Rough set based feature selection : A review

Feature selection aims to determine a minimal feature subset from a problem domain while retaining a suitably high accuracy in representing the original features. Rough set theory (RST) has been used as such a tool with much success. RST enables the discovery of data dependencies and the reduction of the number of attributes contained in a dataset using the data alone, requiring no additional information. This chapter describes the fundamental ideas behind RST-based approaches and reviews related feature selection methods that build on these ideas. Extensions to the traditional rough set approach are discussed, including recent selection methods based on tolerance rough sets, variable precision rough sets and fuzzy-rough sets. Alternative search mechanisms are also highly important in rough set feature selection. The chapter includes the latest developments in this area, including RST strategies based on hill-climbing, genetic algorithms and ant colony optimization.

Tolerance-based and Fuzzy-Rough Feature Selection.

R. Jensen and Q. Shen, 'Tolerance-based and Fuzzy-Rough Feature Selection,' Proceedings of the 16th International Conference on Fuzzy Systems (FUZZ-IEEE'07), pp. 877-882, 2007.

Webpage Classification with ACO-enhanced Fuzzy-Rough Feature Selection.

R. Jensen and Q. Shen, 'Webpage Classification with ACO-enhanced Fuzzy-Rough Feature Selection,' Proceedings of the Fifth International Conference on Rough Sets and Current Trends in Computing (RSCTC 2006), LNAI 4259, pp. 147-156, 2006.

Aiding classification of gene expression data with feature selection: a comparative study

C. Shang and Q. Shen. Aiding classification of gene expression data with feature selection: a comparative study. Computational Intelligence Research, 1(1):68-76.

Fuzzy-Rough Feature Significance for Fuzzy Decision Trees

R. Jensen and Q. Shen, 'Fuzzy-Rough Feature Significance for Fuzzy Decision Trees,' in Proceedings of the 2005 UK Workshop on Computational Intelligence, pp. 89-96, 2005.

Approximation-based feature selection and application for algae population estimation

Q. Shen and R. Jensen, 'Approximation-based feature selection and application for algae population estimation,' Applied Intelligence, vol. 28, no. 2, pp. 167-181, 2008. Sponsorship: EPSRC RONO: EP/E058388/1

Computational Intelligence and Feature Selection : Rough and Fuzzy Approaches

Computational Intelligence and Feature Selection provides a high level audience with both the background and fundamental ideas behind feature selection with an emphasis on those techniques based on rough and fuzzy sets, including their hybridizations. It introduces set theory, fuzzy set theory, rough set theory, and fuzzy-rough set theory, and illustrates the power and efficacy of the feature selections described through the use of real-world applications and worked examples. Program files implementing major algorithms covered, together with the necessary instructions and datasets, are available on the Web.

Na-23, Si-29, and C-13 MAS NMR investigation of glass-forming reactions between Na2CO3 and SiO2

Winter, Rudolf; Jones, A.R.; Greaves, G.N.; Smith, I.H., (2005) 'Na-23, Si-29, and C-13 MAS NMR investigation of glass-forming reactions between Na2CO3 and SiO2', Journal of Physical Chemistry B 109(49) pp.23154-23161 RAE2008

Soil differentiation using fingerprint Fourier transform infrared spectroscopy, chemometrics and genetic algorithm-based feature selection

Elliott, G. N., Worgan, H., Broadhurst, D. I., Draper, J. H., Scullion, J. (2007). Soil differentiation using fingerprint Fourier transform infrared spectroscopy, chemometrics and genetic algorithm-based feature selection. Soil Biology & Biochemistry, 39 (11), 2888-2896. Sponsorship: BBSRC / NERC RAE2008

Depolarization of sperm membrane potential is a common feature of men with subfertility and is associated with low fertilization rate at IVF

STUDY QUESTION. Are significant abnormalities in outward (K+) conductance and resting membrane potential (Vm) present in the spermatozoa of patients undertaking IVF and ICSI and if so, what is their functional effect on fertilization success? SUMMARY ANSWER. Negligible outward conductance (≈5% of patients) or an enhanced inward conductance (≈4% of patients), both of which caused depolarization of Vm, were associated with a low rate of fertilization following IVF. WHAT IS KNOWN ALREADY. Sperm-specific potassium channel knockout mice are infertile with defects in sperm function, suggesting that these channels are essential for fertility. These observations suggest that malfunction of K+ channels in human spermatozoa might contribute significantly to the occurrence of subfertility in men. However, remarkably little is known of the nature of K+ channels in human spermatozoa or the incidence and functional consequences of K+ channel defects. STUDY DESIGN, SIZE AND DURATION. Spermatozoa were obtained from healthy volunteer research donors and subfertile IVF and ICSI patients attending a hospital assisted reproductive techniques clinic between May 2013 and December 2015. In total, 40 IVF patients, 41 ICSI patients and 26 normozoospermic donors took part in the study. PARTICIPANTS/MATERIALS, SETTING, METHODS. Samples were examined using electrophysiology (whole-cell patch clamping). Where abnormal electrophysiological characteristics were identified, spermatozoa were further examined for Ca2+ influx induced by progesterone and penetration into viscous media if sufficient sample was available. Full exome sequencing was performed to specifically evaluate potassium calcium-activated channel subfamily M α 1 (KCNMA1), potassium calcium-activated channel subfamily U member 1 (KCNU1) and leucine-rich repeat containing 52 (LRRC52) genes and others associated with K+ signalling. In IVF patients, comparison with fertilization rates was done to assess the functional significance of the electrophysiological abnormalities. MAIN RESULTS AND THE ROLE OF CHANCE. Patch clamp electrophysiology was used to assess outward (K+) conductance and resting membrane potential (Vm) and signalling/motility assays were used to assess functional characteristics of sperm from IVF and ICSI patient samples. The mean Vm and outward membrane conductance in sperm from IVF and ICSI patients were not significantly different from those of control (donor) sperm prepared under the same conditions, but variation between individuals was significantly greater (P< 0.02) with a large number of outliers (>25%). In particular, in ≈10% of patients (7/81), we observed either a negligible outward conductance (4 patients) or an enhanced inward current (3 patients), both of which caused depolarization of Vm. Analysis of clinical data from the IVF patients showed significant association of depolarized Vm (≥0 mV) with low fertilization rate (P= 0.012). Spermatozoa with electrophysiological abnormities (conductance and Vm) responded normally to progesterone with elevation of [Ca2+]i and penetration of viscous medium, indicating retention of cation channel of sperm (CatSper) channel function. LIMITATIONS, REASONS FOR CAUTION. For practical, technical, ethical and logistical reasons, we could not obtain sufficient additional semen samples from men with conductance abnormalities to establish the cause of the conductance defects. Full exome sequencing was only available in two men with conductance defects. WIDER IMPLICATIONS OF THE FINDINGS. These data add significantly to the understanding of the role of ion channels in human sperm function and its impact on male fertility. Impaired potassium channel conductance (Gm) and/or Vm regulation is both common and complex in human spermatozoa and importantly is associated with impaired fertilization capacity when the Vm of cells is completely depolarized.

A survey of fingerprint classification Part I: taxonomies on feature extraction methods and learning models

This paper reviews the fingerprint classification literature looking at the problem from a double perspective. We first deal with feature extraction methods, including the different models considered for singular point detection and for orientation map extraction. Then, we focus on the different learning models considered to build the classifiers used to label new fingerprints. Taxonomies and classifications for the feature extraction, singular point detection, orientation extraction and learning methods are presented. A critical view of the existing literature have led us to present a discussion on the existing methods and their drawbacks such as difficulty in their reimplementation, lack of details or major differences in their evaluations procedures. On this account, an experimental analysis of the most relevant methods is carried out in the second part of this paper, and a new method based on their combination is presented.

Learning a Family of Detectors

Object detection and recognition are important problems in computer vision. The challenges of these problems come from the presence of noise, background clutter, large within class variations of the object class and limited training data. In addition, the computational complexity in the recognition process is also a concern in practice. In this thesis, we propose one approach to handle the problem of detecting an object class that exhibits large within-class variations, and a second approach to speed up the classification processes. In the first approach, we show that foreground-background classification (detection) and within-class classification of the foreground class (pose estimation) can be jointly solved with using a multiplicative form of two kernel functions. One kernel measures similarity for foreground-background classification. The other kernel accounts for latent factors that control within-class variation and implicitly enables feature sharing among foreground training samples. For applications where explicit parameterization of the within-class states is unavailable, a nonparametric formulation of the kernel can be constructed with a proper foreground distance/similarity measure. Detector training is accomplished via standard Support Vector Machine learning. The resulting detectors are tuned to specific variations in the foreground class. They also serve to evaluate hypotheses of the foreground state. When the image masks for foreground objects are provided in training, the detectors can also produce object segmentation. Methods for generating a representative sample set of detectors are proposed that can enable efficient detection and tracking. In addition, because individual detectors verify hypotheses of foreground state, they can also be incorporated in a tracking-by-detection frame work to recover foreground state in image sequences. To run the detectors efficiently at the online stage, an input-sensitive speedup strategy is proposed to select the most relevant detectors quickly. The proposed approach is tested on data sets of human hands, vehicles and human faces. On all data sets, the proposed approach achieves improved detection accuracy over the best competing approaches. In the second part of the thesis, we formulate a filter-and-refine scheme to speed up recognition processes. The binary outputs of the weak classifiers in a boosted detector are used to identify a small number of candidate foreground state hypotheses quickly via Hamming distance or weighted Hamming distance. The approach is evaluated in three applications: face recognition on the face recognition grand challenge version 2 data set, hand shape detection and parameter estimation on a hand data set, and vehicle detection and estimation of the view angle on a multi-pose vehicle data set. On all data sets, our approach is at least five times faster than simply evaluating all foreground state hypotheses with virtually no loss in classification accuracy.

Recognition of Human Action Using Moment-Based Feature

The performance of different classification approaches is evaluated using a view-based approach for motion representation. The view-based approach uses computer vision and image processing techniques to register and process the video sequence. Two motion representations called Motion Energy Images and Motion History Image are then constructed. These representations collapse the temporal component in a way that no explicit temporal analysis or sequence matching is needed. Statistical descriptions are then computed using moment-based features and dimensionality reduction techniques. For these tests, we used 7 Hu moments, which are invariant to scale and translation. Principal Components Analysis is used to reduce the dimensionality of this representation. The system is trained using different subjects performing a set of examples of every action to be recognized. Given these samples, K-nearest neighbor, Gaussian, and Gaussian mixture classifiers are used to recognize new actions. Experiments are conducted using instances of eight human actions (i.e., eight classes) performed by seven different subjects. Comparisons in the performance among these classifiers under different conditions are analyzed and reported. Our main goals are to test this dimensionality-reduced representation of actions, and more importantly to use this representation to compare the advantages of different classification approaches in this recognition task.

Mining Anomalies Using Traffic Feature Distributions

The increasing practicality of large-scale flow capture makes it possible to conceive of traffic analysis methods that detect and identify a large and diverse set of anomalies. However the challenge of effectively analyzing this massive data source for anomaly diagnosis is as yet unmet. We argue that the distributions of packet features (IP addresses and ports) observed in flow traces reveals both the presence and the structure of a wide range of anomalies. Using entropy as a summarization tool, we show that the analysis of feature distributions leads to significant advances on two fronts: (1) it enables highly sensitive detection of a wide range of anomalies, augmenting detections by volume-based methods, and (2) it enables automatic classification of anomalies via unsupervised learning. We show that using feature distributions, anomalies naturally fall into distinct and meaningful clusters. These clusters can be used to automatically classify anomalies and to uncover new anomaly types. We validate our claims on data from two backbone networks (Abilene and Geant) and conclude that feature distributions show promise as a key element of a fairly general network anomaly diagnosis framework.

Facial Feature Tracking and Occlusion Recovery in American Sign Language

Facial features play an important role in expressing grammatical information in signed languages, including American Sign Language(ASL). Gestures such as raising or furrowing the eyebrows are key indicators of constructions such as yes-no questions. Periodic head movements (nods and shakes) are also an essential part of the expression of syntactic information, such as negation (associated with a side-to-side headshake). Therefore, identification of these facial gestures is essential to sign language recognition. One problem with detection of such grammatical indicators is occlusion recovery. If the signer's hand blocks his/her eyebrows during production of a sign, it becomes difficult to track the eyebrows. We have developed a system to detect such grammatical markers in ASL that recovers promptly from occlusion. Our system detects and tracks evolving templates of facial features, which are based on an anthropometric face model, and interprets the geometric relationships of these templates to identify grammatical markers. It was tested on a variety of ASL sentences signed by various Deaf native signers and detected facial gestures used to express grammatical information, such as raised and furrowed eyebrows as well as headshakes.