How can we use Artificial Intelligence to work in a more efficient and ecological way ?

Wondering how we can use artificial intelligence to help incite better behaviour?
That's the purpose of our application! Using image recognition, the application will identify people's attitudes through image classifications. A database will then be used to match the classified images to a behavior: positive or negative for the environment. Our application uses both a supervised learning machine and can also be associated with an API that will allow to give a score to the people who want it. Thus, by using the "serious game" aspect, people can be encouraged to have better environmental behaviors in the company.

How does it work? How do you achieve this result?

First of all, what is artificial intelligence ?

" every aspect of learning or any other feature of intelligence can in principle be so precisely described that a machine can be made to simulate it. "
John Mc Carthy

Actually our application will use gesture recognition thanks to ml5: Pose net. We have severals parameters to cope with:
Video: VideoElement input to run poses on.
Type: A String value to run single or multiple estimation. Changes the detectionType property of the options. Default is multiple.
Callback: A function that is called when the model is loaded.
Captions:A object that contains properties that effect the posenet model accuracy, results, etc.

If you want to know how to code it here are a few example of code :

Here you can go to the ml5 Posenet page for more informations to code it. Pose Net

You can also use TensorFlow to complete the gesture recognition system by machine learning.It will uses Neural Network to train the model, the system will be more and more accurate thanks to training.
You have differents steps for training:
Training the neural network model requires the following steps:

1. Feed the training data to the model. In this example, the training data is in the train_images and train_labels arrays.
2. The model learns to associate images and labels.
3. You ask the model to make predictions about a test set—in this example, the test_images array.
4. Verify that the predictions match the labels from the test_labels array.

You'll need to feed the model:

And to evaluate accuracy:

Here you can go to the tensor net page for more informations to code it. Tensor Net