Trophic state assessment using hybrid classification tree-artificial neural network
The trophic state is one of the significant environmental impacts that must be monitored and controlled in any aquatic environment. This phenomenon due to nutrient imbalance in water strengthened with global warming, inhibits the natural system to progress. With eutrophication, the mass of algae in...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitas Ahmad Dahlan
2020-03-01
|
| Series: | IJAIN (International Journal of Advances in Intelligent Informatics) |
| Subjects: | |
| Online Access: | http://ijain.org/index.php/IJAIN/article/view/408 |
| _version_ | 1819103763268370432 |
|---|---|
| author | Ronnie Sabino Concepcion II Pocholo James Mission Loresco Rhen Anjerome Rañola Bedruz Elmer Pamisa Dadios Sandy Cruz Lauguico Edwin Sybingco |
| author_facet | Ronnie Sabino Concepcion II Pocholo James Mission Loresco Rhen Anjerome Rañola Bedruz Elmer Pamisa Dadios Sandy Cruz Lauguico Edwin Sybingco |
| author_sort | Ronnie Sabino Concepcion II |
| collection | DOAJ |
| description | The trophic state is one of the significant environmental impacts that must be monitored and controlled in any aquatic environment. This phenomenon due to nutrient imbalance in water strengthened with global warming, inhibits the natural system to progress. With eutrophication, the mass of algae in the water surface increases and results to lower dissolved oxygen in the water that is essential for fishes. Numerous limnological and physical features affect the trophic state and thus require extensive analysis to asses it. This paper proposed a model of hybrid classification tree-artificial neural network (CT-ANN) to assess the trophic state based on the selected significant features. The classification tree was used as a multidimensional reduction technique for feature selection, which eliminates eight original features. The remaining predictors having high impacts are chlorophyll-a, phosphorus and Secchi depth. The two-layer ANN with 20 artificial neurons was constructed to assess the trophic state of input features. The neural network was modeled based on the key parameters of learning time, cross-entropy, and regression coefficient. The ANN model used to assess trophic state based on 11 predictors resulted in 81.3% accuracy. The modeled hybrid classification tree-ANN based on 3 predictors resulted to 88.8% accuracy with a cross-entropy performance of 0.096495. Based on the obtained result, the modeled hybrid classification tree-ANN provides higher accuracy in assessing the trophic state of the aquaponic system. |
| first_indexed | 2024-12-22T01:55:37Z |
| format | Article |
| id | doaj.art-b94b57699586434eba268a209ef6438d |
| institution | Directory Open Access Journal |
| issn | 2442-6571 2548-3161 |
| language | English |
| last_indexed | 2024-12-22T01:55:37Z |
| publishDate | 2020-03-01 |
| publisher | Universitas Ahmad Dahlan |
| record_format | Article |
| series | IJAIN (International Journal of Advances in Intelligent Informatics) |
| spelling | doaj.art-b94b57699586434eba268a209ef6438d2022-12-21T18:42:48ZengUniversitas Ahmad DahlanIJAIN (International Journal of Advances in Intelligent Informatics)2442-65712548-31612020-03-0161465910.26555/ijain.v6i1.408135Trophic state assessment using hybrid classification tree-artificial neural networkRonnie Sabino Concepcion II0Pocholo James Mission Loresco1Rhen Anjerome Rañola Bedruz2Elmer Pamisa Dadios3Sandy Cruz Lauguico4Edwin Sybingco5De La Salle UniversityDe La Salle UniversityDe La Salle UniversityDe La Salle UniversityDe La Salle UniversityDe La Salle UniversityThe trophic state is one of the significant environmental impacts that must be monitored and controlled in any aquatic environment. This phenomenon due to nutrient imbalance in water strengthened with global warming, inhibits the natural system to progress. With eutrophication, the mass of algae in the water surface increases and results to lower dissolved oxygen in the water that is essential for fishes. Numerous limnological and physical features affect the trophic state and thus require extensive analysis to asses it. This paper proposed a model of hybrid classification tree-artificial neural network (CT-ANN) to assess the trophic state based on the selected significant features. The classification tree was used as a multidimensional reduction technique for feature selection, which eliminates eight original features. The remaining predictors having high impacts are chlorophyll-a, phosphorus and Secchi depth. The two-layer ANN with 20 artificial neurons was constructed to assess the trophic state of input features. The neural network was modeled based on the key parameters of learning time, cross-entropy, and regression coefficient. The ANN model used to assess trophic state based on 11 predictors resulted in 81.3% accuracy. The modeled hybrid classification tree-ANN based on 3 predictors resulted to 88.8% accuracy with a cross-entropy performance of 0.096495. Based on the obtained result, the modeled hybrid classification tree-ANN provides higher accuracy in assessing the trophic state of the aquaponic system.http://ijain.org/index.php/IJAIN/article/view/408aquaponicsassessmentartificial neural networkmodelling treetrophic state |
| spellingShingle | Ronnie Sabino Concepcion II Pocholo James Mission Loresco Rhen Anjerome Rañola Bedruz Elmer Pamisa Dadios Sandy Cruz Lauguico Edwin Sybingco Trophic state assessment using hybrid classification tree-artificial neural network IJAIN (International Journal of Advances in Intelligent Informatics) aquaponics assessment artificial neural network modelling tree trophic state |
| title | Trophic state assessment using hybrid classification tree-artificial neural network |
| title_full | Trophic state assessment using hybrid classification tree-artificial neural network |
| title_fullStr | Trophic state assessment using hybrid classification tree-artificial neural network |
| title_full_unstemmed | Trophic state assessment using hybrid classification tree-artificial neural network |
| title_short | Trophic state assessment using hybrid classification tree-artificial neural network |
| title_sort | trophic state assessment using hybrid classification tree artificial neural network |
| topic | aquaponics assessment artificial neural network modelling tree trophic state |
| url | http://ijain.org/index.php/IJAIN/article/view/408 |
| work_keys_str_mv | AT ronniesabinoconcepcionii trophicstateassessmentusinghybridclassificationtreeartificialneuralnetwork AT pocholojamesmissionloresco trophicstateassessmentusinghybridclassificationtreeartificialneuralnetwork AT rhenanjeromeranolabedruz trophicstateassessmentusinghybridclassificationtreeartificialneuralnetwork AT elmerpamisadadios trophicstateassessmentusinghybridclassificationtreeartificialneuralnetwork AT sandycruzlauguico trophicstateassessmentusinghybridclassificationtreeartificialneuralnetwork AT edwinsybingco trophicstateassessmentusinghybridclassificationtreeartificialneuralnetwork |