Abdulla Muradov

It is the final project of my master studies in “Gisma University of Applied Sciencesl” that contains a study on actual industrial problem that involves Data Science, Software Engineering and Management. According to factors that were analysed using previous research literature the questionary which will help to distinguish certain factors in technological adoption. After creation of questionary the data was collected by the help of survey. Afterwards all necessary data was collected and it was analysed using Structural equation modelling (SEM) technique. Since most of the data that were extracted are latent variables, I decided to use SEM. According to the results analysis, discussion and conclusions were made.

• • To predict energy consumption in France for future years and thus know the required energy production at the national level and at the departmental level. This information can minimize the risk of a black out. All renewable and non-renewable energy sources were taken into consideration during this project. Also temperature data set was considered to better predict based on the weather readings.
    
    The volume of energy data was 1,980,288 rows and 32 columns. Temperature dataset had 36,712 rows and 7 columns.
    
    We used Python, Matplotlib, Seaborn, Machine Learning during its courseTo predict energy consumption in France for future years and thus know the required energy production at the national level and at the departmental level. This information can minimize the risk of a black out. All renewable and non-renewable energy sources were taken into consideration during this project. Also temperature data set was considered to better predict based on the weather readings. The volume of energy data was 1,980,288 rows and 32 columns. Temperature dataset had 36,712 rows and 7 columns. We used Python, Matplotlib, Seaborn, Machine Learning during its course

The heart plays a critical role in maintaining the body's circulatory system. In a healthy heart, oxygen-rich blood is pumped from the left ventricle through the body, supplying oxygen and nutrients to the organs. After nourishing the organs, oxygen-poor blood returns to the right side of the heart, where it is carried to the lungs for reoxygenation. This reoxygenated blood is then pumped back into the body through the left ventricle.

Heart failure, characterized by the weakening of the heart's pumping function, can affect either the right side (right heart failure) or the left side (left heart failure) of the heart. In advanced stages, both sides can be impacted, resulting in global heart failure. Heart failure can be either chronic or acute, with chronic heart failure being more prevalent than the sudden onset of acute heart failure. Acute heart failure often occurs in the context of acute cardiovascular events and decompensation of existing heart conditions. Cardiovascular disease is the leading cause of death globally, responsible for approximately 17.9 million deaths annually, accounting for 31% of all deaths worldwide.The primary objective of this project was to analyze heart failure data to identify significant patterns and predictors using advanced machine learning techniques. The goal was to leverage these insights for better diagnosis, prognosis, and treatment planning in clinical settings. The study focused on Catboost, a high-performance gradient boosting algorithm, known for its effectiveness with categorical data.

This project utilized Catboost to analyze a dataset related to heart failure. Catboost is particularly well-suited for this task due to its capability to handle categorical features and its robustness in dealing with diverse types of data. The analysis aimed to evaluate the algorithm’s performance based on various metrics and to compare it with other machine learning methods.

The primary objective of this project was to explore and compare the latest methods for solving text classification problems. By identifying trends and selecting the best algorithms, the study aims to enhance research and commercial applications. The focus was on machine learning techniques, evaluating their properties to choose the most suitable classification method.

This project analyzed various text classification algorithms, with a particular emphasis on the Backpropagation Neural Network (BPNN). The survey conducted spanned from 2011 to 2016, based on highly regarded scientific publications. The comparison included several characteristics such as precision, recall, execution time, incremental mode capabilities, required background information, and language independence.