Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.13091/5943
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Çolak, Andaç Batur | en_US |
dc.contributor.author | Horasan, Bilgehan Yabgu | en_US |
dc.contributor.author | Öztürk, Alican | en_US |
dc.contributor.author | Bayrak, Mustafa | en_US |
dc.date.accessioned | 2024-07-26T11:03:38Z | - |
dc.date.available | 2024-07-26T11:03:38Z | - |
dc.date.issued | 2023 | en_US |
dc.identifier.uri | https://hdl.handle.net/20.500.13091/5943 | - |
dc.description.abstract | As part of this research, the Ladik-Sarayönü area of Konya province’s air quality has been assessed utilizing an AI (Artifcial Intelligence) method. A total of 103 feld samples were analyzed experimentally. Data from experiments was used to inform the design of a multi-layer perceptron feed-forward back-propagation artifcial neural network model. The Bayesian method has been employed as the training procedure in an artifcial neural network model with 15 neurons in its hidden layer. One hundred experimental data points were used to develop a network model that predicts mercury values of the geoaccumulation index value in the output layer based on the following input variables: mercury, distance to the pollution source, source of pollution, characteristics of the sampled place and the primary factor that controls moving parameters. The majority (90%) of the data is used for the model’s training process, while the remaining (10%) is used for validation. By comparing the model’s anticipated outcomes with experimental data, an artifcial neural network was used to evaluate the model’s prediction performance. To forecast mercury values of the geoaccumulation index, the created artifcial neural network had an error rate of−4.04 to 3.98% (with an average of−0.58%). The MSE for the network model is 2.1× 10−1, and the R value is 0.9533. | en_US |
dc.language.iso | en | en_US |
dc.relation.ispartof | Arabian Journal of Geosciences | en_US |
dc.rights | info:eu-repo/semantics/closedAccess | en_US |
dc.subject | Heavy Metal | en_US |
dc.subject | Mercury | en_US |
dc.subject | Artifcial Neural Network | en_US |
dc.subject | Bayesian Algorithm | en_US |
dc.subject | Konya | en_US |
dc.title | An Example of Artificial Neural Networks Modeling the Distribution of Mercury (Hg), Which Poses a Risk to Human Health in the Selection of Settlements: Sarayönü (Türkiye) | en_US |
dc.type | Article | en_US |
dc.relation.issn | 1866-7511 | en_US |
dc.description.startpage | 1 | en_US |
dc.description.endpage | 12 | en_US |
dc.department | Fakülteler, Mühendislik ve Doğa Bilimleri Fakültesi, Jeoloji Mühendisliği Bölümü | en_US |
dc.authorid | 0000-0003-2748-6322 | en_US |
dc.institutionauthor | Öztürk, Alican | en_US |
dc.relation.publicationcategory | Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı | en_US |
item.fulltext | With Fulltext | - |
item.openairetype | Article | - |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
item.languageiso639-1 | en | - |
item.cerifentitytype | Publications | - |
item.grantfulltext | open | - |
crisitem.author.dept | 02.07. Department of Geological Engineering | - |
Appears in Collections: | Mühendislik ve Doğa Bilimleri Fakültesi Koleksiyonu |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
s12517-023-11355-81.pdf | 1.93 MB | Adobe PDF | View/Open |
CORE Recommender
Page view(s)
20
checked on Aug 26, 2024
Download(s)
12
checked on Aug 26, 2024
Google ScholarTM
Check
Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.