5 research outputs found
Machine learning algorithms for stratigraphy classification on uranium deposits
No full textMachine learning today becomes more and more effective instrument to solve many particular problems, where there are difficulties to apply well known and described math model. In other words - it is a great tool to describe non-linear phenomena. We tried to use this technique to improve existing process of stratigraphy, and reduce costs on site by applying computer leaded predictions on the basis of existing on-field collected data. Article describes usage of machine learning algorithms for stratigraphy boundaries classification based on geophysics logging data for uranium deposit in Kazakhstan. Correct marking of stratigraphy from geophysics logging data is complex non-linear task. To solve this task we applied several algorithms of machine learning: random forest, logistic regression, gradient boosting, k nearest neighbour and XGBoost
Optimization of people evacuation plans on the basis of wireless sensor networks
No full textThis paper introduces the optimization process for people salvation in critical situations by organizing their evacuation plan from enclosed areas using modern approaches of data acquisition on the basis of wireless sensor networks. The proposed technology allows the ability to gather information about people density on the surveyed area by the usage of wireless sensor networks, consistently covering the enclosed territory. It enables the update of the evacuation plan on the basis of people density information inside the enclosed areas online. It is proposed to use common video surveillance cameras as sensors. The advantage of visual surveillance using cameras is that it does not require additional technological equipment for the area and much more important does not impose rules and restriction on the surveillance objects (people in this case). Next tasks are to be solved: creation of mathematical model of optimal enclosed area surveillance by wireless sensors, database and data interrogation modelling of wireless sensor network, creation of algorithmic model for automated people counting using video signal for the covering area; creation of dynamic people evacuation model on the basis of maximum flow problem [1, 2]
Theoretical assumptions for saving energy of electrical heating water in the solar collector – battery
No full textIn this article a theoretical assumptions in the energy saving energy source of the solar collector – accumulator is presented. One of the main features of the solar collector - accumulator is the electric hot water in a cold season, or in night days of a sun radiation. The experiments showed that conventional thermoelectric welding device, which is based on conventional power factor could be used to control a temperature of the nozzle from the initial temperature..
