Fuzzy Reasoning Model Research Articles

Parameterized continuous models of fuzzy reasoning

In this paper, the ideas of universal logic is introduced into fuzzy systems. After giving the definitions of the softened fuzzy reasoning models based on Schweizer-Sklar t-norms and Schweizer-Sklar implications, i.e., α-models and β-models, we give the sufficient and necessary conditions for these models to be continuous, and discuss the continuity of some commonly used models. We also prove that when an α-model or a β-model is used as a fuzzy controller, it has universal property with respect to function approximation. The results we obtained show that α-models and β-models are more flexible than the existing models in applications.

A New Approach for Modelling Gene Regulatory Networks Using Fuzzy Petri Nets

SummaryGene Regulatory Networks are models of genes and gene interactions at the expression level. The advent of microarray technology has challenged computer scientists to develop better algorithms for modeling the underlying regulatory relationship in between the genes. Fuzzy system has an ability to search microarray datasets for activator/repressor regulatory relationship. In this paper, we present a fuzzy reasoning model based on the Fuzzy Petri Net. The model considers the regulatory triplets by means of predicting changes in expression level of the target based on input expression level. This method eliminates possible false predictions from the classical fuzzy model thereby allowing a wider search space for inferring regulatory relationship. Through formalization of fuzzy reasoning, we propose an approach to construct a rule-based reasoning system. The experimental results show the proposed approach is feasible and acceptable to predict changes in expression level of the target gene.

A new approach for modelling gene regulatory networks using fuzzy petri nets.

Gene Regulatory Networks are models of genes and gene interactions at the expression level. The advent of microarray technology has challenged computer scientists to develop better algorithms for modeling the underlying regulatory relationship in between the genes. Fuzzy system has an ability to search microarray datasets for activator/repressor regulatory relationship. In this paper, we present a fuzzy reasoning model based on the Fuzzy Petri Net. The model considers the regulatory triplets by means of predicting changes in expression level of the target based on input expression level. This method eliminates possible false predictions from the classical fuzzy model thereby allowing a wider search space for inferring regulatory relationship. Through formalization of fuzzy reasoning, we propose an approach to construct a rulebased reasoning system. The experimental results show the proposed approach is feasible and acceptable to predict changes in expression level of the target gene.

Fuzzy logic controller parameter tuning using particle swarm algorithm

Fuzzy logic models of plants are attractive because they have structures with physical meanings that can be used to predict the performance as well as provide insight into the workings of the modelled system. However, the initial definitions of fuzzy model parameters are subjective, heuristic and therefore, inaccurate. In this paper, the particle swarm optimisation algorithm is used to find the optimum fuzzy relation matrix of a new fuzzy reasoning model for the purpose of modelling. Simulation results show that a good fuzzy model of complex systems can be obtained with no expert input.

Assessment of Corporate Sustainability via Fuzzy Logic

Corporations interact with society and the physical and biological environment in ways that affect both sides. In this capacity, corporations play an important role in the sustainability of a region or country. Symmetrically, a corporation's sustainability depends on the sustainability of its wider environment. In this paper, a multi-stage fuzzy reasoning model is presented to assess a corporation's sustainability. The model has two fundamental components: human and ecological. The human component has up to four inputs: economic, political, knowledge, and welfare. The ecological component can also have up to four inputs: air, water, land, and biodiversity. Each of these eight components has a number of basic inputs suitable for evaluating a given corporation. The model can be used to assess a corporation's sustainability, record its historical evolution, and compare the company to its direct competitors. Equally importantly, sensitivity analysis of the model reveals the most important basic indicators affecting corporate sustainability, identifying areas which managers and executives should place special attention. An application example based on three large international corporations in the same industry illustrates the usefulness of the model.

The selection of trees for thinning with the fuzzy reasoning model

The selection of trees for thinning with the fuzzy reasoning model

Fuzzy case-based reasoning for coping with construction disputes

The nature of the construction business makes the industry one of the most litigious. Most recent studies of dispute settlement assistant system have applied case-based reasoning (CBR) models to identify similar dispute cases that may be used as references in dispute settlements. Typically, either Euclidean distance (EUD) or cosine angle distance (CAD) has been employed in CBR to measure similarity. However, both EUD and CAD present inherent problems. This situation offers the opportunity to further refine and improve the CBR approach. The CBR was combined with fuzzy-set theory to establish the “fuzzy case-based reasoning model” (FCBR) for coping with construction disputes. FCBR incorporates a new similarity measurement (NSM) that fuses EUD and CAD, creating a more effective tool with which to calculate target case similarity with historical construction dispute cases. Information on cases similar to a target case assists mediators to deal effectively with construction disputes. The FCBR simulates the process of human reasoning, allowing users to not only easily review historical data, but also efficiently mine information on similar cases.

A fuzzy reasoning design for fault detection and diagnosis of a computer-controlled system

A fuzzy reasoning and verification Petri nets (FRVPNs) model is established for an error detection and diagnosis mechanism applied to a complex fault-tolerant PC-controlled system. The inference accuracy can be improved through the hierarchical design of a two-level fuzzy rule decision tree and a Petri nets technique to transform the fuzzy rule into the FRVPNs model. Several simulation examples of the assumed failure events were carried out by using the FRVPNs and the Mamdani fuzzy method with MATLAB tools. The reasoning performance of the developed FRVPNs was verified by comparing the inference outcome to that of the Mamdani method. Both methods result in the same conclusions. Thus, the present study demonstrates that the proposed FRVPNs model is able to achieve the purpose of reasoning, and furthermore, determining of the failure event of the monitored application program.

Vendor selection and order allocation using an integrated fuzzy case-based reasoning and mathematical programming model

A basic part of the logistic management of companies is the purchasing function, and the appropriate selection of vendors and allocating orders among them is one of the prime responsibilities of this function. Many conceptual and analytical models have been developed for addressing the vendor selection problem (VSP). This paper focuses on a case-based reasoning (CBR) approach which is a recently recommended method for solving the VSP by making use of previous similar situations. Having applied fuzzy set theory in the proposed model—as a novel innovation—the vague nature of some selection criteria has been incorporated by utilizing the linear membership function of fuzzy type to quantify the vagueness in decision parameters. Moreover, a mixed integer programming model is employed to simultaneously consider suitable vendor selection and order allocation; due to the purchase situation of vendors derived from the CBR system, and with respect to such realistic constraints as meeting the buyer's demand, vendors' capacity, etc.

A fuzzy case-based reasoning model for sales forecasting in print circuit board industries

Reliable prediction of sales can improve the quality of business strategy. Case-based reasoning (CBR), one of the well known artificial intelligence (AI) techniques, has already proven its effectiveness in numerous studies. However, due to the uncertainties in knowledge representation, attribute description, and similarity measures in CBR, it is very difficult to find the similar cases from case bases. In order to deal with this problem, fuzzy theories have been incorporated into CBR allowing for more flexible and accurate models. This research develops a fuzzy case-based reasoning (FCBR) and explores its potential use in supporting a forecaster during the forecast process for forecasting the future sales of a printed circuit board factory. Numerical data of various affecting factors and actual demand of the past 5 years of the printed circuit board (PCB) factory are collected and input into the FCBR for future monthly sales forecasting. Experimental results show the effectiveness of the FCBR model when comparing it with other approaches.

INTEGRATED INFERENCE OF DRIVER'S INTENTIONS AND DRIVING ENVIRONMENT AND REAL-TIME ALGORITHM

Referring former methods of driver's intention inference, according to vehicle dynamics, the balance throttle open on plane and straight road and relative throttle open are defined. Based on these, driver demand acceleration characteristics are discussed and driver intentions on plane and straight road are classified to five relative styles. Driver usual operation characteristics under these five classic conditions are summarized. It is proved that driving environment is equivalent to certain driver intention and they can be integrated to infer. A multi-input single-output fuzzy reasoning model is established and the fuzzy rules are based on test data and driver experiences. This model can be applied to micro controller unit and an improved real-time algorithm is brought up. Validated with the test data, this model can infer the intentions quite well.

Fuzzy reasoning model under quotient space structure

In this paper, we present a theoretical framework of fuzzy reasoning model under quotient space structure. It consists of (1) introducing quotient space structure into fuzzy sets, i.e., constructing fuzzy set representations of different grain-size spaces and their relationships; (2) introducing the concept of fuzzy sets into quotient space theory, i.e., introducing fuzzy equivalence relation and discussing its corresponding reasoning in different grain-size spaces; and (3) discussing the relationship and transformation among different granular computing methodologies. The framework proposed is aimed to combine two powerful abilities in order to enhance the efficiency of fuzzy reasoning: one is the ability of computing with words based on fuzzy set methodology, the other is the ability of hierarchical problem solving based on quotient space approach.

Field-based Fuzzy Spatial Reasoning Model for Geographical Information Systems: Case of Constraint Satisfaction Problem

Humans' representation in nature language about geographic phenomena is usually qualitative rather than quantitative. Qualitative spatial reasoning provides an approach which is considered to be closer to the representation. Commercial GIS software are confronted with a challenge that the software should be equipped with artificial intelligent functions like qualitative spatial reasoning for more and more users, especially for spatial decision-makers. This paper proposes a framework of field-based fuzzy spatial reasoning through which qualitative description usually encountered in spatial reasoning process can be handled quantitatively. As preconditioning, field-based fuzzy representation structure for qualitative description is put forward, then the methods of constructing membership function are discussed. Standard operations of field-based fuzzy spatial reasoning model in the case of constraint satisfaction problem (CSP) are illustrated. An example explains the implication of the model in spatial decision-making process.

A HYBRID MODEL FOR SHARING INFORMATION BETWEEN FUZZY, UNCERTAIN AND DEFAULT REASONING MODELS IN MULTI-AGENT SYSTEMS

This paper develops a hybrid model which provides a unified framework for the following four kinds of reasoning: 1) Zadeh's fuzzy approximate reasoning; 2) truth-qualification uncertain reasoning with respect to fuzzy propositions; 3) fuzzy default reasoning (proposed, in this paper, as an extension of Reiter's default reasoning); and 4) truth-qualification uncertain default reasoning associated with fuzzy statements (developed in this paper to enrich fuzzy default reasoning with uncertain information). Our hybrid model has the following characteristics: 1) basic uncertainty is estimated in terms of words or phrases in natural language and basic propositions are fuzzy; 2) uncertainty, linguistically expressed, can be handled in default reasoning; and 3) the four kinds of reasoning models mentioned above and their combination models will be the special cases of our hybrid model. Moreover, our model allows the reasoning to be performed in the case in which the information is fuzzy, uncertain and partial. More importantly, the problems of sharing the information among heterogeneous fuzzy, uncertain and default reasoning models can be solved efficiently by using our model. Given this, our framework can be used as a basis for information sharing and exchange in knowledge-based multi-agent systems for practical applications such as automated group negotiations. Actually, to build such a foundation is the motivation of this paper.

Self-Tuning of the Fuzzy Inference Rule by Integrated Method

In the fuzzy reasoning model, the fuzzy relation matrix, determined by a human expert according to experience, plays an important role, but may be difficult to extract optimally from an expert, particularly as the system increases in complexity. Moreover, a change in the fuzzy membership function may alter the performance of the fuzzy system significantly. Therefore, in this paper, the genetic algorithm is to be incorporated in the context fuzzy reasoning model in the loop whose function is to search for optimal fuzzy relation matrix and fuzzy membership functions simultaneously. In addition, the genetic algorithm used in this paper is supplemented by a local fine-tuning mechanism with executing the gradient descent genetic operator.

Rules Reduction of Fuzzy Reasoning Model of Multiple Division Layers by Minkowski Norm and Its Application to Modeling of Ceramic Kiln

The simplified fuzzy reasoning model having multi-layer structure has a feature that generation of fuzzy rules is easy even under actual conditions. However, it is reported that redundant fuzzy rules are generated as division layers are iteratively increased. In this paper, we propose a fuzzy reasoning model of multiple division layers, which has a weight in the reasoning output. We reduce redundant fuzzy rules by tuning up the weight using an evaluation function based on Minkowski norm. Moreover, the validity of the proposed method is verified by identification experiments of two nonlinear functions having sparse domains in teaching data. Finally, we apply the proposed method to a modeling of ceramic kiln, and confirm that it is also effective for actual problems.

An Approach of Hybrid models based on Fuzzy reasoning and Logit models

An Approach of Hybrid models based on Fuzzy reasoning and Logit models

分散と相関によるファジィ推論モデルの構築

ファジィモデリングにおいて推論ルールを自動的に生成する手法がいくつか提案されている.本研究では, ルール間の相関を考慮したファジィ推論モデルの構築法を提案し, この手法を相関型ファジィ推論モデルと呼ぶことにする.数値実験では関数近似の実験を行い, その結果, 推論精度が良く少ないルール数の推論モデルを得ることができた.また, 相関型ファジィ推論モデルを削除型ファジィ推論モデルに組み合わせた複合型モデルにより, 学習後の推論ルールに重なりが生じる問題を解決することができた.

逐次移動窓を用いた多分割層ファジィ推論モデル

実数値を直接出力できる特長を持つ簡略化ファジィ推論モデルは制御システムの分野にしばしば応用される.一般的には, ファジィルールの前件部のファジィ分割数を増加させることによって, 精度のより高いファジィ推論モデルの生成が可能である.しかしながら, データ配置に粗密があるような現実環境に近い教師データを用いた場合, データの疎な領域では, ファジィルールの生成に必要な情報が少ないため, その領域におけるファジィルールの推論誤差が大きくなり, 極端な場合にはそのファジィルールの生成もできないことがある.更に, ファジィ分割数を増加させても, 生成できないファジィルール数が一層増えることもあり, その領域で推論誤差を下げられないだけでなく, かえって上げることにもなりかねない.また, 教師データに外乱値を含む場合も, ファジィ分割数の増加にとともに, 外乱値に対して感度が強くなり, 推論誤差が大きくなる.本論文では, これらの問題を解決するために, 逐次移動窓を用いた多分割層ファジィ推論モデルを提案し, 単分割層ファジィ推論モデルの代表的手法である簡略化ファジィ推論モデルと多分割層ファジィ推論モデルの特性の論議を通じて, 多分割層ファジィルールの有効性を検証する.

分解型多次元ファジィ推論モデルとその逆問題解を用いた景観の感性的評価

分解型多次元ファジィ推論モデルとその逆問題解を用いた景観の感性的評価