Pattern Recognition Point Of View Research Articles

On Information Granulation via Data Filtering for Granular Computing-Based Pattern Recognition: A Graph Embedding Case Study

Granular Computing is a powerful information processing paradigm, particularly useful for the synthesis of pattern recognition systems in structured domains (e.g., graphs or sequences). According to this paradigm, granules of information play the pivotal role of describing the underlying (possibly complex) process, starting from the available data. Under a pattern recognition viewpoint, granules of information can be exploited for the synthesis of semantically sound embedding spaces, where common supervised or unsupervised problems can be solved via standard machine learning algorithms. In this companion paper, we follow our previous paper (Martino et al. in Algorithms 15(5):148, 2022) in the context of comparing different strategies for the automatic synthesis of information granules in the context of graph classification. These strategies mainly differ on the specific topology adopted for subgraphs considered as candidate information granules and the possibility of using or neglecting the ground-truth class labels in the granulation process and, conversely, to our previous work, we employ a filtering-based approach for the synthesis of information granules instead of a clustering-based one. Computational results on 6 open-access data sets corroborate the robustness of our filtering-based approach with respect to data stratification, if compared to a clustering-based granulation stage.

Intelligent electronic tongue system for the classification of genuine and false honeys

ABSTRACT Honey quality is a global concern since this product is highly susceptible to adulteration, given its competitive price. As a reliable strategy for honey authenticity determination, this work introduces an intelligent classification system that considers the pattern recognition point of view to develop an economical and quick analytical method to identify and differentiate genuine from adulterated honey. This work used an electronic tongue composed of three working electrodes of carbon, platinum, and gold. The system used Cyclic voltammetry to obtain data from 50 genuine and 50 adulterated honey samples. Subsequently, the system used multivariate data analysis using a pattern recognition methodology composed of three big stages, including data organization and normalization, dimensionality reduction, and k-Nearest Neighbors (k-NN) as a classification method. The process was validated with the Leave One Out Cross Validation technique (LOOCV), reaching a classification accuracy performance of 100%. The results show that it was possible the development of a combined methodology between analytical tools and chemometrics for an in-situ, quick and efficient authenticity honey evaluation.

On Information Granulation via Data Clustering for Granular Computing-Based Pattern Recognition: A Graph Embedding Case Study

Granular Computing is a powerful information processing paradigm, particularly useful for the synthesis of pattern recognition systems in structured domains (e.g., graphs or sequences). According to this paradigm, granules of information play the pivotal role of describing the underlying (possibly complex) process, starting from the available data. Under a pattern recognition viewpoint, granules of information can be exploited for the synthesis of semantically sound embedding spaces, where common supervised or unsupervised problems can be solved via standard machine learning algorithms. In this work, we show a comparison between different strategies for the automatic synthesis of information granules in the context of graph classification. These strategies mainly differ on the specific topology adopted for subgraphs considered as candidate information granules and the possibility of using or neglecting the ground-truth class labels in the granulation process. Computational results on 10 different open-access datasets show that by using a class-aware granulation, performances tend to improve (regardless of the information granules topology), counterbalanced by a possibly higher number of information granules.

Automated handwriting analysis based on pattern recognition: a survey

<span>Handwriting analysis has wide scopes include recruitment, medical diagnosis, forensic, psychology, and human-computer interaction. Computerized handwriting analysis makes it easy to recognize human personality and can help graphologists to understand and identify it. The features of handwriting use as input to classify a person’s personality traits. This paper discusses a pattern recognition point of view, in which different stages are described. The stages of study are data collection and pre-processing technique, feature extraction with associated personality characteristics, and the classification model. Therefore, the purpose of this paper is to present a review of the methods and their achievements used in various stages of a pattern recognition system. </span>

Dynamic Handwriting Analysis for the Assessment of Neurodegenerative Diseases: A Pattern Recognition Perspective.

Neurodegenerative diseases, for instance Alzheimer's disease (AD) and Parkinson's disease (PD), affect the peripheral nervous system, where nerve cells send messages that control muscles in order to allow movements. Sick neurons cannot control muscles properly. Handwriting involves cognitive planning, coordination, and execution abilities. Significant changes in handwriting performance are a prominent feature of AD and PD. This paper addresses the most relevant results obtained in the field of online (dynamic) analysis of handwritten trials by AD and PD patients. The survey is made from a pattern recognition point of view, so that different phases are described. Data acquisition deals not only with the device, but also with the handwriting task. Feature extraction can deal with function and parameter features. The classification problem is also discussed along with results already obtained. This paper also highlights the most profitable research directions.

Four-Dimensional Homogeneous Systolic Pyramid Automata

Cellular automaton is famous as a kind of the parallel automaton. Cellular automata were investigated not only in the viewpoint of formal language theory, but also in the viewpoint of pattern recognition. Cellular automata can be classified into some types. A systolic pyramid automata is also one parallel model of various cellular automata. A homogeneous systolic pyramid automaton with four-dimensional layers (4-HSPA) is a pyramid stack of four-dimensional arrays of cells in which the bottom four-dimensional layer (level 0) has size an (a≥1), the next lowest 4(a-1), and so forth, the (a-1)st fourdimensional layer (level (a-1)) consisting of a single cell, called the root. Each cell means an identical finite-state machine. The input is accepted if and only if the root cell ever enters an accepting state. A 4-HSPA is said to be a real-time 4-HSPA if for every four-dimensional tape of size 4a (a≥1), it accepts the fourdimensional tape in time a-1. Moreover, a 1- way fourdimensional cellular automaton (1-4CA) can be considered as a natural extension of the 1-way two-dimensional cellular automaton to four-dimension. The initial configuration is accepted if the last special cell reaches a final state. A 1-4CA is said to be a real- time 1-4CA if when started with fourdimensional array of cells in nonquiescent state, the special cell reaches a final state. In this paper, we proposed a homogeneous systolic automaton with four-dimensional layers (4-HSPA), and investigated some properties of real-time 4-HSPA. Specifically, we first investigated the relationship between the accepting powers of real-time 4-HSPA’s and real-time 1-4CA’s. We next showed the recognizability of four-dimensional connected tapes by real-time 4-HSPA’s.

Correcting Instrumental Variation and Time-Varying Drift: A Transfer Learning Approach With Autoencoders

Electronic noses (e-noses) are instruments that can be used to measure gas samples conveniently. Based on the measured signal, the type and concentration of the gas can be predicted by pattern recognition algorithms. However, e-noses are often affected by influential factors, such as instrumental variation and time-varying drift. From the viewpoint of pattern recognition, the factors make the posterior distribution of the test data drift from that of the training data, thus will degrade the accuracy of the prediction models. In this paper, we propose drift correction autoencoder (DCAE) to address this problem. DCAE learns to model and correct the influential factors explicitly with the help of transfer samples. It generates drift-corrected and discriminative representation of the original data, which can then be applied to various prediction algorithms. We evaluate DCAE on data sets with instrumental variation and complex time-varying drift. Prediction models are trained on samples collected with one device or in the initial time period, then tested on other devices or time periods. Experimental results show that the DCAE outperforms typical drift correction algorithms and autoencoder-based transfer learning methods. It can improve the robustness of e-nose systems and greatly enhance their performance in real-world applications.

A new approach to intrusion detection in databases by using artificial neuro fuzzy inference system

In this modern era of internet, security of data has become a primary concern due to exposure of databases on the web. The present study approaches the problem of database intrusion detection from a pattern recognition point of view, where artificial neuro fuzzy inference system (ANFIS) is used to capture user behavioural patterns. In this paper, we have proposed a database intrusion detection system using ANFIS as a classifier that is capable of outperforming in many ways and better suits the demands and dynamic nature of the problem. The proposed approach to intrusion detection gives a better detection rate and lowers the false positive rate compared to other traditional techniques.

Mirror representations innate versus determined by experience: a viewpoint from learning theory.

From the viewpoint of pattern recognition and computational learning, mirror neurons form an interesting multimodal representation that links action perception and planning. While it seems unlikely that all details of such representations are specified by the genetic code, robust learning of such complex representations likely requires an appropriate interplay between plasticity, generalization, and anatomical constraints of the underlying neural architecture.

Cochleagram-based audio pattern separation using two-dimensional non-negative matrix factorization with automatic sparsity adaptation

An unsupervised single channel audio separation method from pattern recognition viewpoint is presented. The proposed method does not require training knowledge and the separation system is based on non-uniform time-frequency (TF) analysis and feature extraction. Unlike conventional research that concentrates on the use of spectrogram or its variants, the proposed separation algorithm uses an alternative TF representation based on the gammatone filterbank. In particular, the monaural mixed audio signal is shown to be considerably more separable in this non-uniform TF domain. The analysis of signal separability to verify this finding is provided. In addition, a variational Bayesian approach is derived to learn the sparsity parameters for optimizing the matrix factorization. Experimental tests have been conducted, which show that the extraction of the spectral dictionary and temporal codes is more efficient using sparsity learning and subsequently leads to better separation performance.

Homogeneous Systolic Pyramid Automata with n-Dimensional Layers

Cellular automata were investigated not only in the viewpoint of formal language theory, but also in the viewpoint of pattern recognition. Cellular automata can be classified into some types. A systolic pyramid automata is also one parallel model of various cellular automata. A homogeneous systolic pyramid automaton with n-dimensional layers (n-HSPA) is a pyramid stack of n-dimensional arrays of cells in which the bottom n-dimensional layer (level 0) has size an (a≥1), the next lowest (a-1)n, and so forth, the (a-1)st n-dimensional layer (level (a-1)) consisting of a single cell, called the root. Each cell means an identical finite-state machine. The input is accepted if and only if the root cell ever enters an accepting state. An n-HSPA is said to be a real-time n-HSPA if for every n-dimensional tape of size a n (a≥1) it accepts the n-dimensional tape in time a-1. Moreover, a 1- way n-dimensional cellular automaton (1-nCA) can be considered as a natural extension of the 1-way two- dimensional cellular automaton to n-dimension. The initial configuration is accepted if the last special cell reaches a final state. A 1-nCA is said to be a real- time 1-nCA if when started with n-dimensional array of cells in nonquiescent state, the special cell reaches a final state. In this paper, we propose a homogeneous systolic automaton with n-dimensional layers (n-HSPA), and investigate some properties of real-time n-HSPA. Specifically, we first investigate a relationship between the accepting powers of real-time n-HSPA’s and real-time 1-nCA’s. We next show the recognizability of n-dimensional connected tapes by real-time n-HSPA’s.

Classification of aircraft targets with low-resolution radars based on multifractal spectrum features

The multifractal spectrum characteristics of aircraft echoes from low-resolution radars offer a fine description of dynamic characteristics which induce the echo structure; therefore, they can provide a new way for aircraft target classification and recognition with low-resolution radars. On basis of introducing the scattering mechanism of aircraft echoes from low-resolution radars, the paper analyzed the multifractal characteristics of aircraft echoes as well as the extraction method of their multifractal spectrum features by means of the multifractal analysis of measures and proposed the classification method for different types of aircraft targets from the viewpoint of pattern recognition. The classification experiment results with real recorded echo data showed the multifractal spectrum feature-based classification method can classify different types of aircraft targets effectively, so the defined characteristic parameters could be used as effective features for aircraft target classification and recognition.

Distance and similarity measures between intuitionistic fuzzy sets: A comparative analysis from a pattern recognition point of view

A detailed analysis of the distance and similarity measures for intuitionistic fuzzy sets proposed in the past is presented in this paper. This study aims to highlight the main theoretical and computational properties of the measures under study, while the relationships between them are also investigated. Along with the literature review, a comparison of the analyzed distance and similarity measures from a pattern recognition point of view in three different classification cases is also presented. Initially, some artificial counter-intuitive recognition cases are considered, while in a second phase real data from medical and well known pattern recognition benchmark problems are used to examine the discrimination abilities of the studied measures. Moreover, all the measures are applied in a face recognition problem for the first time and useful conclusions are drawn regarding the accuracy and confidence of the recognition results. Finally, the measures’ suitability and their drawbacks that make the development of more robust and efficient measures’ a still open issue are discussed.

Generating 3 Dimensional Pavilions Described in Mayamatam; a Traditional Indian Architecture Treatise

The traditional or classical architecture of India is an interesting subject for exploration from different perspectives. Taking pavilions described in Mayamatam as a representative of the traditional or classical architecture of India and analyzing them from the viewpoint of pattern recognition and mathematics encouraging results are obtained. A pattern is seen in the development of the design of pavilions and has been coded alpha-numerically. Based on the system of development and employing computer applications software is created to design pavilions, which follow the principles of traditional architecture. This software has multiple benefits. It can be used as a teaching aid for the subject ‘history of Indian Architecture’. For architectural conservationists and heritage enthusiasts it offers itself as a tool to help in visualization and digital reconstruction. For architects it can be a means for making structures of recent times, which have the essence of traditional architecture. The aim of this paper is to highlight the methodology for preparing this software and demonstrating its output.

Matching suitability analysis for geomagnetic aided navigation based on an intelligent classification method

The problem of matching suitability for geomagnetic aided navigation is investigated from the viewpoint of pattern recognition in this article. In order to improve the classification accuracy of candidate matching areas, an intelligent classification method based on genetic algorithm and support vector machine is proposed. Firstly, the geomagnetic datasets and the factors influencing the classification performance of support vector machine are studied. Then support vector machine is employed as the classifier, and genetic algorithm is utilized for feature selection and support vector machine parameters optimization to improve the classification performance. Afterwards the multi-class support vector machine classifiers based on the one-against-one strategy are constructed for analyzing matching suitability. Experimental results show that the proposed method can greatly improve the classification accuracy of candidate matching areas, and moreover, the conclusions of this article can provide beneficial guidance for geomagnetic matching and route planning.

CLASSIFICATION OF AIRCRAFT TARGETS WITH SURVEILLANCE RADARS BASED ON FUZZY FRACTAL FEATURES

The fuzzy fractal characteristics of return signals from aircraft targets in conventional radars ofier a description of dynamic features which induce the echo structure of targets, therefore they can provide a new way for aircraft target classiflcation and recognition with low-resolution surveillance radars. On basis of introducing fuzzy fractal theory, the paper analyzes the fuzzy fractal characteristics of return signals from aircraft targets in a VHF-band surveillance radar by means of the fuzzy fractal analysis, and puts forward a fuzzy- fractal-feature-based classiflcation method for aircraft targets with a low-resolution radar from the viewpoint of pattern recognition. The analysis shows that the fuzzy fractal characteristic parameters such as the local fuzzy fractal dimension (LFFD) and local degree of fractality (LGF) can be used as efiective features for aircraft target classiflcation and recognition. The results of classiflcation experiments validate the proposed method.

Hausdorff-Based RC and IESIL Combined Positioning Algorithm for Underwater Geomagnetic Navigation

This paper presents a primitive solution with novel scheme and algorithm for Underwater geoMagnetic Navigation (UMN), which now occurs as the hot-point in the research field of navigation. UMN as an independent or supplementary technique can theoretically supply accurate locations for marine vehicles, but in practice there are plenty of restrictions for UMN's application (e.g., geomagnetic daily variation). After analysis of the theoretical model of geomagnetic positioning in the correlation-matching mode from the viewpoint of pattern recognition, this paper proposed an appropriate matching scenario and a combined positioning algorithm for UMN. The subalgorithm of Hausdorff-based Relative Correlation (RC) corresponding to the pattern classification module implements the coarse positioning, and the subalgorithm of Isograms Equidistance-Segmenting theIntersection Lines (IESILs) associated with the module of feature extraction continues the fine positioning. The experiments based on the simulation platform and the real-surveyed data both validate the new algorithm, and its efficiency and accuracy are also discussed. It can be concluded that the work introduced in this paper gives an initial and real validation of UMN's potentiality.

Invited paper: Automatic speech recognition: History, methods and challenges

The field of automatic speech recognition (ASR) is discussed from the viewpoint of pattern recognition (PR). This tutorial examines the problem area, its methods, successes and failures, focusing on the nature of the speech signal and techniques to accomplish useful data reduction. Comparison is made with other areas of PR. Suggestions are given for areas of future progress.

Joint Blind Super-Resolution and Shadow Removing

Most learning-based super-resolution methods neglect the illumination problem. In this paper we propose a novel method to combine blind single-frame super-resolution and shadow removal into a single operation. Firstly, from the pattern recognition viewpoint, blur identification is considered as a classification problem. We describe three methods which are respectively based on Vector Quantization (VQ), Hidden Markov Model (HMM) and Support Vector Machines (SVM) to identify the blur parameter of the acquisition system from the compressed/uncompressed low-resolution image. Secondly, after blur identification, a super-resolution image is reconstructed by a learning-based method. In this method, Logarithmic-wavelet transform is defined for illumination-free feature extraction. Then an initial estimation is obtained based on the assumption that small patches in low-resolution space and patches in high-resolution space share a similar local manifold structure. The unknown high-resolution image is reconstructed by projecting the intermediate result into general reconstruction constraints. The proposed method simultaneously achieves blind single-frame super-resolution and image enhancement especially shadow removal. Experimental results demonstrate the effectiveness and robustness of our method.

Soft data mining, computational theory of perceptions, and rough-fuzzy approach

Data mining and knowledge discovery is described from pattern recognition point of view along with the relevance of soft computing. Key features of the computational theory of perceptions and its significance in pattern recognition and knowledge discovery problems are explained. Role of fuzzy-granulation (f-granulation) in machine and human intelligence, and its modeling through rough-fuzzy integration are discussed. Merits of fuzzy granular computation, in terms of performance and computation time, for the task of case generation in large scale case-based reasoning systems are illustrated through an example.