Inspiration
We found inspiration in all the studies that were done on the topic of eye tracking, e-learning facilities, but also in the current COVID-19 context which will accelerate the development of the online learning environments so that learning would not be disrupted. We are also motivated by the results we’ve reached after implementing EyeLearn 1.0. The stages reached by the Iceberg team in the development process for the EyeLearn 1.0 were: -Industrial research: *technical solution development; *MFS implementation (simplified functional model) and platform testing. -Experimental development: *prototype completion; *launch of the platform.
What it does
The eye tracking system, collects information about user interaction with the screen and creates reports with thermal maps (heatmaps) and detailed analysis of the focus points of each user’s gaze. The resulted sets of data can then be further segmented and analyzed on an AI platform which will generate specific reports that the researchers can use to create in depth studies and make more focused recommendations on the metrics they measured.
EyeLearn can provide support for both students and teachers to tackle the challenges of the learning process during isolation and social distancing context. Employing eye tracking technology and an AI/ML driven analytics component, it is a very useful tool for monitoring the way students learn, which in turn can give useful insights for the teacher to improve his/her teaching methods or content. We aim at addressing issues related to: -monitoring of students’ learning process; -examinations; -online interactions/ group learning; -data and privacy issues.
How I built it
The system is developed to work with current hardware and software technologies to maximize their impact, but also for advanced technologies such as Artificial Intelligence and Machine Learning that will be able to use the EyeLearn input resulting from user interaction with the entire system.
Challenges I ran into
- you have to install an app, and the data is saved locally
- lack of specific knowledge regarding NLP (Neuro linguistic Programming) in order to better analyze more user emotions
- the app needs calibration and this takes time and can be hard to do
- in this moment, the app is recording only 3-5 min live, insufficient time for an online class
Accomplishments that I'm proud of
We manage to gather new team members in a short time and work together this weekend. And we are also proud that we poved Eyelearn can be integrated with any existing platform of e-learning, meaning it will be very easy and quickly to be installed and used by institutions of learning.
What I learned
We learnt that social good happens if people join their forces, we managed to work together (some of us people we didn’t know each other previously) to generate a sustainable e-learning solution which can be scaled.
What's next for Eyelearn
EyeLearn currently works as a standalone app that can be installed on computers fitted with a webcam. To better suit the needs under this context we intend to: ● extend its computer vision capabilities; ● as a standalone app – developing versions for other devices (phones, tablets); ● as a plugin – developing the capability to be installed on different e-learning platforms to extend the monitoring and insight generation capabilities of these platforms. We are constantly in search of funding and investment in order to develop it faster, better and to be able to put it in the market to be used by students, teachers and universities.
Log in or sign up for Devpost to join the conversation.