Making Deep Neural Networks Reliable
The wide-ranging possibilities of machine learning are transforming many industries, shaping the development of many essential applications, from self-driving cars, to healthcare, to fraud detection. But what happens when machine learning breaks down?
Like any software, deep learning applications depend on the hardware they run on – hardware that can break down and cause applications to make mistakes. Two ECE graduate students, Zitao Chen and Ali Asgari, are working to prevent these accidents. Their new software solution, Ranger, checks for and corrects faulty values in deep learning systems.
“Basically,” says Zitao Chen, the lead investigator on this project, “The problem we are looking at here is how to make machine learning models be even more reliable.”
Most computer systems are composed of software and hardware working together. However, hardware can be subject to faults such as cosmic rays, stress on the system, age, faulty designs, purposeful attacks, and so-on; all can cause a system to malfunction. When the hardware isn’t working properly, the software will be affected, and computation errors are the result. Usually, when a fault arises in a software’s computation, someone can go in and recompute it manually. But this can be difficult and laborious, and is hard to complete under time constraints, like when a self-driving car is operating.
What Zitao and Ali’s tool, called Ranger, does is anticipate and correct errors in the hardware. It performs range checks (hence the name), checking that the values of the software fall within an accepted statistical range. If there is a value that falls outside this range, it brings this erroneous value back to a safe region.
In the above example, Ranger is correcting an autonomous vehicle’s faulty computer vision. On the far left, the car recognizes the road correctly. In the center, a fault has occurred, affecting the car’s ability to infer which way to go- and directing it into traffic. In the right image, Ranger has corrected this error and the car can proceed safely.
Zitao and co-researcher Ali Asgari began developing this research at the Dependable Systems Lab, led by Karthik Pattabiraiman. “We had been working on another paper, trying to understand why the machine learning model would fail from a hardware fault,” says Zitao. “Long story short….. We came up with a nice way to characterize the patterns of when the model fails and when the model would not fail.” By identifying these patterns, they were able to develop a software that anticipated and corrected errors, bringing values back to a tolerable region.
“The very cool thing about this is that this tool is application-oblivious; so it doesn’t matter if you’re using a self-driving car or you’re using an autonomous robot- you can use this application.” says Ali.
This tool will soon be used in industry. Intel has added this software to OpenVINO – a toolkit that optimizes and improves the reliability of computer vision hardware and software. Ranger will soon be used as part of this toolkit to help develop all different kinds of deep learning technology.
“We can easily incorporate it without a lot of programming interventions.” says Zitao. “You don’t really have to make a lot of changes.” As well, “it’s really low cost…. And super effective. I think this is what makes this technique so appealing for them.”
“Despite its simplicity, it provides a very high level of reliability.” adds Ali.
This was the first project Zitao worked on after joining Karthik’s lab. Says Zitao, “I think to me the most exciting part [of this research] was understanding the problem we’re dealing with… I was playing with tools to see how to model, see how it would fail, and then, through this process, by looking at all these crazy details…gradually this emerged.”
“Once we’d identified what this problem was, we moved on to see how we can make things better based on our understanding.” he says.
“I found this research project interesting because I found it more close to the application.” Ali explains. “This technique is used in the industry and has impact. And the specific area we’re focusing on, artificial intelligence and machine learning, is being used in many applications and is ever-growing in its popularity.”
“I can see an important shift happening- formerly, maybe [developers] didn’t care much about reliability of AI applications.” says Ali. However, he sees this tool as part of a change in the industry. “I think this is a first step that could also lead to looking at reliability [in software] from many different perspectives.”
Explore the research behind Ranger here and here
Learn more about OpenVINO
Connect with Zitao and Ali
Now hiring tenure-track positions!
ECE is hiring for Associate Professor or Professor (Tenure), Canada Excellence Research Chair in Neuroprosthetics!
Sudip Shekhar awarded Killam Teaching Prize
Dr. Sudip Shekhar, Associate Professor at Electrical and Computer Engineering, has been awarded the Killam Teaching Prize.
This award recognizes excellence in teaching, and is awarded through nomination by students, colleagues and alumni. Recipients are noted for their exceptional leadership, mentorship and engagement and for the positive impact they have made on their students’ lives. “[It’s important to me] to influence students in a positive way.” Dr. Shekhar says, “[and] to provide the big picture as well as explain concepts clearly.”
Dr. Shekhar joined the ECE department in 2013. He is a recipient of the IEEE Solid-State Circuits Society (SSCS) Predoctoral Fellowship, the Intel Foundation Ph.D. Fellowship, the Analog Devices Outstanding Student Designer Award, the Young Alumni Achiever Award by IIT Kharagpur, the IEEE Transactions on Circuit and Systems Darlington Best Paper Award and a co-recipient of IEEE Radio-Frequency IC Symposium Best Student Paper Award. He serves on the technical program committee of IEEE International Solid-State Circuits Conference (ISSCC), Custom Integrated Circuits Conference (CICC) and Optical Interconnects (OI) Conference. His research interests include circuits for high-speed interfaces, silicon photonics, radio-frequency transceivers and sensor interfaces.
Of the award, Dr. Shekhar says, “I am happy and humbled [to receive this prize]. It will serve as an encouragement and a reminder to keep doing better as a teacher.”
Read more about the UBC Killam awards
Connect with Dr. Shekhar
Engineers at UBC get under the skin of ionic skin
Original article from UBC Applied Science
In the quest to build smart skin that mimics the sensing capabilities of natural skin, ionic skins have shown significant advantages. They’re made of flexible, biocompatible hydrogels that use ions to carry an electrical charge. In contrast to smart skins made of plastics and metals, the hydrogels have the softness of natural skin. This offers a more natural feel to the prosthetic arm or robot hand they are mounted on, and makes them comfortable to wear.
These hydrogels can generate voltages when touched, but scientists did not clearly understand how — until a team of researchers at UBC devised a unique experiment, published today.
“How hydrogel sensors work is they produce voltages and currents in reaction to stimuli, such as pressure or touch – what we are calling a piezoionic effect. But we didn’t know exactly how these voltages are produced,” said the study’s lead author Yuta Dobashi, who started the work as part of his master’s in biomedical engineering at UBC.
Working under the supervision of ECE researcher Dr. John Madden, Dobashi devised hydrogel sensors containing salts with positive and negative ions of different sizes. He and collaborators in UBC’s physics and chemistry departments applied magnetic fields to track precisely how the ions moved when pressure was applied to the sensor.
“When pressure is applied to the gel, that pressure spreads out the ions in the liquid at different speeds, creating an electrical signal. Positive ions, which tend to be smaller, move faster than larger, negative ions. This results in an uneven ion distribution which creates an electric field, which is what makes a piezoionic sensor work.”
The researchers say this new knowledge confirms that hydrogels work in a similar way to how humans detect pressure, which is also through moving ions in response to pressure, inspiring potential new applications for ionic skins.
“The obvious application is creating sensors that interact directly with cells and the nervous system, since the voltages, currents and response times are like those across cell membranes,” says Dr. Madden, an electrical and computer engineering professor in UBC’s faculty of applied science. “When we connect our sensor to a nerve, it produces a signal in the nerve. The nerve, in turn, activates muscle contraction.”
“You can imagine a prosthetic arm covered in an ionic skin. The skin senses an object through touch or pressure, conveys that information through the nerves to the brain, and the brain then activates the motors required to lift or hold the object. With further development of the sensor skin and interfaces with nerves, this bionic interface is conceivable.”
Another application is a soft hydrogel sensor worn on the skin that can monitor a patient’s vital signs while being totally unobtrusive and generating its own power.
Dobashi, who’s currently completing his PhD work at the University of Toronto, is keen to continue working on ionic technologies after he graduates.
“We can imagine a future where jelly-like ‘iontronics’ are used for body implants. Artificial joints can be implanted, without fear of rejection inside the human body. Ionic devices can be used as part of artificial knee cartilage, adding a smart sensing element. A piezoionic gel implant might release drugs based on how much pressure it senses, for example.”
Dr. Madden added that the market for smart skins is estimated at $4.5 billion in 2019 and it continues to grow. “Smart skins can be integrated into clothing or placed directly on the skin, and ionic skins are one of the technologies that can further that growth.”
The research includes contributions from UBC chemistry PhD graduate Yael Petel and Carl Michal, UBC professor of physics, who used the interaction between strong magnetic fields and the nuclear spins of ions to track ion movements within the hydrogels. Cédric Plesse, Giao Nguyen and Frédéric Vidal at CY Cergy Paris University in France helped develop a new theory on how the charge and voltage are generated in the hydrogels.
Learn more about Dr. John Madden
Read the article from UBC News
Job-Hunting with Yuan Gao, ECE Alumnus and Google Software Engineer
Finding a job after graduation can be an intimidating task. If you’re an ECE student gearing up to enter the industry, the challenges of finding a good position are definitely something on your mind.
ECE alumni Yuan Gao knows this very well. After completing his MEng at ECE in 2021, he began his job search, eventually applying for and successfully landing a position at Google as a software engineer. As a now-veteran of the job application process, we spoke to Yuan to learn about his takeaways from this experience, and his advice and recommendations for other students entering the industry.
Opportunities at ECE and UBC
“UBC and ECE provide various resources and opportunities to help with securing a job. I will share the ones that I attended.
1. Google @ UBC: Building Your Technical Career: ECE department hosted a workshop with two Googlers, Lina and Kevin. They discussed resumes, the technical interview process, and Q&A sessions, and held 1-1 office hours. This event helped give me a better understanding of the hiring and interview process. They also gave me constructive suggestions about my resume and interview preparation in a 1-1 office hour slot. I believe this was the most helpful event for my job search. (Editor’s note: we hope to host more of these events in the coming school year- stay tuned!)
2. Career events and workshops: This page lists the workshops hosted by UBC and companies, and provides personal career advice. I attended some workshops to help me polish my resume and build a professional Linkedin profile. Companies host events to introduce their hiring process and make connections with students. In some events, employees shared their experiences, which helped me learn more about the company culture and values.
3. Career Day: Multiple employers from different industries attend to connect with students to recruit for both paid and volunteer positions.
4. Co-op Program: I secured my first job through the UBC Co-op program. There are many available job opportunities for Co-op students only. Co-op coordinators were enthusiastic and professional, and they provided support with job searching, resume, and mock interviews. I highly recommend it if you want to gain more work experience.”
The importance of co-op
“Before joining Google, I worked at a spending management software company as a co-op student in Vancouver for 12 months. I worked as a backend developer to implement and deliver spending management features.
My co-op experience helped me develop more industrial skills and learn about the software development process, which made me more appealing as a full-time developer.
As a co-op student, you can choose from many different positions, such as backend, frontend, DevOps, and cloud engineer. Based on your co-op experience, you can get an overall idea of your short-term and long-term career goals. It’s also a good opportunity to find what your interests are in your field.”
Interview Process
“My application and interview process at Google had a few steps. This is what it was like:
1. Online application: I submitted my online application through Google Career in September. Google as well as other companies usually open new grad positions in summer, so I set my Linkedin up to get notified if there is a new job posting from followed companies. Besides, I constantly checked a repository to keep track of available new grad positions.
2. Online Coding Exercise: After three weeks, I received a response from Google to complete an online coding exercise within one week. I had 90 minutes to complete 2 standard coding problems, which were based on common Leetcode topics and not tricky at all.
3. Virtual On-site Preparation: I received a survey to schedule a virtual on-site date one week after finishing the online coding exercise. A recruiter reached out to me to help me learn more about the interview process.
4. Virtual On-site: There were five rounds in a single day containing one behavior round and four technical rounds. Each round took ~45 minutes and there was a 15-minute break. I could use my preferred language and write my codes with an online doc. It was an exhausting experience, so make sure to take a good rest before the interview day!
5. Interview results: It took three weeks for me to receive the result due to the Thanksgiving break. Be patient and don’t feel anxious.”
Interview tips
“Some tips from my experience- I hope some of them can be helpful.
1. Watch mock interview videos and practice with peers. There are many mock interview videos on YouTube and they are almost the same as an actual interview. It’s helpful to watch the videos and imagine how to answer the questions under the same situation.
2. After learning about the interview process, you can do mock interviews with peers using prepared questions. Try to be formal and serious, and make sure you completely understand the prepared questions. After each round, give each other detailed feedback. This also helps you learn about expectations from the interviewer’s perspective.
3. Talking while coding. I learnt this lesson from my first mock interview with a Co-op coordinator. While solving a technical problem, we are supposed to demonstrate our knowledge and skills, and the interviewer is there to help us solve the problem- similar to solving a practical problem with a colleague. If you get stuck and just think in silence, it’ll be hard for the interviewer to help. So please try to talk while coding, express what is on your mind, and make sure everyone is on the same page.
4. Practice Leetcode questions!
5. Be confident and relax. You have been well-prepared on the interview day, just take a deep breath and trust yourself :).”
Explore more career resources from UBC Applied Science
Design and Innovation Day 2022: Winners, Projects, and Photos
Thank you to everyone who attended Design and Innovation Day! It was wonderful to see the results of a year of effort and teamwork from ECE’s students. Congratulations, everyone!
Design & Innovation Day was an in-person event showcasing our electrical and computer engineering Capstone projects for 2022. This event was the culmination of 8 months of work where our engineering teams solved technical design challenges from industry and community partners. We also wish to highlight two groups of exceptional teams: our Faculty Awards recognize the best overall projects and the Best Video Awards recognize our teams’ exceptional communication skills.
The winners of the Best Video competition, the Faculty Awards are featured below.
Faculty Award Winners
The faculty awards recognize outstanding projects as selected by all 9 Capstone instructors. In addition to exceptional engineering design, teams also display strengths in professionalism, communication, management, and / or impact on their partner’s organization.
Project Name: Hardware & Software biofeedback for Physiotherapy
Project Client: UBC Tendon Injury Research Group
Project Abstract: Long-term adherence to remote physiotherapy is statistically low. We’ve developed a real-time biofeedback hardware and software package to assist home-based physical therapy. PhysViz supports long-term adherence to rehabilitation exercises as well as allowing clinicians to provide real-time feedback and prescription adjustments, leading to better prognosis.
Check out our feature “Capstone Perspectives” interview, where we took a deeper dive into this award-winning capstone team and their amazing work!
Project Name: Monitor Nature with AI Automatic Change Detection
Project Client: Korotu Technology
Project Abstract: The primary outcome of this project is to create a mobile application and a back-end solution for detecting deforestation changes using AI. Users can select a location on the map and track deforestation changes between different years. Users can also add locations to their watchlist to receive automatic notifications if a significant amount of deforestation has happened in that area. The land cover classification of locations is performed using deep learning. The client’s interest in this project stems from its vision of creating sustainable natural climate solutions that are easily accessible by the general public. The target audience for this project includes individuals and communities interested in tracking the change in land use in the area.
Although there are already existing products regarding natural change detection, they are not easily used by the general public. These tools are used by governments and provinces to monitor changes at large scales. A publicly available, easy-to-use nature-monitoring app has the potential to help protect places that rely on clean air and biodiversity.
Check out our feature “Capstone Perspectives” interview, where we took a deeper dive into this award-winning capstone team and their amazing work!
IoT sensor to improve learning and focus in classrooms
Project Client: Airtame ApS
Project Abstract: “IoT sensor to improve learning and focus in classrooms” is the project that our team (SF-043) has undertaken. The purpose of this project was to design a solution that will aid educators in making decisions and adjustments based on environmental classroom conditions. Studies have shown that classroom environmental conditions play a key role in optimizing student learning.
This project aims to provide actionable recommendations and meaningful representation of the conditions within a classroom setting through the use of IoT sensor hardware. The sensing hardware that our group has designed is focused on sensing and reporting the temperature, humidity, and CO2 environmental conditions within a classroom setting.
Check out our feature “Capstone Perspectives” interview, where we took a deeper dive into this award-winning capstone team and their amazing work!
Best Video Winners
The best video awards recognize our teams’ exceptional ability to communicate their technical design challenge and project’s impact to a general audience. A short list of videos is selected by the Capstone students with the final winners selected by a panel of judges representing diverse perspectives.
First Prize: Slicing-Based Debugging for Java / Android Development Environments
Project Client: UBC ECE, ReSeSS Research Lab, PI: Prof. Julia Rubin.
Our team has worked with the ReSSeS lab to integrate an innovative debugging tool called the Slicer4J Plugin. Slicer4J is a dynamic program analysis tool launched from a command line that allows users to select a statement and take a slice of the program execution to find all the lines which impact that statement. It enables analysis of a full execution of a program with a bird’s-eye view as opposed to the moment-in-time views that are common with traditional debugging tools. The objective of this project is to produce a functional, intuitive, and simple-to-use plugin for IntelliJ IDEA that utilizes the Slicer4J tool.
Danica Xiao
Tristen Raab
Preet Shah
David Fong
John Ramsden
Second Prize: IoT sensor to improve learning and focus in classrooms
Project Client: Airtame ApS
“IoT sensor to improve learning and focus in classrooms” is the project that our team (SF-043) has undertaken. The purpose of this project was to design a solution that will aid educators in making decisions and adjustments based on environmental classroom conditions. Studies have shown that classroom environmental conditions play a key role in optimizing student learning.
This project aims to provide actionable recommendations and meaningful representation of the conditions within a classroom setting through the use of IoT sensor hardware. The sensing hardware that our group has designed is focused on sensing and reporting the temperature, humidity, and CO2 environmental conditions within a classroom setting.
Mitchell Gordon
Matthew Fournier
Lam Hoang
Valentine Sebuyungo
Lary Qian
Third Prize: Hardware and Software Biofeedback for Physiotherapy
Project Client: UBC Tendon Injury Research Group
Long-term adherence to remote physiotherapy is statistically low. We’ve developed a real-time biofeedback hardware and software package to assist home-based physical therapy. PhysViz supports long-term adherence to rehabilitation exercises as well as allowing clinicians to provide real-time feedback and prescription adjustments, leading to better prognosis.
Members
Warren Chan Wan
Stephanie Natcheff
Gabriel Chen
Hugh Chen
Jaiden Martinson-Hatt
Explore All 2022 Capstone Projects
Enhance How We Do Things
Facilitate Personal and Community Connection
Improve How We Make Things
Increase Safety & Reduce Risks
Design and Innovation Day Photo Gallery
Photos by Gabriel Chen Xiao Ming
Jan Hammer awarded Killam Graduate Teaching Assistant Award
ECE PhD candidate Jan Hammer has been awarded the Killam Graduate Teaching Assistant Award for exceptional teaching assistantship. He is one of nineteen graduate students receiving this award across UBC in 2021/22.
“I feel overwhelmed to receive this award!” Jan says. “To be honest, I didn’t expect to receive it.”
The Killam award recognizes the valuable role that teaching assistants play in UBC’s programs. Awardees are recognized for skills, abilities and contributions resulting in a high level of respect from undergraduate students and supervisors.
Jan has been at the ECE department for five years. “My engineering career started probably when I was around eight years old,” he recalls. “I crashed our first computer and my dad had me fixing it which taught me some valuable lessons in engineering.”
Through an apprenticeship in technical IT, and a B.Eng in electrical engineering, Jan discovered an interest in power electronics. He completed a M.Eng degree in systems engineering, while working part-time as a full-stack software developer. During his master’s, he undertook an exchange semester with ECE’s Martin Ordonez in the power electronics lab, working on prototyping power stages for Silicon-Carbide (SiC) power semiconductor applications.
Following his master’s, he worked in the solar industry as a software and controls engineer, before returning to academia. He entered PhD study at ECE under the supervision of Martin Ordonez, and is currently working on printed circuit board (PCB) optimization for Gallium-Nitride (GaN) power semiconductor applications.
“After a steep learning curve in the beginning of my PhD, my efforts seem to be producing results.” says Jan. “To all my peers reading this: perseverance pays off!”
Of TA-ing, Jan says, “I enjoy the mentoring aspect of being a teaching assistant in term projects.”
“The duration of these projects allows me to establish a good relationship with the students that translates to an enhanced learning and teaching environment. I’m able to witness students’ growth in technical and interpersonal skills, which is very fulfilling.”
Congratulations on this achievement, Jan!
Connect with Jan on Linkedin.
Learn more about the Killam Awards
ECE Faculty awarded funding for Trustworthy ML research from UBC VPRI’s Research Excellence Clusters initiative
ECE professor Julia Rubin, together with her colleagues, professors Karthik Pattabiraman and Ali Mesbah, leads the “Trustworthiness of Machine-Learning-Based Systems (TrustML)” research cluster, which has been awarded funding through the 2022/2023 UBC Research Excellence Clusters initiative.
Research excellence clusters are inter-departmental networks of researchers who collectively represent leaders in a particular field of study. They are founded to foster partnerships and collaborations across disciplines, and to create and develop new research through interdisciplinary teamwork.
The goal of TrustML is to facilitate the development of trustworthy machine-learning-based systems- i.e., systems that are reliable, secure, explainable, and ethical. The cluster includes members from six different faculties at UBC, the industry, and the BC government. They will examine trust-related requirements in several life-critical domains, including medicine, manufacturing, urban planning, and aerospace, and will investigate solutions for building trustworthy systems that professionals and the general public can reliably adopt.
The work of the cluster is aligned with Dr. Rubin’s own research, which focuses on software quality and on robustness, explainability, and fairness of ML-based systems. Dr. Rubin is a Canada Research Chair, Tier II, in Trustworty Software. Before joining UBC, she spent almost 10 years in industry, working for IBM Research, where she was a Research Staff Member and a Research Group Manager.
Learn more about the 2022/23 projects funded through Grants for Catalyzing Research Clusters (GCRC).
Solving bias in healthcare AI: A Q&A with Xiaoxiao Li
AI algorithms are used more and more often to improve and automate many parts of healthcare, making decisions about patients’ care. However, the data these algorithms use to operate can come with biases- which means they can make mistakes. Studies have shown that AI systems like neural networks will routinely under-diagnose Hispanic and Black patients.[1]
“Bias can be introduced during data collection, and is fatal in healthcare,” says Xiaoxiao Li, ECE assistant professor. Xiaoxiao is working on a new interdisciplinary project that she hopes will help to solve issues of bias in these systems. Neural networks can be under-trained on data from these groups, making the AI’s results inaccurate. And if doctors trust the erroneous decision the neural network made, their patient could receive subpar healthcare.
Xiaoxiao is one of five researchers working to help solve this problem. Through a collaboration between researchers at the School of Nursing, Computer Science, and ECE, a new interdisciplinary project will focus on improving how these healthcare AI systems deal with patients from underrepresented groups, by improving the data these systems draw and learn from.
Called “Pre-Processing Community Nursing and Allied Health Data for Equity-Informed Artificial Intelligence for Interdisciplinary Wound Care,” this healthcare technology project was recently awarded $25,000 in funding through the Health Innovation Funding Investment (HIFI) Awards, a grant that focuses on cross-faculty health-related work.
We spoke to Xiaoxiao to learn more about how this project will impact equity in healthcare.
What is the focus of this research project?
This project is about creating a pipeline to preprocess community nursing and allied health data for equity-informed artificial intelligence (AI), to improve interdisciplinary wound care.
What does the process of developing this research look like?
Dr. Leanne Currie, from the School of Nursing, came to my faculty talk about trustworthy AI for healthcare- that’s where we first connected. Dr. Currie’s previous student, Dr. Charlene Ronquillo, an assistant professor at UBCO’s school of nursing, is leading this project.
We noticed that equity is an ongoing challenge in developing AI tools for nursing data analysis, despite the fact that there is a pressing need to use AI to leverage large amounts of nursing data.
Dr. Ivan Beschastnikh (my external career mentor), a software engineering and systems expert at the department of computer science, and Lorraine Block, a clinical partner and Vancouver Coastal Health Authority (also a PhD candidate with Dr. Leanne Currie), were later brought on board for this project.
Why is it important that this project is interdisciplinary?
This project brings together early career researchers (Dr. Ronquillo and me), mentors (Dr. Currie and Dr. Beschastnikh), and a clinical partner (Block).
Using AI tools to solve clinical problems, as well as acquiring domain knowledge to aid in the development of trustworthy AI, necessitates the participation of experts on both the clinical and engineering sides. These interdisciplinary perspectives and expertise are necessary; they ensure that the science underpinning this work is novel and rigorous, as well as being grounded in the realities of clinical practice and health systems. Hopefully, this will optimize the potential for truly clinically meaningful and impactful work.
What impact will this project have in health care?
Fairness is a hot topic in AI right now. We’ve seen that AI algorithms can perform erroneously with under-represented groups. This type of bias can be introduced during data collection, and is fatal in healthcare.
Our pilot study will focus on evaluating the representation of diverse populations in datasets. We plan to develop machine learning-based approaches for assessing the fairness or bias of data pre-processing and infrastructure. Finally, we will create AI methods that can be applied to this data to create equity-informed AI applications to aid in wound diagnosis and treatment.
Large amounts of nursing and allied health data are underused in health systems. An aim of this study is to better understand how we can make the best use of this data, which is typically quite “messy”.
We hope this project will contribute to a connected health data infrastructure in BC.
Read more about the projects funded through the Health Innovation Funding Investment (HIFI) Awards.
[1] Chen, Richard J., et al. “Algorithm fairness in ai for medicine and healthcare.” arXiv preprint arXiv:2110.00603 (2021)