Artemis Awake

Artemis Awake| Sleep Shift Scheduling Tool

Sleep Shift Scheduling Tool

Sleep loss and fatigue may lead to reduced performance and an increased risk to safety during many activities, including spaceflight. Your challenge is to develop an operational sleep shift scheduling tool that provides autonomous customization of a schedule for sleep, exercise, and nutrition to manage fatigue.

Summary

It’s known that lack of sleep can cause fatigue that leads to errors while performing critical tasks. Individuals who are fatigued often cannot determine the degree of their impairment. Astronauts frequently suffer from the effects of sleep deprivation and circadian rhythm disruption. Artemis is designed to address such issues. Using AI-powered analytics, Artemis is able to hone in on factors that lead to burnout, analyzing crew members' eyes, their exercise routine, dietary, and other factors. From this, Artemis calculates the recommended procedures to prevent burnout from happening, and if situations are severe, will notify HQ for potential next steps.

How We Addressed This Challenge

The collateral effects of sleep loss and circadian desynchronization increase the chance of personnel making mistakes in their work, and in some cases, can lead to the failure of an entire mission. Artemis Wake eliminates the potential psychological issues that could impede a mission’s success. The system involves monitoring and adjusting sleep schedule, exercise, and nutrition calculation. This entails analyzing data from reading a person's eye to determine if the individual is too exhausted to go through with a critical task.

The data is then processed and compiled into a profile of a crewmember. The crewmember is able to access his or her data and Artemis analyzes if that crew member will burnout or harm others in the mission. Artemis will also be able to give suggestions to a stressed crew member, recommending them to rest, suggest an exercise, or intake specific food for more nutrition. It is important to realize that ALL video will be deleted after processing, leaving only the analysis and the private profile.

The application we have created is available on iPad and Android. It tracks the Astronaut’s activity, tasks, and monitors their activity to prevent fatigue. However, more tasks can be added later. The application prompts the user to let them know whether they should continue with the task.

How We Developed This Project

What inspired your team to choose this challenge?

Our team was inspired by an opportunity to participate in contributing to the space industry by designing a support system for crewmembers. We hoped it would help reduce mission failures and enable a crewmembers to be self-sustaining.

What was your approach to developing this project?

Every member played to their strengths while also trying to learn how to implement new features. We had regular check-ins as a team to review progress and decide next steps. In terms of development, each member had a given task or feature to finish with the knowledge that things will be pieced together or edited for the final version, which other team members were assigned to.

What tools, coding languages, hardware, software did you use to develop your project?

Scratch - for animation

iOS - Swift - for the front-end application

Android - Java - for the front-end application

Python - for the backend

Packages: TensorFlow, OpenCV, imutils, dlib, scipy, kivy

What problems and achievements did your team have?

Outline of issues faced while making Artemis Wake:

Having a split development, one for iOS and one for Android added more work to an already limited time constraint
Remote communication and idea sharing in a multi-timezone environment - we had to record sessions and regular checkins
Language barrier - when there was language barrier issue, team members would help translate the idea or clarify that to the team
Finding data sets that accurately matched our project goals- searching for relevant datasets or even accessible datasets was difficult

We had achieved the following:

We had success with these features: functional scheduling of tasks, a real-time fatigue analysis, exercise tracker, and nutrition calculator.
Another success we had was that both apps can easily be adapted for workers that also have shift schedules, such as truck drivers, nurses and emergency responders.

With more time to work on this project, we could train the AI to have a more granular and sophisticated analysis of the person’s mental and physical state, thus increasing the system’s reliability.

With access to higher-quality datasets, we could increase the accuracy of the system. with limited datasets, it was hard to get an accurate model/assessment.

We also want to include the requirements that NASA and other agencies have already studied, in regards to nutrition, sleep and exercise.

How We Used Space Agency Data in This Project

We used information from NASA’s and the CSA’s websites to learn about how exercise, nutrition and sleep is done in space. This included what types of exercises, what they are for and how many hours a day someone should exercise. Through our research, we did not find other raw data sets (so .csv files, spreadsheets, etc) to assist us in our project. Finally, we have used: shape_predictor_68_face_landmarks.dat. This is trained on the ibug 300-W dataset.