A User’s Guide to Support Vector Machines

Ben-Hur, Asa; Weston, Jason

doi:10.1007/978-1-60327-241-4_13

Cited by 611 publications

(345 citation statements)

References 12 publications

Supporting

Mentioning

316

Contrasting

Unclassified

Order By: Relevance

“…Finally, an optimal single feature-based classifier was adjusted for each of the predictors, using support vector machines (SVM) with radial basis functions [50]. The classifier was evaluated following a leave one patient out cross-validation (LOPCV) scheme [51,52], where shocks within each patient were classified using the optimal SVM obtained for the rest of the shocks.…”

Section: Discussionmentioning

confidence: 99%

Application of Entropy-Based Features to Predict Defibrillation Outcome in Cardiac Arrest

Chicote

Irusta

Alcaraz

et al. 2016

Entropy

View full text Add to dashboard Cite

Prediction of defibrillation success is of vital importance to guide therapy and improve the survival of patients suffering out-of-hospital cardiac arrest (OHCA). Currently, the most efficient methods to predict shock success are based on the analysis of the electrocardiogram (ECG) during ventricular fibrillation (VF), and recent studies suggest the efficacy of waveform indices that characterize the underlying non-linear dynamics of VF. In this study we introduce, adapt and fully characterize six entropy indices for VF shock outcome prediction, based on the classical definitions of entropy to measure the regularity and predictability of a time series. Data from 163 OHCA patients comprising 419 shocks (107 successful) were used, and the performance of the entropy indices was characterized in terms of embedding dimension (m) and matching tolerance (r). Six classical predictors were also assessed as baseline prediction values. The best prediction results were obtained for fuzzy entropy (FuzzEn) with m = 3 and an amplitude-dependent tolerance of r = 80 µV. This resulted in a balanced sensitivity/specificity of 80.4%/76.9%, which improved by over five points the results obtained for the best classical predictor. These results suggest that a FuzzEn approach for a joint quantification of VF amplitude and its non-linear dynamics may be a promising tool to optimize OHCA treatment.

show abstract

Section: Discussionmentioning

confidence: 99%

Application of Entropy-Based Features to Predict Defibrillation Outcome in Cardiac Arrest

Chicote

Irusta

Alcaraz

et al. 2016

Entropy

View full text Add to dashboard Cite

show abstract

“…SVM [26] and Random Forest (RF) [27] classifiers are trained using this encoded feature representations over a corpus of exemplar imagery (X-ray image patches, Figure 3). SVM are trained using Table 1.…”

Section: Bag-of-visual-wordsmentioning

confidence: 99%

On using Feature Descriptors as Visual Words for Object Detection within X-ray Baggage Security Screening

Kundegorski¹,

Akçay²,

Devereux³

et al. 2016

7th International Conference on Imaging for Crime Detection and Prevention (ICDP 2016)

View full text Add to dashboard Cite

“…Table 4 Megherbi et al [66,67] present a comparison of classifier-based approaches using volumetric shape characteristics for the classification of pre-segmented 3D objects in cluttered baggage-CT imagery. Various combinations of three shaped-based descriptors (3D Zernike descriptors [79]; Histogram-of-Shape Index (HSI) [29] and a combination of the two) and five classifiers (Support Vector Machines (SVM) [10]; neural networks [105]; decision trees [85]; boosted decision trees [25] and random forests [25]) are compared. Correct classification rates in excess of 98.0% are achieved on a limited dataset using the HSI descriptor with an SVM or random-forest classifier.…”

Section: Classificationmentioning

confidence: 99%

A review of automated image understanding within 3D baggage computed tomography security screening

Mouton

Breckon

2015

XST

View full text Add to dashboard Cite

(2015) 'A review of automated image understanding within 3D baggage computed tomography security screening.', Journal of X-ray science and technology., 23 (5). pp. 531-555. Further information on publisher's website:http://dx.doi.org/10.3233/XST-150508Publisher's copyright statement:Additional information: Use policyThe full-text may be used and/or reproduced, and given to third parties in any format or medium, without prior permission or charge, for personal research or study, educational, or not-for-prot purposes provided that:• a full bibliographic reference is made to the original source • a link is made to the metadata record in DRO • the full-text is not changed in any way The full-text must not be sold in any format or medium without the formal permission of the copyright holders.Please consult the full DRO policy for further details. We discuss the recent and most pertinent advancements and identify topics for future research within the challenging automated image understanding for baggage security screening CT.

show abstract

A User’s Guide to Support Vector Machines

Cited by 611 publications

References 12 publications

Application of Entropy-Based Features to Predict Defibrillation Outcome in Cardiac Arrest

Application of Entropy-Based Features to Predict Defibrillation Outcome in Cardiac Arrest

On using Feature Descriptors as Visual Words for Object Detection within X-ray Baggage Security Screening

A review of automated image understanding within 3D baggage computed tomography security screening

Contact Info

Product

Resources

About