Floating search methods in feature selection

Pudil, Pavel; Novovičová, Jana; Kittler, Josef

doi:10.1016/0167-8655(94)90127-9

Cited by 2,687 publications

(1,508 citation statements)

References 9 publications

Supporting

Mentioning

1,387

Contrasting

Unclassified

Order By: Relevance

“…not using X, Y coordinates and first-and second-order derivatives of them). These correspond to the following time functions reported in Table I Due to the the low amount of available training data in a signature real case, Sequential Forward Feature Selection (SFFS) algorithm [20] is performed in order to obtain a subset of time functions for each system considered in this work improving the performance in terms of EER (%). This technique offers a suboptimal solution since it does not take into account all the possible feature combinations, although it considers correlations between features.…”

Section: B Feature Extraction and Selectionmentioning

confidence: 99%

Increasing the robustness of biometric templates for dynamic signature biometric systems

Tolosana

Vera-Rodríguez

Ortega‐Garcia

et al. 2015

2015 International Carnahan Conference on Security Technology (ICCST)

View full text Add to dashboard Cite

El acceso a la versión del editor puede requerir la suscripción del recurso Access to the published version may require subscription Abstract-Due to the high deployment of devices such as smartphones and tablets and their increasing popularity in our society, the use of biometric traits in commercial and banking applications through these novel devices as an easy, quick and reliable way to perform payments is rapidly increasing. The handwritten signature is one of the most socially accepted biometric traits in these sectors due to the fact that it has been used in financial and legal transitions for centuries. In this paper we focus on dynamic signature verification systems. Nowadays, most of the state-of-the-art systems are based on extracting information contained in the X and Y spatial position coordinates of the signing process, which is stored in the biometric templates. However, it is critical to protect this sensible information of the users signatures against possible external attacks that would allow criminals to perform direct attacks to a biometric system or carry out high quality forgeries of the users signatures. Following this problem, the goal of this work is to study the performance of the system in two cases: first, an optimal time functions-based system taking into account the information related to X and Y coordinates and pressure, which is the common practice (i.e. Standard System). Second, we study an extreme case not considering information related to X, Y coordinates and their derivatives on the biometric system (i.e. Secure System), which would be a much more robust system against attacks, as this critical information would not be stored anywhere. The experimental work is carried out using e-BioSign database which makes use of 5 devices in total. The systems considered in this work are based on Dynamic Time Warping (DTW), an elastic measure over the selected time functions. Sequential Forward Features Selection (SFFS) is applied as a reliable way to obtain an optimal time functions vector over a development subset of users of the database. The results obtained over the evaluation subset of users of the database show a similar performance for both Standard and Secure Systems. Therefore, the use of a Secure System can be useful in some applications such as banking in order to avoid the lost of important user information against possible external attacks.

show abstract

Section: B Feature Extraction and Selectionmentioning

confidence: 99%

Increasing the robustness of biometric templates for dynamic signature biometric systems

Tolosana

Vera-Rodríguez

Ortega‐Garcia

et al. 2015

2015 International Carnahan Conference on Security Technology (ICCST)

View full text Add to dashboard Cite

show abstract

“…A number of suboptimal selection methods is also discussed in [1]. Of these, [2] found that the so-called Sequential Forward Floating Search [3] method produced the best results, performing close to optimal and demanding lower computational resources than other methods. This method is a bottom-up search procedure, where the term floating identifies that the number of features changes dynamically, with one feature included and/or excluded, at each iteration.…”

Section: Introductionmentioning

confidence: 99%

Automatic covariate selection in logistic models for chest pain diagnosis: A new approach

Harrison

Kennedy

2008

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

A newly established method for optimizing logistic models via a minorizationmajorization procedure is applied to the problem of diagnosing acute coronary syndromes (ACS). The method provides a principled approach to the selection of covariates which would otherwise require the use of a suboptimal method owing to the size of the covariate set. A strategy for building models is proposed and two models optimized for performance and for simplicity are derived via ten-fold crossvalidation. These models confirm that a relatively small set of covariates including clinical and electrocardiographic features can be used successfully in this task.The performance of the models is comparable with previously published models using less principled selection methods. The models prove to be portable when tested on data gathered from three other sites. Whilst diagnostic accuracy and calibration diminishes slightly for these new settings, it remains satisfactory overall.The prospect of building predictive models that are as simple as possible for a required level of performance is valuable if data-driven decision aids are to gain wide acceptance in the clinical situation owing to the need to minimize the time taken to gather and enter data at the bedside.

show abstract

“…These algorithms have quadratic complexity, but they perform poorly for nonmonotonic indices. In such cases, sequential floating searches 3 provide better results, though at the cost of a higher computational complexity. Beam search variants of the sequential algorithms 4 are also used to reduce computational complexity.…”

Section: Introductionmentioning

confidence: 99%

Supervised Feature Ranking Using a Genetic Algorithm Optimized Artificial Neural Network

Lin

Chiu

Tsai

2006

J. Chem. Inf. Model.

View full text Add to dashboard Cite

A genetic algorithm optimized artificial neural network GNW has been designed to rank features for two diversified multivariate data sets. The dimensions of these data sets are 85 × 24 and 62 × 25 for 24 or 25 molecular descriptors being computed for 85 matrix metalloproteinase-1 inhibitors or 62 hepatitis C virus NS3 protease inhibitors, respectively. Each molecular descriptor computed is treated as a feature and input into an input layer node of the artificial neural network. To optimize the artificial neural network by the genetic algorithm, each interconnected weight between input and hidden or between hidden and output layer nodes is binary encoded as a 16 bits string in a chromosome, and the chromosome is evolved by crossover and mutation operations. Each input layer node and its associated weights of the trained GNW are systematically omitted once (the self-depleted weights), and the corresponding weight adjustments due to the omission are computed to keep the overall network behavior unchanged. The primary feature ranking index defined as the sum of self-depleted weights and the corresponding weight adjustments computed is found capable of separating good from bad features for some artificial data sets of known feature rankings tested. The final feature indexes used to rank the data sets are computed as a sum of the weighted frequency of each feature being ranked in a particular rank for each data set being partitioned into numerous clusters. The two data sets are also clustered by a standard K-means method and trained by a support vector machine (SVM) for feature ranking using the computed F-scores as feature ranking index. It is found that GNW outperforms the SVM method on three artificial as well as the matrix metalloproteinase-1 inhibitor data sets studied. A clear-cut separation of good from bad features is offered by the GNW but not by the SVM method for a feature pool of known feature ranking.

show abstract

Floating search methods in feature selection

Cited by 2,687 publications

References 9 publications

Increasing the robustness of biometric templates for dynamic signature biometric systems

Increasing the robustness of biometric templates for dynamic signature biometric systems

Automatic covariate selection in logistic models for chest pain diagnosis: A new approach

Supervised Feature Ranking Using a Genetic Algorithm Optimized Artificial Neural Network

Contact Info

Product

Resources

About