Fuzzy Input Research Articles

Modeling fuzzy data envelopment analysis under robust input and output data

This paper offers a fuzzy optimization framework for data envelopment analysis (DEA) to evaluate the relative efficiency of decision making units (DMUs) with parametric interval-valued fuzzy variable-based inputs and outputs. The parametric interval-valued fuzzy variable-based inputs and outputs is employed to capture the uncertainty of data on the basis of professional judgements or empirical estimations. The DEA problem is formulated as fuzzy expectation model with credibility constraints. When the inputs and outputs are mutually independent parametric interval-valued triangular fuzzy variables, we investigate the parametric equivalent representations of expectation objective function and chance constraints. In order to find the optimal solution of our DEA model, a domain decomposition method is proposed. Finally, the numerical example on the sustainable supplier evaluation and selection problem is provided to demonstrate the efficiency of the proposed DEA model and domain decomposition method.

Fuzzy Load-Shedding Strategy Considering Photovoltaic Output Fluctuation Characteristics and Static Voltage Stability

Based on the equilibrium point equations of a classic three-node system integrated with a large-scale photovoltaic cell (PV) power plant, the impact of PV output fluctuation on the saddle-node bifurcation (SNB) was derived and analyzed. When PV runs in a unity power factor and the PV output active power Ppv is not too large (several hundred MW and below), the PV output fluctuation has little effect on the SNB point position and load margin index, so that the load margin index can be calculated online using the SNB point at Ppv = 0 pu. On the other hand, the local reactive power compensation in the load center can effectively raise the load bus voltage and make the voltage stability problem become more concealed; the traditional under-voltage load-shedding (UVLS) strategy only carries out load shedding when the bus voltage amplitude is below the specified value and cannot effectively maintain the system static voltage stability in some occasions. In this paper, a fuzzy load-shedding strategy considering the impact of PV output fluctuations for the large-scale PV grid-connected system was designed, taking the load bus voltage amplitude and load margin index as fuzzy input variables, and the load-shedding command as a fuzzy output variable. Nine fuzzy IF-THEN rules were extracted for the fuzzy controller and the corresponding practical calculation method of load-shedding quantity was put forward. The simulation results of the classic three-node system and IEEE 14-bus system, both with a 100 MW PV power plant, verified the effectiveness of the fuzzy load-shedding controller whose input variable load margin index was calculated using the SNB point when the PV active power output was 0. The designed fuzzy load-shedding strategy can compensate for the defect—that the traditional UVLS strategy cannot effectively guarantee the system static voltage stability—and it can be widely used in power grids integrated with PV power plants whose scales are at a level of several hundred MW and below.

Method of fuzzy inference for one class of MISO-structure systems with non-singleton inputs

In fuzzy modeling, the inputs of the simulated systems can receive both crisp values and non-Singleton. Computational complexity of fuzzy inference with fuzzy non-Singleton inputs corresponds to an exponential. This paper describes a new method of inference, based on the theorem of decomposition of a multidimensional fuzzy implication and a fuzzy truth value. This method is considered for fuzzy inputs and has a polynomial complexity, which makes it possible to use it for modeling large-dimensional MISO-structure systems.

Evaluation of Developer Efficiency Based on Improved DEA Model

In this paper, we evaluate the developer’s efficiency by an improved DEA model. It is a combination of traditional C2R model and fuzzy mathematics, which forms a new fuzzy DEA model. The model overcomes the strong objective factors that in the traditional DEA model and not support fuzzy input and output. It is conducive to improve the efficiency of the developer, which is very important for decision of makers.

An integrated inverse adaptive neural fuzzy system with Monte-Carlo sampling method for operational risk management

Operational risk refers to deficiencies in processes, systems, people or external events, which may generate losses for an organization. The Basel Committee on Banking Supervision has defined different possibilities for the measurement of operational risk, although financial institutions are allowed to develop their own models to quantify operational risk. The advanced measurement approach, which is a risk-sensitive method for measuring operational risk, is the financial institutions preferred approach, among the available ones, in the expectation of having to hold less regulatory capital for covering operational risk with this approach than with alternative approaches. The advanced measurement approach includes the loss distribution approach as one way to assess operational risk. The loss distribution approach models loss distributions for business-line-risk combinations, with the regulatory capital being calculated as the 99,9% operational value at risk, a percentile of the distribution for the next year annual loss. One of the most important issues when estimating operational value at risk is related to the structure (type of distribution) and shape (long tail) of the loss distribution. The estimation of the loss distribution, in many cases, does not allow to integrate risk management and the evolution of risk; consequently, the assessment of the effects of risk impact management on loss distribution can take a long time. For this reason, this paper proposes a flexible integrated inverse adaptive fuzzy inference model, which is characterized by a Monte-Carlo behavior, that integrates the estimation of loss distribution and different risk profiles. This new model allows to see how the management of risk of an organization can evolve over time and it effects on the loss distribution used to estimate the operational value at risk. The experimental study results, reported in this paper, show the flexibility of the model in identifying (1) the structure and shape of the fuzzy input sets that represent the frequency and severity of risk; and (2) the risk profile of an organization. Therefore, the proposed model allows organizations or financial entities to assess the evolution of their risk impact management and its effect on loss distribution and operational value at risk in real time.

A New Fuzzy Regression Model by Mixing Fuzzy and Crisp Inputs

A New Fuzzy Regression Model by Mixing Fuzzy and Crisp Inputs Magda M. M. Haggag Abstract This paper proposes a new form of the multiple regression model (mixed model) based on adding both fuzzy and crisp input data. The least squares approach of the proposed multiple regression parameters are derived in different cases. This derivation is based on the fact that each fuzzy datum is a nonempty compact interval of the real line. The main contribution is to mix both fuzzy and crisp predictors in the linear regression model. The mixed fuzzy crisp model will be introduced mathematically and by coded via R-language. The least squares of the regression parameters will be derived and evaluated using distance measures. Numerical examples using generated data showed best results for the mixed fuzzy crisp multiple regression models compared to the multiple fuzzy models. Full Text: PDF DOI: 10.15640/arms.v6n2a2

Fuzzy logic approach applied to credit scoring for microfinance in Morocco

Microfinance institutions in Morocco target clients who are excluded from the traditional financial systems and have no guarantees, exposing them to the risks of default and therefore bankruptcy. Also the microfinance sector is experiencing information asymmetry which makes it difficult to apply classical theory given the low databases quality and the lack of depth in the behavioral history of bad customers. The aim of this research is to use fuzzy logic approach that allows an individual and dynamic treatment of the customers by integrating the opinion of the experts in order to evaluate customer behavior to reduce loan default and ensure the viability and the sustainability of the microfinance institutions.The research used three composed Fuzzy Input variables with their trapezoidal membership function, an output variable and seventy eight fuzzy rules in the development of an evaluation model.

An input relaxation model for evaluating congestion in fuzzy DEA

This paper develops a BCC input relaxation model for identifying inputcongestion as a severe form of inefficiency of decision-making units in fuzzy data envelopment analysis. The possibility approach is presented to obtain the models equivalent to fuzzy models. We use a one-model approach to determine input congestion based on the BCC input relaxation model. A numerical example is given to illustrate the proposed model and identify the congestion with precise and imprecise data. The proposed model is also used to determine the congestion in 16 hospitals using four fuzzy inputs and two fuzzy outputs with a symmetrical triangular membership function.

Spam analysis of big reviews dataset using Fuzzy Ranking Evaluation Algorithm and Hadoop

Online reviews are the most easily available free information sources used by both organizations and customers to make decisions. Establishments are utilizing significance of opinions to earn undue profit by hiring professionals known as spammers, giving positive comments on their products and negative opinions on their competitor’s product. This activity is known as opinion spamming and should be identified to give genuine results containing sentiments towards a product. So far, opinion spam detection has been considered as a discrete classification problem, generally as spam and non-spam. However, it involves uncertainty as suspicious behavior of a user might be due to coincidence. As, fuzzy logic handles real world uncertainty very well, we propose a novel fuzzy modeling based solution to the problem. We have proposed four fuzzy input linguistic variable and considered suspicious level of a spammer group to be one of—Ultra, Mega, Immense, Highly, Moderate, Slightly and Feebly. We have defined novel FSL Deduction Algorithm generating 81 fuzzy rules and Fuzzy Ranking Evaluation Algorithm (FREA) to determine the extent to which a group is suspicious. As reviews dataset satisfy the three V’s of big data (Volume, Velocity and Variety), we have considered this problem as a big data problem and used Hadoop for storage and analyzation. We have further demonstrated our proposed algorithm using a sample reviews dataset and Amazon reviews dataset achieving an accuracy of 80.77% which unlike other approaches remains steady for large number of groups and deals well with uncertainty involved in opinion spam detection.

Control for the New Harsh sea Conditions Salvage Crane Based on Modified Fuzzy PID

AbstractThe new salvage crane for harsh sea conditions is a salvage and rescue device that is used for the space launch capsule. The wave compensation algorithm can improve search and rescue ability at sea, and can also provide wave compensation guidance for other sea vessels under harsh sea conditions. Firstly, compared with the traditional fuzzy PID algorithm, the wave compensation algorithm is improved in three aspects: fuzzy rules, fuzzy inputs, and fuzzy outputs. For the fuzzy rules, E and EC are used separately. E plays a main role and EC plays an auxiliary role. For the fuzzy inputs, the angle deviation is the sum of current angle and angle's changing rate. For the fuzzy outputs, the cylinder's inertia and the electro‐hydraulic valve's reverse dead zone factors are taken into account, and the PID output value is set with upper limit, lower limit, and dead zone. Secondly, the control valve and the hydraulic system's model are established in AMESim. The improved algorithm is established in SIMULINK. Combining the hydraulic model with the algorithm model, we do the co‐simulation analysis. Thirdly, the improved algorithm's verification experiments are carried out on a rocky platform, which can simulate the ship's instability in different sea conditions. Finally, the simulation and experimental results verify that the improved fuzzy PID algorithm enhances the salvage crane's response and robustness, and also improves the salvage effect.

An Experimental Fuzzy Inference System for Global Grid Electricity Peak Power Load Forecasting Third Core Module of First Console on G2P3S

Our World gives several symptoms of climate change. Devastating draughts increase (negative for World (-)), global mean temperature increase (-), lightning strikes increase (-), sea ice cover melt (-), tree mortality increase (-), and forest degradation increase (-) have been observed for decades. They are all negative measures for continuity of life. Diversity of species has been decreasing, so that life on Earth is dying. Only responsible specie for this situation is humankind. This study presents a small footstep to prevent this situation. Modeling of a 100% renewable power grid on World (Global Grid) is eminent. Annual peak power load (Gigawatt: GW, Kilowatt: kW) (peak demand or load) forecasting in power demand side is crucial for global grid modeling. This study presents an experimental fuzzy inference system for the third core module (100 years’ power demand forecasting) of the first console (long term prediction) of Global Grid Peak Power Prediction System (G2P3S). The inputs (world population, global annual temperature anomalies °C) and the output (annual peak power load demand of Global Grid in GW) are modeled with seven triangular fuzzy input membership functions and seven constant output membership functions. The constant Sugeno-Type fuzzy inference system is used in the current experimental model. The maximum absolute percentage error (MAP) is calculated as 45%, and the mean absolute percentage error (MAPE) is found as 39% in this experimental study. The MAP and MAPE of the first core module model (Type 1) were 0,46 and 0,36. The MAP and MAPE of the second core module model (Interval Type 2) were 0,46 and 0,36. As a result, this study is a good start for the third core module of the first console on Global Grid Peak Power Prediction System research, development, demonstration, & deployment (RD3) project. This experimental study also warns humankind in this subject. Hopefully, the most polluting societies on our World such as China, United States, India, Russia, Japan, Germany, South Korea, and Canada take urgent actions to start to build the foundations of 100% renewable power global grid by organizing a global grid consortium.

Dynamic network data envelopment analysis model with fuzzy inputs and outputs: An application for Iranian Airlines

Dynamic network data envelopment analysis (DNDEA) is a non-parametric model for evaluating the relative efficiency of decision-making units (DMUs) with network structure in several periods of time. The model uses accurate inputs/outputs data, whereas in many real-world applications, the data often fluctuate. Frontier-type models such as DNDEA models are sensitive to existence uncertainties in data. To deal with fluctuations in data which can be represented by fuzzy numbers, this paper extends the DNDEA model in a fuzzy framework. Since, the efficiency measures are expressed by membership functions rather than by certain values, hence, more information is provided for management. By using the proposed fuzzy DNDEA model, the precise efficiency scores in DNDEA model are extended to the fuzzy numbers for reflecting uncertainty in real evaluation problems. The final efficiency scores generated by the proposed model are intervals which can describe the real situation in better detail. In addition, the proposed model is a useful tool for detecting sensitive decision-making units. To illustrate the capability of the proposed fuzzy DNDEA model, a case study of airlines in Iran is used to explain how the efficiencies of system and process with fuzzy data are calculated.

The model for estimation production cost of embroidery handicraft

Embroidery industry is one of type of micro industry that produce embroidery handicraft. These industries are emerging in some rural areas of Indonesia. Embroidery clothing are produce such as scarves and clothes that show cultural value of certain region. The owner of an enterprise must calculate the cost of production before making a decision on how many products are received from the customer. A calculation approach to production cost analysis is needed to consider the feasibility of each order coming. This study is proposed to design the expert system (ES) in order to improve production management in the embroidery industry. The model will design used Fuzzy inference system as a model to estimate production cost. Research conducted based on survey and knowledge acquisitions from stakeholder of supply chain embroidery handicraft industry at Bukittinggi, West Sumatera, Indonesia. This paper will use fuzzy input where the quality, the complexity of the design and the working hours required and the result of the model are useful to manage production cost on embroidery production.

Forecasting the emergency explosive environment with the use of fuzzy data

We resolved the scientific and technical problem to improve the efficiency of a decision-making processes carried out by a head of emergencies elimination of accidents at potentially dangerous objects by forecasting an emergency explosive environment under conditions of uncertainty. We completed a formalized statement of the problem of identification of the concentration of an explosive gas-air mixture, which makes possible to use fuzzy input and output data. We determined the aspects of solution of the problem of forecasting with a use of expert conclusions in the case of absence or unreliability of input data. We developed the technology of forecasting of parameters of an emergency explosive environment based on the obtained results. The proposed technology can be used in the post-emergency period to clarify fields of an explosive environment. A neuro-fuzzy network can be re-trained in the shortest possible time and used to solve a forecasting problem at all possible points in the zone of explosive environment on the base of the results of measurements of explosive concentration of devices. In addition, this technology can be used to clarify initial values of parameters of an accident, which will improve and objectify a decision making carried out by the head of emergencies elimination

A fuzzy finite element method for sparse experimental data based on a possibilistic approach

AbstractThis work considers the possibilistic interpretation of the fuzzy set theory for the fuzzy finite element method (FFEM). The underlying uncertainty type of design variables arises from sparse experimental data and is referred to as imprecise probability. In this context, a linear elastic body with given sparse experimental results for the design variables Young's modulus and Poisson's ratio is studied. To this end, the fuzzy input parameters are represented by possibility distributions generated by a probability‐possibility transformation. A computational approach involving the α‐level discretization technique [4] is applied in order to calculate the possibility of a quantity of interest. Finally, our method is applied in a numerical example for a plate with a ring hole. (© 2017 Wiley‐VCH Verlag GmbH & Co. KGaA, Weinheim)

A fuzzy logistic regression model based on the least squares estimation

To construct the relationship between fuzzy inputs and fuzzy output described by linguistic variable, we develop a fuzzy logistic regression model, which can be applied for various problems, such as clinical research, risk investment and decision making. In this regard, we introduce the integral calculation of distance of cut sets and a fuzzy adjustment term which could prevent a large fuzzy error for a fuzzy output caused by the output degenerating into crisp number when the independent variables are crisp numbers. The parameters of the fuzzy logistic regression model are derived by means of the least squares method. We adopt three criteria involving mean square error, Kim and Bishu criterion and capability index and also perform two ways of prediction including the in-sample forecast as well as the one-leave-out cross validation. The comparisons with five existing methods show that our proposed method has satisfactory performance and the results are illustrated in some case studies.

An Atanassov intuitionistic fuzzy constraint based method for offer evaluation and trade-off making in automated negotiation

In automated negotiation, one of crucial problems is how a negotiating agent evaluates the acceptability of an offer. Most evaluation methods are mainly based on utility functions that are in the form of linear or nonlinear mathematical formulas. However, in real life, it is hard for human users to input information accurately as these evaluation methods require. To this end, this paper proposes a new approach for offer evaluation, where human users are allowed to input fuzzy and indeterminate information. More specifically, we first propose a framework of prioritised Atanassov intuitionistic fuzzy constraint satisfaction problems. Then we propose a method to evaluate an offer according to the satisfaction degrees and dissatisfaction degrees of all the prioritised Atanassov intuitionistic fuzzy constraints that represent the users’ fuzzy goals for a negotiation. Finally, we discuss how to make counter-offers of trade-off on the basis of the offer evaluation method proposed in this paper. When making a tradeoff, a negotiation agent considers not only a tradeoff alternative’s similarity to the opponent’s previous offer but also its satisfaction degree and dissatisfaction degree towards the most prioritised goal of the agent itself.

Possibilistic linear regression with fuzzy data: Tolerance approach with prior information

We introduce the tolerance approach to the construction of fuzzy regression coefficients of a possibilistic linear regression model with fuzzy data (both input and output). The method is very general: the only assumption is that α-cuts of the fuzzy data are efficiently computable. We take into account possible prior restrictions of the parameters space: we assume that the restrictions are given by linear and quadratic constraints. The method for construction of the possibilistic regression coefficients is in a reduction of the fuzzy-valued model to an interval-valued model on a given α-cut, which is further reduced to a linear-time method (i.e., running in time O(np)) computing with endpoints of the intervals. (Here, n is the number of observations and p is the number of regression parameters.) The speed of computation makes the method applicable for huge datasets. Unlike various approaches based on mathematical programming formulations, the tolerance-based construction preserves central tendency of the resulting regression coefficients. In addition, we prove further properties: if inputs are crisp and outputs are fuzzy, then the construction preserves piecewise linearity and convex shape of fuzzy numbers. We derive an O(n2p)-algorithm for enumeration of breakpoints of the membership function of the estimated coefficients. Similar results are also derived for the fuzzy input-and-output model. We illustrate the theory for the case of triangular and asymmetric Gaussian fuzzy inputs and outputs of an inflation-consumption model.

PENENTUAN JUMLAH PRODUKSI SHAMPO DENGAN FUZZY INFERENCE SYSTEM SUGENO: STUDI KASUS PT. GUARDIAN PHARMATAMA TANGERANG

ABSTRACTHuman are always faced with taking a decision. It also happens to a company in the process of determining which employees. In determination the production plan required a lot of considerations in case of taking decisions. Beside that, the number of employees in a company is to determine who get the production plan of the achievement. System is made to determine employees who will get benefits achievement based on the some criteria have been determined by the company. These criterias will be used as fuzzy input which also process a called fuzzy variables. In this research will construct decision support system by using fuzzy logic with fuzzy variables input that are productivity, quality tabbing and discipline. In of fuzzy logic method there are three stages, namely stage fuzzification, inference and deffuzification. At this stage of the fuzzy inference used the Sugeno method. The results of this experiments has performed that the system is able to display the production planning data for the calculation of the value of production that have been determined based on fuzzy logic with fuzzy variables. Keyword: Decision Support System, Fuzzy Logic, Sugeno.

LOGIKA FUZZY MENENTUKAN JUMLAH PRODUKSI BERDASARKAN PERSEDIAAN DAN JUMLAH PERMINTAAN

The complicated to determine total of product will be production with stock, make the process of decision be slowly. The purpose of this research for implementated fuzzy logic Mamdani method for determine the total of production basis on the total of stock and the total of request at OSI Electronics Batam, Corp and description of accuracy level. The first process analyze the corporation data with total 12 data start from January – December 2015. The data will be processed using MATLAB application with first step is fuzzyfication defene the membership function. There are 2 information as fuzzy input request and stock and will be processed using triangle and trapezoid membership function. Next step is implicated all rules and this research using 26 rules, rule compositions and the last step is defuzzyfication using bisector method. The accuracy using fuzzy logic that was built were 91,67% and error 9,37%.