Results Of Adaptive Neuro-fuzzy Inference System Research Articles

Improving streamflow simulation by combining hydrological process-driven and artificial intelligence-based models.

Accurate and timely monitoring of streamflow and its variation is crucial for water resources management in watersheds. This study aimed at evaluating the performance of two process-driven conceptual rainfall-runoff models (HBV: Hydrologiska Byråns Vattenbalansavdelning, and NRECA: Non Recorded Catchment Areas) and seven hybrid models based on three artificial intelligence (AI) methods (adaptive neuro-fuzzy inference system (ANFIS), support vector machine (SVM), and group method of data handling (GMDH)) in simulating streamflow in four river basins in Indonesia. HBV and NRECA were developed based on precipitation data. Various combinations of 1-month lagged precipitation data together with outputs of HBV and NRECA were used for developing ANFIS and SVM models, and the best results of ANFIS and SVM formed the inputs to GMDH. Results showed that AI-based hybrid models have generally led to more accurate streamflow estimates compared with HBV and NRECA, and the GMDH model had the best performance at Cipero, Kedungdowo, Notog, and Sukowati stations, with RMSEs of 12.21, 6.07, 20.35, and 24.2 m3 s-1, respectively. More accurate estimation of peak values in training set at Cipero and Sukowati stations, and in both training and testing sets at Kedungdowo station was another advantage of GMDH. Hybrid models based on AI methods can be suitable alternatives to hydrological models, particularly in watersheds where there is a lack of measured data (e.g. climatic parameters, land cover-plant growth data, soil data, stream conditions, and properties of groundwater aquifers), provided that appropriate inputs are used.

ANFIS-ARIMA modelling for scheming re-aeration of hydrologically altered rivers

The discharge of a significant amount of wastewater from the urban agglomerations in the rivers is the primary cause for the degradation of the river’s assimilative capacity. The re-aeration process represents an interaction among the air–water interface to absorb oxygen from the atmosphere and indicates the capacity of the water to hold the oxygen that can be used in the degradation of pollutants without affecting the river’s health. Therefore, accurate estimation of re-aeration capacity is the prime requirement to maintain the riverine ecosystem. In this paper, an adaptive neuro-fuzzy inference system (ANFIS) is used to simulate the non-linear behaviour of various water quality parameters by estimating the re-aeration coefficient of Yamuna River, Delhi. The hydraulic and water quality parameters are used to identify the most optimal combination of input parameters for simulation through the Takagi-Sugeno (TS) ANFIS model. The results of ANFIS are ensembled with the time series autoregressive integrated moving average (ARIMA) model to minimize bagging, non-stationarity and biasing. The performance of the ANFIS models was measured using the coefficient of determination (R2), root mean square error (RMSE), and the coefficient of correlation (R). The ARIMA models are evaluated based on standard error, p-value, and t-test. Out of the five different ANFIS models, ANFIS-5 provides the optimal values of R during training and testing of the model as 0.966 and 0.989, respectively, and integrated with the ARIMA model to obtain the re-aeration coefficient for each sampling location. The results indicate that the ensembled ANFIS-ARIMA model reduces the variance significantly with the minimum error of 0.0075 and produces an exceptional improvement in predicting the re-aeration coefficient.

Estimation capabilities of biodiesel production from algae oil blend using adaptive neuro-fuzzy inference system (ANFIS)

ABSTRACTBiodiesel produced from different raw materials is the most effective way to solve problems related to the fuel crisis and environmental problems. In the present study, the methodology of the adaptive neuro-fuzzy inference system (ANFIS) for the modeling and estimation of a process applied to the production of biodiesel from the blend of algae oil. The Gaussian membership function was applied and studied. The results of ANFIS are compared with the actual results obtained through the experiment using the mean root-mean-square error (RMSE) and the determination coefficient (R-square). The results show an improvement in the prediction, accuracy, and capacity of the ANFIS technique for estimation. The statistical characteristics of RMSE were 0.2179 and R-squared was 0.9998 obtained in training. As the ANFIS offers a good estimation, the modeling quality can be applied to the biodiesel production process as well.

Application of adaptive neuro-fuzzy inference system and data mining approach to predict lost circulation using DOE technique (case study: Maroon oilfield)

Lost circulation is the most common problem encountered while drilling oil wells. Occurrence of such a problem can cause a lot of time and cost wastes. In order to drill oil wells, a fast and profitable way is necessary to predict and solve lost circulation problem. Expert system is a method used lately for problems that deal with uncertainty. In this paper, three approaches are carried out for prediction of lost circulation problem. These approaches include design of experiments (DOE), data mining, and adaptive neuro-fuzzy inference system (ANFIS). Data of 61 wells of Maroon oilfield are selected and sorted as the feed of the systems. Seventeen variables are used as inputs of the approaches and one variable is used as the output. First, DOE is conducted to observe the effects of variables. Plackett-Burman method is used to determine the effects of variables on lost circulation. After that, data mining is conducted to predict the amount of lost circulation. The class of regression is used to determine a function to model the data and the error of the model. Then, ANFIS is applied to predict the amount of lost circulation. The chosen data are used in order to train, test, and control the ANFIS. Furthermore, subtractive clustering is used to train the fuzzy inference system (FIS) of the model. The performance of the ANFIS model is assessed through the root mean squared error (RMSE). The results suggest that ANFIS method can be successfully applied to establish lost circulation prediction model. In addition, results of ANFIS and data mining are investigated through their prediction performances. The comparison of both methods reveals that ANFIS error is much lower than data mining.

Prediction of Pressure Drop in Venturi Scrubbers by Multi-Gene Genetic Programming and Adaptive Neuro-Fuzzy Inference System

Abstract Studying the pressure drop in venturi scrubbers had been the subject of many types of researches due to its importance for removing pollutants from polluted gas. In this study, two new approaches based on Multi-Gene Genetic Programming (MGGP) and Adaptive Neuro-Fuzzy Inference System (ANFIS) were used to predict the pressure drop in venturi scrubbers. The main parameters studied were the throat gas velocity of venturi scrubbers (Vgth), the liquid to gas flow rate ratio (L/G), and the axial distance of the venturi scrubbers (z) as the inputs to the network, while the pressure drop was as the output. One set of experimental data, which was gathered from five different venturi scrubbers including a circular and an adjustable prismatic venturi scrubber with a wetted wall irrigation, a rectangular venturi scrubber and two ejector venturi scrubbers with different throat diameters were applied for this study. The results of ANFIS and MGGP were compared with experimental data and those values from Artificial Neural Networks (ANNs) from our previous work. In this work, the coefficient of the determination (i. e. R2 value) was used to show the prediction ability of these new approaches. Results showed that MGGP and ANFIS can accurately predict the pressure drop in venturi scrubbers with R2 values of 0.9972 and 0.9734, respectively. The results also showed that MGGP has more precision than ANFIS and ANNs. Therefore, based on MGGP, two correlations were generated for two clusters of data. The comparison results between one of these correlations (i. e. correlation 1 with R2 value equal to 0.9937) and other models showed that our correlation has a very good precision and can predict the pressure drop in a more agreement with the experimental data.

Construction project risk assessment by using adaptive-network-based fuzzy inference system: An empirical study

Managers require a good understanding about the nature of risks involved in a construction project because the duration, quality, and budget of projects can be affected by these risks. Thus, the identification of risks and the determination of their priorities in every phase of the construction can assist project managers in planning and taking proper actions against those risks. Therefore, prioritizing risks via the risk factors can increase the reliability of success. In this research, first the risks involved in construction projects has been identified and arranged in a systematic hierarchical structure. Next, based on the obtained data an Adaptive Neuro-Fuzzy Inference System (ANFIS) has been designed for the evaluation of project risks. In addition, a stepwise regression model has also been designed and its results are compared with the results of ANFIS. The results show that the ANFIS models are more satisfactory in the assessment of construction projects risks. Our proposed methodology can be applied by managers of construction projects and practitioners to assess of risk factor of construction projects in a proper manner.

Assessing post-anterior cruciate ligament reconstruction ambulation using wireless wearable integrated sensors

A hardware/software co-design for assessing post-Anterior Cruciate Ligament (ACL) reconstruction ambulation is presented. The knee kinematics and neuromuscular data during walking (2–6 km h−1) have been acquired using wireless wearable motion and electromyography (EMG) sensors, respectively. These signals were integrated by superimposition and mixed signals processing techniques in order to provide visual analyses of bio-signals and identification of the recovery progress of subjects. Monitoring overlapped signals simultaneously helps in detecting variability and correlation of knee joint dynamics and muscles activities for an individual subject as well as for a group. The recovery stages of subjects have been identified based on combined features (knee flexion/extension and EMG signals) using an adaptive neuro-fuzzy inference system (ANFIS). The proposed system has been validated for 28 test subjects (healthy and ACL-reconstructed). Results of ANFIS showed that the ambulation data can be used to distinguish subjects at different levels of recuperation after ACL reconstruction.

An Adaptive Neuro-Fuzzy Inference System Based Modeling for Corrosion-Damaged Reinforced HSC Beams Strengthened with External Glass Fibre Reinforced Polymer Laminates

Problem statement: This study presents the results of ANFIS based model proposed for predicting the performance characteristics of reinforced HSC beams subjected to different levels of corrosion damage and strengthened with externally bonded glass fibre reinforced polymer laminates. Approach: A total of 21 beams specimens of size 150, 250´3000 mm were cast and tested. Results: Out of the 21 specimens, 7 specimens were tested without any corrosion damage (R-Series), 7 after inducing 10% corrosion damage (ASeries) and another 7 after inducing 25% corrosion damage (B-Series). Out of the seven specimens in each series, one was tested without any laminate, three specimens were tested after applying 3 mm thick CSM, UDC and WR laminates and another three specimens after applying 5mm thick CSM, UDC and WR laminates. Conclusion/Recommendations: The test results show that the beams strengthened with externally bonded GFRP laminates exhibit increased strength, stiffness, ductility and composite action until failure. An Adaptive Neuro-Fuzzy Inference System (ANFIS) model is developed for predicting the study parameters for input values lying within the range of this experimental study.

Determination of dielectric properties of insulator materials by means of ANFIS: A comparative study

In this study, dielectric properties of polyesters which have abundant use in communication cables and power systems are aimed to be determined by means of adaptive neuro-fuzzy inference system (ANFIS). Measuring the dielectric properties of insulators under various fields of application and operating conditions requires advanced equipments and takes a long time. After measuring in a wide range and different conditions, determining the other required dielectric properties by means of ANFIS will supplement time and cost. To this end, ANFIS models are trained which are built for every measurement value of dielectric permittivity (ɛr) and loss factor (tan δ) with respect to heat-frequency values of polyesters used as insulators. Then, used data in ANFIS and unused data are tested separately. In the models built for determining dielectric permittivity and loss factor, absolute mean percent error-cumulative absolute percent error are found to be 0.0030–0.1092% and 0.0021–0.0766%, respectively. The results of ANFIS are compared with a previous study of multilayer perceptron (MLP) artificial neural networks (ANN) in which the same data sets are used. ANFIS models exhibit good learning precision and generalization according to mean absolute errors (MAEs). Hence, it becomes easy to determine the dielectric permittivity and loss factor without measuring the given temperature–frequency values by ANFIS. The percent effects of dielectric permittivity and loss factor that are determined by ANFIS on total dielectric loss are discussed based on representative analyses.

Adaptive neuro-fuzzy inference system for computing patch radius of circular microstrip antennas

A new method based on the adaptive neuro-fuzzy inference system (ANFIS) is presented to calculate accurately the patch radius of circular microstrip antennas (MSAs). ANFIS combines the benefits of artificial neural networks (ANNs) and fuzzy inference systems (FISs) in a single model. A hybrid learning algorithm based on the least-squares method (LSM) and the backpropagation algorithm is used to identify the parameters of ANFIS. The results of ANFIS are in very good agreement with the experimental results reported elsewhere. © 2006 Wiley Periodicals, Inc. Microwave Opt Technol Lett 48: 1606–1610, 2006; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/mop.21695

ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM FOR COMPUTING THE PHYSICAL DIMENSIONS OF ELECTRICALLY THIN AND THICK RECTANGULAR MICROSTRIP ANTENNAS

A new method for calculating the patch length and width of rectangular microstrip antennas (MSAs) with thin and thick substrates, based on adaptive neuro-fuzzy inference system (ANFIS), is presented. The ANFIS is a class of adaptive networks which are functionally equivalent to fuzzy inference systems (FISs). It combines the powerful features of FISs with those of artificial neural networks (ANNs) to achieve a desired performance. The results of ANFIS are in excellent agreement with the experimental results available in the literature.