Research of the applicability of machine learning methods for assessment of departments’ performance

2021 ◽  
pp. 41-51
Author(s):  
A. R. Mukanova ◽  
Sh. A. Otsokov
Keyword(s):  
Machine Learning ◽  
Performance Indicators ◽  
Research University ◽  
Educational Organizations ◽  
University Staff ◽  
Machine Learning Methods ◽  
Efqm Model ◽  
University Department ◽  
Python Programming ◽  
Engineering Institute

Currently, a number of educational organizations in Russia and abroad, including the National Research University “Moscow Power Engineering Institute” (MPEI), are introducing the European improvement model EFQM, designed to analyze and improve the educational, scientific and other activities of the departments. In accordance with this model, each university department is assigned a score equal to the sum of points for two groups of criteria: criteria from the group of opportunities and criteria from the group of results. To obtain such assessments, a commission consisting of external experts, EFQM assessors and university staff meets with heads of departments. Based on the results of the discussion of the results of the meetings, the commission determines the score and rating of the departments in accordance with the EFQM model.The purpose of the work presented in the article is to study the possibility of using machine learning to simplify the work of experts in terms of obtaining estimates according to criteria from a group of results.The article proposes a system for evaluating the activities of departments according to criteria from a group of results based on machine learning. A program in the Python programming language has been developed, which evaluates the activities of departments according to these criteria for each department of the MPEI. The program receives the initial data for such assessments from the monitoring system of key performance indicators implemented in MPEI.

Machine Learning Made Easy: A Review of Scikit-learn Package in Python Programming Language

2019 ◽  
Vol 44 (3) ◽  
pp. 348-361 ◽  
Author(s):  
Jiangang Hao ◽  
Tin Kam Ho
Keyword(s):  
Machine Learning ◽  
Programming Languages ◽  
Programming Language ◽  
Data Science ◽  
Machine Learning Algorithms ◽  
The Past ◽  
Machine Learning Methods ◽  
Python Programming Language ◽  
And Behavior ◽  
Python Programming

Machine learning is a popular topic in data analysis and modeling. Many different machine learning algorithms have been developed and implemented in a variety of programming languages over the past 20 years. In this article, we first provide an overview of machine learning and clarify its difference from statistical inference. Then, we review Scikit-learn, a machine learning package in the Python programming language that is widely used in data science. The Scikit-learn package includes implementations of a comprehensive list of machine learning methods under unified data and modeling procedure conventions, making it a convenient toolkit for educational and behavior statisticians.

Machine learning for the extragalactic astronomy educational manual

2019 ◽  
Vol 15 (S367) ◽  
pp. 461-463
Author(s):  
Maksym Vasylenko ◽  
Daria Dobrycheva
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Programming Language ◽  
Supervised Machine Learning ◽  
Support Vector ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Python Programming Language ◽  
Python Programming

AbstractWe evaluated a new approach to the automated morphological classification of large galaxy samples based on the supervised machine learning techniques (Naive Bayes, Random Forest, Support Vector Machine, Logistic Regression, and k-Nearest Neighbours) and Deep Learning using the Python programming language. A representative sample of ∼315000 SDSS DR9 galaxies at z < 0.1 and stellar magnitudes r < 17.7m was considered as a target sample of galaxies with indeterminate morphological types. Classical machine learning methods were used to binary morphologically classification of galaxies into early and late types (96.4% with Support Vector Machine). Deep machine learning methods were used to classify images of galaxies into five visual types (completely rounded, rounded in-between, smooth cigar-shaped, edge-on, and spiral) with the Xception architecture (94% accuracy for four classes and 88% for cigar-like galaxies). These results created a basis for educational manual on the processing of large data sets in the Python programming language, which is intended for students of the Ukrainian universities.

scholarly journals Features of the educational program «Nanotechnologies and nanomaterials in energy»: machine learning

2022 ◽  
Vol 2150 (1) ◽  
pp. 012031
Author(s):  
D. D. Babenko ◽  
A. S. Dmitriev ◽  
P.G. Makarov ◽  
I.A. Mikhailova
Keyword(s):  
Machine Learning ◽  
Educational Program ◽  
Research University ◽  
Educational Programs ◽  
Green Energy ◽  
Machine Learning Methods ◽  
Research And Innovation ◽  
The World ◽  
Analysis And Synthesis ◽  
Design Options

Abstract The results of the development of new educational programs in the field of nanotechnology and nanomaterials in the energy sector, which have been developed and are actively used by the National Research University “MPEI”, are presented. Modern nanomaterials and nanotechnological processes in traditional and alternative (“green”) energy require new approaches, including statistical methods for the analysis and synthesis of experimental data and design options. For this reason, without the active use of machine learning methods, it is impossible to train qualified specialists in the field of promising energy problems and their solutions. Through teaching, research, and innovation, «MPEI» exceptional community pursues its mission of service to the nation and the world.

Expert survey and analysis of the results

2019 ◽  
Vol 85 (7) ◽  
pp. 73-82
Author(s):  
Vladimir O. Tolcheev
Keyword(s):  
Data Analysis ◽  
Research University ◽  
Statistical Processing ◽  
Educational Process ◽  
Expert Survey ◽  
Educational Modules ◽  
Training Modules ◽  
Engineering Institute ◽  
Good Agreement ◽  
Statistical Criteria

The issues of organizing an expert survey and carrying out statistical processing and analysis of the results are considered. The experts are the fifth-year students undergoing training at the Department of Management and Informatics «Moscow Power Engineering Institute» of the National Research University. The goal of the survey is revealing the disciplines that are most useful for employment in their specialty. We discuss the special features of the survey and a concept of «work in the specialty», with due regard for statistical reliability of the results. Data of written questionnaire gained in 2018 were processed and analyzed using cluster analysis (construction of dendrograms and application of the K-means method) and non-parametric statistical criteria (Friedman and Mann – Whitney – Wilcoxon). Data processing is implemented in the program STATISTICA. The analysis is carried out to reveal significant differences between the educational courses and assess the degree of consistency of the respondents to divide them into clusters that unite the students with similar judgments. Data analysis revealed that experts’ estimates in 2018 are in fairly good agreement with the estimates of previous studies; among the respondents there are three coalitions corresponding to the training modules «Software», «Management Theory», «Data Analysis»; the overall consistency of students in the two groups is very low (and, on the contrary, high in the identified clusters); grades are homogeneous and do not depend on training groups (and employment – unemployment of the respondents). The obtained results allow us to address a number of important questions regarding the ways of improving the educational process, e.g., to optimize yearly course hours for different educational modules.

Utilizing Blockchain Technology in Social Media Bot Identification

2020 ◽  
Author(s):  
Shreya Reddy ◽  
Lisa Ewen ◽  
Pankti Patel ◽  
Prerak Patel ◽  
Ankit Kundal ◽  
...  
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Gold Standard ◽  
The Internet ◽  
Learning Models ◽  
Current Time ◽  
Machine Learning Methods ◽  
Blockchain Technology ◽  
Modern Age ◽  
Machine Learning Models

<p>As bots become more prevalent and smarter in the modern age of the internet, it becomes ever more important that they be identified and removed. Recent research has dictated that machine learning methods are accurate and the gold standard of bot identification on social media. Unfortunately, machine learning models do not come without their negative aspects such as lengthy training times, difficult feature selection, and overwhelming pre-processing tasks. To overcome these difficulties, we are proposing a blockchain framework for bot identification. At the current time, it is unknown how this method will perform, but it serves to prove the existence of an overwhelming gap of research under this area.<i></i></p>

Sign in / Sign up

Export Citation Format

Share Document