Wyniki wyszukiwania - Biblioteka Nauki

Ten serwis zostanie wyłączony 2025-02-11.

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Rotation-Gamma Correction augmentation on CNN-Dense block for soil image classification

100%

Maiyanti S. I. , Desiani A. , Lamin S. , Puspitashati , Arhami M. , Gofar N. , Cahyana D.

tom Vol. 19, no 3

96--115

Soil is a solid particle that covers the surface of the earth. Soil can be classified based on its color because the color indicates the nature and condition of the soil. CNN works well for image classification, but it requires large amounts of data. Augmentation is a technique to increase the amount of training data with various transformation techniques to the existing data. Rotation and Gamma Correction can be used simply as an augmentation technique and can reproduce an image with as many image variations as desired from the original image. CNN architecture has a convolution layer and Dense block has dense layers. The addition of Dense blocks to CNN aims to overcome underfitting and overfitting problems. This study proposes a combination of Augmentation and classification. In augmentation, a combination of rotation and Gamma correction techniques is used to reproduce image data. The CNN-Dense block is applied for classification. The soil image classification is grouped based on 5 labels black soil, cinder soil, laterite soil, peat soil, and yellow soil. The performances of the proposed method provide excellent results, where accuracy, precision, recall, and F1-Score performances are above 90%. It can be concluded that the combination of rotation and Gamma Correction as augmentation techniques and CNN-Dense blocks is powerful for use in soil image classification.

Modelling and dynamic water analysis for the ecosystem service in the Central Citarum watershed, Indonesia

84%

Suryanta J. , Nahib I. , Ramadhani F. , Rifaie F. , Suwedi N. , Karolinoerita V. , Cahyana D. , Amhar F. , Suprajaka

Journal of Water and Land Development

2024

tom no. 60

122--137

Exploring the drivers of changes in ecosystem services is crucial to maintain ecosystem functionality, especially in the diverse Central Citarum watershed. This study utilises the integrated valuation of ecosystem service and trade-offs (InVEST) model and multiscale geographically weighted regression (MGWR) model to examine ecosystem services patterns from 2006 to 2018. The InVEST is a hydrological model to calculate water availability and evaluate benefits provided by nature through simulating alterations in the amount of water yields driven by land use/cover changes. Economic, topographic, climate, and vegetation factors are considered, with an emphasis on their essential components. The presence of a geographical link between dependent and explanatory variables was investigated using a multiscale geographic weighted regression model. The MGWR model is employed to analyse spatial impacts. The integration of both models simplified the process and enhanced its understanding. The findings reveal the following patterns: 1) decreasing land cover and increasing ecosystem services demand in the watershed, along with a decline in water yield, e.g. certain sub-districts encounter water scarcity, while others have abundant water resources; 2) the impact of natural factors on water yield shifts along vegetation > climate > topography (2006) changes to climate > vegetation > topography (2018).