2021
DOI: 10.31590/ejosat.1014106
|View full text |Cite
|
Sign up to set email alerts
|

Derin Öğrenme ve İstatistiksel Modelleme Yöntemiyle Sıcaklık Tahmini ve Karşılaştırılması

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(3 citation statements)
references
References 11 publications
(5 reference statements)
0
3
0
Order By: Relevance
“…The R 2 value expresses the relationship between actual values and predicted values. The R 2 value takes a value between 0-1, and the closer this value is to 1, the more accurate and sensitive the model becomes [37]. For this reason, the R 2 value was used in this study.…”
Section: Data Set and Feature Selection (Veri Seti Vementioning
confidence: 99%
“…The R 2 value expresses the relationship between actual values and predicted values. The R 2 value takes a value between 0-1, and the closer this value is to 1, the more accurate and sensitive the model becomes [37]. For this reason, the R 2 value was used in this study.…”
Section: Data Set and Feature Selection (Veri Seti Vementioning
confidence: 99%
“…The results are compared using the mean squared error (MSE) metric, and the ANN (MSE = 3.46) method shows the best performance. Sevinç and Kaya estimated the monthly average temperature using LSTM and ARIMA models on the meteorological data of Solhan district of Bingöl province, located in the Eastern Anatolia Region of Turkey, between 2014 and 2020 [11]. The R square score of the selected model was calculated as 0.95 in the LSTM model and 0.97 in the ARIMA model.…”
Section: Literature Reviewmentioning
confidence: 99%
“…SVR makes adjustments to fit the best curve to the data set. To train this model, the optimization problem in Equation (8) needs to be solved according to the constraints given in Equation ( 9)- (11). While making this correction, the error term specified as the maximum error and indicated by the epsilon (ε) value is computed.…”
Section: Support Vector Regression (Svr)mentioning
confidence: 99%