Wyniki wyszukiwania - BazTech

1

Single spiking neuron multi-objective optimization for pattern classification

Juarez-Santini Carlos, Ornelas-Rodriguez Manuel, Soria-Alcaraz Jorge Alberto, Rojas-Domínguez Alfonso, Puga-Soberanes Hector J., Espinal Andrés, Rostro-Gonzalez Horacio

Journal of Automation Mobile Robotics and Intelligent Systems

|

2020

|

Vol. 14, No. 1

73--80

EN

As neuron models become more plausible, fewer computing units may be required to solve some problems; such as static pattern classification. Herein, this problem is solved by using a single spiking neuron with rate coding scheme. The spiking neuron is trained by a variant of Multi-objective Particle Swarm Optimization algorithm known as OMOPSO. There were carried out two kind of experiments: the first one deals with neuron trained by maximizing the inter distance of mean firing rates among classes and minimizing standard deviation of the intra firing rate of each class; the second one deals with dimension reduction of input vector besides of neuron training. The results of two kind of experiments are statistically analyzed and compared again a Mono-objective optimization version which uses a fitness function as a weighted sum of objectives.

2

Pattern classification by spiking neural networks combining self-organized and reward-related spike-timing-dependent plasticity

Nobukawa Sou, Nishimura Haruhiko, Yamanishi Teruya

Journal of Artificial Intelligence and Soft Computing Research

|

2019

|

Vol. 9, No. 4

283--291

EN

Many recent studies have applied to spike neural networks with spike-timing-dependent plasticity (STDP) to machine learning problems. The learning abilities of dopaminemodulated STDP (DA-STDP) for reward-related synaptic plasticity have also been gathering attention. Following these studies, we hypothesize that a network structure combining self-organized STDP and reward-related DA-STDP can solve the machine learning problem of pattern classification. Therefore, we studied the ability of a network in which recurrent spiking neural networks are combined with STDP for non-supervised learning, with an output layer joined by DA-STDP for supervised learning, to perform pattern classification. We confirmed that this network could perform pattern classification using the STDP effect for emphasizing features of the input spike pattern and DA-STDP supervised learning. Therefore, our proposed spiking neural network may prove to be a useful approach for machine learning problems.

3

Machine-learning at the service of plastic surgery: a case study evaluating facial attractiveness and emotions using R language

Štěpánek Lubomír, Měšťák Jan, Kasal Pavel

Annals of Computer Science and Information Systems

|

2019

|

Vol. 18

107--112

EN

Since the plastic surgery should consider that facial impression is always dependent on current facial emotion, it came to be verified how precise classification of facial images into sets of defined facial emotions is.

4

Zespoły klasyfikatorów - aktualne kierunki badań

Woźniak M.

Mechanik

|

2015

|

R. 88, nr 10CD

44--48

PL

Jednym z ciekawych i dynamicznie rozwijających się nurtów uczenia maszynowego jest klasyfikacja kombinowana. Opracowywane, w jej ramach, algorytmy starają się w zbudować model systemu klasyfikacyjnego bazującego na klasyfikatorach składowych, tak aby wykorzystać ich najlepsze cechy i kompetencje potrzebne do rozwiązania danego problemu decyzyjnego W takcie konstrukcji tego typu systemów stykamy się z dwoma typami problemów: jak wybrać wartościowy zespół klasyfikatorów oraz w jaki sposób uzyskać decyzje końcową na bazie odpowiedzi członków wspomnianego zespołu klasyfikatorów. W pracy przedstawiono główne przesłanki świadczące o przydatności projektowania tego typu systemów oraz dokonano ich krótkiej charakterystyki problemów projektowych.

EN

Classifier ensemble is the focus of the intense research, because it is recognized as the one of them most efficient classification approach. It is used in the several practical domains as fraud detection, client behavior recognition, medical decision support systems, or technical diagnostic to enumerate only a few. In this conceptual approach, the main effort is focusing on the two main problems. First, how to choose or train valuable and mutually complimentary set of individual classifiers and how to combine their outputs to exploit the strength of each individuals. The work presents a brief survey of the main issues related with the classifier ensemble domain.

5

Supervised Kernel Principal Component Analysis by Most Expressive Feature Reordering

Ślot K., Adamiak K., Duch P., Żurek D.

Journal of Telecommunications and Information Technology

|

2015

|

nr 2

3--10

EN

The presented paper is concerned with feature space derivation through feature selection. The selection is performed on results of kernel Principal Component Analysis (kPCA) of input data samples. Several criteria that drive feature selection process are introduced and their performance is assessed and compared against the reference approach, which is a combination of kPCA and most expressive feature reordering based on the Fisher linear discriminant criterion. It has been shown that some of the proposed modifications result in generating feature spaces with noticeably better (at the level of approximately 4%) class discrimination properties.

6

Handling class label noise in medical pattern classification systems

Sáez J. A., Krawczyk B., Woźniak M.

Journal of Medical Informatics & Technologies

|

2015

|

Vol. 24

123--130

EN

Pattern classification systems play an important role in medical decision support. They allow to automatize and speed-up the data analysis process, while being able to handle complex and massive amounts of information and discover new knowledge. However, their quality is based on the classification models built, which require a training set. In supervised classification we must supply class labels to each training sample, which is usually done by domain experts or some automatic systems. As both of these approaches cannot be deemed as flawless, there is a chance that the dataset is corrupted by class noise. In such a situation, class labels are wrongly assigned to objects, which may negatively affect the classifier training process and impair the classification performance. In this contribution, we analyze the usefulness of existing tools to deal with class noise, known as noise filtering methods, in the context of medical pattern classification. The experiments carried out on several real-world medical datasets prove the importance of noise filtering as a pre-processing step and its beneficial influence on the obtained classification accuracy.

7

Data Stream Classification Using Classifier Ensemble

Woźniak M., Kasprzak A.

Schedae Informaticae

|

2014

|

Vol. 23

21--32

EN

For the contemporary business, the crucial factor is making smart decisions on the basis of the knowledge hidden in stored data. Unfortunately, traditional simple methods of data analysis are not sufficient for efficient management of modern enterprizes, because they are not appropriate for the huge and growing amount of the data stored by them. Additionally data usually comes continuously in the form of so-called data stream. The great disadvantage of traditional classification methods is that they assume that statistical properties of the discovered concept are being unchanged, while in real situation, we could observe so-called concept drift, which could be caused by changes in the probabilities of classes or/and conditional probability distributions of classes. The potential for considering new training data is an important feature of machine learning methods used in security applications (spam filtering or intrusion detection) or decision support systems for marketing departments, which need to follow the changing client behavior. Unfortunately, the occurrence of concept drift dramatically decreases classification accuracy. This work presents the comprehensive study on the ensemble classifier approach applied to the problem of drifted data streams. Especially it reports the research on modifications of previously developed Weighted Aging Classifier Ensemble (WAE) algorithm, which is able to construct a valuable classifier ensemble for classification of incremental drifted stream data. We generalize WAE method and propose the general framework for this approach. Such framework can prune an classifier ensemble before or after assigning weights to individual classifiers. Additionally, we propose new classifier pruning criteria, weight calculation methods, and aging operators. We also propose rejuvenating operator, which is able to soften the aging effect, which could be useful, especially in the case if quite ”old” classifiers are high quality models, i.e., their presence increases ensemble accuracy, what could be found, e.g., in the case of recurring concept drift. The chosen characteristics of the proposed frameworks were evaluated on the basis of the wide range of computer experiments carried out on the two benchmark data streams. Obtained results confirmed the usability of proposed method to the data stream classification with the presence of incremental concept drift.

8

Application of Two Dimensional Wavelet Transform for Classification of Power Quality Disturbances

Mollayi N., Mokhtari H.

Electrical Power Quality and Utilisation. Journal

|

2014

|

Vol. 17, iss. 2

1--7

EN

Identification of voltage and current disturbances is an important task in power system monitoring and protection. In this paper, the application of two-dimensional wavelet transform for characterization of a wide variety range of power quality disturbances is discussed, and a new algorithm, based on image processing techniques is proposed for this purpose. A matrix is formed based on a specified number of cycles in such a way that the samples of voltage signal in each cycle form one row of that matrix. This matrix can be regarded as a two dimensional image. A two-dimensional wavelet transform is used to decompose the image into approximation and details, which contain low frequency and high frequency components along the rows and columns, respectively. Different disturbances result into different special patterns in detail images. By processing the detail images, specific features are defined which can suitably discriminate various types of disturbances. Combination of the feature generation algorithm and a classifier system leads to a smart system for classification of wide variety range of disturbances.

9

Discrete Fourier transform based pattern classifiers

Hui S., Żak S. H.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2014

|

Vol. 62, nr 1

15--22

EN

A technique for pattern classification using the Fourier transform combined with the nearest neighbor classifier is proposed. The multidimensional fast Fourier transform (FFT) is applied to the patterns in the data base. Then the magnitudes of the Fourier coefficients are sorted in descending order and the first P coefficients with largest magnitudes are selected, where P is a design parameter. These coefficients are then used in further processing rather than the original patterns. When a noisy pattern is presented for classification, the pattern’s P Fourier coefficients with largest magnitude are extracted. The coefficients are arranged in a vector in the descending order of their magnitudes. The obtained vector is referred to as the signature vector of the corresponding pattern. Then the distance between the signature vector of the pattern to be classified and the signature vectors of the patterns in the data base are computed and the pattern to be classified is matched with a pattern in the data base whose signature vector is closest to the signature vector of the pattern being classified.

10

Critical exponent analysis applied to surface EMG signals for multifunction myoelectric control

Phinyomark A., Phothisonothai M., Phukpattaranont P., Limsakul C.

Metrology and Measurement Systems

|

2011

|

Vol. 18, nr 4

645-658

EN

Based on recent advances in non-linear analysis, the surface electromyography (sEMG) signal has been studied from the viewpoints of self-affinity and complexity. In this study, we examine usage of critical exponent analysis (CE) method, a fractal dimension (FD) estimator, to study properties of the sEMG signal and to deploy these properties to characterize different movements for gesture recognition. SEMG signals were recorded from thirty subjects with seven hand movements and eight muscle channels. Mean values and coefficient of variations of the CE from all experiments show that there are larger variations between hand movement types but there is small variation within the same type. It also shows that the CE feature related to the self-affine property for the sEMG signal extracted from different activities is in the range of 1.855∼2.754. These results have also been evaluated by analysis-of-variance (p-value). Results show that the CE feature is more suitable to use as a learning parameter for a classifier compared with other representative features including root mean square, median frequency and Higuchi's method. Most p-values of the CE feature were less than 0.0001. Thus the FD that is computed by the CE method can be applied to be used as a feature for a wide variety of sEMG applications.

11

New optical character recognition method based on Hu invariant moments and weighted voting

Kmieć M.

Journal of Applied Computer Science

|

2011

|

Vol. 19, nr 1

33-50

EN

Optical character recognition is an important image processing task. Its aim is to enable computers to recognise graphic characters without human supervision. The process of optical symbol recognition is divided into two stages. First, certain features of the character undergoing recognition are extracted, and second, a match to them is searched for in the library of models. This paper looks at Hu invariant moments, a well established set of image features, and discusses their performance in optical character recognition. One approach to using Hu invariant moments in pattern recognition is using a metric function to find the pattern in the library of models, that is of the same class as the pattern considered. In this paper a new classification method is proposed that performs better than the classic method of metric function.

12

A Note on a priori Estimations of Classification Circuit Complexity

Albrecht A.A., Chashkin A.V., Iliopoulos C.S., Kasim-Zade O.M., Lappas G., Steinhöfel K.K.

Fundamenta Informaticae

|

2010

|

Vol. 104, nr 3

201-217

EN

The paper aims at tight upper bounds on the size of pattern classification circuits that can be used for a priori parameter settings in a machine learning context. The upper bounds relate the circuit size S(C) to n_L := .log_2mL., where mL is the number of training samples. In particular, we show that there exist unbounded fan-in threshold circuits with less than (a) [formula] gates for unbounded depth, (b) SL [formula] gates for small bounded depth, where in both cases all mL samples are classified correctly. We note that the upper bounds do not depend on the length n of input (sample) vectors. Since n_L << n in real-world problem settings, the upper bounds return values that are suitable for practical applications. We provide experimental evidence that the circuit size estimations work well on a number of pattern classification tasks. As a result, we formulate the conjecture that [formula] gates are sufficient to achieve a high generalization rate of bounded-depth classification circuits.

13

Analysis of extracted cardiotocographic signal features to improve automated prediction of fetal outcome

Jeżewski M., Czabański R., Wróbel J., Horoba K.

Biocybernetics and Biomedical Engineering

|

2010

|

Vol. 30, no. 4

29-47

EN

Cardiotocographic monitoring based on automated analysis of the fetal heart rate (FHR) signal is widely used for fetal assessment. However, the conclusion generation system is still needed to improve the abnormal fetal outcome prediction. Classification of the signals according to the predicted fetal outcome by means of neural networks is presented in this paper. Multi-layer perceptron neural networks were learned through seventeen time-domain signal features extracted during computerized analysis of 749 traces from 103 patients. The analysis included estimation of the FHR baseline, detection of acceleration and deceleration patterns as well as measurement of the instantaneous FHR variability. All the traces were retrospectively verified by the real fetal outcome defined by newborn delivery data. Influence of numerical and categorical representation of the input signal features, different data sets during learning, and gestational age as additional information, were investigated. We achieved the best sensitivity and specificity for the neural networks fed with numerical input variables together with additional information on the gestational age in the categorical form.

14

Some Symmetry Based Classifiers

Saha S., Bandyopadhyay S.

Fundamenta Informaticae

|

2009

|

Vol. 90, nr 1-2

107-123

EN

In this paper, a novel point symmetry based pattern classifier (PSC) is proposed. A recently developed point symmetry based distance is utilized to determine the amount of point symmetry of a particular test pattern with respect to a class prototype. Kd-tree based nearest neighbor search is used for reducing the complexity of point symmetry distance computation. The proposed point symmetry based classifier is well-suited for classifying data sets having point symmetric classes, irrespective of any convexity, overlap or size. In order to classify data sets having line symmetry property, a line symmetry based classifier (LSC) along the lines of PSC is thereafter proposed in this paper. To measure the total amount of line symmetry of a particular point in a class, a new definition of line symmetry based distance is also provided. Proposed LSC preserves the advantages of PSC. The performance of PSC and LSC are demonstrated in classifying fourteen artificial and real-life data sets of varying complexities. For the purpose of comparison, k-NN classifier and the well-known support vector machine (SVM) based classifiers are executed on the data sets used here for the experiments. Statistical analysis, ANOVA, is also performed to compare the performance of these classification techniques.

15

Aggregation Pheromone Density Based Pattern Classification

Halder A., Ghosh A., Ghosh S.

Fundamenta Informaticae

|

2009

|

Vol. 92, nr 4

345-362

EN

The study of ant colonies behavior and their self-organizing capabilities is of interest to machine learning community, because it provides models of distributed adaptive organization which are useful to solve difficult optimization and classification problems among others. Social insects like ants, bees deposit pheromone (a type of chemical) in order to communicate between the members of their community. Pheromone, that causes clumping behavior in a species and brings individuals into a closer proximity, is called aggregation pheromone. This article presents a new algorithm (called, APC) for pattern classification based on this property of aggregation pheromone found in natural behavior of real ants. Here each data pattern is considered as an ant, and the training patterns (ants) form several groups or colonies depending on the number of classes present in the data set. A new test pattern (ant) will move along the direction where average aggregation pheromone density (at the location of the new ant) formed due to each colony of ants is higher and hence eventually it will join that colony. Thus each individual test pattern (ant) will finally join a particular colony. The proposed algorithm is evaluated with a number of benchmark data sets as well as various kinds of artificially generated data sets using three evaluationmeasures. Results are compared with four other well known conventional classification techniques. Experimental results show the potentiality of the proposed algorithm in terms of all the evaluation measures compared to other algorithms.

16

Correlation-based feature selection strategy in classification problems

Michalak K., Kwaśnicka H.

International Journal of Applied Mathematics and Computer Science

|

2006

|

Vol. 16, no 4

503-511

EN

In classification problems, the issue of high dimensionality, of data is often considered important. To lower data dimensionality, feature selection methods are often employed. To select a set of features that will span a representation space that is as good as possible for the classification task, one must take into consideration possible interdependencies between the features. As a trade-off between the complexity of the selection process and the quality of the selected feature set, a pairwise selection strategy has been recently suggested. In this paper, a modified pairwise selection strategy is proposed. Our research suggests that computation time can be significantly lowered while maintaining the quality of the selected feature sets by using mixed univariate and bivariate feature evaluation based on the correlation between the features. This paper presents the comparison of the performance of our method with that of the unmodified pairwise selection strategy based on several well-known benchmark sets. Experimental results show that, in most cases, it is possible to lower computation time and that with high statistical significance the quality of the selected feature sets is not lower compared with those selected using the unmodified pairwise selection process.

17

Wykorzystanie sieci neuronowych cp w wibroakustycznej diagnostyce uszkodzeń przekładni zębatej

Dybała J., Radkowski S.

Diagnostyka

|

2004

|

Vol. 31

59--66

PL

W artykule przedstawiono sposób zastosowywania neuronowego klasyfikatora zbudowanego na bazie sieci neuronowej z propagacją przeciwną w diagnostyce wibroakustycznej przekładni zębatej. Ponadto, w pracy przedstawiono unikalną metodę selekcji cech stanu obiektu opartą na geometrii przestrzeni obserwacji. W końcowej części artykułu przedstawiono jako przykład wyniki eksperymentu laboratoryjnego.

EN

The article presents a way of applying a neural classifier constructed on the basis of counter-propagation neural network in vibroacoustic diagnostics of toothed gears. Moreover, in the paper the unique feature selection method of object state is presented. This method is based on geometry of the observation space. In final unit of article the results of laboratory experiment are presented as example.

18

Geometryczna metoda selekcji informacji diagnostycznej

Dybała J., Radkowski S.

Diagnostyka

|

2004

|

Vol. 30, T. 1

159--162

PL

W pracy przedstawiono metodę selekcji cech stanu obiektu opartą na geometrii przestrzeni obserwacji. Zaprezentowana metoda selekcji informacji wykorzystuje dwa kryteria: zmodyfiko-wane kryterium Sebestyena oraz oryginalne kryterium liczby wzorców klas.

EN

In the paper the feature selection method of object state is presented. This method is based on geometry of the observation space. The presented method of the information selection uses two criteria: the modified Sebestyen's criterion and original criterion of the prototypes classes number.

19

A new method for system modelling and pattern classification

Rutkowski L.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2004

|

Vol. 52, nr 1

11-24

EN

In this paper we present a new class of neuro-fuzzy systems designed for system modelling and pattern classification. Our approach is characterized by automatic determination of fuzzy inference in the process of learning. Moreover, we introduce several flexibility concepts in the design of neuro-fuzzy systems. The method presented in the paper is characterized by high accuracy which outperforms previous techniques applied for system modelling and pattern classification.

20

Effectiveness of active forgetting in machine learning applied to financial problems

Nakayama H., Yoshii K.

Journal of Telecommunications and Information Technology

|

2002

|

nr 3

24-29

EN

One of main features in financial investment problems is that the situation changes very often over time. Under this circumstance, in particular, it has been observed that additional learning plays an effective role. However, since the rule for classification becomes more and more complex with only additional learning, some appropriate forgetting is also necessary. It seemms natural that many data are forgotten as the time elapses. On the other hand, it is expected more effective to forget unnecessary data actively. In this paper, several methods for active forgetting are suggested. The effectiveness of active forgetting is shown by examples in stock portfolio problems.