Machine learning methods in systems forecasting forest fires
Jazyk: | ruština |
---|---|
Rok vydání: | 2022 |
Předmět: | |
DOI: | 10.18720/spbpu/3/2022/vr/vr22-2771 |
Popis: | Тема вÑпÑÑкной квалиÑикаÑионной ÑабоÑÑ: «ÐеÑÐ¾Ð´Ñ Ð¼Ð°Ñинного обÑÑÐµÐ½Ð¸Ñ Ð² ÑиÑÑÐµÐ¼Ð°Ñ Ð¿ÑогнозиÑÐ¾Ð²Ð°Ð½Ð¸Ñ Ð»ÐµÑнÑÑ Ð¿Ð¾Ð¶Ð°Ñов». ÐÐ°Ð½Ð½Ð°Ñ ÑабоÑа поÑвÑÑена Ð°Ð½Ð°Ð»Ð¸Ð·Ñ Ð¿ÑÐ¸Ð¼ÐµÐ½ÐµÐ½Ð¸Ñ Ð¼ÐµÑодов маÑинного обÑÑÐµÐ½Ð¸Ñ Ð² обÑабоÑке даннÑÑ Ð¾ леÑнÑÑ Ð¿Ð¾Ð¶Ð°ÑÐ°Ñ Ð² паÑке ÐонÑеÑинÑо. Ð Ñ Ð¾Ð´Ðµ ÑабоÑÑ ÑеÑалиÑÑ ÑледÑÑÑие задаÑи:- ÐзÑÑение пÑедмеÑной облаÑÑи по ÑемаÑике влиÑÐ½Ð¸Ñ Ð»ÐµÑнÑÑ Ð¿Ð¾Ð¶Ð°Ñов на ÑовÑеменнÑÑ Ð¶Ð¸Ð·Ð½Ñ Ñеловека.- Ðнализ и обÑабоÑка Ð²Ñ Ð¾Ð´Ð½ÑÑ Ð´Ð°Ð½Ð½ÑÑ . - РеализаÑÐ¸Ñ Ð¼Ð¾Ð´ÐµÐ»ÐµÐ¹ меÑодов маÑинного обÑÑениÑ.- ÐÑименение ÑазлиÑнÑÑ Ð¼ÐµÑодов обÑÑÐµÐ½Ð¸Ñ Ð´Ð»Ñ Ð½ÐµÑколÑÐºÐ¸Ñ Ð²Ð°ÑианÑов обÑабоÑаннÑÑ Ð´Ð°Ð½Ð½ÑÑ .- Ðнализ ÑезÑлÑÑаÑов ÑоÑноÑÑи, полÑÑеннÑÑ Ð² ÑезÑлÑÑаÑе обÑÑÐµÐ½Ð¸Ñ .Ð ÑезÑлÑÑаÑе бÑло полÑÑена пÑогÑамма, позволÑÑÑÐ°Ñ Ð¿ÑоводиÑÑ Ð°Ð½Ð°Ð»Ð¸Ð· неÑколÑÐºÐ¸Ñ Ð°Ð»Ð³Ð¾ÑиÑмов бинаÑной клаÑÑиÑикаÑии пÑи ÑазлиÑнÑÑ Ð¿Ð°ÑамеÑÑÐ°Ñ Ð¾Ð±ÑабоÑки даннÑÑ Ñ Ð¸ÑполÑзованием пÑедоÑÑавленного набоÑа даннÑÑ . Topic of the final qualification work: "Methods of machine learning in forest fire forecasting systems". This work is devoted to the analysis of the application of machine learning methods in the processing of data on forest fires in Montesigno Park. During the work the following tasks were solved:- Study of the subject area on the subject of the impact of forest fires on modern human life.- Analysis and processing of input data. - Implementation of models of machine learning methods.- Application of various training methods for several variants of the processed data.- Analysis of accuracy results obtained as a result of training. As a result, a program was obtained that allows the analysis of several binary classification algorithms with various data processing parameters using the provided data set. |
Databáze: | OpenAIRE |
Externí odkaz: |