Smart AI Drones : As Emergency Responders During Accidents

Growing population, growing vehicles and lack of awareness has led to the problem of accidents happening at low to high density vehicle and human population. A witness in an accident has no medical training and often becomes a bystander. Drones as emergency responders exploits the use of ICT with AI to as an add-on to emergency services. With a push of a button by a witness, the drones use the GPS of the phone to reach the spot, the AI model is trained to classify the accident and shares its results with the emergency responders including hospitals. The ambulance reaching the spot is prepared with the basic of what has to be done and the nearest hospital well prepared to act.

 
 

Outline/Structure of the Talk

To bring in focus of using hardware and software into healthcare. Drones and AI in healthcare especially as emergency responders will save a lot of lives and change the course of how emergency situations are handled. Drones trained to identify what kind of injuries has occurred and relaying information to emergency responders will help in being better prepared and organised.

Accident Images Data set:

  1. Accident detection: Images labelled with accident and images labelled without accident.
  2. Vehicles in accident:Images labelled with Light/heavy/motorcycle
  3. Accident Level- Images labelled :high/medium/low

Type of injury data set:

  1. Head Injury: Images labelled head injury and non-head injury
  2. Torso Injury: Images labelled torso injury and non-torso injury
  3. Lower Body Injury- Images labelled lower body injury and non-lower body injury.

All trained using CNN

For drones the best way was to use K-Nearest Neighbour (KNN)

Difficulties:

Apart from using just images, the use of other pointers such as body temperature , hear beat detection, blood clot level/ % of blood clot, dislocated joints/broken bones would make the model more versatile.

One of the major difficulty is to remove the noise from the images which may be due to pixelation or debris in the images.

Breakdown of the talk:

  • Introduction: 2 min
  • The requirement/necessity of the solution: 2 min
  • The how of the solution: 2 min
  • Types of data sets, training and the steps : 7 min
  • Amalgamation of accident trained module with drone trained in KNN: 2 minutes
  • Application of solution:1 min
  • Conclusion: 2 min
  • Questions: 2 min

Learning Outcome

  • Looking at helping the society.
  • Generating awareness on saving the golden minute during accidents.
  • Creating awareness that Drones can be used in Healthcare.
  • Basic awareness about AI application
  • How to build modules

Target Audience

Early Thinkers, AI enthusiasts, Drone developers, ML/Deep Learning enthusiasts

Prerequisites for Attendees

Basics of ML/DL/AI, and an innovative mind

schedule Submitted 3 months ago

Public Feedback

comment Suggest improvements to the Speaker
  • Shiv Anand
    By Shiv Anand  ~  1 month ago
    reply Reply

    I like these aspects of the submission, and they should be retained:

    Futuristic : Do encourage

    I think the submission could be improved by:

    • Asking for another co-speaker to distribute the load and work on the same.
    • Rakshit Prabhakar
      By Rakshit Prabhakar  ~  1 month ago
      reply Reply

      Thank You. There will be co-speaker for the same.

  • Ashay Tamhane
    By Ashay Tamhane  ~  3 months ago
    reply Reply

    Hi Rakshit,

    Could you please clarify if a POC of the proposal is implemented or if this is simply an idea that you would like to pursue?

     

    • Rakshit Prabhakar
      By Rakshit Prabhakar  ~  3 months ago
      reply Reply

      Hi Ashay,

      That's a good question. It was a concept that was just approved a couple of weeks back and I am working on it. I will be sharing more details about it either in the conference or if i get access to my system in the future. My apologies for not being completly able to share everything at the moment.

  • Jesko Lance
    By Jesko Lance  ~  3 months ago
    reply Reply

    I came here through google search for my university hackathon. My thesis defence was this month but got postponed. This concept and work on drone is very promising and exciting. Alles Gute!!!

    • Rakshit Prabhakar
      By Rakshit Prabhakar  ~  3 months ago
      reply Reply

      Thank you ,  all the best for your thesis.

  • Raja Mohan
    By Raja Mohan  ~  3 months ago
    reply Reply

    As a representative from the data science community with over 20 years of hands on experience. My humble request to encourage budding minds like this kid here. The thinking amid the pandemic has potential. We often do not look at the application of it, I am guilty myself. But kids like this make it happen.

    Also, I would like to connect with him.

     

    • Rakshit Prabhakar
      By Rakshit Prabhakar  ~  3 months ago
      reply Reply

      Hi Raja Mohan,

      Thank you. Your kind and encouraging words are a booster to me. I am available on rakshit1383@gmail.com

      • Raja Mohan
        By Raja Mohan  ~  3 months ago
        reply Reply

        Mailed you !

  • Santonu Goswami
    By Santonu Goswami  ~  3 months ago
    reply Reply

    Hi Rakshit,

    The concept of your proposal is potentially good and useful.

    To help reviewing the proposal, I request you to update your slides according to your "Breakdown of the talk". Please add detals on your data and methods. As of now the three slides you provide, do not make things clear enough.

    Please update accordingly.

    Thanks,

    Santonu

     

    • Rakshit Prabhakar
      By Rakshit Prabhakar  ~  3 months ago
      reply Reply

      Hi Santonu

      Thank you. As requested earlier wrt the slides. I do not have access to my system intin  current scenario.I am trying my best to update the feedback remotely. I have mentioned some in the video and in outline.

       

      Regards

      Rakshit P

  • Natasha Rodrigues
    By Natasha Rodrigues  ~  3 months ago
    reply Reply
    Hi Rakshit, Thanks for your proposal! Requesting you to update the Outline/Structure section of your proposal with a time-wise breakup of how you plan to use 20 mins for the topics you've highlighted? To help the program committee understand your presentation style, can you add the slides for your proposal and provide a link to your past recording or record a small 1-2 mins trailer of your talk and share the link to the same? Also, in order to ensure the completeness of your proposal, we suggest you go through the review process requirements (https://confengine.com/review-process#best-chance). Thanks, Natasha
    • Rakshit Prabhakar
      By Rakshit Prabhakar  ~  3 months ago
      reply Reply

      Hi Natasha,

      As suggested, I have uploaded the video which is now under video section and mentioned the breakdown of the talk under outline/structure of the talk.

      Wrt the slides, I am facing a bit difficulty with the access given the situation. Happy to oblige for any other alternative.

      • Natasha Rodrigues
        By Natasha Rodrigues  ~  3 months ago
        reply Reply

        Hi Rakshit,

        Thanks a ton for the updates. I understand the situation, and therefore request you to update some sample slides for the program committee to view for now.

        Thanks,

        Natasha

        • Rakshit Prabhakar
          By Rakshit Prabhakar  ~  3 months ago
          reply Reply

          Hi Natasha,

          As suggested, I have uploaded sample ppt under slides. Just a couple of them.

          Thank you for understanding.

          Regards

          Rakshit P

          • Natasha Rodrigues
            By Natasha Rodrigues  ~  3 months ago
            reply Reply

            Hi Rakshit,

            Thanks for the update. Will let you know if we require more details.

            Thanks,

            Natasha 

    • Rakshit Prabhakar
      By Rakshit Prabhakar  ~  3 months ago
      reply Reply

      Hi Natasha,

      Thank you. I will do as suggested and keep you posted on the same.

  • Vishal Gokhale
    By Vishal Gokhale  ~  3 months ago
    reply Reply

    HI Rakshit, 
    Thanks for the proposal. 
    For the program committee to get a better understanding, request you to please include following details in the proposal:

    • Details of the classification technique used.
    • Data sources and training methodologies used
    • Challenges encountered and solutions found. 

    Thanks,
    Vishal

    • Rakshit Prabhakar
      By Rakshit Prabhakar  ~  3 months ago
      reply Reply

      Hi Vishal,

      Thank you. I have updated it under Outline/Structure of Talk. I am taking a different approach here wherein , I would like to show the requirements or what is needed to the society and inspire the bright minds to fill the gap and develop such applications.

      Regards

      Rakshit P

  • Pradeep Hiremath
    By Pradeep Hiremath  ~  3 months ago
    reply Reply

    A great idea to help the persons in danger especially where the availability of the help is minimal. Drones are the future. With this technology sure one can minimis  like these aspects of the submission, and they should be retained:

    • ...

    I think the submission could be improved by:

    • ...
    • Rakshit Prabhakar
      By Rakshit Prabhakar  ~  3 months ago
      reply Reply

      Hi Pradeep,

      Thank you. I do agree with you. The use of AI for the better of humanity is the key here.

      Please do share your feedback on improvements, I would love to work on them.

  • Pankaj Jain
    By Pankaj Jain  ~  3 months ago
    reply Reply

    I like these aspects of the submission, and they should be retained: the thought process is unique. I see you have other concepts as well, will you share them too ?

    • ...

    I think the submission could be improved by: Too early to comment but this will build the base.

    • ...
    • Rakshit Prabhakar
      By Rakshit Prabhakar  ~  3 months ago
      reply Reply

      Hi Pankaj,

      Thank you. My aim is to introduce the concepts to the young curious participants, that way they try to be innovative. I will definetly share the links to or if time permits share it with everyone there. 

      Please do provide feedbacks. I would love to work on them.


  • Liked Amarjeet Dua
    keyboard_arrow_down

    Amarjeet Dua - Case Study: Fusing Machine Learning into Operations Research Techniques to solve Complex Optimization Problems

    20 Mins
    Experience Report
    Intermediate

    Machine Learning (ML) and Operations Research (OR) have co-existed for long. There have been amazing applications driven by ML and OR that we come across in our day-to-day lives. These applications range from matching algorithms on dating websites to solving large scale vehicle routing problems for complex supply chains. But, have you ever wondered what happens when these two areas of mathematical science come together to solve complex real-world optimization problems?

    Are you curious to know how OR-applications can benefit from the power of ML?

    In this talk, we’ll go through a real-world case study where we used the power of (ML+OR) to create significant dollar savings in the area of airline flight schedules. I will also take you through cases where ML can help OR solutions shine further to solve more generic problems.