Big data mining laboratory – Институт информационных и вычислительных технологий

Head of the laboratory Dr.Eng.Sc.,

associate prof. Pak А.А.

Purpose of the laboratory:

– Research of scientific methods of analysis and processing of big data, namely, the improvement and application of methods for searching and extracting new knowledge and patterns that are not available before processing and analyzing traditional algorithms.

The main tasks of the laboratory are:

Application of machine learning elements in designing an information system of selecting recommendations for clients;
Development of a corporate database for the integrated information structure of specialized systems (environmental and other systems);
Design, operation and development of software for high-performance computing systems, computing clusters and supercomputers;
Expansion of experimental and production sites of computational experiments using a supercomputer (KazNU, KazNTU, etc.).

The main areas of scientific activity of the laboratory:

Data Mining methods;
Mixing and integration of data;
Application of machine learning;
Predictive analytics.

The “Big Data” systems are widely used in various spheres of human activity in the field of:

Marketing;
Retail trade;
Internet advertising;
Search Engines;
Social networks;
Mobile connection;
Information systems of various purposes;
Information security.

Obtained results

A complex of information and logistics models and methods of transportation management has been developed. A spatial-network database was developed on the basis of a graph model in the transport system for efficient planning and management of transportation and modeling of road maps.

The information system of the soil restoration process of contaminated with xenobiotics has been designed. A corporate database has been developed that contains information on pesticide-contaminated territories, the amount of obsolete pesticides in these territories and the level of soil con-tamination with organochlorine pesticides.