Adaptive Network Based Fuzzy Inference System with Meta-Heuristic Optimizations for International Roughness Index Prediction

Development of artificial intelligence models for the prediction of Compression Coefficient of soil: An application of Monte Carlo sensitivity analysis

Providing critical information about daily life, weather forecasting has important role for human being. Especially, temperature forecasting is rather important because it affects not only people but also other atmospheric parameters. Various techniques have been used for analysis of the dynamic behaviour of weather. This ranges from simple observation of weather to using computer technology. In this study, ANFIS (Adaptive Network Based Fuzzy Inference System), ANN (Artificial Neural Network) and MRA (Multiple Regression Analysis) have been applied for weather forecasting. To judge the forecasting capability of the proposed models, the graphical analysis and the indicators of the accuracy of Mean Absolute Deviation (MAD), Mean Square Error (MSE), Root-Mean Squared Error (RMSE), Mean Absolute Percent Error (MAPE), Determination Coefficient (R 2 ), Index of Agreement (IA), Fractional Variance (FV), Coefficient of Variation (CV, %) are given to describe models’ forecasting performance and the error. The results show that ANFIS exhibited best forecasting performance on weather forecasting compared to ANN and MRA.

In this paper, an approach in predicting surface roughness of Titanium Aluminum Nitrite (TiN) coatings using Adaptive Network Based Fuzzy Inference System (ANFIS) is implemented. The TiN coatings were coated on tungsten carbide (WC) using Physical Vapor Deposition (PVD) magnetron sputtering process. The N2 pressure, argon pressure and turntable speed were selected as the input parameters and the surface roughness as an output of the process. Response Surface Methodology (RSM) was used to design the matrix in collecting the experimental data. In the ANFIS structure, triangular, trapezoidal, bell and Gaussian shapes were used for as input membership function (MFs). The collected experimental data was used to train the ANFIS model. Then, the ANFIS model were validated with the actual testing data and compared with regression model in terms of the residual error and model accuracy. The result indicated that the ANFIS model using three bell shapes MFs obtained better result compared to the polynomial regression model. The number of MFs showed significant influence to the ANFIS model performance. The result also indicated that the limited experimental data could be used in training the ANFIS model and resulting accurate predictive result.

A Comparison of machine learning regression models for critical bus voltage and load mapping with regards to max reactive power in PV buses

In this paper we have proposed an adaptive network based fuzzy inference system (ANFIS) model where the number of data pairs employed for training is minimized by application of two techniques called the full factorial design (FFD) and V-fold. Our proposed method is applied in building ANFIS models for the benchmark example of Box and Jenkins gas furnace data and the thermal power plant of the North Eastern Electrical Power Corporation Limited (NEEPCO). By employing our proposed method the number of data required for learning in the ANFIS network could be significantly reduced to around one-eighth of that required for the conventional ANFIS method. The results obtained by applying our proposed method are compared with those obtained by using conventional ANFIS network. It was found that our model compares favourably well with conventional ANFIS model

this paper discusses extended approaches of Adaptive Network Based Fuzzy Inference System (ANFIS) using Self Tuning Regulator (STR) via Fuzzy logic to be implemented in cascade control. Plant used is Pressure RIG 38-714 which supports cascade configuration. The controlled variable in the outer loop is pressure, in the inner loop's flow. The proposed method's used to improve the performance of ANFIS which has been commonly implemented to accomplish control task. Comparison has been conducted between ANFIS using STR and without STR, from experiment could be concluded that controller ANFIS using STR acquired better performance than only used ANFIS. It's derived from the transient response of those. For ANFIS using STR is obtained rise time and settling time are 9 ms and 12 ms respectively. In the other hand, ANFIS without STR resulted 21 ms and 29 ms for rise time and settling time respectively. Cascade control's one of example in the complex architecture of control system. Indeed, it has two control loops, one's used to control main variable (outer loop) and another's used to reject the disturbance (inner loop). An advantage of this structure's if there's a disturbance on the inner loop might be immediately detected and undertaken self correcting, because process on the inner loop has to be much faster than on the outer loop, thereby such structure like that's also able to prevent a stability of the plant simultaneously. Although has an advantage, cascade control's relatively expensive due to utilizing more sensor. Because, there are two control variable to solve one main control variable. Fuzzy logic invented by Zadeh has been widely used in the many applications. In the area of control engineering, fuzzy logic controller with many varieties and structures have been practically developed in the many areas such as: control, forecasting, identification, and etc. The strongest thing of fuzzy logic's can adopt intuition of human feeling mapped in the membership function of fuzzy logic. Such thing like that might replace on-off logic which only understands 2 values as ON and OFF. However, the weakness of fuzzy logic's it does not has a

This paper developed and investigates the performance of intelligent algorithms in order to stabilize the robot when it is tracking to the reference signal. One type of robot is a Two Wheeled Balancing Mobile Robot (TWBMR) that requires control for both balancing and maneuvering. Combination artificial intelligence, Neural Networks (NNs) and Fuzzy Logic Control (FLC) have been recognized as the main tools to improve the performance of coupling nonlinear robot system without using any mathematical model. The input-output data of TWBMR generated from closed loop control system is used to develop a neural network model. In this study, neural networks model can be trained offline and then transferred into a process where an adaptive online learning is carried out using Adaptive Network Based Fuzzy Inference System ANFIS to improve the system performance. The simulation results verify that the considered identification and control strategies can achieve favorable control performance. The ANFIS control design approach does not require an accurate model of the plant. In addition, high-level knowledge of the system is not needed to build a set of rules for a fuzzy controller.

Image super resolution is one of the most popular topics in the field of image processing. However, most of the existing super resolution algorithms are designed for the situation where sufficient training data is available. This paper proposes a new image super resolution approach that is able to handle the situation with sparse training data, using the recently developed ANFIS (Adaptive Network based Fuzzy Inference System) interpolation technique. In particular, the training image data set is divided into different subsets. For subsets with sufficient training data, the ANFIS models are trained using standard ANFIS learning procedure, while for those with insufficient data, the models are obtained through ANFIS interpolation. In the literature, little work exists for image super resolution on sparse data. Therefore, in the experimental evaluations of this paper, the proposed approach is compared with existing super resolution methods with full data, demonstrating that this work is able to produce highly promising results.

Adaptive Network Based Fuzzy Inference System (ANFIS) using time series analize is one of intelligent systems that can be used to predict with good accuracy in all fields like in meteorology. However, some research about forecasting has less emphasis on the structure of the FIS ANFIS. Thus, in this paper, the optimization of the ANFIS model for predicting maritime weather is carried out by analyzing the appropriate initialization determinations of the three fuzzy Inference structures ANFIS which includes FIS structure 1 (grid partition), FIS structure 2 (subtractive clustering) and FIS structure 3 (fuzzy c-means clustering). In this paper, the variable input used are two hours (t-2) and one hour (t-1) before, and data at that time (t), and the output of this system is the prediction of next hour, six hours, twelve hours and next day of variable ocean currents velocity (cm/s) and wave height (m) using the three FIS ANFIS approaches. Based on the smallest goal error (RMSE and MSE) of the three FIS ANFIS approaches used to predict the ocean currents speed (velocity) and wave height, the model is best generated by subtractive clustering. It can be seen that subtractive clustering produces the smallest RMSE and MSE error values of other FIS structure.

Nowadays, the tremendous shrinking of electronic devices has reduced their sizes to very low scales. However, this process has been accompanied unavoidably with many well-recognized reliability challenges basically for MOSFET devices. Our objective, in this work, is the proposition of an Adaptive Network based Fuzzy Inference System (ANFIS) to study the threshold voltage behavior caused by the interface traps generated by the ageing mechanism phenomenon. The consideration of a nanoscale DG MOSFET device makes the application of compact modeling tools a very hard task to carry out, due to approximations made during model development. The obtained results are in a good agreement with numerical simulations based on Atlas 2D-simulator. In addition, the comparison with a feed-forward artificial neural network shows that our fuzzy system provides higher accuracy performances. The proposed approach can be incorporated in Integrated Circuit modeling frameworks in order to support more complex degradation situations.

For improving precision of 3D surface measurement equipments, which are playing important role in reverse engineering, the Adaptive Network based Fuzzy Inference System (ANFIS) is developed to reconstruct 3D surface error, and the measurement error of point cloud is compensated by the presented 3D error ANFIS model. The precision of 3D surface measurement equipments has been improved noticeably

Efficient e-learners activities model is essential for real time identifications and adaptive responses. Determining the most effective Neuro- Fuzzy model amidst plethora of techniques for structure and parameter identifications is a challenge. This paper illustrates the implication of system identification techniques on the performance of Adaptive Network based Fuzzy Inference System (ANFIS) E-learners Activities models. Expert knowledge and Historical data were used to formulate the system and their performances were compared. Similarly, comparison was made between membership functions. The models were simulated in MATLAB editor. The efficiency of the model was determined using both classification uncertainty metrics and confusion matrix–based metrics. The classification uncertainty metrics considered are Mean Absolute Error (MAE) and Root Mean-Squared Error (RMSE). The confusion matrix-based metrics used are Accuracy, Precision and Recall. It was discovered that the model based on Experts Knowledge outperform those based on Historical Data. The performances of the Membershp Functions at the identification of the Historical data respectively are Sigmoid, Gaussian, Triangular and G-Bells.

The applicability of artificial neural networks (ANNs) and the adaptive neuro-fuzzy inference system (ANFIS) for determination of mean velocity and discharge of natural streams is investigated. The 2,184 field data obtained from four different sites on the Sarimsakli and Sosun streams in central Turkey were used in the study. ANNs and ANFIS models use the inputs, water surface velocity and water surface slope, to estimate the mean velocity and discharges of natural streams. The accuracies of both models were compared with the multiple-linear regression (MLR) model. The comparison results showed that the ANFIS model performed better than the ANNs and regression models for estimating mean velocity and discharge. The ANN model also showed better accuracy than the MLR model. The root mean square errors (RMSE) and mean absolute relative errors (MARE) of the MLR model were reduced by 88 and 91 % using the ANFIS model in estimating discharges, respectively. It is found that the optimal ANFIS model with RMSE of 0,063, MARE of 3,47 and determination coefficient (R2) of 0,996 in the test period is superior in estimation of discharge than the MLR model with RMSE of 0,532, MARE of 38,9 and R2 of 0,776, respectively. The study reveals that the ANFIS technique can be successfully used for estimating the mean velocity and discharge of natural streams by using only the inputs of water surface velocity and water surface slope.

A Comparative Study on Prediction of Monthly Streamflow Using Hybrid ANFIS-PSO Approaches

The present article aims to forecast streamflow by using artificial neural networks (ANNs), adaptive neuro-fuzzy inference system (ANFIS), and autoregressive moving average (ARMA). For this purpose, the daily streamflow time series of two hydrometry stations of Hajighoshan and Tamar on Gorgan River are used for two periods of 1983–2007 and 1974–2007, respectively. Root mean square error (RMSE) and correlation coefficient (R) statistics are employed to evaluate the performance of the ANNs, ANFIS, and ARMA models for forecasting streamflow (1 day ahead). Comparison of the results reveals that the ANFIS model outperforms the ARMA model. Based on the results of validation stage, for the forecasting 1 day ahead streamflow, ANN with RMSE = 0.028 m3/s and R = 0.59 for the Hajighoshan station and RMSE = 0.013 m3/s and R = 0.44 for the Tamar station were found to be superior to the ANFIS with RMSE = 1.98 m3/s and R = 0.42 for the Hajighoshan station and RMSE = 2.18 m3/s and R = 0.22 for the Tamar station. In addition, for 2 day and 3 day ahead streamflow forecasts, the ANN models show superiority in the accuracy of forecasting streamflow compared with the ANFIS models.