Classification of Zambian grasslands using random forest feature importance selection during the optimal phenological period

Zhao, Yifan; Zhu, Weiwei; Wei, Panpan; Fang, Peng; Zhang, Xiwang; Niu, Y.; Liu, Wenjun; Zhao, Hao; Wu, Qirui

doi:10.1016/j.ecolind.2021.108529

Cited by 70 publications

(32 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For feature selection, some well-known algorithms: Random Forest feature importance (RF) [ 45 ], Univariate features, Correlation Matrix [ 46 ], Principal Component Analysis method (PCA) [ 47 ] and Wrapper Method [ 48 ] with various configurations are used in this study. Table 8 contains the performance analysis of the RF-XGB model trained on the selected features of various feature selection techniques.…”

Section: Resultsmentioning

confidence: 99%

An Effective Ensemble Machine Learning Approach to Classify Breast Cancer Based on Feature Selection and Lesion Segmentation Using Preprocessed Mammograms

Rafid

Azam

Montaha

et al. 2022

Biology

View full text Add to dashboard Cite

Background: Breast cancer, behind skin cancer, is the second most frequent malignancy among women, initiated by an unregulated cell division in breast tissues. Although early mammogram screening and treatment result in decreased mortality, differentiating cancer cells from surrounding tissues are often fallible, resulting in fallacious diagnosis. Method: The mammography dataset is used to categorize breast cancer into four classes with low computational complexity, introducing a feature extraction-based approach with machine learning (ML) algorithms. After artefact removal and the preprocessing of the mammograms, the dataset is augmented with seven augmentation techniques. The region of interest (ROI) is extracted by employing several algorithms including a dynamic thresholding method. Sixteen geometrical features are extracted from the ROI while eleven ML algorithms are investigated with these features. Three ensemble models are generated from these ML models employing the stacking method where the first ensemble model is built by stacking ML models with an accuracy of over 90% and the accuracy thresholds for generating the rest of the ensemble models are >95% and >96. Five feature selection methods with fourteen configurations are applied to notch up the performance. Results: The Random Forest Importance algorithm, with a threshold of 0.045, produces 10 features that acquired the highest performance with 98.05% test accuracy by stacking Random Forest and XGB classifier, having a higher than >96% accuracy. Furthermore, with K-fold cross-validation, consistent performance is observed across all K values ranging from 3–30. Moreover, the proposed strategy combining image processing, feature extraction and ML has a proven high accuracy in classifying breast cancer.

show abstract

Section: Resultsmentioning

confidence: 99%

An Effective Ensemble Machine Learning Approach to Classify Breast Cancer Based on Feature Selection and Lesion Segmentation Using Preprocessed Mammograms

Rafid

Azam

Montaha

et al. 2022

Biology

View full text Add to dashboard Cite

show abstract

“…ED Chaves, CA Picoli, and D. Sanches [56] stated that Sentinel's two SWIR bands are very sensitive to chlorophyll content, allowing them to distinguish different vegetation types and determine classification accuracy for LULC. In addition, visible and shortwave infrared wavelengths are known for their spectral variations, which can explain variations caused by chlorophyll content, soil type, and soil color [57].…”

Section: Discussionmentioning

confidence: 99%

Improving Land Use/Cover Classification Accuracy from Random Forest Feature Importance Selection Based on Synergistic Use of Sentinel Data and Digital Elevation Model in Agriculturally Dominated Landscape

Ibrahim

2022

Agriculture

View full text Add to dashboard Cite

Land use and land cover (LULC) mapping can be of great help in changing land use decisions, but accurate mapping of LULC categories is challenging, especially in semi-arid areas with extensive farming systems and seasonal vegetation phenology. Machine learning algorithms are now widely used for LULC mapping because they provide analytical capabilities for LULC classification. However, the use of machine learning algorithms to improve classification performance is still being explored. The objective of this study is to investigate how to improve the performance of LULC models to reduce prediction errors. To address this question, the study applied a Random Forest (RF) based feature selection approach using Sentinel-1, -2, and Shuttle Radar Topographic Mission (SRTM) data. Results from RF show that the Sentinel-2 data only achieved an out-of-bag overall accuracy of 84.2%, while the Sentinel-1 and SRTM data achieved 83% and 76.44%, respectively. Classification accuracy improved to 89.1% when Sentinel-2, Sentinel-1 backscatter, and SRTM data were combined. This represents a 4.9% improvement in overall accuracy compared to Sentinel-2 alone and a 6.1% and 12.66% improvement compared to Sentinel-1 and SRTM data, respectively. Further independent validation, based on equally sized stratified random samples, consistently found a 5.3% difference between the Sentinel-2 and the combined datasets. This study demonstrates the importance of the synergy between optical, radar, and elevation data in improving the accuracy of LULC maps. In principle, the LULC maps produced in this study could help decision-makers in a wide range of spatial planning applications.

show abstract

“…Ecosystem service is a general term referring to human beings obtaining benefits from an ecosystem [5]. Research ecosystem services are of great significance for the construction of ecological civilization, the exploration of ecological security patterns, and the improvement of human well-being [6][7][8].…”

Section: Introductionmentioning

confidence: 99%

“…However, the interaction mechanisms between socioeconomic and ecosystem services remain unclear. Currently, most studies focus on the accounting methods, driving mechanism, and scale effect of ESV [5][6][7][8][9][10][11][12][37][38][39][40][41][42]. Little attention has been paid to the relationship between ESV and socioeconomic, especially human well-being.…”

Section: Introductionmentioning

confidence: 99%

Unraveling the Spatio-Temporal Relationship between Ecosystem Services and Socioeconomic Development in Dabie Mountain Area over the Last 10 years

et al. 2022

Self Cite

View full text Add to dashboard Cite

The Dabie Mountain area is a typical poverty-stricken area in China. It is of great significance to evaluate the ecosystem service value and its impact mechanism toward optimizing the ecological structure and coordinating ecological protection and economic development. This study determined the ecosystem service value coefficient and calculated the ecosystem service value (ESV) according to the regional economic development in the past ten years, and the ESV was spatialized based on NPP, which is closely related to ecological function. The temporal and spatial variation of ESV was then analyzed, and an RDE index was proposed to describe its response to land cover change. Further, the relationship between ESV and several parameters that reflect socioeconomic development was researched and analyzed. The results show that the total ESV in the study area first decreased and then increased, with an overall increase of CNY 3.895 billion. Among the land cover types, forest land had the greatest impact, contributing more than 70%. In the ecosystem service functions, the contribution of regulation function exceeded 50%. ESV was found to be sensitive to land cover change. On average, every 1 km2 change leads to an ESV change of about CNY 1 million. Socioeconomic-related parameters were negatively correlated with ESV, among which the correlation with per capita disposable income was the weakest, indicating that there was no obvious contradiction between human well-being and ESV. Therefore, a path for harmonious symbiotic development can be found between man and nature.

show abstract

Classification of Zambian grasslands using random forest feature importance selection during the optimal phenological period

Cited by 70 publications

References 40 publications

An Effective Ensemble Machine Learning Approach to Classify Breast Cancer Based on Feature Selection and Lesion Segmentation Using Preprocessed Mammograms

An Effective Ensemble Machine Learning Approach to Classify Breast Cancer Based on Feature Selection and Lesion Segmentation Using Preprocessed Mammograms

Improving Land Use/Cover Classification Accuracy from Random Forest Feature Importance Selection Based on Synergistic Use of Sentinel Data and Digital Elevation Model in Agriculturally Dominated Landscape

Unraveling the Spatio-Temporal Relationship between Ecosystem Services and Socioeconomic Development in Dabie Mountain Area over the Last 10 years

Contact Info

Product

Resources

About