Professor Azadeh Kushki and her team have designed a prototype software application for the optical head-mounted display Google Glass as a social-skills coach to help children with autism spectrum disorder (ASD).
Their new study, published in the open-access journal Frontiers in Robotics and AI, finds that the wearable technology can recognize conversational prompts and provide the user with suitable responses in return. Moreover, children find it easy to operate and enjoy using it.
ASD is a life-long condition that affects one in 68 children. A defining feature of ASD is difficulties with social communication, which can include initiating and maintaining conversations with others.
“We developed software for a wearable system that helps coach children with autism spectrum disorder in everyday social interactions,” says Kushki, an assistant professor in the Institute of Biomaterials and Biomedical Engineering (IBBME) at the University of Toronto and the Mary & James W. Davie Scientist at Holland Bloorview Kids Rehabilitation Hospital. “In this study, we show that children are able to use this new technology and they enjoy interacting with it.”
Children with autism spectrum disorder are often drawn to technological devices and find them highly motivating tools for delivering interventions designed to help them. The problem with existing technology, however, is that using human-to-computer interaction to teach social skills can have the opposite effect to its goal, in that the user becomes socially isolated.
“The interesting thing about our new technology is that we are not trying to replace human-to-human interactions; instead, we use this app to coach children who are communicating with people in real-world situations,” explains Kushki. “Children can practice their skills outside of their normal therapy sessions and it can provide them with increased independence in everyday interactions.”
Kushki and her colleagues developed the app, named Holli, to be used with wearable technology such as Google Glass — a head-mounted display in the shape of eyeglasses. It listens to conversations and prompts the user with an appropriate reply.
For example, if the user is greeted by a person who says ‘Welcome’, Holli will provide various responses to choose from, such as ‘Hey’, ‘Hello’ or ‘Afternoon’. When Holli recognizes the user’s response, the prompts disappear and Holli waits for the next exchange in conversation.
To assess the usability of the prototype software, the researchers asked 15 children with ASD to be guided by Holli when interacting socially. They saw that Holli could complete most conversations without error, and that children could follow the prompts to carry on a social interaction. In fact, Holli was often able to understand what the user was saying before/he she finished saying it, which helped the conversation to flow naturally. As well as demonstrating its feasibility, the children also said how much they liked using it; they enjoyed the prompts and found it easy to use.
“This study shows the potential of technology-based intervention to help children with ASD,” says Kushki. “These systems can be used in everyday settings, such as home and school, to reinforce techniques learned in therapeutic settings.”
It is hoped that further developments will allow customization for individual users, such as changing prompt location, size and medium, to cater to each child’s unique preference and ability. In addition, more work is needed to improve Holli’s ability to deal with speech differences that can affect those with autism spectrum disorder.
“Technology has tremendous potential to change the way we think about delivering services to those with ASD. It can augment existing face-to-face interventions to make services accessible in a timely and cost-effective way and help increase treatment effectiveness,” concludes Kushki.
—This story was originally published by Frontiers and is reproduced with permission.
U of T Engineering’s Human-Powered Vehicle Design Team (HPVDT) has won the 2017 World Human Powered Speed Challenge. Their recumbent bicycle, named Eta Prime, was clocked at an impressive 127.6 kilometres per hour, the fastest in this year’s competition at Battle Mountain, NV.
“It is a great success for the team,” said Calvin Moes (MSE PhD candidate), Eta Prime’s pilot and captain of the Human Powered Vehicle Design Team. “We have never won this event before, and even though we did not a set a new world record, it is still an excellent accomplishment. I am excited to continue with the project and compete again next year.”
Eta Prime’s design is modelled on Eta, the vehicle that currently holds the record for the world’s fastest bicycle at 144.17 km/h. Eta was built by AeroVelo, a company founded by U of T Engineering alumni Todd Reichert (EngSci 0T5, UTIAS PhD 1T1) and Cameron Robertson (EngSci 0T8, UTIAS MASc 0T9).
Eta, which did not race at this year’s competition, was the result of a long-standing collaboration between AeroVelo and HPVDT, so was only natural that the team build on this expertise to create their next vehicle: they used Eta’s molds to cast Eta Prime’s carbon-fibre shell.
“Within a millimetre or two, it has exactly the same shape,” said Moes. “As far as we know, it is the best shape for a single-person speedbike in the world.”
Still, there were aspects of Eta that Moes and his teammates felt could be improved. They overhauled the carbon-fibre frame that holds up the vehicle and redesigned both the rear wheel and braking system. Through a combination of innovations, they were able to create a bike that was 20 per cent lighter than Eta, while maintaining its internal strength.

But as with any speedbike, much depends on the engine — that is, the rider. “You can build the best bike in the world, but if you can’t produce the energy to get it up to speed, you’re not going to get there,” said Moes.
To provide this power, many of the approximately one dozen teams in the World Human Powered Speed Challenge hire semi-professional cyclists. HPVDT does not, though Moes did undergo extensive training. Over the last eight months, he said he’s managed to reduce the gap in power output between himself and Reichert, Eta’s rider, by about half.
“The fact that we reach the same speeds as the other teams, and in some cases, even surpass them, on significantly less power than their riders can produce is remarkable,” said Moes. “It speaks to the amount of engineering that went into this design.”
Professor Jun Nogami (MSE) is the team’s faculty advisor, and travelled with them to Battle Mountain to act as a timekeeper.
“It is incredibly valuable for students to participate in design teams, and then to appear at international competitions,” said Nogami. “I’m proud of the way the team pushed through adversity to finish with the overall title. Congratulations to Calvin, who is the fastest person in the world for this year!”
Though the competition was intense, Moes said the atmosphere at Battle Mountain is friendly.
“That’s actually one of the best parts of the event,” he said. “We interface with the local community, and display our bikes to students in local schools. Teams will go and talk to each other, and inspect what new design features each bike has. It’s wonderful to be part of this elite group of racers, and learn from experiences that we wouldn’t get anywhere else.”
From pulp and paper to biofuels, many industries are based on turning renewable biomass — trees, plants, food waste — into energy and green materials.
But even though the primary feedstock of these industries is organic matter, inorganic contaminants such as salts and metals are commonly found in the fields and forests where these feedstocks grow. The presence of these contaminants in the process is not just a nuisance; they can damage process equipment, reduce overall efficiency and create environmental headaches for the surrounding community.
Professor Nikolai DeMartini deals with these problems, offering techniques and methods that industrial processors can use to safely remove these contaminants. Before joining U of T Engineering this year, DeMartini spent nine years at Åbo Akademi University in Finland. Writer Tyler Irving sat down with DeMartini to learn more.
Can you explain the focus of your research/teaching?
I work on the process chemistry of inorganics in the industrial processing of biomass and waste. This work is directly applicable to the pulp and paper industry as well as companies involved in converting biomass and waste into liquid fuels and electricity.
Inorganic chemicals — including salts and metals — are often mixed in with biological material. Their presence and behavior impacts energy efficiency, corrosion and emissions. A major goal of my research is to make changes to industrial processes that can effectively deal with these inorganic components and lead to improvements both for the companies and surrounding communities.
I am fortunate to have three new students working on topics related to the water chemistry of the chemical recovery cycle in pulp mills. Two are working on crystallization of salts and the resulting effects on heat transfer scaling within the plant. The third is studying the solubility of metals in pulp mill waters to better help industry in their removal strategies.
I plan to expand into some topics related to thermal conversion as I take on additional students next spring.
Why did you choose U of T Engineering?
The most significant draw for me is the quality of the people I have met in the Department of Chemical Engineering & Applied Chemistry, both faculty and students. Not only is the scientific level extremely high, but the collegiality is recognized as an important element in the department’s success.
The second factor was the close ties to industry as I enjoy working in the interface between companies and academia.
What do you hope to accomplish, and what are you most looking forward to in your new position?
Within the realm of student development, I hope to make the application of chemical engineering more tangible. I know that for myself, it wasn’t until my internships in industry that I started to see how the subjects I was working on in the classroom could be applied. Beyond that, I hope to have a positive influence industry and to see my students in leadership roles in the future.
Last summer, Hai-Ling Margaret Cheng and her team of biomedical engineering researchers developed a new way to monitor the effectiveness of stem cell therapy for heart failure patients. Now, she’s teaching others the techniques, and how they can be used to create new medical diagnostic approaches.
“Magnetic resonance imaging (MRI) is a powerful tool that can offer a wealth of information about the human body,” said Cheng, a MRI expert and a professor of biomedical and electrical engineering at the University of Toronto. “It has the capability to provide a lot more than a pretty picture. Understanding its broad range of capabilities and some of the latest imaging techniques can help medical professionals, engineers and scientists come up with new solutions to address pressing human health challenges.”
Cheng’s new course, BME 1466—Advanced Topics in Magnetic Resonance Imaging, will be offered to graduate students at U of T starting in January 2018. Some of the topics she’ll cover already have a major impact on how scientists and engineers approach several challenging diseases.
“For example, we’re going to look at how to capture precise and useful images of blockage in the heart’s smallest arteries, and how certain drugs might pass through the blood-brain barrier for cancer treatment,” said Cheng. “We’re also going to study some of the current obstacles to diagnosis and treatment in relation to MRI techniques.”
For some current graduate students, this course has the potential to greatly accelerate their research.
“This course will give me the tools to understand the bigger picture behind my research where I focus a lot on MRI acquisition techniques for diagnosis purposes,” said Eric Zakher, an electrical engineering master’s student. “MRI is one of the most complex imaging modalities and this course is a great opportunity to get exposure to a field that is revolutionizing the diagnosis and treatments of many medical conditions.”
“I was taught computed tomography and nuclear medicine techniques during my clinical training so being able to learn about MRI has increased my attraction to this field,” said Tameshwar Ganesh, a pharmaceutical sciences PhD student and a registered nuclear medicine technologist. “This course will help me with my doctoral thesis where I will use MRI to evaluate vascular health.”
The availability of BME 1466 also adds to the Institute of Biomaterials & Biomedical Engineering’s (IBBME) course repertoire behind its Nanotechnology, Molecular Imaging & Systems Biology research theme.
“There are really no comparable courses offered in this area,” said Professor Christopher Yip, IBBME’s former director and U of T’s associate vice-president of international partnerships.
“What is really compelling will be how she will be bringing current, leading-edge research in MRI into her lectures to engage students — helping showcase how this tool can provide insights into molecular and cellular dynamics, and physiological state. In essence — truly functional imaging.”
They are invisible to the naked eye, able to withstand extreme conditions and capable of breathing rocks. They are the microbes that thrive in tailings ponds at mining sites around the world, and a team of Canadian researchers believes they are the key to transforming waste material into something much more valuable.
“There are bugs that thrive on metabolizing sulfur, others on metabolizing iron,” says Professor Vladimiros Papangelakis (ChemE). “If we can control such biochemical reactions, we could both remediate the waste and recover valuable metals that could pay for the cost of processing.”
Papangelakis, along with Professor Elizabeth Edwards (ChemE) is leading the Elements of Bio-mining project, a multidisciplinary collaboration between U of T Engineering, Laurentian University, and the University of British Columbia (UBC), as well as a number of technology, engineering and mining companies, including Glencore, Vale, Teck, Barrick and Hatch.
For a full list of team members and partners, visit the Elements of Bio-mining website
Together, the team is developing ways to process a number of different types of material left over from mining activities across Canada, from nickel mines in Sudbury, Ont. to coal mines in British Columbia. They aim to understand how native microorganisms at these sites convert chemicals one form to another, and how they might encourage certain beneficial reactions while discouraging others.

For example, nickel refining produces tailings, which are rich iron sulfide. When exposed to the oxygen in the atmosphere, chemical reactions begin to convert the sulfides into sulphuric acid. This process — known as Acid Mine Drainage (AMD) — is catalyzed by microorganisms that live in the rainwater or melting snow that washes over the tailings.
The sulphuric acid can dissolve any nickel that remains in the tailings, as well as other metals such as copper and zinc and even toxic elements like arsenic, selenium, cadmium, mercury. Because of its toxic and acidic nature, tailings water cannot be discharged into the environment unless it is collected and treated. Currently, these tailings sit in enormous ponds around the mine sites — the water covers the tailings, acting as an oxygen barrier and slowing the AMD process.
Papangelakis and his collaborators hope to treat these tailings using bioreactors, vessels that enable them to control the temperature, pH, dissolved oxygen levels and other culture conditions. One idea is to encourage the growth of organisms that would convert the sulfide not into sulfuric acid, but into elemental sulfur, which may have some value if recovered. At the same time, the metal-rich wastewater could be captured and refined to recover metals, potentially providing a revenue source to offset the cost of treatment.
Other members of the team are looking at the waste rock that was separated before the refining process. Here sulfur is less of a problem, but there are still potentially valuable metals that could be recovered. Professor Nadia Mykytczuk of Laurentian University is studying ways to encourage bacteria to selectively dissolve these metals from heaps of rock, a process known as in-situ bio-leaching.
“There is a large diversity of organisms out there that we are only starting to understand,” says Mykytczuk. “Some of them like oxygen, but others thrive under anaerobic, or oxygen-free conditions. We’re looking at the whole range of possibilities, and once we find something promising, we can decide how to address specific types of waste.”
A third branch of the team is focusing on waste from coal mines, which is often high in selenium. Though a necessary nutrient in small amounts, too much selenium can be toxic to many forms of life; for example, it can interfere with the development of fish embryos, reducing the number of viable adults in the next generation.
“There are some microorganisms that can actually use selenate, the dissolved form of selenium, for energy,” says Professor Sue Baldwin of UBC, another one of the project partners. “They take the selenate and turn it into elemental selenium, which precipitates out as nanoparticles attached to the organism’s cells. In this form, it’s no longer dissolved and you can just filter it out of the water.”
Baldwin points out that selenium is just one of many pollutants that exist in waste from coal mining. And as with nickel mining, there may also be valuable metals or other materials that could be recovered through biochemical transformations.
Papangelakis says that there may be up to $7 billion worth of nickel alone locked in the tailings from Sudbury’s mines. “The question is, can this value be recovered in a way that makes the treatment and remediation process economically viable?” he says.
In addition to the universities and the industrial partners, the project has attracted support from a number of research funding agencies, including the Natural Sciences and Engineering Research Council (NSERC), Genome British Columbia and Australia’s Commonwealth Scientific and Industrial Research Organisation (CSIRO). Most recently, the project received $4 million from the Ontario Research Fund.
“It’s a very challenging problem that needs to be solved,” says Papangelakis. “But we have assembled a very good knowledge base, with experienced people in mining, chemistry, biochemistry and process engineering. There will be cross-fertilization and new ideas, which will create a springboard to understand new science and launch initiatives we haven’t thought of yet. To me, this is the most exciting part.”
Startups founded by engineering students are poised to address challenges from sustainability to surgery. Twelve companies pitched their vision to a room of judges, investors and faculty members at the fifth annual Hatchery Demo Day, held September 6 at U of T Engineering.
“Five years after we founded the Hatchery, the spirit of entrepreneurship continues to be the engine of all that we do,” said Joseph Orozco, executive director of The Entrepreneurship Hatchery, in his opening remarks. “We nurture the mindset for entrepreneurial thinking, and we have seeded the ideas that I believe will transform our society. Together, we are building the Canada of tomorrow.”
Demo Day is the culmination of The Hatchery Nest program, a four-month accelerator which pairs student teams with experienced mentors — including executives, lawyers, medical professionals and engineers — to develop their businesses. They receive detailed feedback on their business plans, explore their proposed market, learn about patents and marketing and build prototypes using 3D printers and other fabrication resources. A second Hatchery program, Hatchery Launch Lab, focuses on supporting startups built on graduate-level research in the Faculty.
Of the dozen teams that presented at Demo Day 2017, four took home a share of $42,500 in seed funding, including one $20,000 grand prize and two $10,000 runner-up prizes donated by alumnus Anthony Lacavera (CompE 9T7), founder and chairman of Globalive Holdings and former CEO of WIND Mobile. An additional $2,500 Orozco prize is provided through funds raised by the students themselves.
This year’s winners are:
$20,000 Lacavera Prize: Genecis — From food waste to renewable bioplastics

Restaurants throw away a lot of food, and that costs money. In fact, large-chain, full-service restaurants can pay tens of thousands of dollars each year just to dispose of their food waste in landfills. Genecis has a solution that is both greener and less costly.
“We turn restaurant food waste into bioplastics,” said Luna Yu, Founder and CEO of Genecis. “We make money from both the collection fees we charge to the restaurants, and from the bioplastics and compost we produce from them.”
The ‘secret sauce’ of Genecis is two different cultures of microorganisms. One breaks down leftover food into energy; the other uses this energy to grow and accumulate substances called polyhydroxyalkanoates, or PHAs. PHAs are a type of biodegradable plastic, and can be made into products such as thin-film packaging or bottles.
Because they are recovering value from food waste, Genecis believes they will be able to charge lower collection fees than typical waste disposal companies, while enabling restaurant owners to feel good about where their waste goes. The company has done extensive testing in the lab, and the funding they earned at Hatchery Demo Day will enable them to build a 1,000-litre pilot bioreactor to test the process at a larger scale.
“The Hatchery really helped us hone our business models and point us in the right direction in terms of what we should focus on,” said Yu. “I honestly don’t think we would be in the position we are today without them.”
$10,000 Lacavera Prize: Xpan — Expanding keyhole surgery

Laparoscopic surgery — sometimes known as ‘keyhole surgery’ — is an attractive medical option for patients: smaller incisions can reduce both pain and healing time. In this type of surgery, instruments and cameras are inserted into the body through a device known as a trocar. But the members of Team Xpan believe that the trocar can be improved.
“Sometimes, surgeons discover that they need a bigger instrument partway through the surgery,” said Zaid Atto (EngSci 1T6 + PEY), Xpan’s founder. “They have to take the small instrument out, take the small trocar out, insert a bigger trocar, and finally insert the bigger instrument.” The process is inefficient, and exposes the patient to additional risk.
A year ago, surgeon Priscilla Chiu of the Hospital for Sick Children brought the problem to Professor Chris Bouwmeester (IBBME) and the students in his fourth-year class, BME 489 Biomedical Systems Engineering Design. Atto and his teammates developed a trocar that expands to a larger size. Their prototype has won awards both within U of T and at the American Society for Artificial Internal Organs 63rd Annual Conference.
Team Xpan — consisting of Atto, Seray Cicek (EngSci 1T6 + PEY) and Chevis Dilbert (MechE 1T6 + PEY) — continued to develop multiple iterations after the capstone project ended and has also filed a provisional patent on the device. They plan to use their prize to continue to refine the design of their prototype.
“The Hatchery was a great help with the patent application process, and also partnered us with mentors who were experienced and showed us how to get there.” said Cicek. “Tonight is further validation that we really have a solid plan,” added Atto.
$10,000 Lacavera Prize: Tejo — A better way to buy makeup

The North American makeup industry is worth more than $10 billion, but it does a poor job of serving people with darker skin tones. Not only is darker makeup more expensive, but many traditional retailers don’t even carry the brands that provide these shades. Furthermore, buying online can be a gamble, as it’s difficult to choose the right colour without trying the product.
“You’re supposed to pick from swatches, but different screens render colours differently,” said Rachel Baker (IndE 1T7 +PEY), co-founder of Tejo. “What looks great on your smartphone might not look great in real life.”
Baker and her business partner, fashion management student Lakshmy Subramanian, believe that artificial intelligence and machine learning offer a way forward. Tejo users simply take a selfie, which is then fed into software designed by the pair. Using open-source computer vision and a proprietary algorithm that accounts for ambient lighting conditions, Tejo determines a user’s precise skin tone and recommends an appropriate brand. If the user chooses to buy, Tejo collects a 5 to 10 per cent commission on the sale.
“Before we joined The Hatchery, we were really struggling to get people who don’t wear makeup to understand what our business is,” said Baker. “They provided us with excellent mentors and advisors, and really helped us to get a really clear vision of what we want our company to be.”
The pair plan to use the prize money to file a patent on their software and expand their e-commerce platform, which is already accepting early sign-ups online. Once they have penetrated their target market, they plan to expand their “recommendation engine” approach to other areas, including ethically sourced beauty products and men’s grooming.
$2,500 Orozco Prize — enginehire: An engineering career matchmaker

enginehire leverages data to connect young engineers with employers looking for talent. Young engineers create a profile that puts equal emphasis on their experience and their passions, whether they’re interested in structural design, green infrastructure, acoustics or machine learning. Proprietary algorithms then slice through this rich database, delivering companies five to 10 ideal candidates for a given position.
“Traditional job posting sites deliver too many irrelevant candidates, because anyone who sees a job that might be remotely applicable to them applies,” said Aakash Goel, (EngSci 1T6 + PEY), enginehire’s founder. “On the other hand, recruitment agencies are very expensive, and many don’t bother with entry-level jobs. We can deliver that same value for a fraction of the cost.”
The ‘sweet spot’ for enginehire is mid-size engineering companies, who are constantly hiring, yet at the same time do not have large HR resources. “There are thousands of mid-sized engineering companies in the GTA, but most of them are not household names,” said Goel. “We are giving young engineers exposure to companies that may be perfect for them, but that they may never have heard of otherwise.”
enginehire has built a database of thousands of young engineers and has already made several matches. Goel’s near-term goal is to push rapid database growth and to continue building relationships with an ever-increasing array of companies across Ontario, Canada and eventually, the U.S.
This is Goel’s second time in the Hatchery; in his first year, he was part of Team Shour, which developed a smart showerhead that helps users save time, money and the environment by optimizing their water use. The team has applied for a patent on their invention.
“Tonight was a really great opportunity to really refine our message, and to pitch in front of some amazing people,” said Goel. “Tomorrow, we go back to work: we will keep building, keep growing and keep adding more users and customers. Our objective is to make enginehire the place to hire a young engineer.”