Abstract. Rainfall forcasting is a non-linear forecasting process that varies according to area and strongly influenced by climate change. It is a difficult process due to complexity of rainfall trend in the previous event and the popularity of AdaptiveNeuroFuzzyInference System (ANFIS) with hybrid learning method give high prediction for rainfall as a forecasting model. Thus, in this study we investigate the efficient membership function of ANFIS for predicting rainfall in Banyuwangi, Indonesia. The number of different membership functions that use hybrid learning method is compared. The validation process shows that 3 or 4 membership function gives minimum RMSE results that use temperature, wind speed and relative humidity as parameters.
Estimating the xanthate decomposition percentage has a crucial role in the treatment of xanthate contaminated wastewaters and in the improvement of the flotation process performance. In this research, the modeling of xanthate decomposition percentage was performed using the least squares regression method and the AdaptiveNeuro-FuzzyInference System (ANFIS). A multi-variable regression equation and the ANFIS models with various types and numbers of membership functions (MFs) were constructed, trained, and tested for the estimation of xanthate decomposition percentage. The statistical indices such as Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and coefficient of determination (R 2 ) were used to evaluate the performance of various models. The lowest values of RMSE and
FJ Chang, HC Lain. 2014. Adaptiveneuro-fuzzyinference system for the prediction of monthly shoreline changes in northeastern Taiwan. Ocean Engineering. 84: 145-156. GEP Box, GM Jenkins, and GC Reissel. 1994. Time Series Analysis Forecasting and Control, 3rd edition, Englewood Cliffs: Prentice Hall.
IMAGES are often corrupted by impulse noise during image acquisition and transmission over communication channel. Noise elimination and enhancement are essential features in digital image processing. Because the performances of subsequent image processing tasks are strictly dependent on the success of the noise removal operation. However, this is a difficult task because the noise removal operator is imposed with the requirement of preserving useful information in the image while efficiently removing the noise. Digital images are valuable sources of information in many research and application areas including astronomy, biology, medicine, remote sensing, materials science, etc. During image acquisition, digital images are frequently corrupted by noise due to number of imperfections in the imaging process. The image corruption is usually introduced by a nonideal imaging system (sensor noise, limited system accuracy, finite precision, quantization of image data, etc.) or an imperfect medium between the original scene and the imaging system (random scattering, absorption, etc.). The currently available nonlinear filters cannot simultaneously satisfy both of these criteria. The existing filters either suppress the noise at the cost of reduced noise suppression performance. Neural networks and fuzzy systems had been investigated to the problems in digital signal processing. A Neuro-Fuzzy System is a flexible system trained by heuristic learning techniques derived from neural networks can be viewed as a 3-layer neural network with fuzzy weights and special activation functions is always interpretable as a fuzzy system uses constraint learning procedures is a function approximation (classifier, controller). In this paper, AdaptiveNeuro-fuzzyInference System (ANFIS) is presented, which is a fuzzyinference system implemented in the framework of adaptive network. This ANFIS training algorithm is suggested by Jang. By using hybrid learning procedure, the proposed ANFIS can construct an input-output mapping which is based on both human knowledge (in the form of fuzzy if- then rules) and learning. The proposed work is carried in two stages. In first stage, noisy image (i.e. received or captured by camera) is denoised by new tristate switching median filter. The denoised image is further enhanced by ANFIS. . The structure of the proposed hybrid filter, to make the process robust against noise, is a combination of nonlinear switching median filter and neuro-fuzzy network. The internal parameters of the neuro-fuzzy network are adaptively optimized by training. The proposed filter is evaluated under
This paper presents an Edge Detection technique for images corrupted by salt and pepper noise, which is based on an AdaptiveNeuro-FuzzyInference System (ANFIS). This proposed technique first of all filters out the noise by Noise AdaptiveFuzzy Switching Median Filter (NAFSMF) and then find the edges using proposed ANFIS based edge detector. The training pattern for edge detection is proposed to optimize the internal parameters of the ANFIS based edge detector. The edges are directly determined by the proposed ANFIS based edge detector. This proposed edge detector is then compared with popular edge detectors Sobel, Roberts, Prewitt on the basis of performance metrics PSNR (Peak Signal to Noise Ratio), MSE (Mean Square Error) and No. of Edges detected.
Adhoc Networks are new paradigm of wireless communication which lack specific infrastructure. Scalability and Routing are the two major challenging issues that need to be addressed for providing better performance of the network. Due to mobility nature and dynamic topology, the conventional routing protocol should be manipulated to meet QoS requirements required for multimedia traffic. To overcome the scalability issue, QOS parameters are kept in rigorus bound for group communication. FuzzyInference based System (AdaptiveNeuroFuzzyInference) is used to optimize the QoS parameters such as delay and node speed for attaining the better performance of the network. This proposed scheme provides improvement in QoS metric such as delay, packet delivery ratio and minimizes the possibility of link failures and the overhead needed to construct the paths.
An adaptiveneuro-fuzzyinference system or adaptive network-based fuzzyinference system (ANFIS) is a kind of artificial neural network that is based on Takagi–Sugeno fuzzyinference system. The technique was developed in the early 1990s. Since it integrates both neural networks and fuzzy logic principles, it has potential to capture the benefits of both in a single framework. Its inference system corresponds to a set of fuzzy IF–THEN rules that have learning capability to approximate nonlinear functions. Hence, ANFIS is considered to be a universal estimator. For using the ANFIS in a more efficient and optimal way, one can use the best parameters obtained by genetic algorithm.
Abstract— Biometrics plays a very crucial role in various pattern recognitions. Recognition systems are used for offline application and also for online applications. In the biometric family, palmprint based identification system has become one of the active research topics. Palmprint identification system as two phases one is the feature extraction phase and other is the identification phase. The purpose of this paper is to use adaptiveneurofuzzyinference system for the identification phase. The objective of ANFIS is to integrate the best features of fuzzy systems and neural networks. An ANFIS based identification system is described here which uses palmprint as input. Experiments are carried out using the samples. Obtained results show that the system is reliable when considering it as a part of the verification mechanism.
In this study, ANFIS models were developed to predict the Cd concentration in Filyos River. The results of the study indicated that ANFIS methodology produced very successful findings and had the ability to predict Cd concentration in water resources. It was determined that the ANFIS model was a reliable method to predict heavy metal concentrations in water resources with an acceptable degree of robustness and accuracy. Use of adaptiveneuro-fuzzyinference system is significant for unclear system which has no experience with data behavior. The outcomes of this research provide more information, simulation, and prediction about heavy metal concentration in natural aquatic ecosystems. Therefore, ANFIS can be used in further researches on water quality monitoring.
II. ADAPTIVE NEUROFUZZY INFERENCE SYSTEM The adaptiveneurofuzzyinference system (ANFIS), first introduced by Jang (1993), is a universal approximator and as such is capable of approximating any real continuous function on a compact set to any degree of accuracy (Jang et al. 1997). ANFIS is functionally equivalent to fuzzyinference systems (Jang et al. 1997). Specifically the ANFIS system of interest here is functionally equivalent to the Sugeno first-order fuzzy model (Jang et al. 1997; Drake 2000). Below, the hybrid learning algorithm, which combines gradient descent and the least-squares method, is introduced. As a simple example we assume a fuzzyinference system with two inputs x and y and one output z. The first-order Sugeno fuzzy model, a typical rule set with two fuzzy If–Then rules can be expressed as
Abstract — It is difficult to identify the abnormalities in brain specially in case of Magnetic Resonance Image brain image processing. This paper presents a hybrid technique for the classification of MRI human brain images. The proposed hybrid technique consists of three stages namely feature extraction, feature reduction and classification. The feature extraction and reduction is done by Principal Component Analysis and the classification is done by a hybrid Neuro- fuzzy classifier (ANFIS). ANFIS classifier combines the merits of both the neuro classifier and the fuzzy classifier and overcomes the demerits of both the classifiers. Artificial neural networks employed for brain image classification are being computationally heavy and also do not guarantee high accuracy. The major drawback of ANN is that it requires a large training set to achieve high accuracy. On the other hand fuzzy logic technique is more accurate but it fully depends on expert knowledge, which may not always available. Fuzzy logic technique needs less convergence time but it depends on trial and error method in selecting either the fuzzy membership functions or the fuzzy rules. These problems are overcome by the hybrid model namely, neuro- fuzzy model. This system removes essential requirements since it includes the advantages of both the ANN and the fuzzy logic systems. In this paper the classification of different brain images using Adaptiveneuro-fuzzyinference systems (ANFIS technology) is done. Experimental results illustrate promising results in terms of classification accuracy and convergence rate.
Abstract In this paper, an optimization method based on adaptiveNeuro-Fuzzyinference system (ANFIS) for determining the parameters used in the design of a coplanar capacitive coupled probe fed rectangular microstrip antenna. The antenna was analyzed in the 2-10GHz range to demonstrate universal working of the proposed model. Here, an expert knowledge of fuzzyinference system (FIS) and the learning capability of artificial neural network (ANN) have been embedded (ANFIS). By calculating and optimizing the patch dimensions of a rectangular microstrip antenna with air gap, this paper shows that ANFIS produces good results that are in agreement with the mathematical analysis of the design parameters of antenna. Of the parameters considered for optimization, the error difference (average) between the proposed model and the calculated data is 0.21% for L, 0.41% for W, and 0.2% for air gap which are less than 0.5% and acceptably low.
This paper describes the presentation of an IM for high load and high-power applications, this kind of applications the motor have a complex coupling between the field and torque. This can be achieving with an assist of Indirect Field Oriented Control (IFOC) and parallel connection of two motors. The benefit is that parallel connection can provide the decoupled control of flux and torque for each motor and their concert in different operating environments. The Speed control of two Double Star Induction Motors working in parallel configuration with IFOC using a Fuzzy Logic Controller (FLC) and AdaptiveNeuroFuzzyInference (ANFIS) controller is investigate in different operating environments. The two motors are connected in parallel at the output of a single six-phase PWM based inverter fed from a DC source. Performance of the projected method under load disturbances is studied through simulation using a MATLAB and evaluation of speed response of two controllers is analyzed.
Abstract––It is difficult to identify the abnormalities in brain specially in case of Magnetic Resonance Image brain image processing. Artificial neural networks employed for brain image classification are being computationally heavy and also do not guarantee high accuracy. The major drawback of ANN is that it requires a large training set to achieve high accuracy. On the other hand fuzzy logic technique is more accurate but it fully depends on expert knowledge, which may not always available. Fuzzy logic technique needs less convergence time but it depends on trial and error method in selecting either the fuzzy membership functions or the fuzzy rules. These problems are overcome by the hybrid model namely, neuro-fuzzy model. This system removes essential requirements since it includes the advantages of both the ANN and the fuzzy logic systems. In this paper the classification of different brain images using Adaptiveneuro-fuzzyinference systems (ANFIS technology). Experimental results illustrate promising results in terms of classification accuracy and convergence rate.
Abstract: Estimation of evapotranspiration (ET) is needed in water resources management, scheduling of farm irrigation, and environmental assessment. Hence, in practical hydrology, it is often crucial to reliably and constantly estimate evapotranspiration. Accordingly, three artificial intelligence (AI) techniques comprising adaptiveneuro-fuzzyinference system (ANFIS), artificial neural network (ANN) and adaptiveneuro-fuzzyinference-wavelet (ANFIS-Wavelet) were applied in to estimate wheat crop evapotranspiration (ET c ). A case study in a Dashtenaz region located in Mazandaran, Iran, was
This Paper presents two adaptive vehicle suspension control methods, which significantly improve the performance of mechatronic suspension systems in full car model by absorbing shocks caused by bumpy roads and preventing vibrations from reaching the cockpit and providing stability and coherence required. The first control approach is an extension to the AdaptiveNeuro-FuzzyInference System (ANFIS) called Extended adaptiveNeurofuzzyinference system (EANFIS). The second control approach is a special type of multi-inputs multi-outputs ANFIS model called Co-Active adaptiveNeurofuzzyinference system (CANFIS). MATLAB Simulink has used to build controllers and the full vehicle active suspension model with seven degrees of freedom. Three types of disturbances have been applied individually as excitations to test the robustness of the proposed controllers. In addition, a comparison between EANFIS controller, CANFIS controller and open loop model (passive suspension) has made with the three types of disturbances.
ABSTRACT: This paper focuses on the power quality improvement of three phase diode rectifier for DC drive applications. The input current harmonics distortion (THD), power factor at input side and voltage regulation of the three phase diode rectifier is investigated for power quality improvement. In this method, bidirectional switches are connected across the front end rectifier to improve the conduction of input current in order to improve the Total Harmonic Distortion (THD). The buck regulator is connected at the output stage of three phase diode rectifier for the voltage regulation. The circuit with buck regulator is simulated for different torque conditions of DC motor using PI current controller, Fuzzy Logic Controller (FLC) and AdaptiveNeuro-FuzzyInference Systems (ANFIS) and the results are compared for the power factor improvement. Design of Fuzzy controller and AdaptiveNeuro-FuzzyInference Systems (ANFIS) are based on heuristic knowledge converter behavior. The design of PI control is based on the frequency response of the converter. For the DC drive applications, the performance of the Fuzzy controller and AdaptiveNeuro-FuzzyInference Systems (ANFIS) are superior in some respects to that of the PI controller.
Neuro-fuzzy models are neural networks with intrinsic fuzzy logic abilities, i.e. the weights of the neurons in the network define the premise and consequent parameters of a fuzzy in- ference system. Premise parameters determine the shape and size of the input membership functions, whilst consequent parameters determine the characteristics of the output mem- bership functions and define the rules guiding the fuzzy in- ference system. The AdaptiveNeuro-FuzzyInference Sys- tem (ANFIS) algorithm (Jang et al., 1996) generates a fuzzyinference system which maps an input data set to an output data set by adjusting its membership functions using a hybrid algorithm: a combination of the error back-propagation algo- rithm and the least squares method. This requires less com- putation than the back-propagation algorithm alone, since
Several methods have been proposed in the literature for tracking the MPP of PV systems. Among these methods, Hill climbing perturb and observe (P and O) algorithms were commonly used due to their straight forward and low cost implementation. An alternative approach that overcomes this effect is called the increment inductance method. However, all these listed methods did not respond correctly under rapidly changing atmospheric conditions. Recently MPPT methods based on artificial intelligence techniques such as neural networks, genetic algorithmsand fuzzy controllers have emerged. The use of Adaptiveneurofuzzyinference controller (ANFIS) is more suitable for MPPT compared with conventional controllers because they produce a better performance with changing atmospheric conditions
Fuzzy Neural Networks (FNNs) have been widely applied in business and economics like supply chain management, stock market, price prediction, gas condensate, energy consumption, electric load forecasting etc. (Kar et al., 2014). Practically, there exist three types of fuzzy systems: pure fuzzy systems, Mamdani type and Sugeno type fuzzyinference systems (Liu et al., 2004). But, the most commonly used is Sugeno model since it is computationally less expensive and more transparent than other counterpart models (Awadallah et al., 2009). AdaptiveNeuro-FuzzyInference System (ANFIS) is the first order Sugeno-type FNN which uses derivative based learning which has high probability of falling in local minima. The derivative- free techniques using metaheuristic algorithms are more powerful for ANFIS learning (Shoorehdeli et al., 2009). Thus, this research improves the newly developed metaheuristic algorithm Mine Blast Algorithm (MBA) by modifying its exploitation phase. The modified MBA is then used for training parameters of ANFIS and optimizing its rule-set.