Approximately 80% of the people across globe do not use gym, yet they pay $30 to $125/month.Attrition from gym is linked with discouraging results and lack of engagement. Traditional gym users don’t know proper exercise regimen and users prefer workout regimens that are fun, customizable and social.

To combat above problem, we came up with idea to provide customized fitness solutions using Artificial Intelligence. In this talk, we showcase how we can leverage Deep Learning based Architectures like CNN to develop "Workout pose detection" that tracks user movement and classify it corresponding to specific trained workout and will determine whether the performed pose is correct or wrong.


Keywords: CNN, Deep Learning, Image classification Model, Computer Vision.

 
 

Outline/Structure of the Talk

1) What, why, Application
2) Dataset Discussion
3) Model Training
4) Model Comparison
5) Result
6) Challenges and Future Scope

Learning Outcome

1) Candidate will get understanding of product development related to computer vision

2) End to end understanding of applied data Science

3) concepts related to computer vision

4) Comparision of Deep Learning Architectures with different hyper-parameters.

5) working example of usage of Deep learning architecture like CNN in real life.

Target Audience

Data Scientist, Deep Learning Enthusiast, Student, computer vision practicioner, Managers

Prerequisites for Attendees

1) Basic Idea of Neural Network

2) Interest in Deep Learning, computer vision

schedule Submitted 7 months ago

Public Feedback

comment Suggest improvements to the Speaker
  • Kuldeep Jiwani
    By Kuldeep Jiwani  ~  7 months ago
    reply Reply

    Hi Aakash,

    Good to see that you have picked an interesting and useful application of DL.

    For the purpose of Conference it would be good to know what kind of knowledge you will be sharing with the audience. Are you planning to share some Computer Vision concepts on how the image feature changes due to angle of camera, position, etc. ?

    Then besides just showing the use of DL are you also planning to show visual images of what did the intermediate layers of convolutional network captured in your application. Then in the slides you have tested 4 models and chosen 1. Can you also provide some information besides accuracy to explain why the other convnets were not performing well may be by showcasing intermediate CNN outputs to or by some other means.

    • Aakash Goel
      By Aakash Goel  ~  7 months ago
      reply Reply

      Hi Kuldeep,

      We are glad that you have shown interest in proposal. Please find below reply:

      1) Knowledge sharing will be on:

      a) Image Pre-processing - Person Extraction from Frame
      b) Image Augmentation (How to deal with the image classification challenges like angle of camera, different position)
      c) Model - CNN, Hyper-parameter tuning in CNN

      2) Our model selection criteria was only based on accuracy and categorical cross entropy loss. The idea was to select the best model based on accuracy and not focussing on why the model failed to deliver good results.Though we will cover why our models failed at the first stage and what steps we covered to improve accuracy.

       

      Please do let us know if we haven't answered your question or any other suggestion.

       

      Thanks

      Aakash Goel

       

  • Manish
    By Manish  ~  7 months ago
    reply Reply
    Sound interesting. Looking forward for your talk.
    • Aakash Goel
      By Aakash Goel  ~  7 months ago
      reply Reply

      Thanks Manish for showing interest. Yes, it is indeed going to be very exciting.


  • Liked Venkatraman J
    keyboard_arrow_down

    Venkatraman J - Entity Co-occurence and Entity Reputation scoring from Unstructured data using Semantic Knowledge graph

    Venkatraman J
    Venkatraman J
    Sr. data Software engineer
    Metapack
    schedule 8 months ago
    Sold Out!
    20 Mins
    Talk
    Intermediate

    Knowledge representation has been a research for many years in AI world and its continuing further too. Once knowledge is represented, reasoning from that extracted knowledge is done by various inferencing techniques. Initial knowledge bases were built using rules from domain experts and different inferencing techniques like Fuzzy inference, Bayesian inference were applied to extract reasoning from those knowledge bases. Semantic networks is another form of knowledge representation which can represent structured data like WordNet, DBpedia which solves problems in a specific domain by storing entities and relations among entities using onotologies.

    Knowledge graph is another representation technique deeply researched in academia as well as used by businesses in production to augment search relevancy in information retrieval(Google knowledgegraph), improve recommender systems, semantic search applications and also Question answering problems.In this talk i will illustrate the benefits of semantic knowledge graph, how it differs from Semantic ontologies, different technologies involved in building knowledge graph, how i built one to analyse unstructured (twitter data) to discover hidden relationships from the twitter corpus. I will also show how Knowledge graph is data scientist's tool kit to discover hidden relationships and insights from unstructured data quickly.

    In this talk i will show the technology and architecture used to determine entity reputation and entity co-occurence using Knowledge graph.Scoring an entity for reputation is useful in many Natural language processing tasks and applications such as Recommender systems.

  • 45 Mins
    Talk
    Beginner

    Today more than 3 billion people are using social media and using it as a medium to express their real feelings which makes different social media platform like Facebook, Twitter etc. an ideal source for capturing interest of users. Obviously, data mined from social media alone cannot be used to achieve target i.e. predict user's Interest, it needs some form of supervision.
    Our talk propose how Semantic web a.k.a Knowledge bases add supervision into system and can prove helpful to predict user's Interest given social media data. Once, User's Interest is captured, it can be widely used for many purposes like Recommendation system, campaigning, analytics over user interests etc.

    Keywords: Knowledge systems, linked data, OpenIE, NLP, Semantic Web, User Interest, SPARQL.