Pattern Recognition Applications Research Articles

The Enhanced-Earned Value Management (E-EVM) Model: A Proposal for the Aerospace Industry

The framework of this paper is the aerospace industry, which is one of the world’s leading sectors, thus playing a noteworthy role in current society. This makes it especially important to try to optimize the management of the aerospace sector. Therefore, the main objective of this paper is to propose the so-called Enhanced-Earned Value Management (hereinafter, E-EVM) model, able to explore the simultaneous evaluation of many projects, from which the management of the project can take advantage. Additionally, this model considers the possibility of forecasting pending tasks, measurable in time units or cost units, until the end of the project. The main contribution of E-EVM methodology is its capacity to detect both delayed and advanced projects by converting times (hours) into monetary units (EUR). Empirically, this enhanced model has been applied to a real case study in the aerospace industry composed of thousands of subprojects and the results provide the project manager with valuable information to make decisions in a short term. Through computer graphic representation techniques, the visualization of project deployment can be improved. Finally, the E-EVM model can be used even in big projects where a very large volume of information must be simultaneously treated and also, it will be suitable to apply pattern recognition concerning the project performance.

Distilling Structure from Imagery:Graph-based Models for the Interpretation of Document Images

From its early stages, the community of Pattern Recognition and Computer Vision has considered the importance of leveraging the structural information when understanding images. Usually, graphs have been proposed as a suitable model to represent this kind of information due to their flexibility and representational power able to codify both, the components, objects, or entities and their pairwise relationship. Even though graphs have been successfully applied to a huge variety of tasks, as a result of their symbolic and relational nature, graphs have always suffered from some limitations compared to statistical approaches. Indeed, some trivial mathematical operations do not have an equivalence in the graph domain. For instance, in the core of many pattern recognition applications, there is a need to compare two objects. This operation, which is trivial when considering feature vectors defined in ℝn, is not properly defined for graphs. In this thesis, we have investigated the importance of the structural information from two perspectives, the traditional graph-based methods and the new advances on Geometric Deep Learning. On the one hand, we explore the problem of defining a graph representation and how to deal with it on a large scale and noisy scenario. On the other hand, Graph Neural Networks are proposed to first redefine a Graph Edit Distance methodologies as a metric learning problem, and second, to apply them in a real use case scenario for the detection of repetitive patterns which define tables in invoice documents. As experimental framework, we have validated the different methodological contributions in the domain of Document Image Analysis and Recognition.

Pythagorean fuzzy points and applications in pattern recognition and Pythagorean fuzzy topologies

Pythagorean fuzzy points and applications in pattern recognition and Pythagorean fuzzy topologies

Fuzzy Information Inequalities and Application in Pattern Recognition

Fuzzy Information Inequalities and Application in Pattern Recognition

The Wasserstein-Fourier Distance for Stationary Time Series

We propose the Wasserstein-Fourier (WF) distance to measure the (dis)similarity between time series by quantifying the displacement of their energy across frequencies. The WF distance operates by calculating the Wasserstein distance between the (normalised) power spectral densities (NPSD) of time series. Yet this rationale has been considered in the past, we fill a gap in the open literature providing a formal introduction of this distance, together with its main properties from the joint perspective of Fourier analysis and optimal transport. As the main aim of this work is to validate WF as a general-purpose metric for time series, we illustrate its applicability on three broad contexts. First, we rely on WF to implement a PCA-like dimensionality reduction for NPSDs which allows for meaningful visualisation and pattern recognition applications. Second, we show that the geometry induced by WF on the space of NPSDs admits a geodesic interpolant between time series, thus enabling data augmentation on the spectral domain, by averaging the dynamic content of two signals. Third, we implement WF for time series classification using parametric/non-parametric classifiers and compare it to other classical metrics. Supported on theoretical results, as well as synthetic illustrations and experiments on real-world data, this work establishes WF as a meaningful and capable resource pertinent to general distance-based applications of time series.

Adaptive Electrode Calibration Method Based on Muscle Core Activation Regions and Its Application in Myoelectric Pattern Recognition.

To reduce the bad effect of electrode shifts on myoelectric pattern recognition, this paper presents an adaptive electrode calibration method based on core activation regions of muscles. In the proposed method, the high-density surface electromyography (HD-sEMG) matrix collected during hand gesture execution is decomposed into source signal matrix and mixed coefficient matrix by fast independent component analysis algorithm firstly. The mixed coefficient vector whose source signal has the largest two-norm energy is selected as the major pattern, and core activation region of muscles is extracted by traversing the major pattern periodically using a sliding window. The electrode calibration is realized by aligning the core activation regions in unsupervised way. Gestural HD-sEMG data collection experiments with known and unknown electrode shifts are carried out on 9 gestures and 11 participants. A CNN+LSTM-based network is constructed and two network training strategies are adopted for the recognition task. The experimental results demonstrate the effectiveness of the proposed method in mitigating the bad effect of electrode shifts on gesture recognition accuracy and the potentials in reducing user training burden of myoelectric control systems. With the proposed electrode calibration method, the overall gesture recognition accuracies increase about (5.72~7.69)%. In specific, the average recognition accuracy increases (13.32~17.30)% when using only one batch of data in data diversity strategy, and increases (12.01~13.75)% when using only one repetition of each gesture in model update strategy. The proposed electrode calibration algorithm can be extended and applied to improve the robustness of myoelectric control system.

Open Access Dataset, Toolbox and Benchmark Processing Results of High-Density Surface Electromyogram Recordings.

We provide an open access dataset of High densitY Surface Electromyogram (HD-sEMG) Recordings (named "Hyser"), a toolbox for neural interface research, and benchmark results for pattern recognition and EMG-force applications. Data from 20 subjects were acquired twice per subject on different days following the same experimental paradigm. We acquired 256-channel HD-sEMG from forearm muscles during dexterous finger manipulations. This Hyser dataset contains five sub-datasets as: (1) pattern recognition (PR) dataset acquired during 34 commonly used hand gestures, (2) maximal voluntary muscle contraction (MVC) dataset while subjects contracted each individual finger, (3) one-degree of freedom (DoF) dataset acquired during force-varying contraction of each individual finger, (4) N-DoF dataset acquired during prescribed contractions of combinations of multiple fingers, and (5) random task dataset acquired during random contraction of combinations of fingers without any prescribed force trajectory. Dataset 1 can be used for gesture recognition studies. Datasets 2-5 also recorded individual finger forces, thus can be used for studies on proportional control of neuroprostheses. Our toolbox can be used to: (1) analyze each of the five datasets using standard benchmark methods and (2) decompose HD-sEMG signals into motor unit action potentials via independent component analysis. We expect our dataset, toolbox and benchmark analyses can provide a unique platform to promote a wide range of neural interface research and collaboration among neural rehabilitation engineers.

Identification of Babbitt Damage and Excessive Clearance in Journal Bearings through an Intelligent Recognition Approach

Journal bearings play an important role on many rotating machines placed on industrial environments, especially in steam turbines of thermoelectric power plants. Babbitt damage (BD) and excessive clearance (C) are usual faults of steam turbine journal bearings. This paper is focused on achieving an effective identification of these faults through an intelligent recognition approach. The work was carried out through the processing of real data obtained from an industrial environment. In this work, a feature selection procedure was applied in order to choose the features more suitable to identify the faults. This feature selection procedure was performed through the computation of typical testors, which allows working with both quantitative and qualitative features. The classification tasks were carried out by using Nearest Neighbors, Voting Algorithm, Naïve Associative Classifier and Assisted Classification for Imbalance Data techniques. Several performance measures were computed and used in order to assess the classification effectiveness. The achieved results (e.g., six performance measures were above 0.998) showed the convenience of applying pattern recognition techniques to the automatic identification of BD and C.

Fractional‐order generalized Laguerre moments and moment invariants for grey‐scale image analysis

Here, a new set of fractional-order moments, named fractional-order generalized Laguerre moments (FGLM), is introduced. These proposed moments are defined on the Cartesian coordinate system and their basis functions are represented by the fractional-order generalized Laguerre polynomials. Contrary to the classical Chebyshev, Legendre and Gegenbauer moments, which provide only global feature, our proposed FGLM have the ability to extract both global and local features. Moreover, a new set of rotation, scale and translation invariants of the FGLM, is derived and introduced for image classification and invariant pattern recognition. Just as important, we have presented a systematic parameter selection method for finding the optimal fractional parameter values with respect to pattern recognition applications. Finally, several recursive methods for reducing the computation time of our proposed invariants are also provided in this study. Therefore, to demonstrate the performance of the introduced fractional-order moments and moment invariants, a number of experimental analysis are performed in terms of global and local features extraction, robustness to noise, invariance to geometric deformations, object recognition and computational speed. The presented theoretical and experimental results clearly show that the proposed fractional-order moments and their corresponding invariants could be extremely useful in the field of image analysis.

A kernel-based weight decorrelation for regularizing CNNs

Recent years has witnessed the success of convolutional neural networks (CNNs) in many machine learning and pattern recognition applications, especially in image recognition. However, due to the increasing model complexity, the parameter redundancy problem arises, and greatly degrades the performance of CNNs. To alleviate this problem, various regularization techniques, such as Dropout, have been proposed and proved their effectiveness. In this paper, we propose a novel adaptive kernel-based weight decorrelation (AKWD) framework, in order to regularize CNNs for better generalization. Different from existing works, the correlation between paring weights is measured by the cosine distance defined in RKHS associated with a specific kernel. The case with the well-known Gaussian kernel is investigated in detail, where the bandwidth parameter is adaptively estimated. By regularizing CNN models of different capacities using AKWD, better performance is achieved on several benchmark databases for both object classification and face verification tasks. In particular, when Dropout or BatchNorm is present, even higher improvements are obtained using the proposed AKWD, that demonstrates a good compatibility of the proposed regularizer with other regularization techniques.

New similarity measures for single-valued neutrosophic sets with applications in pattern recognition and medical diagnosis problems

The single-valued neutrosophic set (SVNS) is a well-known model for handling uncertain and indeterminate information. Information measures such as distance measures, similarity measures and entropy measures are very useful tools to be used in many applications such as multi-criteria decision making (MCDM), medical diagnosis, pattern recognition and clustering problems. A lot of such information measures have been proposed for the SVNS model. However, many of these measures have inherent problems that prevent them from producing reasonable or consistent results to the decision makers. In this paper, we propose several new distance and similarity measures for the SVNS model. The proposed measures have been verified and proven to comply with the axiomatic definition of the distance and similarity measure for the SVNS model. A detailed and comprehensive comparative analysis between the proposed similarity measures and other well-known existing similarity measures has been done. Based on the comparison results, it is clearly proven that the proposed similarity measures are able to overcome the shortcomings that are inherent in existing similarity measures. Finally, an extensive set of numerical examples, related to pattern recognition and medical diagnosis, is given to demonstrate the practical applicability of the proposed similarity measures. In all numerical examples, it is proven that the proposed similarity measures are able to produce accurate and reasonable results. To further verify the superiority of the suggested similarity measures, the Spearman’s rank correlation coefficient test is performed on the ranking results that were obtained from the numerical examples, and it was again proven that the proposed similarity measures produced the most consistent ranking results compared to other existing similarity measures.

Performances of non-parameterised radial basis functions in pattern recognition applications

Pattern recognition appears in many applications with most popular scheme are those involved the so-called ‘Radial Basis Function (RBF)’. It is known that the shape parameter contained in some RBFs used has great influence on the final quality of prediction. This study focusses on RBFs which contains no parameters where three data patterns are used for performance validation. With a good choice of number of centres, it is clearly possible to obtain satisfactory results with no burden on choosing the suitable or optimal shape. This can well shed more light into applications with more complexity with less user’s judgment and be more automatic in the process.

Fault Diagnosis of an Analog Circuit Based on Hierarchical DVS

Analog circuit fault diagnosis technology is widely used in the diagnosis of various electronic devices. The basic strategy is to extract circuit fault characteristics and then to use a clustering algorithm for diagnosis. The discrete Volterra series (DVS) is a common feature extraction method; however, it is difficult to calculate its parameters. To solve the problem of feature extraction in fault diagnosis, we propose an improved hierarchical Levenberg–Marquardt (LM)–DVS algorithm (IDVS). First, the DVS is simplified on the basis of the hierarchical symmetry of the memory parameters, the LM strategy is used to optimize the coefficients, and a Bayesian information criterion based on the symmetry of entropy is introduced for order selection. Finally, we propose a fault diagnosis method by combining the improved DVS algorithm and a condensed nearest neighbor algorithm (CNN) (i.e., the IDVS–CNN method). A simulation experiment was conducted to verify the feature extraction and fault diagnosis ability of the IDVS–CNN. The results show that the proposed method outperforms conventional methods in terms of the macro and micro F1 scores (0.903 and 0.894, respectively), which is conducive to the efficient application of fault diagnosis. In conclusion, the improved method in this study is helpful to simplify the calculation of the DVS parameters of circuit faults in analog electronic systems, and provides new insights for the prospective application of circuit fault diagnosis, system modeling, and pattern recognition.

Applications of picture fuzzy similarity measures in pattern recognition, clustering, and MADM

Picture fuzzy set (PFS) is a direct extension of fuzzy sets (FSs) and intuitionistic fuzzy sets (IFSs) and is quite powerful than FSs and IFSs in expressing the uncertainty and vagueness in our daily life problems. In this article, we propose some new similarity measures for PFSs which are capable of distinguishing highly similar but inconsistent PFSs. We also demonstrate their applications in pattern recognition using some illustrative examples as well as with real data. We assess the performance of the proposed measures using the concept of degree of confidence. We also extend the maximum spanning tree (MST) clustering algorithm to PF (picture fuzzy)-environment and propose a picture fuzzy maximum spanning tree (PFMST) clustering method. Further, we introduce a new attribute weight determining formula based on PF-similarity measures in multi-attribute decision-making (MADM) problem. We also establish the superiority of our proposed PF-similarity measures over some existing PF-similarity measures in view of the structured linguistic variables.

New set of adapted Gegenbauer–Chebyshev invariant moments for image recognition and classification

Orthogonal moments and their invariants to geometric transformations for gray-scale images are widely used in many pattern recognition and image processing applications. In this paper, we propose a new set of orthogonal polynomials called adapted Gegenbauer–Chebyshev polynomials (AGC). This new set is used as a basic function to define the orthogonal adapted Gegenbauer–Chebyshev moments (AGCMs). The rotation, scaling, and translation invariant property of (AGCMs) is derived and analyzed. We provide a novel series of feature vectors of images based on the adapted Gegenbauer–Chebyshev orthogonal moments invariants (AGCMIs). We practice a novel image classification system using the proposed feature vectors and the fuzzy k-means classifier. A series of experiments is performed to validate this new set of orthogonal moments and compare its performance with the existing orthogonal moments as Legendre invariants moments, the Gegenbauer and Tchebichef invariant moments using three different image databases: the MPEG7-CE Shape database, the Columbia Object Image Library (COIL-20) database and the ORL-faces database. The obtained results ensure the superiority of the proposed AGCMs over all existing moments in representation and recognition of the images.

Image Classification Schemes Based on Statistical Moments of Wavelet and Sliced Radial Energy Distribution of DCT

Texture recognition is used in various pattern recognition applications and texture classification that possess a characteristic appearance. This research paper aims to provide an improved scheme to provide enhanced classification decisions and to decrease processing time significantly. This research studied the discriminating characteristics of textures by extracting them from various texture images using discrete Wavelate transform (DWT) and discrete Cosine transform DCT. Two sets of features are proposed; the first set was extracted using the traditional DCT, while the second used DWT. The features from the Cosine domain are calculated using the radial distribution of spectra, while for those extracted from Wavelet was statistical distribution of various relative moments. Four types of Euclidean distance metrics were used for classification decision purposes. The considered method was applied on 475 classes of textures belonged to 32 sets from Salzburg Texture Image Database, each set holding 16 images per class, so the a total of 7600 images were tested. Each image was separated into three bands of color component (i.e., red, green, blue). Concepts of average and standard deviation were calculated to determine the inter/intra scatter analysis for each feature to find out the best discriminating features that can be used. The final result of DWT was 99.98 for the testing sets and 99.71 for the training sets, while the final result of DCT was 99.06 for the testing sets and 96.77 for the training sets.

Image Classification Schemes Based on Gradient Matrix and Contrast Matrices

Texture classification and categorizing are used in various pattern recognition applications and classification texture that possesses a characteristic appearance. This work aims to provide an improved scheme of enhanced classification decision with the need to increase the precision time significantly. This research studied the discriminating characteristics of textures by extracting the feature from gradient matrix (GM), the features were extracted using the first-order gradient feature vector, three Gradient Matrices were established, one for Max value, another for Min value and last was the Average value, these matrices were calculated by extracting the gradient along x-axis and y-axis and the gradient along the diagonal. A feature vector consist of 210 features was calculated to represent each image sample and contrast matrix CM, The feature extracted from CM1 was The difference between the sum of the neighborhood values of 3x3 pixels those larger than the pixel values (center pixels) divided by their number and the sum of the neighborhoods values of 3x3 pixels those smaller than the pixel value divided by their number total feature vector was 210, Four types of Euclidean distance metrics were used for classification decision purposes. The concepts “average” and “standard deviation” were calculated to perform the interentra scatter analysis for each feature to find out the best discriminating features that can be used. The final result of the test set of GM is 98.3 while training set was 97.3, the final result of the test set of CM is 98.2 while training set was 95.7.

Applying Pattern Recognition as a Robust Approach for Silicone Oil Droplet Identification in Flow-Microscopy Images of Protein Formulations.

Discrimination between potentially immunogenic protein aggregates and harmless pharmaceutical components, like silicone oil, is critical for drug development. Flow imaging techniques allow to measure and, in principle, classify subvisible particles in protein therapeutics. However, automated approaches for silicone oil discrimination are still lacking robustness in terms of accuracy and transferability. In this work, we present an image-based filter that can reliably identify silicone oil particles in protein therapeutics across a wide range of parenteral products. A two-step classification approach is designed for automated silicone oil droplet discrimination, based on particle images generated with a flow imaging instrument. Distinct from previously published methods, our novel image-based filter is trained using silicone oil droplet images only and is, thus, independent of the type of protein samples imaged. Benchmarked against alternative approaches, the proposed filter showed best overall performance in categorizing silicone oil and non-oil particles taken from a variety of protein solutions. Excellent accuracy was observed particularly for higher resolution images. The image-based filter can successfully distinguish silicone oil particles with high accuracy in protein solutions not used for creating the filter, showcasing its high transferability and potential for wide applicability in biopharmaceutical studies.

Unsupervised color image segmentation: A case of RGB histogram based K-means clustering initialization.

Color-based image segmentation classifies pixels of digital images in numerous groups for further analysis in computer vision, pattern recognition, image understanding, and image processing applications. Various algorithms have been developed for image segmentation, but clustering algorithms play an important role in the segmentation of digital images. This paper presents a novel and adaptive initialization approach to determine the number of clusters and find the initial central points of clusters for the standard K-means algorithm to solve the segmentation problem of color images. The presented scheme uses a scanning procedure of the paired Red, Green, and Blue (RGB) color-channel histograms for determining the most salient modes in every histogram. Next, the histogram thresholding is applied and a search in every histogram mode is performed to accomplish RGB pairs. These RGB pairs are used as the initial cluster centers and cluster numbers that clustered each pixel into the appropriate region for generating the homogeneous regions. The proposed technique determines the best initialization parameters for the conventional K-means clustering technique. In this paper, the proposed approach was compared with various unsupervised image segmentation techniques on various image segmentation benchmarks. Furthermore, we made use of a ranking approach inspired by the Evaluation Based on Distance from Average Solution (EDAS) method to account for segmentation integrity. The experimental results show that the proposed technique outperforms the other existing clustering techniques by optimizing the segmentation quality and possibly reducing the classification error.

A Method of Classification Performance Improvement Via a Strategy of Clustering-Based Data Elimination Integrated with k-Fold Cross-Validation

Non-system errors that occur during data entry or data collection create noisy data that reduce the success of classification systems. To eliminate this data, a classification system with a new data reduction method consisting of a modified k-means algorithm using relief algorithm coefficients named MKMA-RAC was developed. The main theme of this article is the elimination of noisy data and its consistent application to the classification system using the k-fold cross-validation method. By means of the developed system, the training data became free from noisy data by integrating the support vector machine, linear discriminant analysis (LDA) and decision tree classifiers with MKMA-RAC-based data reduction for every fold. The data reduction process was not applied for the test data. Datasets used in the proposed method were the Hepatitis, Liver Disorders, SPECT images and Statlog (Heart) dataset taken from the UCI database. Classification performance values obtained both from the proposed method and without the proposed method with tenfold CV were given for these datasets. For Hepatitis, Liver Disorders, SPECT images and Statlog (Heart) datasets, and classification successes of the proposed system with SVM classifier were 96.88%, 74.56%, 87.24%, and 90.00%, classification successes of the proposed system with LDA classifier were 94.91%, 69.05%, 82.38%, and 88.52%, classification successes of the proposed system with decision tree classifier were 96.25%, 77.73%, 88.77% and 89.63%, respectively. The test results have shown that the proposed system generally achieved higher classification performance than other literature results. Therefore, the performance is very encouraging for pattern recognition applications.