Improvements to Platt's SMO Algorithm for SVM Classifier Design

Keerthi, S. Sathiya; Shevade, Shirish; Bhattacharyya, Chiranjib; Murthy, K. R. K.

doi:10.1162/089976601300014493

Cited by 1,548 publications

(930 citation statements)

References 1 publication

Supporting

Mentioning

913

Contrasting

Unclassified

Order By: Relevance

“…We previously evaluated [5] the ability of the extracted features to differentiate epileptic from non-epileptic epochs by examining several classification algorithms implemented by the WEKA machine learning toolkit software [24] including the BayesNet [24,26], RandomCommittee, RandomForest [27], IBk [28] and SMO [29,30] with RBF kernel. Since the overall highest accuracy was achieved by the BayesNet classifier, we now evaluate the examined fusion schemes with respect to the BayesNet.…”

Section: Methodsology For Classification Of Generalized Epileptic Andmentioning

confidence: 99%

Data fusion for paroxysmal events’ classification from EEG

Pippa

Zacharaki

Koutroumanidis

et al. 2017

Journal of Neuroscience Methods

View full text Add to dashboard Cite

 highly accurate classification of epileptic and non-epileptic EEG events  comparison between EI and LI fusion schemes regarding this problem  novel LI fusion to handle the high dimensionality and the limited number of samples  study of the behavior of each scheme as a function of the dimensionality  dimensionality reduction through PCA Abstract.Background: Spatiotemporal analysis of electroencephalography is commonly used for classification of events since it allows capturing dependencies across channels. The significant increase of feature vector dimensionality however introduce noise and thus it does not allow the classification models to be trained using a limited number of samples usually available in clinical studies.New Method: Thus, we investigate the classification of epileptic and non-epileptic events based on temporal and spectral analysis through the application of three different fusion schemes for the 2 combination of information across channels. We compare the commonly used early-integration (EI) scheme -in which features are fused from all channels prior to classification -with two late-integration (LI) schemes performing per channel classification when: (i) the temporal context varies significantly across channels, thus local spatial training models are required, and (ii) the spatial variations are negligible in comparison to the inter-subject variation, thus only the temporal variation is modeled using a single global spatial training model. Furthermore, we perform dimensionality reduction either by feature selection or by principal component analysis. Results:The framework is applied on events that manifest across most channels, as generalized epileptic seizures, psychogenic non-epileptic seizures and vasovagal syncope. The three classification architectures were evaluated on EEG epochs from 11 subjects.Comparison with Existing Methods: Although direct comparison with other studies is difficult due to the different characteristics of each dataset, the achieved recognition accuracy of the LI fusion schemes outperforms the performance reported in the literature. Conclusions:The best scheme was the LI with global model which achieved 97% accuracy.

show abstract

Section: Methodsology For Classification Of Generalized Epileptic Andmentioning

confidence: 99%

Data fusion for paroxysmal events’ classification from EEG

Pippa

Zacharaki

Koutroumanidis

et al. 2017

Journal of Neuroscience Methods

View full text Add to dashboard Cite

show abstract

“…The corresponding condition for C-SVM has been widely applied in the SMO technique, see, e.g., [20] and [14]. When τ varies, I λ * up and I λ * down are different.…”

Section: Dual Problem Of Pin-svmmentioning

confidence: 99%

“…Thus, the strategies of selecting two dual variables for C-SVM are applicable to pin-SVM. The simplest selection is the maximal violating pair, which has been discussed in [20].…”

Section: Working Set Selection and Initial Solutionmentioning

confidence: 99%

Sequential minimal optimization for SVM with pinball loss

2015

View full text Add to dashboard Cite

To pursue the insensitivity to feature noise and the stability to re-sampling, a new type of support vector machine (SVM) has been established via replacing the hinge loss in the classical SVM by the pinball loss and was hence called a pin-SVM. Though a different loss function is used, pin-SVM has a similar structure as the classical SVM. Specifically, the dual problem of pin-SVM is a quadratic programming problem with box constraints, for which the sequential minimal optimization (SMO) technique is applicable. In this paper, we establish SMO algorithms for pin-SVM and its sparse version. The numerical experiments on real-life data sets illustrate both the good performance of pin-SVMs and the effectiveness of the established SMO methods.

show abstract

“…SMO SMO (Keerthi et al 2001) is an algorithm of support vector machine classifier that globally transforms nominal attributes into binary ones and multiclass problems are solved using pairwise classification.…”

Section: Normalized Gaussian Radial Basis Function Network (Rbf)mentioning

confidence: 99%

Using robust Bayesian network to estimate the residuals of fluoroquinolone antibiotic in soil

Xie

et al. 2015

Environ Sci Pollut Res

View full text Add to dashboard Cite

Prediction of antibiotic pollution and its consequences is difficult, due to the uncertainties and complexities associated with multiple related factors. This article employed domain knowledge and spatial data to construct a Bayesian network (BN) model to assess fluoroquinolone antibiotic (FQs) pollution in the soil of an intensive vegetable cultivation area. The results show: (1) The relationships between FQs pollution and contributory factors: Three factors (cultivation methods, crop rotations, and chicken manure types) were consistently identified as predictors in the topological structures of three FQs, indicating their importance in FQs pollution; deduced with domain knowledge, the cultivation methods are determined by the crop rotations, which require different nutrients (derived from the manure) according to different plant biomass. (2) The performance of BN model: The integrative robust Bayesian network model achieved the highest detection probability (pd) of high-risk and receiver operating characteristic (ROC) area, since it incorporates domain knowledge and model uncertainty. Our encouraging findings have implications for the use of BN as a robust approach to assessment of FQs pollution and for informing decisions on appropriate remedial measures.

show abstract

Improvements to Platt's SMO Algorithm for SVM Classifier Design

Abstract: Convergence of a generalized version of the modified SMO algorithms given by Keerthi et al. for SVM classifier design is proved. The convergence results are also extended to modified SMO algorithms for solving ν-SVM classifier problems.

Cited by 1,548 publications

References 1 publication

Data fusion for paroxysmal events’ classification from EEG

Data fusion for paroxysmal events’ classification from EEG

Sequential minimal optimization for SVM with pinball loss

Using robust Bayesian network to estimate the residuals of fluoroquinolone antibiotic in soil

Contact Info

Product

Resources

About