A hybrid machine learning technique for feature optimization in object-based classification of debris-covered glaciers
Object-based features like spectral, topographic, and textural are supportive to determine debris-covered glacier classes. The original feature space includes relevant and irrelevant features. The inclusion of all these features increases the complexity and renders the classifier’s performance. Ther...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-11-01
|
| Series: | Ain Shams Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2090447922001204 |
| _version_ | 1811197592886837248 |
|---|---|
| author | Shikha Sharda Mohit Srivastava Hemendra Singh Gusain Naveen Kumar Sharma Kamaljit Singh Bhatia Mohit Bajaj Harsimrat Kaur Hossam M. Zawbaa Salah Kamel |
| author_facet | Shikha Sharda Mohit Srivastava Hemendra Singh Gusain Naveen Kumar Sharma Kamaljit Singh Bhatia Mohit Bajaj Harsimrat Kaur Hossam M. Zawbaa Salah Kamel |
| author_sort | Shikha Sharda |
| collection | DOAJ |
| description | Object-based features like spectral, topographic, and textural are supportive to determine debris-covered glacier classes. The original feature space includes relevant and irrelevant features. The inclusion of all these features increases the complexity and renders the classifier’s performance. Therefore, feature space optimization is requisite for the classification process. Previous studies have shown a rigorous exercise in manually selecting the best combination of features to define the target class and proven to be a time-consuming task. The present study proposed a hybrid feature selection technique to automate the selection of the best suitable features. This study aimed to reduce the classifier’s complexity and enhance the performance of the classification model. Relief-F and Pearson Correlation filter-based feature selection methods ranked features according to the relevance and filtered out irrelevant or less important features based on the defined condition. Later, the hybrid model selected the common features to get an optimal feature set. The proposed hybrid model was tested on Landsat 8 images of debris-covered glaciers in Central Karakoram Range and validated with present glacier inventories. The results showed that the classification accuracy of the proposed hybrid feature selection model with a Decision Tree classifier is 99.82%, which is better than the classification results obtained using other mapping techniques. In addition, the hybrid feature selection technique has sped up the process of classification by reducing the number of features by 77% without compromising the classification accuracy. |
| first_indexed | 2024-04-12T01:17:33Z |
| format | Article |
| id | doaj.art-56f57445f4bb40deb2d718cea162d4f7 |
| institution | Directory Open Access Journal |
| issn | 2090-4479 |
| language | English |
| last_indexed | 2024-04-12T01:17:33Z |
| publishDate | 2022-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ain Shams Engineering Journal |
| spelling | doaj.art-56f57445f4bb40deb2d718cea162d4f72022-12-22T03:53:54ZengElsevierAin Shams Engineering Journal2090-44792022-11-01136101809A hybrid machine learning technique for feature optimization in object-based classification of debris-covered glaciersShikha Sharda0Mohit Srivastava1Hemendra Singh Gusain2Naveen Kumar Sharma3Kamaljit Singh Bhatia4Mohit Bajaj5Harsimrat Kaur6Hossam M. Zawbaa7Salah Kamel8Department of Electronics and Communication Engineering, I.K. Gujral Punjab Technical University, Jalandhar, Punjab 144603, IndiaDepartment of Electronics and Communication Engineering, Chandigarh Engineering College, Mohali, Punjab 140307, IndiaInstitute of Technology Management (ITM-DRDO), Mussoorie 248179, IndiaDepartment of Electrical Engineering, I. K. Gujral Punjab Technical University, Jalandhar, Punjab 144603, IndiaDepartment of Electronics and Communication Engineering, G.B. Pant Institute of Engineering and Technology, Pauri Garhwal 246194, IndiaDepartment of Electrical and Electronics Engineering, National Institute of Technology, Delhi 110040, IndiaDepartment of Electronics and Communication Engineering, CT Institute of Engineering and Technology, Jalandhar, Punjab 144623, IndiaFaculty of Computers and Artificial Intelligence, Beni-Suef University, Beni-Suef, Egypt; Technological University Dublin, Dublin, Ireland; Corresponding author at: Technological University Dublin, Park House, 191 N Circular Rd, Cabra East, Grangegorman, Dublin D07 EWV4, Ireland.Electrical Engineering Department, Faculty of Engineering, Aswan University, 81542 Aswan, EgyptObject-based features like spectral, topographic, and textural are supportive to determine debris-covered glacier classes. The original feature space includes relevant and irrelevant features. The inclusion of all these features increases the complexity and renders the classifier’s performance. Therefore, feature space optimization is requisite for the classification process. Previous studies have shown a rigorous exercise in manually selecting the best combination of features to define the target class and proven to be a time-consuming task. The present study proposed a hybrid feature selection technique to automate the selection of the best suitable features. This study aimed to reduce the classifier’s complexity and enhance the performance of the classification model. Relief-F and Pearson Correlation filter-based feature selection methods ranked features according to the relevance and filtered out irrelevant or less important features based on the defined condition. Later, the hybrid model selected the common features to get an optimal feature set. The proposed hybrid model was tested on Landsat 8 images of debris-covered glaciers in Central Karakoram Range and validated with present glacier inventories. The results showed that the classification accuracy of the proposed hybrid feature selection model with a Decision Tree classifier is 99.82%, which is better than the classification results obtained using other mapping techniques. In addition, the hybrid feature selection technique has sped up the process of classification by reducing the number of features by 77% without compromising the classification accuracy.http://www.sciencedirect.com/science/article/pii/S2090447922001204Decision treeFeature selectionMachine learningObject-based classification |
| spellingShingle | Shikha Sharda Mohit Srivastava Hemendra Singh Gusain Naveen Kumar Sharma Kamaljit Singh Bhatia Mohit Bajaj Harsimrat Kaur Hossam M. Zawbaa Salah Kamel A hybrid machine learning technique for feature optimization in object-based classification of debris-covered glaciers Ain Shams Engineering Journal Decision tree Feature selection Machine learning Object-based classification |
| title | A hybrid machine learning technique for feature optimization in object-based classification of debris-covered glaciers |
| title_full | A hybrid machine learning technique for feature optimization in object-based classification of debris-covered glaciers |
| title_fullStr | A hybrid machine learning technique for feature optimization in object-based classification of debris-covered glaciers |
| title_full_unstemmed | A hybrid machine learning technique for feature optimization in object-based classification of debris-covered glaciers |
| title_short | A hybrid machine learning technique for feature optimization in object-based classification of debris-covered glaciers |
| title_sort | hybrid machine learning technique for feature optimization in object based classification of debris covered glaciers |
| topic | Decision tree Feature selection Machine learning Object-based classification |
| url | http://www.sciencedirect.com/science/article/pii/S2090447922001204 |
| work_keys_str_mv | AT shikhasharda ahybridmachinelearningtechniqueforfeatureoptimizationinobjectbasedclassificationofdebriscoveredglaciers AT mohitsrivastava ahybridmachinelearningtechniqueforfeatureoptimizationinobjectbasedclassificationofdebriscoveredglaciers AT hemendrasinghgusain ahybridmachinelearningtechniqueforfeatureoptimizationinobjectbasedclassificationofdebriscoveredglaciers AT naveenkumarsharma ahybridmachinelearningtechniqueforfeatureoptimizationinobjectbasedclassificationofdebriscoveredglaciers AT kamaljitsinghbhatia ahybridmachinelearningtechniqueforfeatureoptimizationinobjectbasedclassificationofdebriscoveredglaciers AT mohitbajaj ahybridmachinelearningtechniqueforfeatureoptimizationinobjectbasedclassificationofdebriscoveredglaciers AT harsimratkaur ahybridmachinelearningtechniqueforfeatureoptimizationinobjectbasedclassificationofdebriscoveredglaciers AT hossammzawbaa ahybridmachinelearningtechniqueforfeatureoptimizationinobjectbasedclassificationofdebriscoveredglaciers AT salahkamel ahybridmachinelearningtechniqueforfeatureoptimizationinobjectbasedclassificationofdebriscoveredglaciers AT shikhasharda hybridmachinelearningtechniqueforfeatureoptimizationinobjectbasedclassificationofdebriscoveredglaciers AT mohitsrivastava hybridmachinelearningtechniqueforfeatureoptimizationinobjectbasedclassificationofdebriscoveredglaciers AT hemendrasinghgusain hybridmachinelearningtechniqueforfeatureoptimizationinobjectbasedclassificationofdebriscoveredglaciers AT naveenkumarsharma hybridmachinelearningtechniqueforfeatureoptimizationinobjectbasedclassificationofdebriscoveredglaciers AT kamaljitsinghbhatia hybridmachinelearningtechniqueforfeatureoptimizationinobjectbasedclassificationofdebriscoveredglaciers AT mohitbajaj hybridmachinelearningtechniqueforfeatureoptimizationinobjectbasedclassificationofdebriscoveredglaciers AT harsimratkaur hybridmachinelearningtechniqueforfeatureoptimizationinobjectbasedclassificationofdebriscoveredglaciers AT hossammzawbaa hybridmachinelearningtechniqueforfeatureoptimizationinobjectbasedclassificationofdebriscoveredglaciers AT salahkamel hybridmachinelearningtechniqueforfeatureoptimizationinobjectbasedclassificationofdebriscoveredglaciers |