AI clinical

Dina Katabi: A new way to monitor vital signs (that can see through walls) | TED Talk

So if you think about it, wireless signals, they travel through space, they go through obstacles and walls and occlusions, and some of them, they reflect off our bodies, because our bodies are full of water, and some of these minute reflections, they come back. And if, just if, I had a device that can just sense these minute reflections, then I would be able to feel people that I cannot see. So I started working with my students on building such a device, and I want to show you some of our early results.

So here is our device, transmitting very low power wireless signal, analyzes the reflections using AI and spits out the sleep stages throughout the night. So we know, for example, when this person is dreaming. Not just that … we can even get your breathing while you are sitting like that, and without touching you. So he is sitting and reading and this is his inhales, exhales. We asked him to hold his breath, and you see the signal staying at a steady level because he exhaled. And I want to zoom in on the signal. These are the inhales, these are the exhales. And you see these blips on the signal? These are not noise. They are his heartbeats. And you can see them beat by beat.

Capturing heartbeat while the subject is holding breath. Using WiFi.

Further reading


Will Marshall: The mission to create a searchable database of Earth’s surface | TED Talk

And we now have over 200 satellites in orbit, downlinking their data to 31 ground stations we built around the planet. In total, we get 1.5 million 29-megapixel images of the Earth down each day. And on any one location of the Earth’s surface, we now have on average more than 500 images. A deep stack of data, documenting immense change.

Anyone can go online to open an account and see all of our imagery online. It’s a bit like Google Earth, except it’s up-to-date imagery, and you can see back through time. You can compare any two days and see the dramatic changes that happen around our planet. Or you can create a time lapse through the 500 images that we have and see that change dramatically over time.

What we’re doing with artificial intelligence is finding the objects in all the satellite images. The same AI tools that are used to find cats in videos online can also be used to find information on our pictures. So, imagine if you can say, this is a ship, this is a tree, this is a car, this is a road, this is a building, this is a truck. And if you could do that for all of the millions of images coming down per day, then you basically create a database of all the sizable objects on the planet, every day. And that database is searchable.

I can imagine us abstracting out the imagery entirely and just having a queryable interface to the Earth. Imagine if we could just ask, “Hey, how many houses are there in Pakistan? Give me a plot of that versus time.” “How many trees are there in the Amazon and can you tell me the locations of the trees that have been felled between this week and last week?” Wouldn’t that be great?

This is fantastic. It’s well worth putting aside 20 minutes to watch the video and then go play around at

Up-to-date high res image of Cape Town.
ethics health physiotherapy students

Developing compassion and empathy as part of a Professional Ethics module

I’ve been spending some time this week working with our 4th year students in the Professional Ethics module. One of our biggest challenges is that our students (and most other students in healthcare programmes) see characteristics like compassion, empathy, courage, shame, and emotional response as something that they need to “have”, like a stethoscope or comfortable shoes. I’m trying to get them to see that these are really “ways of being”. Being a caring person isn’t part of your job, it’s a part of who you are. Perceiving and responding to the suffering of others isn’t something that a professional code of conduct can help you with.

I’ve been trying to explore these ideas using music and videos in the classroom, along with reflective writing exercises and, as I’m such a big fan of two of the videos I used recently, I thought I’d share them here.

twitter feed

Twitter Weekly Updates for 2011-09-12

  • @ryantracey they’re passages I highlight using diigo, they get pulled into the blog post so I can find them later #
  • @amcunningham Often use personal experience in class, never thought of them as stories. Maybe it’s the “telling” of the story that matters #
  • We learn from stories and experience Been thinking how to integrate stories into my teaching but haven’t managed yet #
  • Study Highlights Superficiality of Digital Native Concept Socio-economic background impacts digital sophistication #
  • Revisiting the Purpose of Higher Education There needs to be a shift away from knowledge and skills #
  • Are we missing reflection in learning? We need to create formal space for reflection within the curriculum #
  • TED video: a next generation digital book #
  • 5 Myths About Collaboration #
  • The Sad State of Educational Research Educational researchers also responsible for spreading poorly developed ideas? #
  • @amcunningham nice…didn’t know about some of those tools. Been meaning to have a look at but haven’t had the chance yet #
  • @amcunningham pretty cool…is it a list of all your tweets, or just those related to a specific theme? #
  • Video: Hands-on with Inkling 2.0, the iPad textbook — Tech News and Analysis #
  • The real cost of academic publishing via @guardian #
  • So when does academic publishing get disrupted? #
  • Why the Impossible Happens More Often #
  • Achieving substrate-independent minds: no, we cannot ‘copy’ brains #
education health PhD teaching workshop

Developing cases for Problem-Based Learning

Workshop on the development of case-based studies

Facilitators: Dr. Ethel Stanley, Dr. Margaret Waterman

Part of my PhD will be to look at alternative approaches to clinical education, including uses cases in problem-based learning (PBL). My specific interest is in the use of emerging technology to design and teach with those cases in small groups. Unfortunately I was only able to attend the first half of the workshop, and didn’t get the opportunity to develop my own case.

Here are my notes from the workshop:

Biology is an important topic for everyone to understand, as it impacts on every major health-related decision that has to be made, so we used biological case studies as working examples

Students must be able to ask good questions in order to solve their own problems in preparation for the types of adult learning (androgogy, as opposed to pedagogy) behaviour we’d expect to see in practice. Memorising content isn’t a good strategy for learning how to solve problems like “Why is this patient walking in a way that is different from “normal”?”

A lecture is a good method to deliver content, but is a poor method for active learning around problem solving

Case-based learning (CBL) is a good way to explore realistically complex situations

Begin by introducing a problem with no expectation that the student can solve the problem. Use that as a springboard to explore their ability to develop good research questions

CBL requires the confidence from teachers to give up control, but giving up control is the only way to get students to actively construct their own learning experiences by asking questions, gathering information, testing hypotheses, and convince others of their findings

Structure for working through a basic case

  • Define the boundaries / outline of the case
  • What do you already know (group knowledge, as well as information that can be obtained from the case study) / what do you still need to know (this can be used as a basis for a short lecture) in order to answer the question
  • Choose the most important questions to explore
  • Get into small groups and discuss / share information, knowledge, assumptions
  • Go away and try to answer the questions that were generated
  • Come back and only then get the teachers objectives
  • Then go away again and refine the questions and information collected

Why use cases?

  • To initiate investigations
  • To use new technologies and resources to solve problems
  • Develop local and international / global perspectives
  • Emphasise the value of interdisciplinary and collaborative approaches
  • Structure student assessment through student products
  • Support diverse objectives within a shared workspace (would be interesting to investigate the possibility of using a wiki to develop and build on cases using this approach)

Used Gapminder to demonstrate alternative ways of visually representing data while working through a case study. See Hans Rosling (founder of Gapminder) on the Joy of Statistics, and his TED presentations.

The teacher can set the context of the class, and the depth to which students should explore questions, by using an appropriate framework / case. Can also decide which questions are prioritised, and which ones can be answered via different methods e.g. lecture, essay, assignment, etc.

Highlight the fact that, as the teacher, you don’t have all the answers and that you’re a co-learner in the classroom. Students should understand that the teacher isn’t a font of all knowledge on the subject, and that it’s acceptable and appropriate for the teacher to have to also do research on the topic

twitter feed

Twitter Weekly Updates for 2011-03-07

twitter feed

Twitter Weekly Updates for 2011-01-17

learning personal students teaching

Authenticity and vulnerability

Yesterday I posted a reflection on how I’m coming to realise that the personal and social aspects of myself are always present, even when I’m in professional mode. I discussed this as it related to connecting with students on Facebook and the possible benefits that might have for everyone involved.

Coincidentally, I also came across this post on Presentation Zen yesterday, discussing the profound impact and importance of vulnerability in our lives. I thought I’d share it here, as it links strongly to the way I’m thinking about teaching and learning right now. Which is to say that sharing our authentic selves in the classroom may be one way to really connect with our students.

The post makes reference to the video below, where Brene Brown discusses the power of vulnerability in our lives. It’s 20 minutes well spent.

education ethics research students

Predictably irrational: decision-making in teaching

I’m busy reading Dan Ariely’s Predictably Irrational: The Hidden Forces that Shape Our Decisions, and wanted to share some of the takeaway points that made me think about how I could change my own teaching practice. I haven’t finished the book yet, so I may update this post when I do.

The premise of the book is that we aren’t always the rational beings we believe we are, and that there are powerful emotional factors that cause us to make decisions that are often counterintuitive. If we understand how these factors predictably make us less rational, we might be able to affect greater self-control over our lives, and be better off for it.

One of the ideas that really got my attention was how we respond to social and market norms in our everyday interactions with other people. When you think about it, a lot of what we do as teachers has nothing to do with market norms i.e. we don’t work the hours we do because we’re paid appropriately. Social norms mean that we go above and beyond what is required of us possibly because we have a sense of shared purpose or a belief that we’re contributing to something more important than money. In other words, people are motivated to work harder when they believe they’re in a socially-orientated relationship, rather than one in which market values dominate. Ariely also conducted experiments showing that when market and social norms collide, relationships that were based on the social norms are disrupted and can take years to rebuild. This has implications when we start thinking about building communities of practice in our professional domains, and it seems that we would do well to base our interactions on a shared sense of purpose, rather than financial reward. I know from recent conversations with students with whom I have a good relationship, that they try harder to impress me with their work, and worry less about the mark they receive, than they do with other lecturers who don’t engage with them at all. For me, this is a powerful incentive to engage with students not only on a cognitive level, but on a social level as well.

Ariely also shows clearly how emotionally heightened states cause us to make bad decisions for ourselves and for those around us. How many times have we made a bad decision when we’re angry? When I think about it (and if I’m honest with myself), I know that I’ve been guilty of being a stricter assessor when I’m in a bad mood, than when I’m having a good day. I know that my marking isn’t as objective as I’d like it to be, but to be shown the evidence of how much it influences my behaviour has made me commit to avoid marking students’ work when I’m upset.

When discussing procrastination, Ariely makes the observation that when students are given absolute submission dates for assignments that are appropriately spaced, they do better than students who are given flexibility in determining their own submission dates. I know that recently I’ve started including draft deadlines into assignments to “encourage” students to begin work their on assignments early, and to continue improving their work up until the final submission date. Last year I saw students who participated in the drafting process score significantly higher marks than those who chose to submit only one, final version of the assignment. Students will procrastinate if left to themselves, and I guess we need to decide if we’re OK with that, or to rather try and figure out how to more effectively guide them through the process of making regular improvement through regular feedback.

The final point I wanted to highlight is from a TED presentation that Ariely gave (although it might be in the book too), where he finds that students are less likely to cheat after thinking about the 10 commandments. It turns out that signing an honour code might not be as pointless as I’d previously thought.

You can also see Ariely discuss some of his ideas at these 2 TED talks:

twitter feed

Twitter Weekly Updates for 2009-11-16

Powered by Twitter Tools