infants do not have a full supply of mother’s milk. In this instance human donor milk can be lifesaving particularly as it helps to protect preterm infants from necrotizing enterocolitis, a life-threatening bowel disease,” says Dr. Sharon Unger (Temerty Medicine, Nutritional Sciences), a neonatologist and the medical director of the Rogers Hixon Ontario Human Milk Bank.  

“The new program developed by Dr. Chan helps to ensure that each batch of human donor milk meets the protein and calorie needs of preterm infants.”  

Currently, many milk banks, including Mount Sinai’s, rely on individual decision making when pooling donor milk. This presents a significant challenge in producing a consistent donor milk product that contains sufficient macronutrients for premature and sick babies in neonatal intensive care units.  

“It takes a lot of time to create these recipes without a defined method,” says Chan.  

“While there are studies that show that milk that comes from donors who are early in their postpartum period tends to be more protein rich, our approach provides a good prediction of the actual macronutrient content that will allow milk bank employees to make better pooling decisions.”  

Given that milk banks are often non-profit entities operating on lean budgets, a low-cost alternative to obtaining a consistent, nutrient-balanced product could be useful across the entire sector.   

Devices known as human milk analyzers can be used to measure the exact macronutrient content of each milk sample at a milk bank. However, these devices are costly and require extensive regulatory approval for use, with the result that only half of all milk banks in North America use one. On top of that, analyzing every donation is a costly endeavour that is labour and resource intensive.  

“Our data-driven framework bypasses the need for a device to analyze the donor milk by using an artificial intelligence model to predict the macronutrient content of each donation,” says Rachel Wong (MIE MASc 2T2), a lead researcher of the study.   

“In addition, by using an optimization model to choose which donations to pool together, we can increase the consistency of macronutrient content in the donor milk product.”   

The multi-phased study included a one-year implementation trial at the Rogers Hixon milk bank that was designed to test whether AI-informed models could help to fill the gap.   

In the first phase, researchers collected the necessary data to create a machine learning model to predict the macronutrient content of the pooled recipes, and then designed an optimization model to create the recipes based on macronutrient requirements, that is, the necessary levels of protein and fat.  

The team then created a simulation model to test the method before embarking on an experiment in the milk bank, which took place over 16 months in 2021 and 2022.  

“Since our study was performed in the milk bank during regular operating hours, rather than in a controlled environment, there were a number of unexpected challenges that we had to adapt to,” says Wong.  

“During the COVID-19 pandemic, the volume of donations fluctuated based on the provincial restrictions — during the lockdown periods there was an unprecedented increase in the number and volume of donations.  

“We also needed to adapt the AI decisions that had already been proposed to ensure that we abided with the milk bank’s operating protocols.”   

The last phase of the study began by observing the milk bank’s operation for six months and measuring the fat, protein and bacteria levels in the pooled recipes.   

For the following six months, the milk bank used the data-driven optimization framework to create the pooled milk recipes. At the end of the year, the researchers compared the optimized recipes to the previous ones to assess which recipes met the macronutrient targets.   

“We found that our pooled recipes met the bar for protein and fat simultaneously up to 75% more often, without compromising other factors like an increase in bacteria,” says Chan. “And it took us 60% less time to make the recipes.”  

The team’s optimized recipes also have an added benefit for pre-term and sick babies, who have underdeveloped digestive systems that make it especially crucial to ensure that the milk they are consuming isn’t overly rich in protein or fat.  

Chan’s team is currently working towards expanding this research to measure other nutrients in human donor milk to see if their models can optimize them. The research has won INFORMS’s 2023 Pierskalla Best Paper Award and an Excellence in Quality and Safety award from Sinai Health.  

“Our ultimate goal is to show that our tool is applicable to other milk banks,” says Chan. “We would like to design a system that can plug into hospital systems to optimize recipes in a way that is sustainable for milk bank staff.”  

Wong says that the entire team is grateful to all those who have made the project possible.  

“We couldn’t have done this without all of the mothers who donate to the milk bank and the staff who work incredibly hard to provide donor milk to infants across Ontario and beyond,” she says.   

“I hope that this research will provide a framework to help milk banks across North America increase the consistency of macronutrient content in their donor milk product. The eventual end goal would be to see a downstream impact of improved growth and developmental outcomes for the infants that receive this donor milk.”   

– This story was originally published on the University of Toronto’s Faculty of Applied Science and Engineering News Site on November 20, 2023 by Safa Jinje.

Lucas Hilden (Year 1, MechE) was a Grade 8 student in the rural town of Falmouth, N.S., when he developed an aid that uses facial recognition technology to help Alzheimer’s patients recognize their loved ones.

Inspired by his grandfather, who suffers from the disease, the project won him a gold medal and innovation award at the Canada-Wide Science Fair that year.

“That experience showed me that the world of STEM is definitely where I belong and where I could make the most impact on society,” says the now-17-year-old, who is one of just 100 students from across Canada to win a coveted 2023 Schulich Leader Scholarship — including 10 now studying at the University of Toronto.

Awarded to incoming undergraduate students who demonstrate exceptional promise and leadership in science, technology, engineering and mathematics (STEM) and entrepreneurship, the Schulich Leader Scholarships are designed to foster the next generation of global STEM pioneers.

For Hilden, who started three businesses in high school while nurturing his love of STEM and hosting coding camps for children, winning the scholarship reassured him that he was on the right path.

“I read the Schulich Leader Scholarship requirements and thought, ‘Wow.’ If I could write scholarship criteria to describe what I’m good at and what I do, it would literally be this scholarship,” he says. “When I found out I had won it, it felt like an important confirmation that I’m doing what I should be doing.”

The Schulich Leader Scholarships are an investment in Canada’s brightest minds

The Schulich Leader Scholarships were established in 2012 by businessman Seymour Schulich, who credits his success to a scholarship that enabled him to attend McGill University’s first-ever MBA class in 1965.

Valued at $120,000 each for students pursuing engineering programs and $100,000 each for science, technology and mathematics students, the scholarships cover the total cost of an undergraduate education — allowing Schulich Leaders to focus entirely on pursuing their goals.

“Schulich Leaders are extraordinary young people with big dreams, big ideas and unparalleled potential to change the world,” says University of Toronto President Meric Gertler.

“We are incredibly excited to welcome the newest Schulich Leaders to U of T, and we could not be more grateful to Seymour Schulich and the Schulich Foundation for investing in the ambitions of these remarkable students.”

This year, the 10 Schulich Leader Scholarship winners attending U of T come from across Canada — from Nova Scotia to British Columbia — and are pursuing engineering, computer science and actuarial science programs. Their interests range from robotics to artificial intelligence, programming to entrepreneurship in STEM and beyond.

For U of T’s Schulich Leaders, the future starts now

Sandy Welsh, U of T’s Vice Provost, Students, says it’s been inspiring to witness the impact of the Schulich Leader Scholarships on some of Canada’s brightest students year after year.

“These scholarships open doors to unlimited opportunity for some of our country’s most ambitious and brilliant young minds,” she says.

“They not only provide the financial support students need to pursue a U of T education, but they also come with an incredible network of peers, mentors and supporters and offer access to world-class faculty and leading industry experts. We are incredibly grateful to the Schulich Foundation for helping these future STEM leaders start their journeys here at U of T.”

Hilden, who is studying mechanical engineering, isn’t sure yet what his future career will look like, but he knows he wants to combine his interests in business and engineering.

“I’m really interested in the entrepreneurship side of things, and I have big goals for the future,” he says. “There are so many opportunities in the city and at the University to explore the different paths available to me. I’m just getting started.”

Meet the 2023 U of T Engineering Schulich Leaders

Adam Omarali, Engineering Science

 

 

The Department of Mechanical and Industrial Engineering is saddened to announce the passing of Professor Emeritus James (Jim) Fennell Keffer in Toronto on September 29, 2023. A distinguished professor, researcher, teacher and administrator at U of T, Professor Emeritus Keffer made lasting innovations in fluid mechanics and heightened the international research profile of the University of Toronto during his remarkable career.

Born in 1933, Jim pursued his undergraduate mechanical engineering studies at U of T. Maintaining an honours standing while playing football for the Varsity Blues, Jim was also a member of the U of T Hall of Fame team that won the Yates Cup in 1954. After graduating in 1956, Jim joined the research division of Canadian General Electric, which led to his return to U of T for graduate studies. Advised by Professor Doug Baines, Jim obtained his PhD in mechanical engineering in 1962 and then spent two years as a postdoctoral fellow at the Cavendish Laboratory at Cambridge. On his return to Canada, he joined U of T’s Department of Mechanical Engineering as an Assistant Professor.

Jim’s lifetime of research advanced understanding of fluid mechanics with emphasis on two fundamental shear flows: the wake and the jet. He used novel experimental techniques to investigate these basic flows, which are relevant to environmental problems such as pollutant dispersion, smokestack dispersion, and climate effects. Jim and his students developed rigorous theoretical analyses to support their experimental data and to evaluate their validity and limitations, an important contribution to computer models.

Jim had a keen ability to recognize and plan for the future. Through his efforts, he helped the department and university acquire a unique wind tunnel in the 1970s that remains in use to this day. This facility allowed him to perform sophisticated measurements for the first time and contributed to his widely-cited and highly respected work. The quality and significance of his research brought many interested students to his lab. Those under his supervision graduated to become university professors and global industry leaders who continue to contribute to turbulence measurement and analysis.

Jim’s roles at U of T extended far beyond the classroom and his lab, as he undertook several administrative positions. He served as the Director of Graduate Studies for Mechanical Engineering, which led to appointments as the Associate Dean at the School of Graduate Studies, and later as Vice-Provost, Professional Faculties. Before retirement, Jim’s final appointment was as Vice-President, Research and International Relations. In this role, he firmly established a professional service orientation within the portfolio, made major organizational innovations that his successors have built on to increase U of T’s international research profile; and brought the first Cray supercomputer to the campus.

Jim formally retired from U of T in 1999, but continued to pursue research and graduate teaching in the following few years.

For more information about Professor Emeritus Jim Keffer and his family please see: https://www.legacy.com/ca/obituaries/theglobeandmail/name/james-keffer-obituary?id=53244726

U of T will welcome a cohort of competitively selected graduate students from across South Korea to study applied Artificial Intelligence (AI) in January 2024.

Funded by the government of South Korea and administered through U of T’s Faculty of Applied Science & Engineering, the six-month program is designed for students from diverse disciplines in technology, engineering, and the natural and mathematical sciences with ambitions to drive the innovative use of AI in their fields.

At U of T, the students will participate in intensive coursework in Machine Learning (ML) and AI, offered through the Department of Mechanical & Industrial Engineering (MIE), with support from the Centre for Analytics and Artificial Intelligence Engineering (CARTE).

“This partnership builds on the very successful Master of Engineering program offered by the Department of Mechanical & Industrial Engineering, with many of our students taking courses in ML/AI; and it represents another engagement with South Korea, as MIE already hosts an international doctoral cluster with KAIST, the Korea Advanced Institute of Science and Technology,” says Professor Markus Bussmann, MIE Chair.

“We very much look forward to hosting and welcoming the first cohort of Korean students in January.”

Throughout the program, students will have access to customized AI drop-in clinics provided by CARTE, which provides research and training support in AI to external academic and industry partners. Students will also have access to a number of applied AI seminars offered at U of T, AI and ML projects from industry, government and non-profit sectors, as well as a dedicated workspace to facilitate collaborative opportunities to apply their knowledge and skills in the booming AI ecosystem in Toronto.

“This partnership is another example of the influence of the University of Toronto and the CARTE program in AI training,” says Professor Alex Mihailidis (BME), Associate Vice-President International Partnerships at U of T. “Our partnership with South Korea is an important one to our institution, and we are thrilled to be partnering with them to provide this opportunity to their students.”

– This story was originally published on the University of Toronto’s Faculty of Applied Science and Engineering News Site on September 29, 2023 by Somayeh Sadat.

 

LaShawn Murray (MIE PhD candidate) comes from a long line of engineers and educators — and though she grew up in Toronto and Oakville, she always felt connected with her family’s roots in the Caribbean and South America.

“My family taught me the importance of understanding my identity and being proud of who I am and the legacy of my community,” she says.

“I have been reminded that I am here to make a difference in the lives of others.”

That motivation led Murray toward the health sciences. She recently completed her master’s degree in health informatics at DePaul University in Chicago. It was there that she first became aware of the field of human factors engineering in healthcare.

“I took a course called System Design in Healthcare, taught by Professor Enid Montague,” she says.

“My research for the course examined unintentional acetaminophen errors and overdose in children through a system analysis of the role of parents and caregivers in the home administration of acetaminophen. This project demonstrated the interdisciplinary nature of human factors engineering.”

Murray is one of three 2023 recipients of the IBET Momentum Fellowships, along with fellow graduate students Raylene Mitchell (MIE PhD candidate) and Chantel Campbell (BME PhD candidate). Fellowship recipients receive financial support, mentorship, training and networking opportunities to foster a robust professional community.

For her PhD at U of T, she will once again be working with Professor Montague, who joined U of T’s Department of Mechanical & Industrial Engineering in 2022. Murray will also work with Professor Myrtede Alfred (MIE), as both professors work through an equity lens to understand disparities and improve safety and outcomes in marginalized populations both within Canadian and American contexts.

“My proposed doctoral research aims to explore the role of human factors engineering in advancing health equity for marginalized populations with an intentional focus on the health of Black communities,” she says.

“Specifically, I’ll be examining the role of automation in primary care. Automating certain types of clinical work can improve clinician work life and professional well-being, mitigating burnout. This in turn can improve access to quality care for patients.

“But in order to decide what to automate and how to go about it, we need to first understand whether historically and currently marginalized communities have equitable primary care experiences, and then design our systems accordingly.”

Murray says that she is proud to be a recipient of the IBET Momentum Fellowship.

“I am appreciative that the University recognizes the historic and systemic barriers faced by Black and Indigenous students,” she says.

“This fellowship affords me the opportunity to deepen my scholarship through mentorship opportunities with industry leaders and professors whose work focuses on artificial intelligence and human factors engineering.”

In addition to her scholarly work, Murray says that helping to nurture the next generation will be a key focus of hers over the next few years.

“Working within the community is part of my lived experience, and I expect to continue with this endeavor through mentorship with young students who will be able to see this as a pathway for the future,” she says.

“I’m hopeful that through this fellowship and my doctoral studies, I can encourage others who look like me to pursue opportunities within the intersection of STEM and academia.”

– This story was originally published on the University of Toronto’s Faculty of Applied Science and Engineering News Site on September 13, 2023 by Tyler Irving.

The rise of generative artificial intelligence tools like ChatGPT is prompting many educators to reimagine the role of technology in the classroom.

 

At the University of Toronto, Susan McCahan, vice-provost, academic programs and vice-provost, innovations in undergraduate education, has been on the front lines of the response to this fast-evolving technology.

McCahan, a professor of mechanical and industrial engineering in the Faculty of Applied Science & Engineering, says the proliferation of generative AI tools presents both opportunities and challenges for higher education.

Her office is supporting projects on the applications of generative AI in teaching and learning and providing guidance to help instructors navigate this emerging technology.

She recently spoke to U of T News about the lessons that have been learned about the academic implications of generative AI and the big questions that still remain.

---

What are some of the ways generative AI is impacting teaching and learning?

Large language models have significant implications for how we teach coding and writing because it will change the way people code and write – particularly when it comes to routine tasks.

A lot of the writing I do in a day isn’t deeply intellectual. It’s the kind of writing that LLMs do pretty well. However, it’s probably not going to write as well as me when I’m writing an academic paper, because of my knowledge and understanding of the field and my own unique perspective.

Right now, the technology is pretty good at writing at the level of a first-year or second-year student, but it’s not up to what would be expected of a student in their third or fourth year.

The biggest challenge is making sure students are still progressing to that third- or fourth-year level if they are taking shortcuts in their first years of university – or even high school or middle school.

People have compared this to a calculator, but I don’t think that’s the right analogy because a calculator is a very domain-specific tool and generative AI has much broader applications.

There was an existential crisis in math education in the 1980s when calculators capable of symbolic manipulation came along. Educators questioned if we should teach our students how to do differentials and integrals if these programs can solve those complex equations. Yet, we came through that, and we still teach students how to add and subtract, multiply and divide, do differentials and integrals. We also teach students how to use these symbolic manipulation programs in ways that allow them to go deeper than if they were to do it all by hand.

I think we will come to a point where people recognize when it is useful to use AI to help and when is it not going to be very helpful. Hopefully, we will arrive in a place where it allows people to advance through the basics faster and move on to more complex writing and coding.

Does U of T consider the use of generative AI tools to be cheating?

We expect students to complete individual assignments on their own. If an instructor decides to explicitly restrict the use of generative AI tools, then their use would be considered an “unauthorized aid” under the Code of Behaviour on Academic Matters. This is considered an academic offence and will be treated as such.

Some might ask why we don’t classify this as plagiarism. One of the biggest misconceptions that people have is that LLMs take what’s on the internet, mash up the text and ideas and repackage it as a compilation. However, that’s not how the technology works.

Tools like ChatGPT are trained on large amounts of online materials to identify patterns of speech and make predictions about words most likely to go together. If I say, “one, two, three,” it knows that “four” probably comes next. It knows “four” is a noun, but it doesn’t associate the concept with a square or the horsemen of the apocalypse.

When you enter a prompt into ChatGPT, it’s not combing through information to produce sentences or paragraphs or ideas – it’s making word-by-word predictions that imitate patterns of speech around a subject. That’s why we don’t treat the use of these tools as plagiarism; we treat it as an unauthorized aid.

What resources are available to help instructors adapt to this emerging technology? Are there any best practices they should follow?

We’ve put together an FAQ addressing some of the considerations around generative AI, while providing instructors with resources to help them communicate what technology is – or isn’t – allowed in their courses.

I think we’re in a moment when it’s really important for faculty to be really clear on their syllabi about whether they explicitly allow it or explicitly don’t. If it is permitted, it should be clear how AI tools can be used, for what assignments and to what degree, and if students must explain, document or cite what tools they use and how.

This is new, and both faculty and students are not altogether clear if this will be the next Wikipedia of the world – where everyone uses it, but no one talks about it anymore. Or if it should never be used because it’s just unreliable.

What are some other considerations around the use of generative AI in an academic context?

LLMs often get things wrong – and very confidently wrong. For example, back in January, I asked ChatGPT for my biography. It told me that I had worked at the University of British Columbia and I was a leading researcher in biomedical engineering – things that seem believable, but are factually untrue. The technology has improved since then, but LLMs still get things wrong in ways that are not immediately apparent or obvious. These are called “hallucinations,” and they can be so subtle that they’re hard to detect unless you really know the subject.

Ultimately, the student is responsible for the material they submit, and if they’re submitting material that is factually wrong, they’re responsible for it. You can’t blame the chatbot, the same way the chatbot can’t take credit. It’s not like a team project where you’re working with another student, and you can say, ‘It wasn’t me, it was my partner.’ If your partner is AI, you are responsible for all of the work you submit whether or not there are parts that were co-created with AI.

– This story was originally published on the University of Toronto’s U of T News on September 13, 2023 by Adina Bresge.

Starting in September 2023, U of T Engineering’s new certificate in Justice, Equity, Diversity and Inclusion in Engineering will enable undergraduate students to strengthen their knowledge of concepts such as ethics, equity, justice and the interactions between technology and society.

“Social justice continues to be of great concern around the world: how do we ensure that we build societies that are as fair as we can make them?” says Professor Dionne Aleman, Associate Dean of Cross-Disciplinary Programs at U of T Engineering.

“Some people might think that engineering, due to its technical nature, is somehow immune to issues of justice, equity, diversity and inclusion, but certainly it is not. Engineers, like everyone, are impacted by these issues, and they also have a direct impact on them through their work.”

To show how social issues are inextricably linked to the engineering ones, Aleman gives the example of siting a new water treatment plant.

“An engineer designing such a facility would consider the technical, economic and environmental factors. Social factors are very much part of that as well: how do your design decisions impact the communities who live near the site, versus those who are served by it? Are you considering the needs and concerns of those communities in fair balance?”

To earn the new certificate, students will enrol in three courses from an approved list. The courses are divided into three broad categories: equity and justice; technology and society; and ethics and broader considerations.

The courses are cross-disciplinary and are taught by professors from across the University of Toronto. Some are offered by divisions within the Faculty of Arts & Science, such as the Institute for the History & Philosophy of Science & Technology and the Women & Gender Studies Institute.

Other courses are offered by U of T Engineering’s Institute for Studies in Transdisciplinary Engineering Education & Practice, for example: TEP 324 Engineering and Social Justice or CME 259 Technology in Society and the Biosphere I.

“As the engineering student body becomes more diverse, a growing number of our incoming students want to be agents of social change, both for their own communities and for others,” says Mikhail Burke (MSE 1T2, BME PhD 1T8).

While serving as Associate Director, Access and Inclusive Pedagogy at U of T Engineering, Burke was one of the key architects of the new certificate. In January 2023, he became the Manager of Equity, Diversity and Inclusion at U of T’s Division of Student Life.

“Engineering has always been a sociotechnical process — it both exerts social influence and is also shaped by a variety of social factors. The certificate leans into this notion, providing students with an avenue to broach these intersectional topics in the classroom, where learning and discourse can be collaborative in nature. This is something our students value.”

“The Canadian engineering profession’s North Star is to protect society’s wellbeing — this is the value proposition and why engineering is a regulated profession,” says Marisa Sterling, P.Eng., Assistant Dean & Director, Diversity, Inclusion and Professionalism at U of T Engineering. Sterling is also a past president of Professional Engineers Ontario.

“Engineering work done poorly can harm the public, the environment and society’s welfare. And while engineering problems may be viewed as technical in nature, they all will have an ultimate human consequence. We discuss justice in engineering as there are injustices in society. To increase knowledge of these, their history and root causes, helps engineering students better define the problems they are trying to solve and therefore produces engineering solutions that positively consider more people.”

“This certificate encourages students to mirror a practice that all licensed professionals adhere to, which is undertaking continuing competency and seeking out continuous practice evaluation and knowledge in fulfilling their duty to public protection.”