جستجوی مقالات مرتبط با کلیدواژه "{pattern recognition" در نشریات گروه "ریاضی"

A multiple set is an extended version of a fuzzy set that simultaneously addresses an element’s multiplicity and uncertainty. In this paper, we define the approximate equality of multiple sets and study some relevant properties associated with it. We then apply the notion of approximation equality of multiple sets to solve a pattern recognition problem. A novel class of similarity measures involving implication operators is introduced and the characteristics of approximate equality corresponding to these similarity measures are discussed. Further, we propose the concepts of σ-entropy, σ-distance measure, and σ-similarity measure of multiple sets and illustrate these with some examples. Finally, we define the theory of similarity measures between elements in multiple sets.

Intuitionistic fuzzy set (IFS) is a reliable device for resolving uncertainty and haziness encountered in decision-making process. In most cases, the significance of IFSs are explored based on correlation measures in myriad of areas like in engineering, image segmentation, pattern recognition, diagnosticanalysis, etc. Some methods for computing intuitionistic fuzzy correlation coefficient (IFCC) have been investigated, however with some inadequacies. In this present work, a new method of IFCC is developed to correct the drawbacks in some existing techniques in terms of mathematical presentation and the exclusion of the hesitation parameter to enhance reasonable output. A comparative analysis is presented to ascertain the edge of the new technique over some similarapproaches. In addition, the new correlation coefficient technique is applied to discuss some pattern recognition problems. This new IFCC method could be investigated based on spherical fuzzy data, q-rung orthopair fuzzy data, and picture fuzzy data.

Stock and price index prediction are among the main challenges for market players, traders, and economic analysts. Pattern recognition is one of the most common methods for analyzing complex data such as financial data. Elliot waves are used as one of the most robust models for predicting many markets, and it works based on a hypothesis that argued that upward and downward market price action always showed up in the same repetitive patterns. The need for expert knowledge and skills to detect these waves makes using it difficult for many traders. So far, little research has been done on the automatic identification of these waves. In this paper, we have attempted to recognize these patterns automatically and use them in predicting future upward/downward trends in prices. For this purpose, twelve patterns have been selected as representing Elliot waves. These patterns are stored in a self-organized map neural network and the network is used to identify the waves in the target stock. The proposed algorithm has been tested with several stocks from the Forex financial market. The results have an average accuracy of 93.94 percent in predicting stock trends and it indicates an improvement in prediction accuracy compared to other works.

In recent years, Machine Learning (ML) algorithms, especially Artificial Neural Networks (ANNs), have achieved remarkable success in various fields such as Pattern Recognition, Computer Vision, and Voice Recognition. Where ANNs algorithms have proven their superiority over traditional ML algorithms like (Support Vector Machines, Decision Trees, and Naïve Bayes) in various fields. Multi-layer Perceptron (MLP) network is one of the popular ANNs types and is used in various fields. The field of healthcare pattern recognition is considered one of the most important fields in our modern age, as this field is concerned with patterns extracted from raw data. There are many studies that dealt with MLP networks to detect and classify patterns in such a scope. In this study, a body of work deals with using the MLP networks for healthcare pattern recognition in five different topics (Diabetes, Heart disease, Liver, Breast cancer, and Parkinson's disease). The goal of the research is to identify strengths and weaknesses, and to identify the latest developments of adapting MLP network to recognize patterns in different data sets in the Healthcare field.

Fermatean Fuzzy Sets (FFSs) provide an effective way to handle uncertainty and vagueness by expanding the scope of membership and Non-Membership Degrees (NMDs) of Intuitionistic Fuzzy Set (IFS) and Pythagorean Fuzzy Set (PFS), respectively. FFS handles uncertain information more easily in the process of decision making. The concept of composite relation is an operational information measure for decision making. This study establishes Fermatean fuzzy composite relation based on max-average rule to enhance the viability of FFSs in machine learning via soft computing approach. Some numerical illustrations are provided to show the merit of the proposed max-average approach over existing the max-min-max computational process. To demonstrate the application of the approach, we discuss some pattern recognition problems of building materials and mineral fields with the aid of the Fermatean fuzzy modified composite relation and Fermatean fuzzy max-min-max approach to underscore comparative analyses. In recap, the objectives of the paper include: 1) discussion of FFS and its composite relations, 2) numerical demonstration of Fermatean fuzzy composite relations, 3) establishment of a decision application framework under FFS in pattern recognition cases, and 4) comparative analyses to showcase the merit of the new approach of Fermatean fuzzy composite relation. In future, this Fermatean fuzzy modified composite relation could be studied in different environments like picture fuzzy sets, spherical fuzzy sets, and so on.

In this article, we propose a new distance measure between intuitionistic fuzzy sets(IFSs), which takes into account the membership degree, non-membership degree, and their difference between membership and non-membership degree of intuitionistic fuzzy sets, as well as the exponential distance measure to avoid information loss. Meanwhile we prove that it satisfies the axiomatic definition of distance measure, and do comparison analysis with some widely used distance measures. Finally, we apply our distance measure in pattern recognition, these results show that our distance measure can significantly overcome the drawback of information loss and have more widely application scope.

To address the hesitancy, inconsistency and uncertainty of decision makers’ cognitions, linguistic interval hesitant fuzzy sets (LIHFSs) are efficient tools. This paper focuses on studying the application of LIHFSs. To do this, two correlation coefficients of LIHFSs are defined, which needn't consider the length of elements in LIHFSs or the arrangement of their possible interval values. To address the situation where the weights of elements in a set are different and correlative, two linguistic interval hesitant fuzzy Shapley weighted correlation coefficients are defined. Considering the situation where the weight information of features/attributes is partly known, programming models to determine the optimal fuzzy measures on them are constructed, respectively. After that, an approach to pattern recognition and multi-attribute decision making with linguistic interval hesitant fuzzy information is developed, respectively. Meanwhile, illustrative examples about medical diagnosis and selecting constructors for tunnel bidding are selected to verify the application of new approaches, and comparison with a previous method is offered.

In this contribution, we first introduce the concept of metrical T-norm-based similarity measure for hesitant fuzzy sets (HFSs) {by using the concept of T-norm-based distance measure}. Then, the relationship of the proposed {metrical T-norm-based} similarity {measures} with the {other kind of information measure, called the metrical T-norm-based} entropy measure {is} discussed. The main feature of the proposed { metrical T-norm-based similarity measures} is a possibility of comparing {similarity between HFSs} without regarding what {value is returned by} the similarity measure.{To illustrate the application of the proposed metrical T-norm-based similarity measures, we consider two problems of} medical diagnosis {and pattern recognition} to compare the proposed {metrical T-norm-based similarity measures} with a number of {the} existing HFS similarity measures

A new approach to define the similarity measure between interval-valued fuzzy sets is presented. The proposed approach is based on a weighted measure in which the normalized similarities between lower functions and also between upper functions arecombined by a weight parameter. The properties of this similarity measure are investigated. It is shown that, the proposed measure has some advantages in comparison with the commonly used similarity measures.