Global Data Science Forum

Announcing a Call for Code AI Spot Challenge for a Safer Planet. Starting tomorrow July 27

By Julianna Delua posted Mon July 26, 2021 11:24 AM

  

Using prediction, optimization and automation to make the world more secure and resilient.

 

Julianna DeLua

 

With increased availability of automated AI development tools and best practices of bringing AI to production, organizations are driving business performance, governmental operations and regulations, and social good with the expanded use of AI. In particular, there is a global interest in applying AI for making our world a safer place. Through AI-powered prediction, optimization, and automation, we can help mitigate both physical and cyber threats and risks. For example, AI and machine learning can help in the following ways:

 

  • Predict potential construction risks and hazardous conditions
  • Develop contextual intelligence to share with the public
  • Anticipate weather events and disasters for increased readiness
  • Reduce construction or worksite accidents, theft, and vandalism
  • Optimize scheduling and allocations of resources, and match supply and demand
  • Assess risk and needs, and deliver solutions to communities in need

 

AI is also a crucial skill for us to acquire and improve. It is an opportune time for us to build AI skills and make a positive impact on the world. You can use the latest cloud and AI technologies to translate your ideas into action.

 

Introducing 2021 Call for Code AI Spot Challenge

In partnership with Call for Code, we are introducing an AI Spot Challenge. This Spot Challenge invites developers, data scientists and problem solvers around the world to build and contribute to sustainable, open source technology projects that make our planet safer.

 

Start Date: July 27, 2021, 12:00am PDT

Submission Deadline: August 18, 2021, 11:59pm PDT (EXTENDED TO August 21).

Winner Announcement Date: August 24, 2021, 8am PDT via YouTube

Key Rules:

  • You will build a new solution for the AI Spot Challenge
  • You can compete alone or part of a team of up to five people
  • You must use IBM Cloud and Watson Studio. You can absolutely add more services within IBM Cloud.

Judging: IBM will use a panel of experts to evaluate your submissions on

  • Completeness and transferability (5 points)
  • Effectiveness and efficiency (5 points)
  • Design and usability (5 points)
  • Creativity and innovation (5 points)

Prizes:

  • GRAND PRIZE: $15,000.00 USD
  • RUNNER UP PRIZE: $5,000.00 USD
  • 2nd RUNNER UP PRIZE: $2,500.00 USD

 

We invite you to address specific problems in unique, clearly demonstrable ways. The most successful solutions are those scoped to have the greatest impact with the smallest technological footprint. While you can create an entirely brand new solution following the guidelines above, we encourage you to review DroneAid and Intelligent Supervision Assistant as your inspirations for your final submissions.

 

DroneAid to detect call for help

The idea for DroneAid was conceived based on Pedro Cruz’s experience in Puerto Rico after Hurricane Maria. Pedro flew his drone around his neighborhood and saw handwritten messages indicating what people need and realized he could standardize a solution to provide a response. DroneAid uses machine learning to detect calls for help on the ground placed by those in need. At the heart of DroneAid is a Symbol Language that is used to train a visual recognition model. That model analyzes video from a drone to detect and count specific images. A dashboard can be used to plot those locations on a map and initiate a response. You can learn more about DroneAid on the Call for Code blog and github

 

Intelligent Supervision Assistant for Construction to validate safety

Intelligent Supervision Assistant for Construction - Sistema Inteligente de Monitoreo de Obra (ISAC-SIMO) is a system to validate that the intervention work done for homeowners in Colombia has been done correctly and safely. The technology consists of a mobile application tracking the progression of an intervention on a home throughout the process to complete work. The application shows the progress of the work, and it can be validated through the analysis of the quality of two building elements, rebar and walls, by guiding the users through a series of checks. In addition to the mobile application, the tool also consists of a web interface that facilitates the management of checks and image processing pipelines implemented in the mobile application. You can learn more about ISAC-SIMO on the Call for Code blog and github.  

Project examples

Here is a general-purpose repo example you can review as you submit your solution https://github.com/Call-for-Code/Project-Sample and description

Getting started

Are you ready to answer the call for the safer planet?  Follow the steps below:

 

Step 1: Sign up for AI Bootcamp

 

  • Join live or on-demand to participate in presentations and Q&A on August 3, August 10 and August 17. Register.

 

Step 2: Register for IBM Cloud account with the Call for Code Open Source community

 

  • Log in with your IBM Cloud Account, or if you don’t have one, you can create a new account with this link. Make sure that when you start building, that you are using Watson Studio as one of your services.
  • When you join the community, you will have the option to accept a Code of Conduct, which will provide an automated invitation to the Call for Code Slack Workspace. Use the verification code sent to your email to complete IBM Cloud registration.

 

Step 3: Join the Call for Code Slack

 

Sign up to join the Call for Code Slack Workspace. Once there, find and join #ai-spot-challenge channel.  You’ll be able to connect with other participants and get help from IBM Mentors on this channel.

 

Step 4: Watch the Call for Code AI Spot Challenge announcement on YouTube

 

  • Participate in the YouTube Live Streaming on Call for Code AI Spot Challenge on July 27 or watch on-demand after the session here

 

Step 5: Review the submission guidelines and AI Spot Challenge Participation Agreement. 

 

  • Once your project is done, one member of each team should open the submission form here to see details on the information required and the field length limits.
  • All other team members must complete a form and accept the participation agreement where the rules, prize details, and eligibility criteria are specified.

 

Step 6: Join the AI Bootcamp group on IBM Community

 

  • Join the IBM Community and click here for the AI Bootcamp group, watch out for announcements and join the discussions.

 

Step 7: Complete your submission

 

  • You MUST complete your submission by the August 24, 2021 deadline.

 

We look forward to reviewing your submissions. For questions, please join the #ai-spot-challenge channel on the Call for Code Slack or contact me by email, julianna@ibm.com.

 

Addendum - Potential data sources and useful links
 

Source: Call for Code Useful Datasets

 

Ways to Find Datasets: Go to locations where there are many datasets.

Many governments, and institutions such as the UN, and the World Economic Bank provide datasets. The following are some examples:

  • data.gov: The NASA (National Aeronautics and Space Administration) open data portal offers tens of thousands of datasets which are often used in the annual NASA Space Apps Challenge
  • UNdata: You can find data about agriculture, crime, education, energy, industry, labor, national accounts, population and tourism at UNdata. The statistics available through UNdata are produced by United Nations Statistics and Population Divisions as well as other United Nations agencies.

Dataset Aggregator Sites and Miscellaneous Catalogs: Some sites collate datasets into categories sourced from other locations including datasets from the data.gov sites. It is worth taking a look at these sites, noting that some do charge for specialized access, but these aggregator sites do give you an idea of what's available. Examples of sites that aggregate collections of datasets or provide introductions to open datasets include :

Final_PDF_YouTube_Announcement_on_Call_for_Code_AI_Spot_Challenge_for_a_Safer_Planet.pdf

0 comments
87 views

Permalink