NOESYS-AI Regression

The following figure demonstrates the Data Analysis & Predictions process of NOESYS software. Following a vast amount of studies, we developed a generic software environment, capable to analyze any database, composed by continuous variables. Data preparation and Pre-Processing is an important stage, aiming to understand the basic structure of the data, detect the outliers, reveal the distribution of the variables and their inter-relationships. We utilize a variety of methods in order to validate the results and focus on the conceptual interpretation, though Sensitivity Analysis. The prediction models are generated into an executable programme and mathematical formula in MS Excel.


Related Projects and Publications

Real Estate Mass Appraisals

Real Estate Mass Appraisals

A recent scientometric study by DImopoulos and Bakas (2018), on the relevant to Mass Appraisals and Property Valuations literature, revealed a transformation from traditional statistics to more complex numerical models, computational procedures, and automated methods, from the field of Artificial Intelligence ...
Sensitivity Analysis of Workplace Related Risks

Sensitivity Analysis of Workplace Related Risks

In this work, presented in the Employability21 Conference, we implemented Machine Learning Algorithms, to analyze the Employee Experience Feedback. In the current, post-crisis period in Greece, after a long period of uncertainty under continuous and stressful change, both governmental & ...
Statistical analyses for the ECO-Cement Research Project

Statistical analyses for the ECO-Cement Research Project

Eco-Cement is a new proposed material for the construction industry that uses waste products of multiple industries in its manufacture. It is a composite material of bacteria, urea, calcium carbonate, cement kiln dust, a hydraulic agent, and sand. Through numerical simulations, ...
Artificial Neural Networks for the Assessment of Structural Response

Artificial Neural Networks for the Assessment of Structural Response

The following video highlights the procedure utilized in the work of Bakas, Makridakis and Papadrakakis, Torsional parameters importance in the structural response of multiscale asymmetric-plan buildings.  This work’s approach constitutes the creation and utilization of a large database of multiscale ...
Publications

Publications

Our scientific publications on Computational Methods, Mechanical Learning & Artificial Intelligence are reported in the following list. They cover a variety of applications, in engineering, medicine, business, new materials and computer systems. Nikolaos P. Bakas: Numerical solution for the extrapolation ...