Search

This paper considers the use of machine learning for diagnosis of diseases that is based on the analysis of a complete gene expression profile. This distinguishes our study from other approaches that require a preliminary step of finding a limited number of relevant genes (tens or hundreds of genes). We conducted experiments with complete genetic expression profiles (20 531 genes) that we obtained after processing transcriptomes of 801 patients with known oncologic diagnoses (oncology of the lung, kidneys, breast, prostate, and colon). Using the indextron (instant learning index system) for a new purpose, i.e., for complete expression profile processing, provided diagnostic accuracy that is 99.75% in agreement with the results of histological verification. [ABSTRACT FROM AUTHOR]

Sign language is a non-verbal communication tool used by the deaf. A robust sign language recognition framework is needed to develop Human–Robot Interaction (HRI) platforms that are able to interact with humans via sign language. Iranian sign language (ISL) is composed of both static postures and dynamic gestures of the hand and fingers. In this paper, we present a robust framework using a Deep Neural Network (DNN) to recognize dynamic ISL gestures captured by motion capture gloves in Real-Time. To this end, first, a dataset of fifteen ISL classes was collected in time series; then, this dataset was virtually augmented and pre-processed using the "state-image" method to produce a unique collection of images, each image corresponding to a specific set of sequential data representing a class. Next, by implementing a continuous Genetic algorithm, an optimal deep neural network with the minimum number of weights (trainable parameters) and the maximum overall accuracy was found. Finally, the dataset was fed to the DNN to train the model. The results showed that the optimization process was successful at finding a DNN structure highly suitable for this application, with 99.7% accuracy on the verification (test) data. Then, after implementing the module in a robotic architecture, an HRI experiment was conducted to assess the system's performance in real-time applications. Preliminary statistical analysis on the standard UTAUT model for eight participants showed that the system can recognize ISL signs quickly and accurately during human–robot interaction. The proposed methodology can be used for other sign languages as no specific characteristics of ISL were used in the preprocessing or training stage. [ABSTRACT FROM AUTHOR]

This paper provides a short survey of the main direction of activity of the Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences (FRC CSC RAS) in the areas concerning the topics of the journal Pattern Recognition and Image Analysis. The FRC CSC RAS was founded in December 2014 through the reorganization of the Institute of Informatics Problems of the Russian Academy of Sciences (IIP RAS) (by including the Institute for System Analysis of the Russian Academy of Sciences (ISA RAS) and the Dorodnycin Computing Center of the Russian Academy of Sciences (DCC RAS)). Section 1 reviews the activity of these institutes before their merger. Section 2 studies the work performed after 2015. [ABSTRACT FROM AUTHOR]

Semantic segmentation involves extracting meaningful information from images or input from a video or recording frames. It is the way to perform the extraction by checking pixels by pixel using a classification approach. It gives us more accurate and fine details from the data we need for further evaluation. Formerly, we had a few techniques based on some unsupervised learning perspectives or some conventional ways to do some image processing tasks. With the advent of time, techniques are improving, and we now have more improved and efficient methods for segmentation. Image segmentation is slightly simpler than semantic segmentation because of the technical perspective as semantic segmentation is pixels based. After that, the detected part based on the label will be masked and refer to the masked objects based on the classes we have defined with a relevant class name and the designated color. In this paper, we have reviewed almost all the supervised and unsupervised learning algorithms from scratch to advanced and more efficient algorithms that have been done for semantic segmentation. As far as deep learning is concerned, we have many techniques already developed until now. We have studied around 120 papers in this research area. We have concluded how deep learning is helping in solving the critical issues of semantic segmentation and gives us more efficient results. We have reviewed and comprehensively studied different surveys on semantic segmentation, specifically using deep learning. [ABSTRACT FROM AUTHOR]

Fungi are one of the major causes that contributed to plant diseases. There are lots of fungi species but it is estimated that only 10% have been described. There are two major approaches to identifying fungi species, morphological identification, and molecular test which need cautious clarification to make good interpretations and are time-consuming. In this paper, we propose a Machine Learning approach that involves the use of the K-Means clustering technique, and Decision Tree to highlight the observed fungi spore images taken under the microscopic view and discard background pixels to produce digital images database which later can be used for Deep Learning. [ABSTRACT FROM AUTHOR]

Precision livestock farming consists of technological tools and techniques to improve livestock management. Proper detection and classification of jaw movement (JM) events are indispensable for the estimation of dry matter intake, detection of health problems, and flag the onset of estrus, among other information. The analysis of acoustic signals is one of the most accepted ways to monitor the feeding behavior of free-grazing cattle. Different acoustic methods have been developed for recognizing JM-events in recent years. However, their operation is limited to off-line analysis on a personal computer. The lack of on-line acoustic monitoring systems is associated with the challenging operation requirements (low-power consumption, autonomy, portability, robustness and non-intrusive on the animal). In this paper, a fixed-point variant of the chew-bite energy-based algorithm is presented. This algorithm is implemented on a new low-power audio processor system for real-time recognition of JM-events. The system includes a Nanocontroller processor, which is always-on and detects JM-events; and a second transport-triggered architecture (TTA) based processor, which is mainly in power-down and classifies JM-events. The results demonstrate that the proposed fixed-point JM-events recognizer achieves a recognition rate of 91.4% and 90.2% in noiseless and noisy conditions, respectively. The recognition rate increases by 6.1% regarding a previous reference on-line system. Moreover, the proposed audio processor system chip consumes 4 μW on average, i.e., only 2.3% of the power of an always-on TTA-based processor system for the same audio sequence. An exemplary implementation of the proposed system in a 65 nm low-leakage CMOS technology is given. [ABSTRACT FROM AUTHOR]

Methods for face verification works reasonably well on face images with standardized (frontal) face positions and good spatial resolution. However such methods have significant challenges on poor resolution images, poor lighting conditions and not standard (frontal) face positions. In this paper, we survey the capability of existing face restoration and verification methods, with the aim of understanding how useful face restoration methods are for face verification. We propose a qualitative and quantitative comparison benchmark, and apply it on eight methods for face restoration and six methods for face verification, on several real-world low-quality images from a surveillance context, and outline observed advantages and limitations. Experiments shows that each restoration method can affect each face verification method differently, with fewer than the half of face restoration methods helping face verification. Interestingly, some face restoration methods with less good qualitative evaluation helped face verification the most. Experiments also show that face verification works less good if the resolution decreases. [ABSTRACT FROM AUTHOR]

Machine Learning (ML) and Deep Learning (DL) have achieved high success in many textual, auditory, medical imaging, and visual recognition patterns. Concerning the importance of ML/DL in recognizing patterns due to its high accuracy, many researchers argued for many solutions for improving pattern recognition performance using ML/DL methods. Due to the importance of the required intelligent pattern recognition of machines needed in image processing and the outstanding role of big data in generating state-of-the-art modern and classical approaches to pattern recognition, we conducted a thorough Systematic Literature Review (SLR) about DL approaches for big data pattern recognition. Therefore, we have discussed different research issues and possible paths in which the abovementioned techniques might help materialize the pattern recognition notion. Similarly, we have classified 60 of the most cutting-edge articles put forward pattern recognition issues into ten categories based on the DL/ML method used: Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Generative Adversarial Network (GAN), Autoencoder (AE), Ensemble Learning (EL), Reinforcement Learning (RL), Random Forest (RF), Multilayer Perception (MLP), Long-Short Term Memory (LSTM), and hybrid methods. SLR method has been used to investigate each one in terms of influential properties such as the main idea, advantages, disadvantages, strategies, simulation environment, datasets, and security issues. The results indicate most of the articles were published in 2021. Moreover, some important parameters such as accuracy, adaptability, fault tolerance, security, scalability, and flexibility were involved in these investigations. [ABSTRACT FROM AUTHOR]

Systematic pattern recognition as well as the corresponding description of determined patterns entail numerous challenges in the application context of high-dimensional communication data. These can cause increased effort, especially with regard to machine-based processing concerning the determination of regularities in underlying datasets. Due to the increased expansion of dimensions in multidimensional data spaces, determined patterns are no longer interpretable by humans. Taking these challenges into account, this paper investigates to what extent pre-defined communication patterns can be interpreted for the application area of high-dimensional business communication data. An analytical perspective is considered by taking into account a holistic research approach and by subsequently applying selected Machine Learning methods from Association Rule Discovery, Topic Modelling and Decision Trees with regard to the overall goal of semi-automated pattern labelling. The results show that meaningful descriptions can be derived for the interpretation of pre-defined patterns. [ABSTRACT FROM AUTHOR]

Nowadays, political parties have widely adopted social media for their party promotions and election campaigns. During the election, Twitter and other social media platforms are used for political coverage to promote the party and its candidates. This research discusses and estimates the stability of many volumetric social media approaches to forecast election results from social media activities. Numerous machine learning approaches are applied to opinions shared on social media for predicting election results. This paper presents a machine learning model based on sentiment analysis to predict Pakistan's general election results. In a general election, voters vote for their favorite party or candidate based on their personal interests. Social media has been extensively used for the campaign in Pakistan general election 2018. Using a machine learning technique, we provide a five-step process to analyze the overall election results, whether fair or unfair. The work is concluded with detailed experimental results along with discussion on the outcomes of sentiment analysis for real-world forecasting and approval of general elections in Pakistan. [ABSTRACT FROM AUTHOR]

Bioinformatics is one of the emerging and rapidly developing research areas that is predominantly used for genetic data analysis and processing. Bioinformatics is characterized by its huge and voluminous data that is growing in nature which in turn complicates data analysis. In most cases, Bioinformatics data analysis and processing involve big data analytics due to the complex nature of the data. Previous research works handled data analytics using traditional tools and conventional big data analytical methods. However, it can be proved that machine learning algorithms and approaches can be effectively deployed to perform parallel, distributed and incremental processing of complex big data analytics especially in the case of gene big data analytics to enhance the efficiency in processing this large chunk of Bioinformatics-based gene big data. This paper provides a Machine Learning algorithm-based Convolution Neural Network (ML-CNN) approach for the process of identifying potential target genes, predicting miRNAs, visualizing the unique miRNA patterns, and validating genomes. The proposed approach has experimented with MATLAB software using deep learning toolbox on the pre - miRNA dataset. Experimental results indicate that machine learning algorithms certainly increases the efficiency of Bioinformatics-based methods of processing gene data in terms of prediction accuracy and reduced processing time. The mean performance of ML-CNN is improved 7% high than the existing system. [ABSTRACT FROM AUTHOR]

This paper develops a prognostic technique called the logical analysis of survival curves (LASC). This technique is used to learn the degradation process of any physical asset, and consequently to predict its failure time (T). It combines the reliability information that is obtained from a classical Kaplan–Meier non-parametric curve to that obtained from online measurements of multiple sensed signals of degradation. An analysis of these signals by the machine learning technique, logical analysis of data (LAD), is performed to exploit the instantaneous knowledge about the state of degradation of the asset studied. The experimental results of the predictions of failure times for cutting tools are reported. The results show that LASC prognostic results are better than the results obtained by well-known machine learning techniques. Other advantages of the proposed techniques are also discussed. [ABSTRACT FROM AUTHOR]

Iris image-based biometric systems are commonly used in applications that demand security, authentication, recognition and faster login access. In solving these real-time problems, the impact of soft computing techniques which employ cognitive skills is very high. Although this system has been commercialized, the scope for improvement is still plenty. This paper introduces the reader to different segments of an iris recognition system and reviews the techniques involved with each segment. It reports on how research articles validate the robustness of an iris-based recognition system. As these systems are fallible, it also shows the vulnerabilities associated with each segment and provides insights to develop much better intelligent and robust techniques which will make the system more accurate. This paper also shows that in spite of versatility of soft computing techniques, it is not fully exploited for iris recognition systems. The present challenges and directions for future research are also discussed. [ABSTRACT FROM AUTHOR]

The systematic processing of unstructured communication data as well as the milestone of pattern recognition in order to determine communication groups in negotiations bears many challenges in Machine Learning. In particular, the so-called curse of dimensionality makes the pattern recognition process demanding and requires further research in the negotiation environment. In this paper, various selected renowned clustering approaches are evaluated with regard to their pattern recognition potential based on high-dimensional negotiation communication data. A research approach is presented to evaluate the application potential of selected methods via a holistic framework including three main evaluation milestones: the determination of optimal number of clusters, the main clustering application, and the performance evaluation. Hence, quantified Term Document Matrices are initially pre-processed and afterwards used as underlying databases to investigate the pattern recognition potential of clustering techniques by considering the information regarding the optimal number of clusters and by measuring the respective internal as well as external performances. The overall research results show that certain cluster separations are recommended by internal and external performance measures by means of a holistic evaluation approach, whereas three of the clustering separations are eliminated based on the evaluation results. [ABSTRACT FROM AUTHOR]

This paper starts a brief historical overview of occurrence and development of fuzzy systems and their applications. Integration methods are proposed to construct a fuzzy system using other AI methods, achieving synergy effect. Accuracy and interpretability are selected as main properties of rule-based fuzzy systems. The tradeoff between interpretability and accuracy is considered to be the actual problem. The purpose of this paper is the in-depth study of the methods and tools to achieve a tradeoff for accuracy and interpretability in rule-based fuzzy systems and to describe our interpretability indexes. A comparison of the existing ways of interpretability estimation has been made We also propose the new way to construct heuristic interpretability indexes as a quantitative measure of interpretability. In the main part of this paper we describe previously used approaches, the current state and original authors' methods for achieving tradeoff between accuracy and complexity. [ABSTRACT FROM AUTHOR]

This paper is concerned with the problem of improving the convergence properties of evolutionary neural networks, particularly in the context of hybrid neural networks that adopt a diversity of transfer functions at their nodes, i.e.: neural diversity machines. The paper explores the potential of solution complementarity, in the context of pattern recognition problems, and focuses on its incorporation in the selection process of recombination heuristics. In a pattern recognition context, complementarity is defined as the ability of different solutions to correctly classify complementary subsets of patterns. A broad set of experiments was conducted demonstrating that solution selection based on complementarity is statistically significantly better than random selection, in a wide range of conditions, e.g.: different datasets, recombination heuristics and architectural constraints. Although the experiments demonstrated the statistical significance and robustness of the effect, they also indicated that more work is required to increase the degree of the effect and to scale-up to larger and more complex datasets. [ABSTRACT FROM AUTHOR]

The existing matrixized learning machines (MLMs) use bilateral weight vectors on both side of one pattern as the constraints to manipulate matrix-based datasets directly. However, MLM might be challenged while the input pattern is a vector whose features are independent from each others. The traditional solution is to transform the vector into its all corresponding matrix forms, which is not only irrational, but also requiring extra computation in preprocessing. To overcome the problem, this paper proposes a novel matrixized learning model that utilizes an efficient clustering-based interpolation strategy to mapping the original vector-based pattern to an unique matrix. The proposed method first selects the most typical features defined as $$candidate\hbox {s}$$ from each dimension of all patterns in the same class through a fast clustering method, and then measures the relationship between the features of each training pattern and the $$candidate\hbox {s}$$ to generate a new matrix named the candidate-matrix in turn. Afterwards, the candidate-matrix is combined with the pattern to form the corresponding final matrix. At last, all final matrices are collected to form the new training set for the subsequent matrixized classifier. Named FCIMLM for short, the proposed matrixized method is proved more effective and efficient than the traditional MLM under the same structural risk minimum framework through the designed experiments on 21 vector-based benchmark datasets from UCI repository. The main contributions of this paper are: (1) proposing a new matrixized learning model with a more efficient matrixization process using a feature-based fast clustering strategy; (2) combining the feature-clustering-based interpolation to the matrix-pattern-oriented classifier for the first time; (3) extending the existing MLM design techniques. [ABSTRACT FROM AUTHOR]

Machine Learning as network attack detection is one of the popular methods researched. Signature based network attack detection is no longer convinced the efficiency in the diversified intrusions (Limmer and Dressler in 17th ACM Conference on Computer and Communication Security, ). Moreover, as the various Zero-day attacks, non notified attacks cannot be detected (Wu and Banzhaf in Appl Soft Comput 10(1):1-35, ). This paper suggests an effective update method of data set on Machine Learning to detect non notified attacks. In addition, this paper compares and verifies the effects of Machine Learning Detection with updated data set to the former methods. [ABSTRACT FROM AUTHOR]

Studies recently accomplished on the Enteric Nervous System have shown that chronic degenerative diseases affect the Enteric Glial Cells (EGC) and, thus, the development of recognition methods able to identify whether or not the EGC are affected by these type of diseases may be helpful in its diagnoses. In this work, we propose the use of pattern recognition and machine learning techniques to evaluate if a given animal EGC image was obtained from a healthy individual or one affect by a chronic degenerative disease. In the proposed approach, we have performed the classification task with handcrafted features and deep learning-based techniques, also known as non-handcrafted features. The handcrafted features were obtained from the textural content of the ECG images using texture descriptors, such as the Local Binary Pattern (LBP). Moreover, the representation learning techniques employed in the approach are based on different Convolutional Neural Network (CNN) architectures, such as AlexNet and VGG16, with and without transfer learning. The complementarity between the handcrafted and non-handcrafted features was also evaluated with late fusion techniques. The datasets of EGC images used in the experiments, which are also contributions of this paper, are composed of three different chronic degenerative diseases: Cancer, Diabetes Mellitus, and Rheumatoid Arthritis. The experimental results, supported by statistical analysis, show that the proposed approach can distinguish healthy cells from the sick ones with a recognition rate of 89.30% (Rheumatoid Arthritis), 98.45% (Cancer), and 95.13% (Diabetes Mellitus), being achieved by combining classifiers obtained on both feature scenarios. [ABSTRACT FROM AUTHOR]

This paper presents an optical character/text recognition (OCR) system for cursive scripts like those of Arabic, Urdu, Persian, Kurdish, etc. This OCR system is a large-scale one in the sense of architecture, training data size, and state-of-the-art performance. The paper introduces the theoretical derivation and experimental assessment of our two main contributions deployed in this OCR. The first contribution is the design of a new autonomously normalized, lossless, and compact feature vector that enables the production of a truly robust omnifont OCR system for cursive scripts with an ASR-like HMM-based architecture. Half of the components in this feature vector are analogs and the other half are discrete, which obstructs the use of continuous Gaussian mixtures to model an aggregate of such features and mandates the use of discrete HMMs instead, which in turn necessitates the deployment of vector clustering and quantization. The second contribution is a new soft (i.e., probabilistic) vector quantization (VQ) scheme, as opposed to conventional hard-deciding VQ that we analytically derive and then deploy to alleviate overfitting and boost the robustness of our OCR against different kinds of obtrusive variances. We present experimental evidence of these benefits of the presented soft VQ scheme to our OCR. Other machine-learning systems with VQ modules may also deploy soft VQ to obtain the same benefits. [ABSTRACT FROM AUTHOR]

Purpose: The development and application of intelligent models to perform vibration-based condition monitoring in industry seems to be receiving attention in recent years. A number of such research studies using the artificial intelligence, machine learning, pattern recognition, etc., are available in the literature on this topic. These studies essentially used the machine vibration responses with known machine faults to develop smart fault diagnosis models. These models are yet to be tested for all kinds of machine faults and/or different operating conditions. Therefore, the purpose is to develop a generic machine faults diagnosis model that can be applied blindly to any identical machines with high confidence level in accuracy of the predictions. Methods: In this paper, a supervised smart fault diagnosis model is developed. This model is developed using the available measured vibration responses for the different rotor faults simulated on an experimental rotating rig operating at a constant speed. The developed smart vibration-based machine learning (SVML) model is then blindly tested to identify the healthy and faulty conditions of the rig when operating at different speeds. Results and conclusions: Several scenarios are proposed and examined during the development of the SVML model. It is observed that scenario of the vibration measurements simultaneously from all bearings from a machine is capable to fully map the machine dynamics in the VML model. Therefore, this developed when applied blindly to the sets of data at a different machine speed, the results are observed to be encouraging. The results clearly show a possibility for a centralised vibration-based condition monitoring (CVCM) model for identical machines operating at different rotating speeds. [ABSTRACT FROM AUTHOR]

In the world of information retrieval, recognizing hand-written digits stands as an interesting application of machine learning (deep learning). Though this is already a matured field, a way to recognize digits using an effective optimization using soft computing technique is a challenging task. Training such a system with larger data often fails due to higher computation and storage. In this paper, a recurrent deep neural network with hybrid mini-batch and stochastic Hessian-free optimization (MBSHF) is for accurate and faster convergence of predictions as outputs. A second-order approximation is used for achieving better performance for solving quadratic equations which greatly depends on computation and storage. Also, the proposed technique uses an iterative minimization algorithm for faster convergence using a random initialization though huge additional parameters are involved. As a solution, a convex approximation of MBSHF optimization is formulated and its performance on experimenting with the standard MNIST dataset is discussed. A recurrent deep neural network till a depth of 20 layers is successfully trained using the proposed MBSHF optimization, resulting in a better quality performance in computation and storage. The results are compared with other standard optimization techniques like mini-batch stochastic gradient descent (MBSGD), stochastic gradient descent (SGD), stochastic Hessian-free optimization (SHF), Hessian-free optimization (HF), nonlinear conjugate gradient (NCG). The proposed technique produced higher recognition accuracy of 12.2% better than MBSGD, 27.2% better than SHF, 35.4% better than HF, 40.2% better than NCG and 32% better than SGD on an average when applied to 50,000 testing sample size. [ABSTRACT FROM AUTHOR]

In statistical process monitoring, data mining algorithms are applied for control chart pattern recognition (CCPR) not only to detect but also to identify abnormal patterns associated with assignable causes. Recently, the use of support vector machines (SVMs) has achieved remarkable results in statistical process control applications due to its excellent generalization performance. Although there is a lot of research that highlights the superiority of support vector machine over other algorithms used in systems based on data mining control, there are no studies that analyze the design elements of a SVM classifier. Consequently, a comprehensive review, classification and an analysis of information found in the literature are presented in this paper regarding to the SVM classifier. The aim of this research is to provide researchers a starting point to potentiate the performance of the SVM classifier for assuring the best possible classification and improving the detection efficiency. Sixty-one research articles from 2001 to 2015 are critically analyzed based on their methodology following a classification scheme derived from the support vector classification framework. The analysis showed that the feature extraction and selection play a crucial role on the performance of classifiers. Studies revealed that using extracted features or a combination of raw data and feature extraction achieves better classification performances than using only raw data as an input. On the other hand, there is an ample gap to extend the research on internal structure configurations under various types of kernels, multi-classification, and ensemble approaches. Finally, this paper evidences that the application of nature inspired algorithms for kernel parameter selection in auto-correlated SVM-based process monitoring systems remains unexplored. [ABSTRACT FROM AUTHOR]

The main problem in the handwritten character recognition systems (HCR) is to describe each character by a set of features that can distinguish it from the other characters. Thus, in this paper, we propose a robust set of features extracted from isolated Amazigh characters based on decomposing the character image into zones and calculate the density and the total length of the histogram projection in each zone. In the experimental evaluation, we test the proposed set of features, to show its performance, with different classification algorithms on a large database of handwritten Amazigh characters. The obtained results give recognition rates that reach 99.03% which we presume good and satisfactory compared to other approaches and show that our proposed set of features is useful to describe the Amazigh characters. [ABSTRACT FROM AUTHOR]

Nowadays, while steganography is the main mean of illegal secret communication, the need of detecting steganographic content and especially stego images is becoming more compulsory. Since multimedia content can be easily spread over the internet and more complicated steganography algorithms in different domains i.e. spatial, transform are utilized, the task of identifying stego images becomes very difficult. Early steganalysis methods deploy statistical attacks on stego images while more recent ones use deep learning techniques. The latter ones mainly utilize convolutional neural networks and show promising results. In this paper we propose a novel method to identify stego images derived from two different steganographic algorithms S-UNIWARD (Spatial-UNIversal WAvelet Relative Distortion) and WOW (Wavelet Obtained Weights) for various embedding rates. The proposed method initially utilizes a dilated convolutional neural network as a feature extractor and afterwards the extracted feature vector trains a random forest classifier. More specifically it is proved that in steganalysis, a dilated convolutional neural network could be an excellent feature extractor and the traditional softmax layer could be replaced by another machine learning classifier. Extensive experiments were conducted, and the proposed model was also compared against state-of the-art convolutional neural networks utilized in spatial image steganalysis, and other feature extraction methods. Results showed that the proposed method achieves high classification accuracy and outperforms other analogous steganalysis approaches. [ABSTRACT FROM AUTHOR]

Machine learning has played an essential role in the past decades and has been in lockstep with the main advances in computer technology. Given the massive amount of data generated daily, there is a need for even faster and more effective machine learning algorithms that can provide updated models for real-time applications and on-demand tools. This paper presents FEMa—a finite element machine classifier—for supervised learning problems, where each training sample is the center of a basis function, and the whole training set is modeled as a probabilistic manifold for classification purposes. FEMa has its theoretical basis in the finite element method, which is widely used for numeral analysis in engineering problems. It is shown FEMa is parameterless and has a quadratic complexity for both training and classification phases when basis functions are used that satisfy certain properties. The proposed classifier yields very competitive results when compared to some state-of-the-art supervised pattern recognition techniques. [ABSTRACT FROM AUTHOR]

Workers healthcare gained a lot of attention recently as many countries are increasingly concerning about welfare. This paper faces the problem of predicting occupational disease risks by means of computational intelligence and pattern recognition techniques. Specifically, three different machine learning approaches are compared: the first one is based on the k-means algorithm, in charge to determine a set of meaningful labelled clusters as the final model. The latter two are based on fully supervised techniques, namely Support Vector Machines and K-Nearest Neighbours. Real data regarding both the worker and the workplace by mixing numerical and categorical attributes have been used for testing. The three approaches are automatically tuned by means of genetic algorithms in order to simultaneously find the optimal hyperparameters for the classification systems and the optimal ad-hoc dissimilarity measure weights in order to maximize the classification performances. Computational results show that the three approaches are rather comparable in terms of performances, but a clustering-based approach allows a deeper knowledge discovery phase, helpful for further risk assessment and forecasting. [ABSTRACT FROM AUTHOR]

Mineral grain recognition is an extremely important task in many fields, especially in mineral exploration, when trying to identify locations where precious minerals can possibly be found. The usual manual method would be to collect samples; a specialized individual using expensive equipment would manually identify and then count the grain minerals in the sample. This is a tedious task that is time-consuming and expensive. It is also limited because small portions of areas can be surveyed; even then, it might require extremely long periods. In addition, this process is still prone to human errors. Developing an automatic system to identify, recognize, and count grain minerals in samples from images would allow for more precise results than the time required by humans. In addition, such systems can be fitted on robots that collect samples, take images of the samples, and then proceed with the automated recognition and counting algorithm without human intervention. Vast amounts of land can be surveyed in this way. This paper proposes a modified approach for microscopic grain mineral recognition and classification using hybrid features and ensemble algorithms from images. The enhanced approach also included a modified segmentation approach, which enhanced the results. For 10 classes of microscopic mineral grains, using the modified approach and the ensemble algorithm resulted in an average accuracy of 84.01%. For 8 classes, the average reported accuracy is 94.93% using the Boosting ensemble learning with the C4.5 classifier. The results obtained outperform similar methods reported in the extant literature. [ABSTRACT FROM AUTHOR]

A brief outline of a report made November 12, 2018 at the Scientific Session of the Mathematical Science Branch of the Russian Academy of Sciences is presented in the paper. The report is orientated to an audience far from the problems on data mining. The report is an overview and presents the author's personal considerations on the examined scientific field. [ABSTRACT FROM AUTHOR]

The most effective well-known methods in the context of static machine learning offer no alternative to evolution and dynamic adaptation to integrate new data or to restructure problems already partially learned. In this area, the incremental learning represents an interesting alternative and constitutes an open research field, becoming one of the major concerns of the machine learning and classification community. In this paper, we study incremental supervised learning techniques and their applications, especially in the field of pattern recognition. This article presents an overview of the main concepts and supervised algorithms of incremental learning, including a synthesis of research studies done in this field and focusing on neural networks, decision trees and support vector machines. [ABSTRACT FROM AUTHOR]

New channels, new carriers continue to produce new data types, how to deal with complex and volatile multi-source data under IoT big data environment has become an important issue. Information perception is the basic content of the development of things, but also an important means to achieve information perception. Information interaction is the basic condition for the realization of Internet of things, but also the basic technology of interconnection. The information sensing of the Internet of Things is mainly the source of information provided by it, which is also the application base of the Internet of Things itself. To effectively process the IoT data, this paper proposes the multimodal intelligent data analyzing paradigm for Internet of things systems. Our proposed multiple game theory based data analyzing paradigm will guarantee the optimal combination of the mentioned model to construct the effect and robust analyzing pattern. We construct the optimal combination of Bayesian model, Decision Tree, Random Forest, Logistic Regression, SVM, Adaboost, Markov and Neural Network under the multiple game framework. Several new ideas are proposed to enhance the traditional Nash Equilibrium. Performance of the proposed method is validated through the simulation compared with the other state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

In this paper, we propose an anomaly detection system of machines using a hybrid learning mechanism that combines two kinds of machine learning approaches, namely unsupervised and non-parametric learning. To do so, we used vibration data, which is known to be suitable for anomaly detection in machines during operation. Furthermore, in order to take into account various characteristics of abnormal data such as scarcity and diversity, we propose a novel method that can detect anomalous behaviors using normal patterns instead of abnormal patterns from the machines. That is, we first perform a machine learning of the normal patterns of the machines during operation, and if any of the operation patterns deviates from the normal pattern, we identify that pattern as abnormal. A key characteristic of our system is that it does not use any prior information such as predefined data labels or data distributions to learn the normal operation patterns. To demonstrate the superiority of our system, we constructed a test bed consisting of a washing machine and a 3-axis accelerometer. We also demonstrated that our system can improve the accuracy of anomaly detection for the machines compared to other approaches. [ABSTRACT FROM AUTHOR]

Abstract: The real-time analysis of network data is of great significance to network security. Visualization technology and machine learning can assist in network data analysis from different aspects. However, there is little research regarding combining these two methods to process real-time network data. This paper proposes a novel real-time network security system. Combining unsupervised learning and visualization technology, it can identify network behavior patterns and provide a visualization module to adjust models interactively. The system is primarily divided into three parts. In the feature extraction part, we train a deep auto-encoder to compress the feature dimension. In the behavior pattern recognition part, normal and abnormal pattern SOINNs are trained incrementally. In visualization part, analysts can use multiple views to judge recognition results rapidly and adjust models so that the identification accuracy can be increased. We use the data in VAST Challenge 2013 to show that our system can identify network behavior patterns in real time and find the correlations between them. Graphical abstract: [ABSTRACT FROM AUTHOR]

In this paper, a new Chinese character recognition (CCR) approach is proposed based on the fuzzy clustering analysis theory. Chinese characters (CCs) have various similar radicals and stroke components, which make it difficult to recognize features in the CCR process. At the same time, the recognition accuracy and the efficiency are lower when the objects to be recognized are complex. In order to solve these problems, a fuzzy clustering analysis method is introduced to enhance the computing efficiency. At first, the CCs including learning samples and testing samples are transformed into binarization templates in the form of matrixes. Then, the minimum distance algorithm is applied to calculate 'distances' between the testing sample templates and the learning sample templates. At last, the character recognition can be achieved by searching the minimum distance from the results. The experiment results of the CCR process can prove the effectiveness and accuracy of the new method. [ABSTRACT FROM AUTHOR]

The use of computer-readable visual codes became common in our everyday life both in industrial environments and for private use. The reading process of visual codes consists of two steps, namely, localization and data decoding. In this paper we examine the localization step of visual codes using conventional and deep rectifier neural networks. They are also evaluated in the discrete cosine transform domain and shown to be efficient, which makes full decompression unnecessary for setups involving JPEG images. This approach is also efficient from a storage viewpoint and computation cost viewpoint, since camera hardware can provide a JPEG stream as output in many cases. The use of neural networks implemented on graphics processing unit allows real-time automatic code object localization. In our earlier studies, the proposed approach was evaluated on the most popular code type, quick response code, and some other 2D codes as well. Here, we also prove that deep rectifier networks are also suitable for 1D barcode localization and present extensive evaluation and comparison to state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Nowadays, millions of people are affected by heart diseases worldwide, whereas a considerable amount of them could be aided through an electrocardiogram (ECG) trace analysis, which involves the study of arrhythmia impacts on electrocardiogram patterns. In this work, we carried out the task of automatic arrhythmia detection in ECG patterns by means of supervised machine learning techniques, being the main contribution of this paper to introduce the optimum-path forest (OPF) classifier to this context. We compared six distance metrics, six feature extraction algorithms and three classifiers in two variations of the same dataset, being the performance of the techniques compared in terms of effectiveness and efficiency. Although OPF revealed a higher skill on generalizing data, the support vector machines (SVM)-based classifier presented the highest accuracy. However, OPF shown to be more efficient than SVM in terms of the computational time for both training and test phases. [ABSTRACT FROM AUTHOR]

Extreme learning machine (ELM) has become one of the new research hotspots in the field of pattern recognition and machine learning. However, the existing extreme learning machine algorithms cannot better use identification information of data. Aiming at solving this problem, we propose a regularized extreme learning machine (algorithm) based on discriminative information (called IELM). In order to evaluate and verify the effectiveness of the proposed method, experiments use widely used image data sets. The comparative experimental results show that the proposed algorithm in the paper can significantly improve the classification performance and generalization ability of ELM. [ABSTRACT FROM AUTHOR]

The number of traffic accidents in Brazil has reached alarming levels and is currently one of the leading causes of death in the country. With the number of vehicles on the roads increasing rapidly, these problems will tend to worsen. Consequently, huge investments in resources to increase road safety will be required. The vertical R-19 system for optical character recognition of regulatory traffic signs (maximum speed limits) according to Brazilian Standards developed in this work uses a camera positioned at the front of the vehicle, facing forward. This is so that images of traffic signs can be captured, enabling the use of image processing and analysis techniques for sign detection. This paper proposes the detection and recognition of speed limit signs based on a cascade of boosted classifiers working with haar-like features. The recognition of the sign detected is achieved based on the optimum-path forest classifier (OPF), support vector machines (SVM), multilayer perceptron, k-nearest neighbor (kNN), extreme learning machine, least mean squares, and least squares machine learning techniques. The SVM, OPF and kNN classifiers had average accuracies higher than 99.5 %; the OPF classifier with a linear kernel took an average time of 87 $$\upmu$$ s to recognize a sign, while kNN took 11,721 $$\upmu$$ s and SVM 12,595 $$\upmu$$ s. This sign detection approach found and recognized successfully 11,320 road signs from a set of 12,520 images, leading to an overall accuracy of 90.41 %. Analyzing the system globally recognition accuracy was 89.19 %, as 11,167 road signs from a database with 12,520 signs were correctly recognized. The processing speed of the embedded system varied between 20 and 30 frames per second. Therefore, based on these results, the proposed system can be considered a promising tool with high commercial potential. [ABSTRACT FROM AUTHOR]

Facial Expression Recognition is an already well-developed research area, mainly due to its applicability in the construction of different system types. Facial expressions are especially important in the area which relates to the construction of discourses through sign language. Sign languages are visual-spatial languages that are not assisted by voice intonation. Therefore, they use facial expressions to support the manifestation of prosody aspects and some grammatical constructions. Such expressions are called Grammatical Facial Expressions (GFEs) and they are present at sign language morphological and syntactic levels. GFEs stand out in automated recognition processes for sign languages, as they help removing ambiguity among signals, and they also contribute to compose the semantic meaning of discourse. This paper aims to present a study which applies inductive reasoning to recognize patterns, as a way to study the problem involving the automated recognition of GFEs at the discourse syntactic level in the Libras Sign Language (Brazilian Sign Language). In this study, sensor Microsoft Kinect was used to capture three-dimensional points in the faces of subjects who were fluent in sign language, generating a corpus of Libras phrases, which comprised different syntactic constructions. This corpus was analyzed through classifiers that were implemented through neural network Multilayer Perceptron, and then a series of experiments was conducted. The experiments allowed investigating: the recognition complexity that is inherent to each of the GFEs that are present in the corpus; the use suitability of different vector representations, considering descriptive characteristics that are based on coordinates of points in three dimensions, distances and angles therefrom; the need for using time data regarding the execution of expressions during speech; and particularities that are connected to data labeling and the evaluation of classifying models in the context of a sign language. [ABSTRACT FROM AUTHOR]

One of the main disadvantages of artificial neural networks is slow learning associated with the need to calculate a large number of coefficients. The article shows that learning can be substantially accelerated. Acceleration is achieved by a sharp reduction in the number of training patterns. In addition, the inverse pattern method was used both for the formation of features and for the subsequent recognition of objects; this has made it possible to dispense with coefficients, which significantly reduces the amount of calculations. In instantaneous learning, as in deep learning, features are generated automatically. Computational experiments have shown the invariance of the method with respect to not only scaling and rotations but also large deformations of objects to be recognized. [ABSTRACT FROM AUTHOR]

Static security analysis is an important study carried out in the control centers of electric utilities. Static security assessment (SSA) is the process of determining whether the current operational state is in a secure or emergency (insecure) state. Conventional method of security evaluation involves performing continuous load flow analysis, which is highly time consuming and infeasible for real-time applications. This led to the application of pattern recognition (PR) approach for static security analysis. This paper presents a more efficient design of a PR system suitable for on-line SSA. The feature selection stage in the PR system uses many algorithms to select the optimal feature set. This paper proposes the use of Support Vector Machine (SVM), a recently introduced machine learning tool, in the classifier design stage of PR system. The developed PR system is implemented in IEEE standard test systems for SSA and classification. The performance of SVM classifier is compared with the conventional K-nearest neighbor, method of least squares and neural network classifiers. Simulation results prove that the SVM-PR classifier outperforms other equivalent classifier algorithms, giving high classification accuracy and less misclassification rate. The feasibility of SVM-PR classifier for on-line security assessment process is also presented. [ABSTRACT FROM AUTHOR]

The problem to recognize objects that form an array of interrelated data is investigated. In the problem of machine learning, the array components belong to some class of a finite set. In this paper the interrelationship of array elements is presented by its adjacency graph. An efficient noniterative recognition algorithm for restoring an a posteriori marginal distributions of hidden classes for array elements is developed for a treelike adjacency graph. This algorithm modifies for each array element the hidden class distribution obtained as a result of learning for independent objects. Usually arbitrary graphs for real data contain cycles, for example, the rectangular adjacency lattice of points for 2D raster images or 3D seismic data. The treelike approximation of such graphs inevitably strongly distorts the interrelations between array elements. In the present paper, the reduced set of interrelations between array elements is balanced by an extended set of acyclic graphs themselves. By the example of the segmentation problem for texture raster images, we investigate a set of acyclic graphs and present the experimental results. [ABSTRACT FROM AUTHOR]

In this paper, we report on a prototype augmented reality (AR) platform for accessing abstract information in real-world pervasive computing environments. Using this platform, objects, people, and the environment serve as contextual channels to more information. The user's interest with respect to the environment is inferred from eye movement patterns, speech, and other implicit feedback signals, and these data are used for information filtering. The results of proactive context-sensitive information retrieval are augmented onto the view of a handheld or head-mounted display or uttered as synthetic speech. The augmented information becomes part of the user's context, and if the user shows interest in the AR content, the system detects this and provides progressively more information. In this paper, we describe the first use of the platform to develop a pilot application, Virtual Laboratory Guide, and early evaluation results of this application. [ABSTRACT FROM AUTHOR]

How to extract robust feature is an important research topic in machine learning community. In this paper, we investigate robust feature extraction for speech signal based on tensor structure and develop a new method called constrained Nonnegative Tensor Factorization (cNTF). A novel feature extraction framework based on the cortical representation in primary auditory cortex (A1) is proposed for robust speaker recognition. Motivated by the neural firing rates model in A1, the speech signal first is represented as a general higher order tensor. cNTF is used to learn the basis functions from multiple interrelated feature subspaces and find a robust sparse representation for speech signal. Computer simulations are given to evaluate the performance of our method and comparisons with existing speaker recognition methods are also provided. The experimental results demonstrate that the proposed method achieves higher recognition accuracy in noisy environment. [ABSTRACT FROM AUTHOR]

Historically, medical imaging repositories have been supported by indoor infrastructures. However, the amount of diagnostic imaging procedures has continuously increased over the last decades, imposing several challenges associated with the storage volume, data redundancy and availability. Cloud platforms are focused on delivering hardware and software services over the Internet, becoming an appealing solution for repository outsourcing. Although this option may bring financial and technological benefits, it also presents new challenges. In medical imaging scenarios, communication latency is a critical issue that still hinders the adoption of this paradigm. This paper proposes an intelligent Cloud storage gateway that optimizes data access times. This is achieved through a new cache architecture that combines static rules and pattern recognition for eviction and prefetching. The evaluation results, obtained from experiments over a real-world dataset, show that cache hit ratios can reach around 80%, leading to reductions of image retrieval times by over 60%. The combined use of eviction and prefetching policies proposed can significantly reduce communication latency, even when using a small cache in comparison to the total size of the repository. Apart from the performance gains, the proposed system is capable of adjusting to specific workflows of different institutions. [ABSTRACT FROM AUTHOR]

This paper presents a modified TLBO (teaching-learning-based optimization) approach for the local linear radial basis function neural network (LLRBFNN) model to classify multiple power signal disturbances. Cumulative sum average filter has been designed for localization and feature extraction of multiple power signal disturbances. The extracted features are fed as inputs to the modified TLBO-based LLRBFNN for classification. The performance of the proposed modified TLBO-based LLRBFNN model is compared with the conventional model in terms of convergence speed and classification accuracy. Also, an extreme learning machine (ELM) approach is used to optimize the performance of the proposed LLRBFNN and is compared with the TLBO method in classifying the multiple power signal disturbances. The classification results reveal that although the TLBO approach produces slightly better accuracy in comparison with the ELM approach, the latter is much faster in implementation, thus making it suitable for processing large quantum of power signal disturbance data. [ABSTRACT FROM AUTHOR]

A method of personality recognition by echographic parameters of the human ear is developed based on the naive Bayes classifier in the two following modes: the biometric identification (EER = 0.0053) and the biometric authentication (FRR = 0.0002 at FAR ≤ 0.0001), respectively. A device is developed for recording the biometric characteristics of the external ear, and a set of echographic data is collected from the external ears of 75 subjects. The spectral and cepstral characteristics of the signals reflected from the ear canal are used as biometric parameters. Several window functions for constructing spectra and cepstrograms are considered. It is established that more than 90% of "cepstral" features have a weak correlation, which allows us to use the naive Bayesian classifier and to obtain highly accurate results of user recognition at the same time. An advantage of the Bayesian classification is the possibility of the robust fast learning of the identification system. [ABSTRACT FROM AUTHOR]

The discrimination of similar patterns is important because they are the major sources of the classification error. This paper proposes a novel method to improve the discrimination ability of convolutional neural networks (CNNs) by hybrid learning. The proposed method embeds a collection of discriminators as well as a recognizer in a shared CNN. By visualizing contrastive class saliency, we show that learning with embedded discriminators leads the shared CNN to detect and catch the differences among similar classes. Also proposed is a hybrid learning algorithm that learns recognition and discrimination together. The proposed method learns recognition focusing on the differences among similar classes, and thereby improves the discrimination ability of the CNN. Unlike conventional discrimination methods, the proposed method does not require predefined sets of similar classes or additional step to integrate its result with that of the recognizer. In experiments on two handwritten Hangul databases SERI95a and PE92, the proposed method reduced classification error from 2.56 to 2.33, and from 4.04 to 3.66 % respectively. These improvement lead to relative error reduction rates of 8.97 % on SERI95a, and 9.42 % on PE92. Our best results update the state-of-the-art performance which were 4.04 % on SERI95a and 7.08 % on PE92. [ABSTRACT FROM AUTHOR]

Invasive weed optimization (IWO) is a recently published heuristic optimization technique that resembles other evolutionary optimization methods. This paper proposes a new classification technique based on the IWO algorithm, called the invasive weed classification (IWC), to face the problem of pattern classification for multi-class datasets. The aim of the IWC is to find the set of the positions of the class centers that minimize the multi-objective function, i.e., the optimal positions of the class centers. The classification performance is computed as the percentage of misclassified patterns in the testing dataset achieved by the best plants in terms of fitness performance. The performance of the IWC algorithm, both in terms of classification accuracy and training time, is compared with other commonly used classification algorithms. [ABSTRACT FROM AUTHOR]

This article is devoted to the history of development and main research areas of the scientific school in the field of pattern recognition, image processing and analysis, and artificial intelligence and machine learning, founded in the early 1990s at the Skobeltsyn Institute of Nuclear Physics, Lomonosov Moscow State University (SINP MSU) by Prof. Igor' Georgievich Persiantsev. For many years Persiantsev was the permanent leader of this scientific school; he laid down the basic principles and approaches to scientific research that still guide his disciples to this day. During this time, more than 30 people became students of Persiantsev's school, who carried out scientific work under his leadership or under the leadership of his disciples, defended their candidate's dissertations or diploma at the Faculty of Physics, Lomonosov Moscow State University. The article provides a brief historical background and an overview of the areas of research and major works published over more than 30 years (from 1992 to 2023) by Persiantsev and his disciples. [ABSTRACT FROM AUTHOR]