Adaptive Neuro-fuzzy Inference System Network Research Articles

Adaptive Neuro-Fuzzy Determination of the Effect of Experimental Parameters on Vehicle Agent Speed Relative to Vehicle Intruder.

Intelligent Transportation Systems rely on understanding, predicting and affecting the interactions between vehicles. The goal of this paper is to choose a small subset from the larger set so that the resulting regression model is simple, yet have good predictive ability for Vehicle agent speed relative to Vehicle intruder. The method of ANFIS (adaptive neuro fuzzy inference system) was applied to the data resulting from these measurements. The ANFIS process for variable selection was implemented in order to detect the predominant variables affecting the prediction of agent speed relative to intruder. This process includes several ways to discover a subset of the total set of recorded parameters, showing good predictive capability. The ANFIS network was used to perform a variable search. Then, it was used to determine how 9 parameters (Intruder Front sensors active (boolean), Intruder Rear sensors active (boolean), Agent Front sensors active (boolean), Agent Rear sensors active (boolean), RSSI signal intensity/strength (integer), Elapsed time (in seconds), Distance between Agent and Intruder (m), Angle of Agent relative to Intruder (angle between vehicles °), Altitude difference between Agent and Intruder (m)) influence prediction of agent speed relative to intruder. The results indicated that distance between Vehicle agent and Vehicle intruder (m) and angle of Vehicle agent relative to Vehicle Intruder (angle between vehicles °) is the most influential parameters to Vehicle agent speed relative to Vehicle intruder.

A New Load-shedding Approach for Microgrids in the Presence of Wind Turbines

Following the penetration of microgrids in distribution systems, frequency deviations in contingency conditions are becoming increasingly important. Therefore, effective load shedding is necessary to regulate the frequency. This article develops a new load-shedding method for microgrids considering wind speed changes. The proposed method uses a combination of frequency and voltage data for determining load-shedding amounts in each contingency condition. For this purpose, the total required load shedding is determined first by using transient stability analysis in different contingency scenarios in microgrids. This will establish a database for an adaptive neuro-fuzzy inference system network to determine the total required load shedding. Then a fuzzy system is used to determine the load shedding in each step dynamically based on the severity of contingencies. The proposed method capability is compared with the conventional load-shedding method. Simulation results show the effectiveness of the proposed method for microgrid control in contingency conditions.

Application of adaptive neuro-fuzzy methodology for performance investigation of a power-augmented vertical axis wind turbine

Wind power is generating a lot of interest in many countries as a way to produce sustainable and low-cost electrical power. Since the power in the wind is known to be proportional to the cubic power of the wind velocity approaching the wind turbine, this means that any slight increase in wind speed can lead to a substantial increment in the energy output. Power augmentation device is an interesting option in this respect. The aim of this study is to determine the accuracy of a soft computing technique on the rotational speed estimation of a Sistan rotor vertical axis wind turbine with PAGV (power-augmentation-guide-vane) based upon a series of measurements. An ANFIS (adaptive neuro-fuzzy inference system) was used to predict the wind turbine rotational speed. The ANFIS network was developed with three neurons in the input layer, and one neuron in the output layer. The inputs for the network were time (t), wind velocity (v) and presence of the PAGV (0 with PAGV and 1 without PAGV). The precision of ANFIS technique was assessed against the experimental results using RMSE (root-mean-square error) and coefficient of determination (R2).

Modelling the failure behaviour of magnesium alloy sheet forming at warm temperatures by using new hybrid ICA-ANFIS model

In traditional methods for modelling the behaviour of manufacturing processes by using artificial neural networks, design of optimal architecture of these networks needs many trials and errors. Sometimes it may not achieve the best architecture of networks because of the time-consuming and tedious procedure of these methods. In this paper, the failure behaviour of magnesium alloy sheet forming at warm temperature is modelled by using the adaptive neuro-fuzzy inference systems (ANFIS) network. In order to reduce the time of finding the best architecture of ANFIS network, an optimisation algorithm, imperialistic competitive algorithm, was used. By combining this optimisation algorithm with the ANFIS, the best architecture of ANFIS network can be proposed to model the accurate behaviour of the manufacturing process in the least time possible.

Electrochromic device modeling using an adaptive neuro-fuzzy inference system: A model-free approach

This paper presents a new approach for the modeling of an Electrochromic (EC) device. The proposed system relies on an adaptive network-based fuzzy inference system or equivalently, Adaptive Neuro-Fuzzy Inference System (ANFIS). The ANFIS network has used 33 experimental data sets of which, 24 data sets were taken as training data and 9 data sets were taken as testing data. The ANFIS performance statistical indices mean absolute error (MAE), root mean square error (RMSE), and non-dimensional error index (NDEI) are found to be close to zero and coefficient of determination (R2) and linear correlation coefficient (ρ) and variance account for (VAF) are found to be close to one. Some interpretability issues regarding the ANFIS models, such as rule consistency, rule separation, and rule completeness are discussed. Simulation examples are provided to illustrate the effectiveness of the proposed approach. This study also includes experiments that confirm the good performance and the potential of the ANFIS models for datasets with noise. The proposed models can be seen as virtual luminous transmittance sensors.

Sensitivity analysis of the photoactivity of Cu–TiO2/ZnO during advanced oxidation reaction by Adaptive Neuro-Fuzzy Selection Technique

One of the most pivotal limitations of TiO2 or ZnO based lattices is their photocatalysis activity under visible light irradiation. In this study, a hybrid photocatalyst was generated by doping TiO2/ZnO lattice with copper in order to improve their photo-activity. The main aim was to analyse the sensitivity of photoactivity of Cu–TiO2/ZnO toward operating conditions in advanced oxidation reaction for photodegradation of two different dyes under visible light irradiation. The sol–gel-prepared composite was characterized in detail to confirm its properties in terms of band gap, crystalline structure/size, optical absorption and surface area. Then, ANFIS (Adaptive Neuro Fuzzy Inference System) was employed to investigate the effects of five independent variables including dye and catalyst concentrations, pH, intensity of light irradiation and reaction time on the photocatalytic performance of Cu–TiO2/ZnO. This process includes several ways of discovering a subset from the group of the recorded parameters and predicting which variable has the strongest effect on the response of interest. Besides, variable search was performed using the ANFIS network. According to variable selection using ANFIS analysis, catalyst concentration and reaction time were the most effective parameters for MO degradation whereas dye concentration and pH were the most influential factors on MB removal using Cu–TiO2/ZnO. Furthermore, Cu–TiO2/ZnO photocatalyst presented the maximum removal efficiency of: color: 83.35%, COD: 73.54% and TOC: 54.46% for MO degradation and color: 75.50%, COD: 68.00% and TOC: 46.41% for MB degradation.

Extraction of fetal electrocardiogram (ECG) by extended state Kalman filtering and adaptive neuro-fuzzy inference system (ANFIS) based on single channel abdominal recording

Fetal electrocardiogram (ECG) gives information about the health status of fetus and so, an early diagnosis of any cardiac defect before delivery increases the effectiveness of appropriate treatment. In this paper, authors investigate the use of adaptive neuro-fuzzy inference system (ANFIS) with extended Kalman filter for fetal ECG extraction from one ECG signal recorded at the abdominal areas of the mother’s skin. The abdominal ECG is considered to be composite as it contains both mother’s and fetus’ ECG signals. We use extended Kalman filter framework to estimate the maternal component from abdominal ECG. The maternal component in the abdominal ECG signal is a nonlinear transformed version of maternal ECG. ANFIS network has been used to identify this nonlinear relationship, and to align the estimated maternal ECG signal with the maternal component in the abdominal ECG signal. Thus, we extract the fetal ECG component by subtracting the aligned version of the estimated maternal ECG from the abdominal signal. Our results demonstrate the effectiveness of the proposed technique in extracting the fetal ECG component from abdominal signal at different noise levels. The proposed technique is also validated on the extraction of fetal ECG from both actual abdominal recordings and synthetic abdominal recording.

Thermal Performance Prediction of Two-Phase Closed Thermosyphon Using Adaptive Neuro-Fuzzy Inference System

In this paper the Adaptive Neuro-Fuzzy Inference System (ANFIS) is used for the prediction of thermal efficiency and thermal resistance of a two-phase closed thermosyphon (TPCT). Aqueous suspensions of pristine multiwalled carbon nanotubes (CNTs) and functionalized CNTs with ethylene diamine were used as nanofluid in the TPCT. The experimental results regarding the TPCT performance including thermal efficiency and thermal resistance were modeled by the ANFIS technique. The ANFIS network was initiated by 70% of experimental data, and 30% of primary data were considered for testing and checking the suitability of the ANFIS model. The modeling results were compared with five arithmetical criteria. The arithmetical criteria suggested that the obtained modeling by ANFIS is valid and it could be expanded for other conditions. Also, to determine optimal ranges of experimental conditions, three-dimensional diagrams were traced by the modeling data. The proposed method of ANFIS modeling may be applied for optimization of other TPCTs with different configurations.

Determining the joints most strained in an underactuated robotic finger by adaptive neuro-fuzzy methodology

The main purpose of this paper is to determine what joints are most strained in the proposed underactuated finger by adaptive neuro-fuzzy methodology. For this, kinetostatic analysis of the finger structure is established with added torsional springs in every single joint. Since the finger’s grasping forces depend on torsional spring stiffness in the joints, it is preferable to determine which joints have the most influence on grasping forces. Hence, the finger joints experiencing the most strain during the grasping process should be determined. It is desirable to select and analyze a subset of joints that are truly relevant or the most influential to finger grasping forces in order to build a finger model with optimal grasping features. This procedure is called variable selection. In this study, variable selection is modeled using the adaptive neuro-fuzzy inference system (ANFIS). Variable selection using the ANFIS network is performed to determine how the springs implemented in the finger joints affect the output grasping forces. This intelligent algorithm is applied using the Matlab environment and the performance is analyzed. The simulation results presented in this paper show the effectiveness of the developed method.

Adaptive neuro-fuzzy inference system for the prediction of monthly shoreline changes in northeastern Taiwan

This study intends to model the shoreline change by investigating monthly shoreline position data collected from seven sandy beaches located at the Yilan County in Taiwan during 2004–2011. The harmonic analysis results indicate shorelines appear significantly periodic with great variation. The adaptive neuro-fuzzy inference system network (ANFIS) is configured with two scenarios, namely lumped and site-specific ones, to extract significant features of shoreline changes for making shoreline position predictions in the next year. The lumped models for all stations are first investigated based on a number of possible input information, such as month, location, and the maximum and mean wave heights. The results, however, are not as favorable as expected, and wave heights do not contribute to modeling due to their high variability. Consequently, a site-specific model is constructed for each station, with its current position and nearby stations׳ positions as model inputs, to predict its shoreline position in the next year. Compared with the harmonic analysis and the autoregressive exogenous (ARX) model, the ANFIS model produces more accurate prediction results. The results indicate that the constructed ANFIS models can accurately predict shoreline changes and can serve as a valuable tool for future coastline erosion warning and management.

Contact positions estimation of sensing structure using adaptive neuro-fuzzy inference system

Purpose – Tactile sensing is the process of determining physical properties and events through contact with objects in the world. The purpose of this paper is to establish a novel design of an adaptive neuro-fuzzy inference system (ANFIS) for estimation of contact position of a new tactile sensing structure. Design/methodology/approach – The major task is to investigate implementations of carbon-black-filled silicone rubber for tactile sensation; the silicone rubber is electrically conductive and its resistance changes by loading or unloading strains. Findings – The sensor-elements for the tactile sensing structure were made by press-curing from carbon-black-filled silicone rubber. The experimental results can be used as training and checking data for the ANFIS network. Originality/value – This system is capable to find any change of contact positions and thus indicates state of the current contact location of the tactile sensing structure. The behavior of the use silicone rubber shows strong non-linearity, therefore, the sensor cannot be used for high accurate measurements. The greatest advantage of this sensing material lies in its high elasticity.

RETRACTED ARTICLE: Adapting project management method and ANFIS strategy for variables selection and analyzing wind turbine wake effect

We present a project management methodology designed for the selection of wind turbines wake effect most influential parameters, who need to run wind farm project for large energy conversion. Very frequently, the managers of these projects are not project management professionals, so they need guidance to have autonomy, using minimal time and documentation resources. Therefore, agile method is adapted to assist the project management. Wind energy poses challenges such as the reduction in the wind speed due to the wake effect by other turbines. If a turbine is within the area of turbulence caused by another turbine, or the area behind another turbine, the wind speed suffers a reduction and, therefore, there is a decrease in the production of electricity. In order to increase the efficiency of a wind farm, analyzing the parameters, which have influence on the wake effect, is one of the focal research areas. To maximize the power produced in a wind farm, it is important to determine and analyze the most influential factors on the wake effects or wake wind speeds since the effect has most influence on the produced power. This procedure is typically called variable selection, and it corresponds to finding a subset of the full set of recorded variables that exhibits good predictive abilities. In this study, architecture for modeling complex systems in function approximation and regression was used, based on using adaptive neuro-fuzzy inference system (ANFIS). Variable searching using the ANFIS network was performed to determine how the five parameters affect the wake wind speed. Our article answers the call for renewing the theoretical bases of wind farm project management in order to overcome the problems that stem from the application of methods based on decision-rationality norms, which bracket the complexity of action and interactions in projects.

Design and development of low-cost blood serum analyser using adaptive neuro fuzzy inference system

A predictive method, based on Adaptive Neuro Fuzzy Inference System (ANFIS), has been developed to study absorbance and pH effects on the equilibrium of blood serum. This strategy has been used to analyse the serum samples and to predict the calcium concentration in blood serum. The data acquisition system is designed and fabricated using ARM CORTEX microcontroller. ANFIS model developed is based on the data collected from calcium test. ANFIS is used to simulate different concentration of calcium (Ca2+) as a function of absorbance and pH, to correlate and predict calcium concentration. The sensor modules were designed and calibrated to measure pH and absorbance. ANFIS network is trained and validated using test data to predict the actual calcium concentration of blood serum.

Analysis of Inverse Kinamtics of an Anthropomorphic Robotic hand

In this paper, a new method for solving the inverse kinematics of the fingers of an anthropomorphic hand is proposed. Solution of inverse kinematic equations is a complex problem, the complexity comes from the nonlinearity of joint space and Cartesian space mapping and having multiple solutions.This is a typical problem in robotics that needs to be solved to control the fingers of an anthropomorphic robotic hand to perform tasks it is designated to do. With more complex structures operating in a 3-dimensional space deducing a mathematical soluation for the inverse kinematics may prove challenging. In this paper, using the ability of ANFIS (Adaptive Neuro-Fuzzy Inference System) to learn from training data, it is possible to create ANFIS network, an implementation of a representative fuzzy inference system using ANFIS structure, with limited mathematical representation of the system. The main advantages of this method with respect to the other methods are implementation is easy, very fast and shorter computation time and better response with acceptable error.

Prediction of supercritical extraction recovery of EGCG using hybrid of Adaptive Neuro-Fuzzy Inference System and mathematical model

Supercritical extraction of antioxidants and pharmaceuticals is one of the most important applications in the field of supercritical fluids. Epigallocatechin gallate (EGCG) has pharmacological properties which include anti-oxidative, apoptotic, anti-obesity, anti-arteriosclerotic, anti-diabetic, anti-bacterial, anti-viral, and anti-mutagenic effects. In this study, recovery of EGCG supercritical extraction from green tea was modeled by hybrid of Adaptive Neuro-Fuzzy Inference System (ANFIS) and mathematical modeling with the constant distribution coefficient. Different ANFIS networks (by changing the type and number of membership functions and training algorithms) were compared with evaluation of networks accuracy in EGCG recovery prediction and subsequently the suitable network was determined. The obtained results in this work indicated that ANFIS was effective method for prediction of EGCG recovery and was successfully validated with experimental data. Finally the proposed hybrid model optimized with genetic algorithm in order to achieve maximum EGCG extraction recovery.

Macrocell path loss prediction using artificial intelligence techniques

The prediction of propagation loss is a practical non-linear function approximation problem which linear regression or auto-regression models are limited in their ability to handle. However, some computational Intelligence techniques such as artificial neural networks (ANNs) and adaptive neuro-fuzzy inference systems (ANFISs) have been shown to have great ability to handle non-linear function approximation and prediction problems. In this study, the multiple layer perceptron neural network (MLP-NN), radial basis function neural network (RBF-NN) and an ANFIS network were trained using actual signal strength measurement taken at certain suburban areas of Bauchi metropolis, Nigeria. The trained networks were then used to predict propagation losses at the stated areas under differing conditions. The predictions were compared with the prediction accuracy of the popular Hata model. It was observed that ANFIS model gave a better fit in all cases having higher R2 values in each case and on average is more robust than MLP and RBF models as it generalises better to a different data.

Surface roughness prediction in end milling process using intelligent systems

The mechanism behind the formation of surface finish is very complicated and process dependent, therefore it is very difficult to calculate the value of surface roughness through analytical formula. In this paper, a study is presented to model surface roughness in end milling process. Three types of intelligent networks have been considered to numerically identify the end milling process. They are (i) radial basis function neural networks (RBFN) (ii) adaptive neuro-fuzzy inference systems (ANFIS), and (iii) genetically evolved fuzzy inference systems (G-FIS). The machining parameters, namely, the spindle speed, feed rate and depth of cut have been used as inputs to model the workpiece surface roughness. The contribution of this work is to investigate different methodologies which could be used to get the best prediction accuracy. The procedure is illustrated using experimental data of end-milling 6,061 aluminum alloy. The three networks have been trained using experimental training data. After training, they have been examined using another set of data, i.e. validation data. Results are compared with previously published results. It is concluded that ANFIS networks may suffer the local minima problem and genetic tuning of fuzzy networks cannot insure perfect optimality unless suitable parameter setting (population size, number of generations … etc.) and tuning range for the fuzzy inference systems (FIS) parameters are used which can be hardly satisfied. It is shown that the RBFN model has the best performance (prediction accuracy) in this particular case.

Adaptive neuro fuzzy selection of heart rate variability parameters affected by autonomic nervous system

Heart rate variability (HRV) parameters can be used as specific indicator of autonomic nervous system (ANS) behavior. ANS, with its main two branches, sympathetic and parasympathetic, may be considered as a coordinated neuronal network which controls heart rate continually. Many parameters define heart rate variability in different domains such as time, frequency or nonlinear. An excessively high computational complexity can occur when developing models for medical applications when the best set of inputs to use is not known. To build a model that can predict a specific process output, it is desirable to select a subset of variables that are truly relevant or the most influential to this output. This procedure is typically called variable selection, and it corresponds to finding a subset of the full set of recorded variables that exhibits good predictive abilities. In this study an architecture for modeling complex systems in function approximation and regression was used, based on using adaptive neuro-fuzzy inference system (ANFIS). Variable searching using the ANFIS network was performed to determine how the ANS branches affect the most relevant HRV parameters. The method utilized may work as a basis for examination of ANS influence on HRV activity.

A comparative artificial intelligence approach to inverse heat transfer modeling of an irradiative dryer

In this work, a variety of new approaches are developed and results are compared for solving inverse heat transfer problems where radiation is the dominant mode of thermal energy transport. An artificial neural network (ANN), two hybrid methods of genetic algorithms and artificial neural networks (GA–ANNs), and an adaptive neuro-fuzzy inference system network (ANFIS) were designed. These were trained and then employed to estimate the required input power in an irradiative batch drying process. A comparison of the results shows that the most accurate method is ANFIS but the number of parameters in ANFIS is larger than ANNs. Consequently, the ANFIS solution is time consuming in this application; however other neuro-fuzzy techniques may require fewer parameters and these will be considered in future studies. For the studied ANNs, the hybrid method of GA–ANN is optimal using the Levenberg–Marquardt optimization algorithm during back propagation in terms of accuracy and network's performance.

Novel Adaptive Neuro-Fuzzy based Edge Detection Technique

Digital image processing is a subset of the electronic domain where the image is converted to an array of small integers, called pixels, symbolizing a physical quantity such as scene radiance, stored in a digital memory, and processed by computer or other digital hardware. Interest in digital image processing methods stems from two principals applications areas: improvement of pictorial information for human interpretation; and processing of image data for storage, transmission, and representation for autonomous machine perception. Edges characterize boundaries and edge detection is one of the most difficult tasks in image processing hence it is a problem of fundamental importance in image processing. Edges in images are areas with strong intensity contrasts and a jump in intensity from one pixel to the next can create major variation in the picture quality. Edge detection of an image significantly reduces the amount of data and filters out useless information, while preserving the important structural properties in an image. This research problem deals with a novel adaptive neuro-fuzzy inference system (ANFIS) for edge detection in digital images. The internal parameters of the proposed ANFIS edge detector are optimized by training using by proposed training pattern. The edges are directly determined by ANFIS network