A survey of feature selection methods for Gaussian mixture models and hidden Markov models

Adams, Stephen; Beling, Peter A.

doi:10.1007/s10462-017-9581-3

Cited by 48 publications

(23 citation statements)

References 106 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Feature selection is a concept in machine learning where a subset of collected features are selected as inputs into an algorithm [1,14,17,43,50]. While feature selection's primary benefit is to eliminate noisy features and improve the performance of a model, feature selection can also help reduce the cost of a predictive model by limiting the data that must be collected, stored, and processed.…”

Section: Introductionmentioning

confidence: 99%

ROC with Cost Pareto Frontier Feature Selection Using Search Methods

Meekins

Adams

Farinholt

et al. 2020

Data-Enabled Discov. Appl.

Self Cite

View full text Add to dashboard Cite

Cyber-physical systems (CPS) are finding increasing application in many domains. CPS are composed of sensors, actuators, a central decision-making unit, and a network connecting all of these components. The design of CPS involves the selection of these hardware and software components, and this design process could be limited by a cost constraint. This study assumes that the central decision-making unit is a binary classifier, and casts the design problem as a feature selection problem for the binary classifier where each feature has an associated cost. Receiver operating characteristic (ROC) curves are a useful tool for comparing and selecting binary classifiers; however, ROC curves only consider the misclassification cost of the classifier and ignore other costs such as the cost of the features. The authors previously proposed a method called ROC Convex Hull with Cost (ROCCHC) that is used to select ROC optimal classifiers when cost is a factor. ROCCHC extends the widely used ROC Convex Hull (ROCCH) method by combining it with the Pareto analysis for cost optimization. This paper proposes using the ROCCHC analysis as the evaluation function for feature selection search methods without requiring an exhaustive search over the feature space. This analysis is performed on 6 real-world data sets, including a diagnostic cyber-physical system for hydraulic actuators. The ROCCHC analysis is demonstrated using sequential forward and backward search. The results are compared with the ROCCH selection method and a popular Pareto selection method that uses classification accuracy and feature cost.

show abstract

Section: Introductionmentioning

confidence: 99%

ROC with Cost Pareto Frontier Feature Selection Using Search Methods

Meekins

Adams

Farinholt

et al. 2020

Data-Enabled Discov. Appl.

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, many irrelevant and redundant features will reduce the accuracy of classification and raise the complexity of dimensions. erefore, feature selection is a very effective solution [15]. Feature selection and classification methods are widely used in high-dimensional and multiclass data sets [16,17], which can improve the accuracy of model prediction by removing irrelevant and redundant features.…”

Section: Introductionmentioning

confidence: 99%

An Improved Hybrid Feature Selection Algorithm for Electric Charge Recovery Risk

Suxiang

Shi

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

In order to extract more information that affects customer arrears behavior, the feature extraction method is used to extend the low-dimensional features to the high-dimensional features for the warning problem of user arrears risk model of electric charge recovery (ECR). However, there are many irrelevant or redundant features in data, which affect prediction accuracy. In order to reduce the dimension of the feature and improve the prediction result, an improved hybrid feature selection algorithm is proposed, integrating nonlinear inertia weight binary particle swarm optimization with shrinking encircling and exploration mechanism (NBPSOSEE) with sequential backward selection (SBS), namely, NBPSOSEE-SBS, for selecting the optimal feature subset. NBPSOSEE-SBS can not only effectively reduce the redundant or irrelevant features from the feature subset selected by NBPSOSEE but also improve the accuracy of classification. The experimental results show that the proposed NBPSOSEE-SBS can effectively reduce a large number of redundant features and stably improve the prediction results in the case of low execution time, compared with one state-of-the-art optimization algorithm, and seven well-known wrapper-based feature selection approaches for the risk prediction of ECR for power customers.

show abstract

“…However, the noisy data and small 59 sample size pose a great challenge for many modelling problems in bioinformatics 60 making necessary to use adequate evaluation criteria or stable and robust FS models [7]. 61 In general, FS techniques can be classified into three main categories: filters, 62 wrappers, and embedded [7] [8]. Filters take as input all the features and reduce them 63 into a relevant subset independent of the model parameters.…”

mentioning

confidence: 99%

“…The most common parametric latent variable models 77 are the Gaussian mixture models (GMM) and hidden Markov models (HMM). The 78 mixture model is often used to model multimodal data, while the HMM is often used for 79 modeling time series data [8].…”

mentioning

confidence: 99%

“…CC-BY 4.0 International license It is made available under a (which was not peer-reviewed) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. Parameters estimated from data using FSHMM strategy were compared to the 262 models presented in [8] [12] and [14], with the conclusion that saliency variables were 263 found not to be necessary, making it all more feasible for a genomic context where the 264 number of observations is low so the less parameters to estimate, the better. The it is necessary to remove the offset value of each feature by computing the differences in 288 gene expression between consecutive time points.…”

mentioning

confidence: 99%

See 1 more Smart Citation

A feature selection strategy for gene expression time series experiments with hidden Markov models

Cárdenas-Ovando

Fernández-Figueroa

Rueda-Zárate

et al. 2018

Preprint

View full text Add to dashboard Cite

1Studies conducted in time series could be far more informative than those questioning 2 at a specific moment in time. However, when it comes to genomic data, time points are changes and quality of replicates as a measure of how much they deviate from the mean. 13 An important highlight is that this strategy overcomes the few samples limitation, 14 common in genomic experiments through a process of data transformation and 15 rearrangement. To prove this method, our strategy was applied to three publicly 15, 2018; available data sets. Results show that feature domain is reduced to up to 90% leaving 17 only few but relevant features yet with findings consistent to those previously reported. 18 Moreover, our strategy proved to be robust, stable and working on studies where sample 19 size is an issue otherwise. Hence, even with two biological replicates and/or three time 20 points our method proves to work well.is made available under a (which was not peer-reviewed) is the author/funder, who has granted bioRxiv a license to display the preprint in perpetuity. The copyright holder for this preprint . http://dx.doi.org/10.1101/392761 doi: bioRxiv preprint first posted online Aug. 21Author summary

show abstract

A survey of feature selection methods for Gaussian mixture models and hidden Markov models

Cited by 48 publications

References 106 publications

ROC with Cost Pareto Frontier Feature Selection Using Search Methods

ROC with Cost Pareto Frontier Feature Selection Using Search Methods

An Improved Hybrid Feature Selection Algorithm for Electric Charge Recovery Risk

A feature selection strategy for gene expression time series experiments with hidden Markov models

Contact Info

Product

Resources

About