Enhanced recursive feature elimination

Ramírez-Hernández, J.A.; Fernandez, Emmanuel

doi:10.1109/icmla.2007.35

Cited by 239 publications

(104 citation statements)

References 10 publications

Supporting

Mentioning

103

Contrasting

Unclassified

Order By: Relevance

“…To do so, standard RFE removes a feature if it is weak or redundant at a particular step and retains independent and relevant features. EnRFE is a RFE-derived technique which redefines the criterion of removing features at each state of the training so that redundant or weak features that improve performance estimates when combined between them or with other relevant features can be retained [ 35 ]. In an iterative scheme, the SVM-EnRFE classifier is trained until a core set of variables with the highest discriminative power remains.…”

Section: Figmentioning

confidence: 99%

Predictors of schizophrenia spectrum disorders in early-onset first episodes of psychosis: a support vector machine model

Pina‐Camacho

García-Prieto

Parellada

et al. 2014

Eur Child Adolesc Psychiatry

View full text Add to dashboard Cite

Identifying early-onset schizophrenia spectrum disorders (SSD) at a very early stage remains challenging. To assess the diagnostic predictive value of multiple types of data at the emergence of early-onset first-episode psychosis (FEP), various support vector machine (SVM) classifiers were developed. The data were from a 2-year, prospective, longitudinal study of 81 patients (age 9-17 years) with early-onset FEP and a stable diagnosis during follow-up and 42 age- and sex-matched healthy controls (HC). The input was different combinations of baseline clinical, neuropsychological, magnetic resonance imaging brain volumetric and biochemical data, and the output was the diagnosis at follow-up (SSD vs. non-SSD, SSD vs. HC, and non-SSD vs. HC). Enhanced recursive feature elimination was performed for the SSD vs. non-SSD classifier to select and rank the input variables with the highest predictive value for a diagnostic outcome of SSD. After validation with a test set and considering all baseline variables together, the SSD vs. non-SSD, SSD vs. HC and non-SSD vs. HC classifiers achieved an accuracy of 0.81, 0.99 and 0.99, respectively. Regarding the SSD vs. non-SSD classifier, a combination of baseline clinical variables (severity of negative, disorganized symptoms and hallucinations or poor insight) and neuropsychological variables (impaired attention, motor coordination, and global cognition) showed the highest predictive value for a diagnostic outcome of SSD. Neuroimaging and biochemical variables at baseline did not add to the predictive value. Thus, comprehensive clinical/cognitive assessment remains the most reliable approach for differential diagnosis during early-onset FEP. SVMs may constitute promising multivariate tools in the search for predictors of diagnostic outcome in FEP.

show abstract

Section: Figmentioning

confidence: 99%

Predictors of schizophrenia spectrum disorders in early-onset first episodes of psychosis: a support vector machine model

Pina‐Camacho

García-Prieto

Parellada

et al. 2014

Eur Child Adolesc Psychiatry

View full text Add to dashboard Cite

show abstract

“…A linear kernel was used to represent the data, reduce computational cost and improve classification accuracy (i.e., the overall rate of correct classification). An enhanced recursive feature procedure (Chen and Jeong, 2007) was implemented to ensure that discrimination accuracy was not due to overfitting and to select the best predictive features (brain areas). Finally, we used leave-one-out cross-validation (Geisser, 1993) to test classification accuracy and whether the results were independent of the initial training data.…”

Section: Methodsmentioning

confidence: 99%

Heart evoked brain oscillatory networks and its interruption in early stages of Alzheimer’s disease

Castellanos

Diez

Pereda

et al. 2018

Preprint

View full text Add to dashboard Cite

Understanding how the heart influences brain dynamics will suppose a deep change for the neuroscience, psychology and medicine. A mainstay questions is the heart modulation of resting state brain networks and its relation with both the cardiac dynamics and the cognitive status. We evaluated the heart evoked basal networks for controls and two groups of mild cognitive impairment patients, stable and progressive to Alzheimer's disease without cardiovascular alteration symptoms. Our results in controls show that a healthy cognitive performance correlates with the heart modulation of brain dynamics in areas of the default mode network, and that the heart influence on brain networks varies along the cardiac cycle and the spectral band. However, the cognitive deficit produced by dementia correlates with the lack of heart modulation on brain activity. The heart influence on brain networks is disrupted in patients by producing hypersynchronization, accompanied by decreased cardiac complexity.We designed a surrogate and predictive procedure based on machine learning to compare the heart evoked results with the neural activity no locked to heartbeats. Based on our longitudinal data, we conclude that the prediction to progression to Alzheimer's disease is higher when considering the heart -brain interaction than when taking into account only the brain dynamics.We can conclude that brain networks in control subjects were more responsive to the heart cycle, allowing a wealthier, more complex pattern of oscillations. Our results highlight the role of heart in cognitive neuroscience by showing that basal brain networks are modulated by the cardiac dynamics.Heart-brain synchronization in dementia

show abstract

“…Segmentation is an essential process in GEOBIA, and the definition of segmentation parameters could have a significant influence on classification accuracy [19][20][21]. While the introduction of abundant features brings additional information that is relevant in target recognition, it could also introduce noise or redundant information that can degrade classification accuracy [22,23]. Moreover, several classification algorithms have been proposed and their performances (accuracy, efficiency and feasibility) in GEOBIA vary considerably [24][25][26].…”

Section: Introductionmentioning

confidence: 99%

“…It is also important to note that when the number of features is large, it is difficult to evaluate the accuracy of all possible feature combinations due to the huge computational work and time required. Thus for operational purposes, a series of search strategies are used in screening the most optimal feature subset [22,47]. However, few studies have evaluated the performance of these feature selection methods especially in GEOBIA crop recognition applications involving multisource satellite imagery.…”

Section: Introductionmentioning

confidence: 99%

“…In view of the research gaps in the use of GEOBIA in crop recognition outlined in the above paragraphs, this paper, based on the information gain ratio, proposed a novel supervised optimal SP selection method for comparison with an unsupervised optimal SP selection method. Additionally, based on the recursive feature elimination (RFE) [54] and enhanced RFE (EnRFE) [22] algorithms, this paper proposed an improved EnRFE (iEnRFE) algorithm for the selection of the optimal feature subset for GEOBIA. Using the optimal segmentation scale parameter and feature subset, the widely used classification algorithms of RF, SVM and GBDT were evaluated for accuracy and efficiency in crop recognition with GEOBIA and multisource satellite imagery (Sentinel-2A, Landsat-8 OLI and GF-1 WFV), and results obtained are envisaged to provide a valuable reference for relevant operational scenarios.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimal Segmentation Scale Parameter, Feature Subset and Classification Algorithm for Geographic Object-Based Crop Recognition Using Multisource Satellite Imagery

et al. 2019

View full text Add to dashboard Cite

Geographic object-based image analysis (GEOBIA) has been widely used in the remote sensing of agricultural crops. However, issues related to image segmentation, data redundancy and performance of different classification algorithms with GEOBIA have not been properly addressed in previous studies, thereby compromising the accuracy of subsequent thematic products. It is in this regard that the current study investigates the optimal scale parameter (SP) in multi-resolution segmentation, feature subset, and classification algorithm for use in GEOBIA based on multisource satellite imagery. For this purpose, a novel supervised optimal SP selection method was proposed based on information gain ratio, and was then compared with a preexisting unsupervised optimal SP selection method. Additionally, the recursive feature elimination (RFE) and enhanced RFE (EnRFE) algorithms were modified to generate an improved EnRFE (iEnRFE) algorithm, which was then compared with its precursors in the selection of optimal classification features. Based on the above, random forest (RF), gradient boosting decision tree (GBDT) and support vector machine (SVM) were applied to segmented objects for crop classification. The results indicated that the supervised optimal SP selection method is more suitable for application in heterogeneous land cover, whereas the unsupervised method proved more efficient as it does not require reference segmentation objects. The proposed iEnRFE method outperformed the preexisting EnRFE and RFE methods in optimal feature subset selection as it recorded the highest accuracy and less processing time. The RF, GBDT, and SVM algorithms achieved overall classification accuracies of 91.8%, 92.4%, and 90.5%, respectively. GBDT and RF recorded higher classification accuracies and utilized much less computational time than SVM and are, therefore, considered more suitable for crop classification requiring large numbers of image features. These results have shown that the proposed object-based crop classification scheme could provide a valuable reference for relevant applications of GEOBIA in crop recognition using multisource satellite imagery.

show abstract

Enhanced recursive feature elimination

Cited by 239 publications

References 10 publications

Predictors of schizophrenia spectrum disorders in early-onset first episodes of psychosis: a support vector machine model

Predictors of schizophrenia spectrum disorders in early-onset first episodes of psychosis: a support vector machine model

Heart evoked brain oscillatory networks and its interruption in early stages of Alzheimer’s disease

Optimal Segmentation Scale Parameter, Feature Subset and Classification Algorithm for Geographic Object-Based Crop Recognition Using Multisource Satellite Imagery

Contact Info

Product

Resources

About