PROJECT HIGHLIGHTS

Long-term forecast for 6 months or more

High accuracy (over 95%)

Adjustability for any region of the world

Low resource using for neural network learning

SKILLS & TECHNOLOGIES

Using the most advanced technologies in programming neural networks and computer training based on past periods

Development
Design
Marketing
Testing
0
Days of Work
0
Specialists
0
Success test
0
Prototypes Done

SOME DETAILS

Neural Network Model for Carbon Emission Estimation Problem.

A multi-layer neuro chain structure is used to estimate the CO2 emission.

The neural network consists of a group of receptors, 4 hidden layers and one output neuron.

The group of receptors is supplied with a segment of historical CO2 emission data.

Each hidden layer of the neural network consists of n-neurons, each next layer is fully connected with the following one.

The function of activating hidden blocks ensures non-linearity of the network.

The network was trained by using the Back Propagation (BP) algorithm.

The output layer consists of one output neuron which is producing an appropriate

CO2 emissions.

The node of the output level has a sigmoidal activation function.