Clustering is an unsupervised machine learning technique with many practical applications that has gathered extensive research interest. Aside from deterministic or probabilistic techniques, fuzzy C-means clustering (FCM) also a common technique. Since the advent of FCM method, improvements have been made to increase efficiency. These focus on adjusting membership representation elements in clusters, fuzzifying and defuzzifying as well distance function between elements. This study proposes...

In this paper we present the fuzzy description logic ALCFH introduced, where primitive concepts are modified by means of hedges taken from hedge algebras. is strictly more expressive than Fuzzy- ALC defined in [11]. We show that given a linearly ordered set can be to any desired degree prefixing them with appropriate chains hedges. Furthermore, define decision procedure for unsatisfiability problem FH , and discuss knowledge base expansion when using terminologies, truth bounds, expressivity...

Clustering is an unsupervised machine learning method with many practical applications that has gathered extensive research interest. It a technique of dividing data elements into clusters such in the same cluster are similar. belongs to group techniques, meaning there no information about labels elements. However, when knowledge points known advance, it will be beneficial use semi-supervised algorithm. Within clustering techniques available, fuzzy C-means (FCM) common one. To make FCM...

The co-authorship recommendation problem is attractive since it helps researchers extend collaboration to improve the quality of scientific articles as well promote innovation. This involves suggesting authors join research groups based on their interests, areas expertise, and past collaborative experiences write together. In this paper, we tackle by modeling a network, where each author represented vertex, between two an edge. Since number pairs without much larger than those with...

Approximate reasoning is based on generalized modus ponens (GMP). Its principle that from an observation different but approximately equal to the rule premise, we can deduce a fact conclusion. However, deduced not obtained with arbitrary way. In this paper, propose new of GMP in linguistic many-valued logic framework using hedge moving rules for reasoning.

Based on our previous researchs about generalized modus ponens (GMP) with linguistic modifiers for If … Then rules, this paper proposes new tollens (GMT) inference rules in many–valued logic framework using hedge moving inverse approximate reasoning.

This paper studies the linguistic truth value domain based on finite monotonous hedge algebra in an attempt to propose a derivatives system moving rules and ∧, ∨, ⊗, ′, → Lukasiewicz algebra.

In this paper, we propose a new class of type-2 fuzzy sets: Hedge Algebraic Type-2 Fuzzy Sets - HaT2FS. The particular feature HaT2FS is that the membership grades each element are linguistic truth values hedge algebras. We consider some important aspects operations on including aggregation, meet and join; HaT2FSs representation by union k-level embedded HaT2FSs; intersection, complement HaT2FSs.

This paper studies the linguistic truth value domain (AX) based on finite monotonous hedge algebra and then we extend lukasiewicz (0;1) to (AX), in an attempt propose a general resolution for many-valued logic moving rules reasoning. Its theorems of soundness completeness associated with are also proved. reflects symbolic approach acts by direct reasoning domain.

In this paper, we propose a method to construct hedge algebra based type-2 fuzzy logic systems (HA-T2FLS). these systems, the footprints of uncertainty (FOU) sets are optimized by genetic algorithm and dispersion data. The key ingredient our system is concept centroid sets. It used in type-reducing HA-T2FLS, transforming interval As an application, show how can be predict survival time myeloma patients. results that more accurate than type-1 class problems.

In this paper, we have proposed a method for constructing Hedge Algebraic Type-2 Fuzzy Logic Systems (HaT2-FLS) from input-output data with two main phases. the first phase, data-driven Type-1 System (T1-FLS) is designed under combination of C-Means algorithm and Genetic Algorithm (GA). Then construct HaT2-FLS on basis above T1-FLS in second phase. The rule base employed generating by using same number fuzzy sets rules both logic systems. difference that antecedent consequent HaT2FLS...

In this study, we propose an adaptive fuzzy weight algorithm for the problem of two-class imbalanced learning. Initially, our finds a set values data samples based on distance from each sample to centres both minority and majority classes. Then, iteratively adjusts sensitive either positive or negative margins class label noises. By doing so, increases influence decreases in forming classifier model. Experimental results four benchmark real-world datasets including Transfusion, Ecoli, Yeast,...

This paper proposes a method for constructing Hedge Algebraic Type-2 Fuzzy Logic Systems (HaT2-FLS) from input-output data. consists of two main phases. In the first phase, Type-1 System (T1-FLS) is designed under combination C-Means algorithm and training Then we construct HaT2-FLS on basis above T1-FLS in second phase. The rule base foundation which created. difference now that antecedent consequent sets are Sets (HaT2FSs). Experiments show effectiveness method.

The paper studies the properties of inverse mappings hedges in monotonic hedge algebras, which have dealt [5,6,7].We propose new criteria to determine hedges.Some approaches construct are also given.Tóm tȃ ´t.Bài báo nghiên cú .u các tính châ ´t cu 'a ánh xa .ngu .o . .c gia tu .' du .a ra trong [5,6,7], dê `xuâ tiêu chuâ ' n xác di .nh , tù .dó xây .ng tiê ´p câ .n tìm .1. D Ȃ .T V Â ´N Ê Cùng vó .i su .phát triê a khoa ho máy tính, vâ ´n `mô hình hoá cách biê u da .t .duy trên ngôn ngũ .tu...