Fuzzy Genetic Models Research Articles

Fuzzy-Genetic Model for Load Balancing and Machine Utilization in Job Shop Scheduling

Fuzzy-Genetic Model for Load Balancing and Machine Utilization in Job Shop Scheduling

A Fuzzy-Genetic Modelling Approach to Maintenance Scheduling for the Minimization of Fishing Vessel Idle Time in the Maritime Industry

As the marine industry becomes more complex and challenging to manage optimizing the idle time of vessels is critical. Although previous idle time reduction efforts in maintenance were through the evaluation of crisp numerical values in optimization models, none of the studies has considered the effect of uncertainty and imprecision on the system. Consequently, in this paper, a linguistic-based optimization model is developed using the fuzzy-genetic model for the discredited time-maintenance manpower-cost saving problem. The suggested model is moved for the following reasons: (1) it considers linguistic terms to express the optimization of vessels' idle time from a unique perspective of deploying genetic algorithm while considering the minimum and maximum number of times vessels may return for maintenance (2) it has an indirect measure of the quality of maintenance service which is absent in previous models (3) a cost-saving dimension is introduced where the ideas of low, medium and high-cost savings are examined. The results show the feasibility of the approach. The model advanced promises to provide vessel controllers with an idle time assessment framework, which enhances the chances of generating the utmost profit for companies.

Hybrid Fuzzy-Genetic Model for Fitness-Based Performance Optimization in Wireless Networks

In recent times, the application of autonomic soft computing techniques for design and optimization of wireless access networks is progressively becoming prevalent. These computational learning techniques are capable of handling uncertain and imprecise networking information while driving toward the optimal solution set in the problem search space. The approach proposed by this paper presents the application of the fuzzy logic inference combined with the evolutionary genetic algorithm to optimize the performance parameters in wireless networks. In particular, we consider optimal bit rate allocation and transmission power consumption through the joint design of fuzzy-genetic modeling framework. The sample training data generated through simulations of IEEE 802.11 wireless access network are analyzed for optimization by supplying it to the expert hybrid model comprising of the conjunctive design of both the computational intelligent techniques. Specifically, we contemplate the binary encoding scheme, single-point crossover, reversing mutation, and two fitness functions for executing the binary genetic operations of crossover and mutation. It is generally observed that the proposed hybrid model with polynomial fitness function yields better performance with scalable network datasets than the logarithmic fitness function in terms of higher objective value. Moreover, the results obtained through simulation experiments exhibit significant throughput gains and power efficiency for the deployed fitness functions with the evolving size of training dataset. Compared with the existing methods, our hybrid learning model demonstrates performance enhancement with higher expected fitness measure, improved throughput and power efficiency.

Solubility modeling of supercritical fluid extraction in a wide range compounds: comparison between fuzzy-genetic and new empirical models

ABSTRACTIn the current study, two methods based on a new empirical equation and fuzzy-genetic model are proposed to estimate solute solubility in supercritical fluid (SCF). New proposed models are trained with comprehensive dataset collected from literature with more than 3,260 experimental data at different temperature and pressure. In order to testify the accuracy, the proposed models are compared to other empirical equations. The amounts of average values of absolute relative deviation ()were obtained 7.74% for fuzzy-genetic model and 9.27% for new proposed empirical model. The reasonable accuracy of developed models for estimating the solubility of solutes in SCF extraction process is represented. From literature solubility data, the authors obtained new estimation models for solute solubility in CO2 supercritical which are in agreement with measured experimental values.

Hybrid sediment transport model for the “linguado” channel, state of Santa Catarina, Brazil

This study involves an assessment of various artificial intelligence-related techniques which aim to produce a more robust system for sediment transport modeling. The intelligent systems developed in this research are directly applicable to academic knowledge and use data from a report on "water circulation assessment in the “Linguado” Channel and Babitonga Bay ,”Santa Catarina”, Brazil, developed by Military Engineering Institute (IME). The solution employed for sediment transport was built using an intelligent system from the conception of two hybrid models. The first was a Neuro-Fuzzy (ANFIS) hybrid model for the study of hydrodynamic behavior, aiming to determine flow rate in the channel. The second was a fuzzy genetic model, able to assess sediment transport in the “Linguado” Channel. The study's conclusion compares the different effects involved in the dredging equilibrium in the “Linguado” Channel according to this hybrid model with the results obtained using a finite element model in the MIKE21® software.

Pan evaporation modeling using four different heuristic approaches

Evaporation plays important roles in regional water resources management, climate change and agricultural production. This study investigates the abilities of fuzzy genetic (FG), least square support vector regression (LSSVR), multivariate adaptive regression spline (MARS), M5 model tree (M5Tree) and multiple linear regression (MLR) in estimating daily pan evaporation (Ep). Daily climatic data, air temperature (Ta), surface temperature (Ts), wind speed (Ws), relative humidity (RH) and sunshine hours (Hs) at eight stations in the Dongting Lake Basin, China are used for model development and validation. The first part of this study focuses on testing the model accuracies at each station using local input and output data. The results show that LSSVR and FG models with more input variables perform better than the MARS, M5Tree and MLR models in predicting daily Ep at most stations with respect to mean absolute errors (MAE), root mean square errors (RMSE) and determination coefficient (R2). In the second part of this study, the models are tested using cross-validation method in two different applications. The daily Ep of Yueyang station is estimated using the input and output data of Jingzhou and Changsha, respectively. Comparisons of the models indicate that the FG, LSSVR and MARS models outperform the M5Tree model, Ts, Hs and Ta are major influencing factors and adding Ws or RH into model inputs significantly improve the model performances. The overall results indicate that above models can be successfully used for estimating daily Ep using local input and output data while the FG and LSSVR generally perform better than the other models without local input and outputs.

Multi objective optimization of rotorcraft compact spinning system using fuzzy-genetic model

In this paper, the mechanical and physical properties of rotorcraft compact spinning yarns were evaluated. For this aim, the filament pre-tension, yarn count and type of sheath fibers were selected as the controllable factors, and the effect of them on the elongation and hairiness was investigated statistically and the obtained results indicated that controllable factors have significant effect on the measured properties. In the next step, the relation between factors and measured properties was modeled by fuzzy interface system and genetic algorithm was used to optimize the number of membership function and its kind. It was observed that the accuracy of obtained models for both elongation and hairiness is acceptable (correlation coefficient for both models was: 0.99). Finally, to find a set of controllable factors to produce a yarn with high elongation and low hairiness, multi objective optimization was applied by means of non-dominated sorting genetic algorithm and a set of trade off solutions obtained so that each solution can be accepted as a response.

Evaporation modelling using different machine learning techniques

ABSTRACTAccurate prediction of pan evaporation (Ep) is critical for water resource management. This article investigates the capabilities of three different soft computing methods at estimating monthly Ep at six stations in the Yangtze River Basin using climatic factors, including the air temperature (Ta), solar radiation (Rg), air pressure (Pa) and wind speed (Ws) for the period of 1961–2000. The first part of the study focused on testing and comparing model accuracy levels at each station using local input combinations. The results indicate that the fuzzy genetic (FG) model generally produces better results than adaptive neuro‐fuzzy inference systems with grid partition (ANFIS‐GP) and M5 model tree (M5Tree) specifications in terms of the root mean square error , mean absolute error and coefficient of determination values. The performance of the above models was also examined using cross‐station applications (estimating Ep without local input or output data) in the second part of the study. The third part focused on estimating Ep using generalized FG, ANFIS‐GP and M5Tree models. Collectively, the results demonstrate that the FG model can be successfully used to estimate Ep without any local inputs and outputs and that a single generalized FG model can also be used at six different locations.

Fuzzy-Genetic Model for the Identification of Falls Risk Gait

This paper investigates the effectiveness of a hybrid genetic and fuzzy set algorithm for the recognition of gait patterns in falls risk patients. In a previous work, we have shown the usefulness of fuzzy set techniques for gait pattern identification. In this paper, we apply a genetic algorithm in conjunction with fuzzy logic rules to better select the optimal combination of pathological gait features for improved gait diagnostic capability. Gait features were calculated using minimum foot clearance data collected during continuous walking on a treadmill for 20 older adults. The subjects are composed of two groups, 10 individuals with normal gait, and 10 with a history of falls. Fuzzy rules were extracted from the gait dataset using subtractive clustering. The genetic algorithm was introduced in order to select the optimum combination of gait features. Using cross validation test data, the results indicated that the generalization performance, in terms of accuracy, for the hybrid system was 97.5%, compared to89.3% that was obtained using only the fuzzy system. The generalization performance of the gait classifier was also analyzed by determining the areas under the receiver operating characteristic plot. We observed that an improved gait classification performance became evident when the fuzzy system classifier used a small number of features that were selected by the genetic algorithm.

Expert System Modeling for Land Suitability based on Fuzzy Genetic for Cereal Commodities: Case Study Wetland Paddy and Corn

Nowadays, threats of food shortages are happen in Indonesia. Most of crops that are consumed as main food are cereals commodities. Cereals cultivation often experience some problems in determining whether land is suitable or not for the crops. Expert system can help researcher and practitioners to identify land suitability for cereal crops. In this research, an expert system model of land suitability for cereals crop was built. The model implemented soft computing methods to develop inference engine which combines fuzzy system and genetic algorithm. There are 16 parameters to define land suitability which consists of 12 numeric parameters and 4 categorical parameters. Two types of cereal crops that were used in this study namely wetland paddy and corn. Trapezoid membership function was used to represent fuzzy sets for numerical parameters. Genetic algorithm was used for tuning the membership function of fuzzy set for land suitability which consists of very suitable (S1), quite suitable (S2), marginal suitable (S3) and not suitable (N). This expert system is able to choose land suitability classes for cereals using the fuzzy genetic model with accuracy of 90% and 85% for corn and wetland paddy respectively.

Modeling solar radiation of Mediterranean region in Turkey by using fuzzy genetic approach

The study investigates the ability of FG (fuzzy genetic) approach in modeling solar radiation of seven cities from Mediterranean region of Anatolia, Turkey. Latitude, longitude, altitude and month of the year data from the Adana, K. Maras, Mersin, Antalya, Isparta, Burdur and Antakya cities are used as inputs to the FG model to estimate one month ahead solar radiation. FG model is compared with ANNs (artificial neural networks) and ANFIS (adaptive neruro fuzzzy inference system) models with respect to RMSE (root mean square errors), MAE (mean absolute errors) and determination coefficient (R2) statistics. Comparison results indicate that the FG model performs better than the ANN and ANFIS models. It is found that the FG model can be successfully used for estimating solar radiation by using latitude, longitude, altitude and month of the year information. FG model with RMSE = 6.29 MJ/m2, MAE = 4.69 MJ/m2 and R2 = 0.905 in the test stage was found to be superior to the optimal ANN model with RMSE = 7.17 MJ/m2, MAE = 5.29 MJ/m2 and R2 = 0.876 and ANFIS model with RMSE = 6.75 MJ/m2, MAE = 5.10 MJ/m2 and R2 = 0.892 in estimating solar radiation.

Applicability of Mamdani and Sugeno fuzzy genetic approaches for modeling reference evapotranspiration

This study investigates the applicability of Mamdani and Sugeno fuzzy genetic approaches in modeling reference evapotranspiration (ET0). The daily air temperature, solar radiation, relative humidity and wind speed data from Adana and Antalya stations, Turkey, were used as inputs to the fuzzy genetic models for estimating ET0 obtained using the standard FAO-56 Penman–Monteith equation. Comparison of two different fuzzy genetic methods indicated that the Sugeno fuzzy genetic (SFG) method was faster and had a better accuracy than the Mamdani fuzzy genetic (MFG) method in modeling daily ET0. SGF and MFG models were also compared with the recently proposed Valiantzas’s equations and following empirical models: Hargreaves–Samani and Priestley–Taylor methods. Root mean-squared errors (RMSE), mean-absolute errors (MAE) and determination coefficient (R2) were used for the evaluation of the models’ performances. Results revealed that the SFG and MFG models were performed better than the empirical models in modeling daily ET0 process. Comparison of the two different fuzzy genetic approaches indicated that the SFG had a better accuracy than the MFG. For the Adana and Antalya stations, the SFG1 model with RMSE = 0.219 and 111 mm/day, MAE = 0.097 and 0.080 mm/day and R2 = 0.983 and 0.998 in validation period was found to be superior in modeling daily ET0 than the other models, respectively.

Monthly pan evaporation modeling using linear genetic programming

Summary This study compares the accuracy of linear genetic programming (LGP), fuzzy genetic (FG), adaptive neuro-fuzzy inference system (ANFIS), artificial neural networks (ANN) and Stephens–Stewart (SS) methods in modeling pan evaporations. Monthly climatic data including solar radiation, air temperature, relative humidity, wind speed and pan evaporation from Antalya and Mersin stations, in Turkey are used in the study. The study composed of two parts. First part of the study focuses the comparison of LGP models with those of the FG, ANFIS, ANN and SS models in estimating pan evaporations of Antalya and Mersin stations, separately. From the comparison results, the LGP models are found to be better than the other models. Comparison of LGP models with the other models in estimating pan evaporations of the Mersin Station by using both stations’ inputs is focused in the second part of the study. The results indicate that the LGP models better accuracy than the FG, ANFIS, ANN and SS models. It is seen that the pan evaporations can be successfully estimated by the LGP method.

Evolutionary neural networks for monthly pan evaporation modeling

• Evolutionary neural networks (ENN) is used for modeling pan evaporation. • Data from two stations of Turkey are used in the study. • ENN models are compared with fuzzy genetic, neuro-fuzzy and ANN methods. • ENN models perform better than the other models. • Pan evaporation can be successfully estimated by the ENN method. Estimating pan evaporation is very important for monitoring, survey and management of water resources. This study proposes the application evolutionary neural networks (ENN) for modeling monthly pan evaporations. Solar radiation, air temperature, relative humidity, wind speed and pan evaporation data from two stations, Antalya and Mersin, in Mediterranean Region of Turkey are used in the study. In the first part of the study, ENN models are compared with those of the fuzzy genetic (FG), neuro-fuzzy (ANFIS), artificial neural networks (ANN) and Stephens–Stewart (SS) methods in estimating pan evaporations of Antalya and Mersin stations, separately. Comparison results indicate that the ENN models generally perform better than the FG, ANFIS, ANN and SS models. In the second part of the study, models are compared with each other in estimating Mersin’s pan evaporations using input data of both stations. Results reveal that the ENN models performed better than the FG, ANFIS and ANN models. It was concluded that monthly pan evaporations can be successfully estimated by the ENN method. The performance of the ENN model with full weather data as inputs presents 0.749 and 0.759 mm of mean absolute error for the Antalya and Mersin stations, respectively.

Fuzzy Genetic Approach for Estimating Reference Evapotranspiration of Turkey: Mediterranean Region

The applicability of fuzzy genetic (FG) approach in modeling reference evapotranspiration (ET0) is investigated in this study. Daily solar radiation, air temperature, relative humidity and wind speed data of two stations, Isparta and Antalya, in Mediterranean region of Turkey, are used as inputs to the FG models to estimate ET0 obtained using the FAO-56 Penman–Monteith equation. The FG estimates are compared with those of the artificial neural networks (ANN). Root mean-squared error, mean absolute error and determination coefficient statistics were used as comparison criteria for the evaluation of the models’ accuracies. It was found that the FG models generally performed better than the ANN models in modeling ET0 of Mediterranean region of Turkey.

The prediction of prismatic beam behaviours with polypropylene fiber addition under high temperature effect through ANN, ANFIS and fuzzy genetic models

Fibers of different kinds in various proportions are added to the concrete in order to improve its mechanical properties and make it resistant to fires. Steel or plastic based polypropylene fibers (PP) are preferred as fiber stuff. An inhomogeneous distribution of fiber in the concrete makes it difficult to accurately determine its mechanical characteristics under high temperature effect. This complicates establishing correlations between experimental data. A training mechanism is needed to establish the desired correlation. The significance of this study is that F19 and M12 type PPs were added to concrete mixtures and 216 pieces cylinders sized 150×300 and 216 pieces prismatic beam specimens sized 150×150×750mm were produced in total. The specimens were exposed to high temperature effect and their energy absorption capacity was experimentally determined. Moreover, with the model developed, the prediction of the values was made depending on the experimental data. In this study, multi-layered artificial neural network, fuzzy logic and fuzzy genetic models were used. The predicted models provided a strong correlation between the target values and result values and they were successful in predicting with small error values according to target value magnitudes. When the experimental data and the inferences of the models are compared, the fuzzy-genetic model yielded results in a more successful range by which behaviours can be defined than the multi layered artificial neural network and fuzzy logic models.

Experimental investigation of mechanical properties of hybrid fiber reinforced concrete samples and prediction of energy absorption capacity of beams by fuzzy-genetic model

There have been a great number of studies aiming to improve the mechanical qualities of concrete material which is a basic component of reinforced concrete bearing systems. Attempts to reinforce the concrete through fiber addition have an important place among these studies. This study is an experimental research on the mechanical features of hybrid fiber added concretes which are obtained using steel fibers and polypropylene (PP) fibers together in certain proportions. Test specimens consist of 180 cylindrical samples (150×300mm) and 90 prismatic (150×150×750mm) beams produced in C40 concrete class. The specimens were exposed to temperatures ranging from room temperature to 100, 200, 400, 600 and 800°C in a certain order following their cure periods of 7, 28 and 90days. It was observed that hybrid fiber addition has a significant contribution into the compressive strength, flexural strength and energy absorption capacity of the concrete. Significance of hybrid fiber addition was put forward for the increase in ductility of the concrete which displays a brittle behavior when forced to bending.In the experimental studies with a numerous test specimens, losing of data due to some reasons and being unable to receive data was considered as a problem to be solved. Therefore, a fuzzy-genetic model was suggested to predict not only the experimental gaps, but also the untested value ranges of experimental parameters. Model was taken consideration in three different applications and it showed a satisfactory performance in predicting data.

Modeling monthly pan evaporations using fuzzy genetic approach

► We estimate monthly pan evaporation ( PE ) by using fuzzy genetic (FG) approach. ► FG estimates are compared with neuro-fuzzy (NF) and neural network (NN) techniques. ► Comparison results indicate the superiority of FG models to the NF and NN models. ► Models are also compared in estimating one station’s PE using nearby station’s data. ► Results reveal that monthly PE can be successfully estimated by FG approach. This study investigates the ability of fuzzy genetic (FG) approach in estimation of monthly pan evaporations. Various monthly climatic data, that are, solar radiation, air temperature, relative humidity and wind speed from two stations, Antalya and Mersin, in Mediterranean Region of Turkey, were used as inputs to the FG technique so as to estimate monthly pan evaporations. In the first part of the study, FG models were compared with neuro-fuzzy (ANFIS), artificial neural networks (ANNs) and Stephens–Stewart (SS) methods in estimating pan evaporations of Antalya and Mersin stations, separately. Comparison of the models revealed that the FG models generally performed better than the ANFIS, ANN and SS models. In the second part of the study, models were compared to each other in two different applications. In the first application the input data of Antalya Station were used as inputs to the models to estimate pan evaporation data of Mersin Station. The pan evaporation data of Mersin Station were estimated using the input data of Antalya and Mersin stations in the second application. Comparison results indicated that the FG models performed better than the ANFIS and ANN models. Comparison of the accuracy of the applied models in estimating total pan evaporations showed that the FG model provided the closest estimate. It was concluded that monthly pan evaporations could be successfully estimated by the FG approach.

A comparative modeling study to estimate wear of concrete

This paper investigates the impacts of fuzzy genetic (FG), a new fuzzy logic model with genetic algorithm, artificial neural networks (ANN) and general linear model (GLM) approaches on abrasive wear of concrete. For this purpose, experimental studies were made to investigate the influence on wear of the following input parameters: hematite, cement, compressive strength and different loads on the experiments. In these models, 60 data sets were used. For training set, 48 data (80 %) were randomly selected and the residual data (12 data, 20 %) were test set. Model results were compared with experimental results. In this paper, main model performance criterion was root mean square errors. Also, sum of squared error and determination coefficient statistics were used as comparing criteria for the evaluation of models’ performances. Comparison results indicate that FG models are superior to ANN and GLM models in modeling of influence hematite, cement, compressive strength and loads on wear of concrete.

Fuzzy genetic approach for modeling of the critical submergence of an intake

The vertical distance between the water level and upper level of intake is called submergence. When the submergence of the intake pipe is not sufficient, air enters the intake pipe and reduction in discharge occurs. The submergence depth at which incipient air entrainment occurs at a pipe intake is called the critical submergence (S c ). It can also cause mechanical damage, vibration in pipelines and loss of pump performance. Therefore, the determination of the S c value is a significant problem in hydraulic engineering. To estimate the S c values for different pipe diameters, experimental works are conducted and results obtained are used for modeling of critical submergence ratio (S c /D i ). In this study, a fuzzy genetic (FG) approach is proposed for modeling of the S c /D i . The channel flow velocity (U), intake pipe velocity (V i ) and porosity (n) are used as input variables, and the critical submergence ratio (S c /D i ) is used as output variable. The 44 data sets obtained by experimental work were divided into two parts and 28 data sets (approximately 64 %) were used for training, and 16 data sets (approximately 36 %) were used for testing of models. The experimental results were compared with FG, an adaptive neuro-fuzzy inference system (ANFIS) and artificial neural networks (ANNs). The comparison revealed that the FG models outperformed the ANFIS and ANN in terms of root mean square error (RMSE) and determination coefficient (R 2) statistics for the data sets used in this study. In addition to RMSE and R 2, which are used as main model evaluation criteria, mean absolute error is used to evaluate the performance of models.