On the optimal number of features in the classification of multivariate Gaussian data

Jain, Anil K.; Waller, W.G.

doi:10.1016/0031-3203(78)90008-0

Cited by 100 publications

(43 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In practice, feature selection must proceed from sample data, which leads to the well-known peaking phenomenon, ie, the tendency of achieving improved classification performance with an increasing number of features only to a point, beyond which more features lead to degradation of the classification accuracy. [12][13][14][15][16] Therefore, employing too many features in a small-sample setting yields poorer classification accuracy, thereby leading to the need for feature selection. This raises a critical question: can one expect a feature selection algorithm to yield a feature set whose error is close to that of an optimal feature set?…”

Section: Cancer Informaticsmentioning

confidence: 99%

Model-based study of the Effectiveness of Reporting Lists of Small Feature Sets using RNA-Seq Data

Kim

Ivanov

Jiang

et al. 2016

Proceedings of the 7th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics

View full text Add to dashboard Cite

Ranking feature sets for phenotype classification based on gene expression is a challenging issue in cancer bioinformatics. When the number of samples is small, all feature selection algorithms are known to be unreliable, producing significant error, and error estimators suffer from different degrees of imprecision. The problem is compounded by the fact that the accuracy of classification depends on the manner in which the phenomena are transformed into data by the measurement technology. Because next-generation sequencing technologies amount to a nonlinear transformation of the actual gene or RNA concentrations, they can potentially produce less discriminative data relative to the actual gene expression levels. In this study, we compare the performance of ranking feature sets derived from a model of RNA-Seq data with that of a multivariate normal model of gene concentrations using 3 measures: (1) ranking power, (2) length of extensions, and (3) Bayes features. This is the model-based study to examine the effectiveness of reporting lists of small feature sets using RNA-Seq data and the effects of different model parameters and error estimators. The results demonstrate that the general trends of the parameter effects on the ranking power of the underlying gene concentrations are preserved in the RNA-Seq data, whereas the power of finding a good feature set becomes weaker when gene concentrations are transformed by the sequencing machine.

show abstract

Section: Cancer Informaticsmentioning

confidence: 99%

Model-based study of the Effectiveness of Reporting Lists of Small Feature Sets using RNA-Seq Data

Kim

Ivanov

Jiang

et al. 2016

Proceedings of the 7th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics

View full text Add to dashboard Cite

show abstract

“…The value t (see section 2.2.2) is determined according to bibliographic research [16,12,13,11], in which the optimal dimension size depends on the experimental part in combination with the LVQ algorithms. These algorithms typically operate to preserve neighbourhoods on a network of nodes which encode the feature vector.…”

Section: Feature Vector Extractionmentioning

confidence: 99%

Specific Selection of FFT Amplitudes from Audio Sports and News Broadcasting for Classification Purposes

Poulos¹,

Bokos²,

Kanellopoulos³

et al. 2007

JGAA

View full text Add to dashboard Cite

In this paper we investigate the problem of classification between sports and news broadcasting. We detect and classify files that consist of speech and music or background noise (news broadcasting), and speech and a noisy background (sports broadcasting). More specifically, this study investigates feature extraction and training and classification procedures. We compare the Average Magnitude Difference Function (AMDF) method, which we consider more robust to background noise, with a novel proposed method. This method uses several spectral audio features which may be considered as specific semantic information. We base the extraction of these features on the theory of computational geometry using an Onion Algorithm (OA). We tested the classification procedure as well as the learning ability of the two methods using a Learning Vector Quantizer One (LVQ1) neural network. The results of the experiment showed that the OA method has a faster learning procedure, which we characterise as an accurate feature extraction method for several audio cases.

show abstract

“…The use of feature selection algorithms is motivated by the need for highly precise results, computational reasons and a peaking phenomenon often observed when classifiers are trained with a limited set of training samples. If the number of features is increased, the classification rate of the classifiers decreases after a peak (10,11).…”

Section: Definition Of Features For Detection Of Malignant Melanomamentioning

confidence: 99%

Computational vision systems for the detection of malignant melanoma

Kosmopoulos¹

2006

Oncol Rep

View full text Add to dashboard Cite

Abstract. In recent years, computational vision-based diagnostic systems for dermatology have demonstrated significant progress. We review these systems by first presenting the installation, visual features utilized for skin lesion classification and the methods for defining them. We also describe how to extract these features through digital image processing methods, i.e. segmentation, registration, border detection, color and texture processing, and present how to use the extracted features for skin lesion classification by employing artificial intelligence methods, i.e. discriminant analysis, neural networks, and support vector machines. Finally, we compare these techniques in discriminating malignant melanoma tumors versus dysplastic naevi lesions.

show abstract

On the optimal number of features in the classification of multivariate Gaussian data

Cited by 100 publications

References 22 publications

Model-based study of the Effectiveness of Reporting Lists of Small Feature Sets using RNA-Seq Data

Model-based study of the Effectiveness of Reporting Lists of Small Feature Sets using RNA-Seq Data

Specific Selection of FFT Amplitudes from Audio Sports and News Broadcasting for Classification Purposes

Computational vision systems for the detection of malignant melanoma

Contact Info

Product

Resources

About