Welcome to SCEnAT 4.0

SCenAT 4.0

AI & ML

SCEnAT 4.0 AI & ML is a prediction experiencer powered by Microsoft AI on Azure. SCEnAT 4.0 provides a range of resource sustainability prediction capabilities using Microsoft Azure Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) cognitive services. The benefit of machine learning are the predictions and the models that make predictions. We followed a five steps process for this analysis; Problem definition, Data preparation, Spot-check algorithms, ML model evaluation and Deployment of results.

Instructions:

In order to test this tool, you need to click in one of the below experiments, and then you will need to log in with a Microsoft account. Inside you will find a request/response data collection form where you will be able to provide data from the below links. Every time you enter the set of  values into the request form you are helping to train these models to improve the accuracy of their results. For the Sustainable Development Goals experiment you need to provide or upload  images of countries (maps) in formats jpg, png, bmp or image URL.

Go to Global Innovation Score

Global Innovation Score

By taking into account the current and the annual GDP growth from the World Data Bank database, we are trying to predict what would be the next country innovation score. In this case, we are using Machine Learning trough a linear regression algorithm.

Go to WBD Population Growth %

WBD Population Growth %

By considering datasets from the World Bank Data; Total Population, Life expectancy and Energy Use Kg oil pp we are predicting the potential population Growth % in the main Economic and Geographical regions of the World. In this case, we are using Machine Learning trough a linear regression algorithm.

Go to SUSTAINABLE DEVELOPMENT GOALS

SUSTAINABLE DEVELOPMENT GOALS

Based on images of countries boundaries and by using cognitive services for image recognition (deep learning), we can identify their potential performance in terms of Sustainable Development Goals (SDG).

Links for the Global Innovation Score experiment: https://www.globalinnovationindex.org/analysis-indicatorGDP (current US$), GDP growth (annual %)

Links for the WBD Population Growth experiment: Population, total, Population growth (annual %) range of values for population growth % (Ave; 1.77, Max; 19.59, Min; -10.00) Energy use (kg of oil equivalent per capita) range of values for energy use Kg (Ave; 1114.7, Max; 40710.0, Min; 10.00) Life expectancy at birth, total (years) range of values for Life expectancy (Ave; 55.47, Max; 85.41, Min; 18.90)

Results Interpretation:

In the Global Innovation Score experiment, the Scored Labels numbers are the result of the trained machine-learning model and they represent the predicted next score for each country. In the WBD Regional Population growth experiment experiment, the Scored Labels numbers are the result of the trained machine-learning model and they represent the predicted population growth in % for each country. Finally, for the sustainable development goal experiment, the image/maps result will display the potential performance of each country.

AI + Machine Learning Procedures

About this tool

SCEnAT 4.0

This is a pilot version of SCEnAT 4.0, which has been created as a platform to incorporate Artificial Intelligence in the analysis of Social Science Studies.

  • Machine Learning and Cognitive Services

SCEnAT Product Suits

Welcome to SCEnAT 4.0

wpChatIcon