Common Feature Extraction Research Articles

Common spatial pattern-based feature extraction from the best time segment of BCI data

Feature extraction is one of the most crucial stages in the field of brain computer interface (BCI). Because of its ability to directly influence the performance of BCI systems, recent studies have generally investigated how to modify existing methods or develop novel techniques. One of the most successful and well-known methods in BCI applications is the common spatial pattern (CSP). In existing CSP-based methods, the spatial filters were extracted either by using the whole data trial or by dividing the trials into a number of overlapping/nonoverlapping time segments. In this paper, we developed a CSP-based moving window technique to obtain the most distinguishable CSP features and increase the classifier performance by finding the best time segment of electroencephalogram trials. The extracted features were tested by using support vector machines (SVMs). The performance of the classifier was measured in terms of classification accuracy and kappa coefficient (κ) . The proposed method was successfully applied to the two-dimensional cursor movement imagery data sets, which were acquired from three healthy human subjects in two sessions on different days. The experiments proved that instead of using the whole data length of EEG trials, extracting CSP features from the best time segment provides higher classification accuracy and κ rates.

Rational function approximation for feature reduction in hyperspectral data

ABSTRACTIn this letter, we propose a feature extracting technique by using rational function curve fitting. A unique rational function curve is developed to fit the spectral signature of each pixel in a hyperspectral image. Polynomial coefficients in the numerator and denominator of the fitted curve are considered as new extracted features. The main contribution of this letter is utilization of curve-fitting ability in order to classify and compress hyperspectral data. In other words, naturally different curves can be discriminated when they are approximated by rational functions with equal form, but different amounts of coefficients. This rational function curve fitting feature extraction method provides better classification results compared to some common feature extraction algorithms when a maximum likelihood classifier is used. The method also has the ability of lossy data compression since the original data can be reconstructed using the fitted curves. In addition, the proposed algorithm has the possibility to be applied to all pixels of image individually, independently and simultaneously, unlike methods like principal component analysis which need to know all data points to compute the transformation matrix before transforming data points to new feature space.

Group Component Analysis for Multiblock Data: Common and Individual Feature Extraction.

Real-world data are often acquired as a collection of matrices rather than as a single matrix. Such multiblock data are naturally linked and typically share some common features while at the same time exhibiting their own individual features, reflecting the underlying data generation mechanisms. To exploit the linked nature of data, we propose a new framework for common and individual feature extraction (CIFE) which identifies and separates the common and individual features from the multiblock data. Two efficient algorithms termed common orthogonal basis extraction (COBE) are proposed to extract common basis is shared by all data, independent on whether the number of common components is known beforehand. Feature extraction is then performed on the common and individual subspaces separately, by incorporating dimensionality reduction and blind source separation techniques. Comprehensive experimental results on both the synthetic and real-world data demonstrate significant advantages of the proposed CIFE method in comparison with the state-of-the-art.

Statistical, Morphometric, Anatomical Shape Model (Atlas) of Calcaneus.

The aim was to develop a morphometric and anatomically accurate atlas (statistical shape model) of calcaneus. The model is based on 18 left foot and 18 right foot computed tomography studies of 28 male individuals aged from 17 to 62 years, with no known foot pathology. A procedure for automatic atlas included extraction and identification of common features, averaging feature position, obtaining mean geometry, mathematical shape description and variability analysis. Expert manual assistance was included for the model to fulfil the accuracy sought by medical professionals. The proposed for the first time statistical shape model of the calcaneus could be of value in many orthopaedic applications including providing support in diagnosing pathological lesions, pre-operative planning, classification and treatment of calcaneus fractures as well as for the development of future implant procedures.

Single trial EEG classification applied to a face recognition experiment using different feature extraction methods.

Research on brain machine interface (BMI) has been developed very fast in recent years. Numerous feature extraction methods have successfully been applied to electroencephalogram (EEG) classification in various experiments. However, little effort has been spent on EEG based BMI systems regarding familiarity of human faces cognition. In this work, we have implemented and compared the classification performances of four common feature extraction methods, namely, common spatial pattern, principal component analysis, wavelet transform and interval features. High resolution EEG signals were collected from fifteen healthy subjects stimulated by equal number of familiar and novel faces. Principal component analysis outperforms other methods with average classification accuracy reaching 94.2% leading to possible real life applications. Our findings thereby may contribute to the BMI systems for face recognition.

Feature extraction approaches from natural language requirements for reuse in software product lines: A systematic literature review

Requirements for implemented system can be extracted and reused for a production of a new similar system. Extraction of common and variable features from requirements leverages the benefits of the software product lines engineering (SPLE). Although various approaches have been proposed in feature extractions from natural language (NL) requirements, no related literature review has been published to date for this topic. This paper provides a systematic literature review (SLR) of the state-of-the-art approaches in feature extractions from NL requirements for reuse in SPLE. We have included 13 studies in our synthesis of evidence and the results showed that hybrid natural language processing approaches were found to be in common for overall feature extraction process. A mixture of automated and semi-automated feature clustering approaches from data mining and information retrieval were also used to group common features, with only some approaches coming with support tools. However, most of the support tools proposed in the selected studies were not made available publicly and thus making it hard for practitioners’ adoption. As for the evaluation, this SLR reveals that not all studies employed software metrics as ways to validate experiments and case studies. Finally, the quality assessment conducted confirms that practitioners’ guidelines were absent in the selected studies.

IBEX: an open infrastructure software platform to facilitate collaborative work in radiomics.

Radiomics, which is the high-throughput extraction and analysis of quantitative image features, has been shown to have considerable potential to quantify the tumor phenotype. However, at present, a lack of software infrastructure has impeded the development of radiomics and its applications. Therefore, the authors developed the imaging biomarker explorer (IBEX), an open infrastructure software platform that flexibly supports common radiomics workflow tasks such as multimodality image data import and review, development of feature extraction algorithms, model validation, and consistent data sharing among multiple institutions. The IBEX software package was developed using the MATLAB and c/c++ programming languages. The software architecture deploys the modern model-view-controller, unit testing, and function handle programming concepts to isolate each quantitative imaging analysis task, to validate if their relevant data and algorithms are fit for use, and to plug in new modules. On one hand, IBEX is self-contained and ready to use: it has implemented common data importers, common image filters, and common feature extraction algorithms. On the other hand, IBEX provides an integrated development environment on top of MATLAB and c/c++, so users are not limited to its built-in functions. In the IBEX developer studio, users can plug in, debug, and test new algorithms, extending IBEX's functionality. IBEX also supports quality assurance for data and feature algorithms: image data, regions of interest, and feature algorithm-related data can be reviewed, validated, and/or modified. More importantly, two key elements in collaborative workflows, the consistency of data sharing and the reproducibility of calculation result, are embedded in the IBEX workflow: image data, feature algorithms, and model validation including newly developed ones from different users can be easily and consistently shared so that results can be more easily reproduced between institutions. Researchers with a variety of technical skill levels, including radiation oncologists, physicists, and computer scientists, have found the IBEX software to be intuitive, powerful, and easy to use. IBEX can be run at any computer with the windows operating system and 1GB RAM. The authors fully validated the implementation of all importers, preprocessing algorithms, and feature extraction algorithms. Windows version 1.0 beta of stand-alone IBEX and IBEX's source code can be downloaded. The authors successfully implemented IBEX, an open infrastructure software platform that streamlines common radiomics workflow tasks. Its transparency, flexibility, and portability can greatly accelerate the pace of radiomics research and pave the way toward successful clinical translation.

COMPARATIVE STUDY OF CONTENT BASED IMAGE RETRIEVAL TECHNIQUES FOR BACTERIAL CELLS CLASSIFICATION

Abstract A major challenge in microbial ecology is to develop reliable and facile methods of computer assisted microscopy that can analyze digital images of complex microbial communities at single cell resolution, and compute useful quantitative characteristics of their organization and structure without cultivation. This paper performs a fair comparative study of three most common feature extraction methods for content based bacterial image classification; Color Coherence Vector (CCV), Gray Level Co-occurrence Matrix (GLCM) and Color Moments. The comparison is made on the basis of these parameters: Run time, CPU time, Recall, F-measure and Precision measures. Performance of Feature Extraction techniques based on the number of retrieved images, Run time and CPU time. Experiments results are given to analyses the effectiveness of each techniques and how that Color Moments technique is more suitable than other techniques. Keywords: Bacteria - Image processing – CBIR-CCV- GLCM- Color Moments.

Face recognition using PCA and different distance classifiers

A facial recognition system is a computer application for automatically identifying or verifying a person from a digital image or a video frame from a video source. One of the way is to do this is by comparing selected facial features from the image and a facial database. It is typically used in security systems and can be compared to other biometrics such as fingerprint or eye iris recognition systems. In this paper we focus on 3-D facial recognition system and biometric facial recognition system. We do critics on facial recognition system giving effectiveness and weaknesses. This paper also introduces scope of recognition system in India. Face recognition has received substantial attention from researchers in biometrics, pattern recognition field and computer vision communities. Face recognition can be applied in Security measure at Air ports, Passport verification, Criminals list verification in police department, Visa processing, Verification of Electoral identification and Card Security measure at ATM's. Principal Component Analysis (PCA) is a technique among the most common feature extraction techniques used in Face Recognition. In this paper, a face recognition system for personal identification and verification using Principal Component Analysis with different distance classifiers is proposed. The test results in the ORL face database produces interesting results from the point of view of recognition success, rate, and robustness of the face recognition algorithm. Different classifiers were used to match the image of a person to a class (a subject) obtained from the training data. These classifiers are: the City-Block Distance Classifier, the Euclidian distance classifier, the Squared Euclidian Distance Classifier, and

Fault Detection of Non-Gaussian Processes Based on Model Migration

In this paper, a new modeling approach is proposed for common and specific feature extraction. The original space of a mode can be separated into two different parts, namely, the common and specific ones. There are both non-Gaussian similarity and dissimilarity in the underlying correlations of different modes. After two different non-Gaussian blocks are separated, one can obtain the common and specific blocks, respectively. They play different roles in industrial batch processes, which are referred to as repetitive and complementary effects, respectively. Then, the common block and specific block are analyzed. A new multiblock monitoring method is proposed and the monitoring process is carried out in each block. The proposed method is applied to process monitoring of a continuous annealing process. Application results indicate that the proposed approach effectively captures the non-Gaussian relations to build the process model and improves the detection ability.

In silico identification of EGFR-T790M inhibitors with novel scaffolds: start with extraction of common features

BackgroundEpidermal growth factor receptor (EGFR) is an attractive therapeutic target for a number of human tumors including non-small cell lung cancer (NSCLC). Most patients with NSCLC and somatic mutations have shown a dramatic initial clinical response to reversible EGFR inhibitors. The clinical efficacy of reversible inhibitors is, however, ultimately limited due to the emergence of drug resistance, which is usually conferred by the EGFR T790M mutation. Importantly, irreversible, synthetic small molecule inhibitors are currently evaluated and some of them have been shown to overcome the acquired resistance that is oftentimes observed in these patients. Thus far, irreversible EGFR inhibitors as a drug class have not received regulatory approval due in part to their poor effectiveness at clinically achievable concentrations. Therefore, there is an urgent need to discover and develop novel, potent irreversible inhibitors against the EGFR T790M mutation.Material and methodsIn the following study, we report a novel “hybrid strategy” to identify irreversible EGFR inhibitors with active scaffolds starting with the identification and extraction of a common chemical reactive feature and a pharmacophore feature. The chemical reactive feature was elucidated by investigating 138 currently known irreversible inhibitors at B3LYP/6-31G(d) level using the density function theory method. The pharmacophore feature was extracted from the same inhibitors using pharmacophore modeling. Based on these unique features, two constraints were set while calibrating the protocols of in silico screening. Compounds bearing these specific features were obtained from the National Cancer Institute diversity database to form our subsequent library. Finally, a structure based virtual screening against the library was conducted using standard protocols validated in our lab.ResultsTwenty-eight candidate compounds that demonstrated antitumor activity and that had novel scaffolds different from commonly known quinazoline/quinoline analogs were obtained. The interaction modes between three representative candidates and our model system are similar to that between the model system and the reference compound T-001, which has previously been reported to be one of the most potent of the 138 irreversible inhibitors.ConclusionThe hybrid strategy starting with the extraction of common features is an effective approach to design potential irreversible inhibitors with novel scaffolds and therefore to obtain lead molecules in the selection process. These candidates possessing unique scaffolds have a strong likelihood to act as further starting points in the preclinical development of potent irreversible T790M EGFR inhibitors.

Compressed sensing with MCT and I(2D)2PCA processing for efficient face recognition

This article describes an effective human face recognition algorithm. Even though the principle component analysis (PCA) is one of the most common feature extraction methods, it is not suitable to implement a real-time embedded system for face recognition because large amount of computational load and memory capacity are necessary. To overcome this problem, we employ the incremental two-directional two-dimensional PCA (I(2D)2PCA) which is a combination of the (2D)2PCA to demand much less computational complexity than the conventional PCA and the incremental PCA (IPCA) to adapt the eigenspace only by using a new incoming sample datum without reusing of all the previous trained data. Furthermore, the modified census transform (MCT), a local normalization method useful for real-world application and implementation in an embedded system, is adopted to address robustness to illumination variations. To achieve better recognition accuracy with less computational load, the processed features are classified by the compressive sensing approach using l2–minimization. Experimental results on the Yale Face Database B show that the described system using the l2–minimization-based classification method for input data processed by the I(2D)2PCA and the MCT provided efficient and robust face recognition. © 2013 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 23, 133–139, 2013

Hot Rolling State Analysis Based on Kernel Principal Component Analysis and Information Entropy

With more and more process data acquired from manufacturing process, extracting useful information to build empirical models of past successful operations is urgently required to get higher product quality. Clustering is the important data mining methods, where feature extraction is a significant factor to ensure the accurate rate of clustering and classification. As a common non-linear feature extraction method, kernel principal component analysis (KPCA) uses the variance as the information metric, but the variance is not always effective in some cases. Since information entropy is nonlinear and can effectively represent the dependencies of features, the Renyi entropy is used as the information metric to extract the feature in this paper. Simulation data, Tennessee Eastman and hot rolling process data are used for model validation. As a result the proposed method has better performance on feature extraction, compared with traditional KPCA.

A novel automated spike sorting algorithm with adaptable feature extraction

To study the electrophysiological properties of neuronal networks, in vitro studies based on microelectrode arrays have become a viable tool for analysis. Although in constant progress, a challenging task still remains in this area: the development of an efficient spike sorting algorithm that allows an accurate signal analysis at the single-cell level. Most sorting algorithms currently available only extract a specific feature type, such as the principal components or Wavelet coefficients of the measured spike signals in order to separate different spike shapes generated by different neurons. However, due to the great variety in the obtained spike shapes, the derivation of an optimal feature set is still a very complex issue that current algorithms struggle with. To address this problem, we propose a novel algorithm that (i) extracts a variety of geometric, Wavelet and principal component-based features and (ii) automatically derives a feature subset, most suitable for sorting an individual set of spike signals. Thus, there is a new approach that evaluates the probability distribution of the obtained spike features and consequently determines the candidates most suitable for the actual spike sorting. These candidates can be formed into an individually adjusted set of spike features, allowing a separation of the various shapes present in the obtained neuronal signal by a subsequent expectation maximisation clustering algorithm. Test results with simulated data files and data obtained from chick embryonic neurons cultured on microelectrode arrays showed an excellent classification result, indicating the superior performance of the described algorithm approach.

Novel approach to 3D thermography and energy efficiency evaluation

This paper describes a new approach to multi-sensor registration of infrared images and 3D-laser scanner models, based on the extraction of common features in the IR image and the range image obtained from a laser-scanner 3D-point cloud. The workflow developed in this paper allows the automatic registration of two different sensors with completely different characteristics, including fields of view, spatial resolution and spatial position. As a result of the workflow, thermographic and geometric data are combined in a thermographic 3D-model and its projection as an orthothermogram, where thermal defects can be visually detected and precisely located, and heat losses can be quantified given the availability of surface measurements. This approach is applied to different types of constructions and building materials, showing its efficiency and appropriateness for building inspection and energy studies.

水下光束漂移激光图像抗畸变识别

Beam drift exists in underwater laser propagation. Influence of the beam drift on the images correlation recognition and the irrelevance between the random noise of inter-frame images were analyzed. The distortion-invariant matched filter design was studied, a phase-matching extraction of common features between distorted images was proposed, and the common features were used as the training samples of the synthetic discriminant function, based on which anti-distortion matching filter was designed and verified by a simulation. The Matlab simulation results show that the design of anti-distortion synthetic discriminant matching filter, combined with the pre-filtering of the image to be recognized, can effectively improve the PCE value (peak- the correlation energy ratio) of the correlation peak output and the disk values (peak identification rate).

A multi-center study of pediatric uroflowmetry data using patterning software

ObjectiveWe created software for patterning uroflowmetry (UFM) curves, and validated its utility. Patients and MethodsThe software patterns a given UFM curve upon four parameters: sex, voided volume, maximal flow rate, and amplitude of fluctuation. Using the software, 6 urologists from 4 institutes assessed 30 test curves. Further, 329 UFM curves obtained from children presenting to 3 institutes for daytime and/or nighttime wetting were assessed. Clinical presentation was divided into 3 groups: group A, daytime incontinence; group B, non-monosymptomatic nocturnal enuresis without daytime wetting; and group C, monosymptomatic nocturnal enuresis. ResultsUsing the software, inter-rater agreement ranged from 0.85 to 1.00 (mean, 0.93 ± 0.04). It could pattern 310 out of 329 clinical curves. In each institute, the tower pattern was prevalent according to severity of daytime symptoms, although not significantly. The merged data showed that the percent tower pattern significantly correlated with presence of daytime symptoms (groups A, B, and C, 29.7%, 27.0%, and 16.3%, respectively; p < 0.05). No correlation with daytime symptoms was noted for fluctuated (staccato and interrupted) and plateau patterns. ConclusionThe software creates a common platform for evaluating pediatric UFM, enabling extraction of common and biased features of different cohorts, and their integration into one single cohort.

Automatic Recognition of Boredom in Video Games Using Novel Biosignal Moment-Based Features

This paper presents work conducted toward the biosignals-based automatic recognition of boredom, induced during video-game playing. For this purpose, common biosignal feature extraction methods were exploited and their capability to identify boredom was assessed. Moreover, for the first time, Legendre and Krawtchouk moments, as well as novel moment variations, were extracted as biosignal features and their potential toward automatic affect recognition was examined using the specific application scenario. The present analysis was conducted with ECG and GSR data collected from 19 different subjects, while boredom was naturally induced during the repetitive playing of a 3D video game. Conventional biosignal features as well as moment-based ones were found to be effective for the automatic recognition of boredom by achieving classification accuracies around 85 percent. Then, the joint use of moments and moment variations with conventional features was found to significantly improve classification accuracy by producing a maximum correct classification ratio of 94.17 percent.

A public data hub for benchmarking common brain–computer interface algorithms

Methods of statistical machine learning have recently proven to be very useful in contemporary brain–computer interface (BCI) research based on the discrimination of electroencephalogram (EEG) patterns. Because of this, many research groups develop new algorithms for both feature extraction and classification. However, until now, no large-scale comparison of these algorithms has been accomplished due to the fact that little EEG data is publicly available. Therefore, we at Team PhyPA recorded 32-channel EEGs, electromyograms and electrooculograms of 36 participants during a simple finger movement task. The data are published on our website www.phypa.org and are freely available for downloading. We encourage BCI researchers to test their algorithms on these data and share their results. This work also presents exemplary benchmarking procedures of common feature extraction methods for slow cortical potentials and event-related desynchronization as well as for classification algorithms based on these features.

A modular CUDA-based framework for scale-space feature detection in video streams

Multi-scale image processing techniques enable extraction of features where the size of a feature is either unknown or changing, but the requirement to process image data at multiple scale levels imposes a substantial computational load. This paper describes the architecture and emerging results from the implementation of a GPGPU-accelerated scale-space feature detection framework for video processing. A discrete scale-space representation is generated for image frames within a video stream, and multi-scale feature detection metrics are applied to detect ridges and Gaussian blobs at video frame rates. A modular structure is adopted, in which common feature extraction tasks such as non-maximum suppression and local extrema search may be reused across a variety of feature detectors. Extraction of ridge and blob features is achieved at faster than 15 frames per second on video sequences from a machine vision system, utilizing an NVIDIA GTX 480 graphics card. By design, the framework is easily extended to additional feature classes through the inclusion of feature metrics to be applied to the scale-space representation, and using common post-processing modules to reduce the required CPU workload. The framework is scalable across multiple and more capable GPUs, and enables previously intractable image processing at video frame rates using commodity computational hardware.