Search

• We develop an adaptive neural-network to control of ultrafiltration in haemodialysis. • Neural network tools are used to adjust the controller for patient specific needs. • Results show adequate performance when submitted to different haemodialysis patterns. • The adaptive nature of the controller makes it possible a personalized treatment. Currently, haemodialysis treatment is performed using an open-loop control approach, with initial settings of parameters such as ultrafiltration rate and dialyser composition being adapted to the current haemodynamic condition of each patient, although unexpected events may require additional adjustments to be made. Therefore, an artificial neural network-based approach has been presented to automatically control the ultrafiltration rate according to the specific patient conditions during the haemodialysis session, in order to regulate body weight loss, and the elimination of electrolytes and uremic toxins. This modelling task is performed using a mathematical model of fluid and solute exchange based on first principles, which is used to simulate the process of a haemodialysis session in a specific patient under SIMULINK in order to define the underlying dynamic equations. Alongside this, MATLAB neural network tools are used to adjust the settings of the automatic controller for different body weight loss regulation profiles and variable dialysate sodium conditions during haemodialysis treatment. Computer simulation results show the adequate performance of the body weight loss neuroadaptive control system when submitted to different haemodialysis patterns, uremic toxins and sodium elimination evolution under changing dialysate sodium conditions. The proposed approach proves to be a valuable tool as a test bench for the assessment of alternate haemodialysis profiles aimed to improve the treatment of patients by preventing dialysis-induced haemodynamic complications. The adaptive nature of the model-based control approach here presented makes it possible to personalize the haemodialysis treatment to the specific needs of each patient. [ABSTRACT FROM AUTHOR]

Highlights: [•] This research is the first trial for networked Lagrangian systems with flexible joints. [•] Simple local controllers are designed regardless of the order of followers and the complexity of communication links. [•] Derivative terms of multiple dynamic leaders are not required to implement the controllers. [Copyright &y& Elsevier]

The systematic choice, update, and implementation of periodic (t) action plans define the feed conversion rate (F C R t ) in poultry farming, an acceptable measure for successful production. Appropriate plans provide tailored resources, allowing broilers to grow within the so-called comfort zone, without waste or lack of resources. Although the implementation of an action plan is automatic, its configuration depends on a specialist, which result in variable F C R t . In this article, the specialist's perception is reproduced, to some extent, by computational intelligence. By combining deep learning and genetic algorithms, we show how action plans can adapt their performance over the time, based on previous well succeeded plans. We also implement a network infrastructure to replicate our method over distributed poultry houses, for their smart and interconnected control. A supervision system is provided as interface to users. Experiments using real data suggest an improvement of 5% on the performance of the most productive specialist, staying close to the optimal F C R t . • Computational intelligence applied to improve poultry farming. • Deep learning and genetic algorithms to reproduce human perception. • Adaptation of practices based on previous well succeeded practices. • Network infrastructure to replicate the method over distributed poultry houses. • Supervision system as interface for smart, interconnected, and adaptive control. [ABSTRACT FROM AUTHOR]

Abstract: This study deals with modeling the flank wear of cryogenically treated AISI M2 high speed steel (HSS) tool by means of adaptive neuro-fuzzy inference system (ANFIS) approach. Cryogenic treatment has recently been found to be an innovative technique to improve wear resistance of AISI M2 HSS tools but precise modelling approach which also incorporates the cryogenic soaking temperature to simulate the tool flank wear is still not reported in any open literature. In order to obtain data for developing the ANFIS model, turning of hot rolled annealed steel stock (C-45) by cryogenically treated tools treated at various cryogenic soaking temperatures was performed in steady state conditions while varying the cutting speed and cutting time. The model combined modeling function of fuzzy inference with the learning ability of artificial neural network; and a set of rules has been generated directly from experimental data. It was determined that the predictions usually agreed well with the experimental data with correlation coefficients of 0.994 and mean errors of 2.47%. The proposed model can also be used for estimating tool flank wear on-line but the accuracy of the model depends upon the proper training and selection of data points. [Copyright &y& Elsevier]

Abstract: This study proposes an indirect adaptive self-organizing RBF neural control (IASRNC) system which is composed of a feedback controller, a neural identifier and a smooth compensator. The neural identifier which contains a self-organizing RBF (SORBF) network with structure and parameter learning is designed to online estimate a system dynamics using the gradient descent method. The SORBF network can add new hidden neurons and prune insignificant hidden neurons online. The smooth compensator is designed to dispel the effect of minimum approximation error introduced by the neural identifier in the Lyapunov stability theorem. In general, how to determine the learning rate of parameter adaptation laws usually requires some trial-and-error tuning procedures. This paper proposes a dynamical learning rate approach based on a discrete-type Lyapunov function to speed up the convergence of tracking error. Finally, the proposed IASRNC system is applied to control two chaotic systems. Simulation results verify that the proposed IASRNC scheme can achieve a favorable tracking performance. [Copyright &y& Elsevier]

Abstract: This paper proposes a self-adaptive interval type-2 neural fuzzy network (SAIT2NFN) control system for the high-precision motion control of permanent magnet linear synchronous motor (PMLSM) drives. The antecedent parts in the SAIT2NFN use interval type-2 fuzzy sets to handle uncertainties in PMLSM drives, including payload variation, external disturbance, and sense noise. The SAIT2NFN is firstly trained to model the inverse dynamics of PMLSM through concurrent structure and parameter learning. The fuzzy rules in the SAIT2NFN can be generated automatically by using online clustering algorithm to obtain a suitable-sized network structure, and a back propagation is proposed to adjust all network parameters. Then, a robust SAIT2NFN inverse control system that consists of the SAIT2NFN and an error-feedback controller is proposed to control the PMLSM drive in a changing environment. Moreover, the Kalman filtering algorithm with a dead zone is derived using Lyapunov stability theorem for online fine-tuning all network parameters to guarantee the convergence of the SAIT2NFN. Experimental results show that the proposed SAIT2NFN control system achieves the best tracking performance in comparison with type-1 NFN control systems. [Copyright &y& Elsevier]

Abstract: This paper presents the design of adaptive load-shedding strategy by executing the artificial neural network (ANN) and transient stability analysis for an Industrial cogeneration facility. ► To prepare the training data set for ANN, the transient stability analysis has been performed to solve the minimum load shedding for various operation scenarios without causing tripping problem of cogeneration units. Various training algorithms have been adopted and incorporated into the back-propagation learning algorithm for the feed-forward neural networks. ► By selecting the total power generation, total load demand and frequency decay rate as the input neurons of the ANN, the minimum amount of load shedding is determined to maintain the stability of power system. ► To demonstrate the effectiveness of the ANN minimum load-shedding scheme, the traditional method and the present load shedding schemes of the selected cogeneration system are also applied for comparison and verification of the proposed methodology. [Copyright &y& Elsevier]

Abstract: Chaotic system is a nonlinear deterministic system that displays complex, noisy-like and unpredictable behavior, so how to synchronize chaotic system become a great deal in engineering community. In this paper, an adaptive fuzzy wavelet neural synchronization controller (AFWNSC) is proposed to synchronize two nonlinear identical chaotic gyros. The proposed AFWNSC system is composed of a neural controller and a fuzzy compensator. The neural controller uses a fuzzy wavelet neural network to online approximate an ideal controller and the fuzzy compensator is used to guarantee system stable without chattering phenomena. All the parameter learning algorithms of the proposed AFWNSC scheme are derived in the Lyapunov stability sense. Finally, some simulation results verify the chaotic behavior of two nonlinear identical chaotic gyros can be synchronized by the proposed AFWNSC scheme after learning of the controller parameters. Moreover, the convergence of the tracking error and control parameters can be accelerated by the developed proportional-integral type adaptation learning algorithm. [Copyright &y& Elsevier]

Abstract: Improving the sales forecasting accuracy has become a primary concern for automobile industry. Here, we only focus on new automobile sales in Taiwan. The data set is based on monthly sales, and the data can be divided into three styles of automobile sales. To address our concern, we developed a sales forecasting methodology that considers several variables such as current automobile sales quantity, coincident indicator, leading indicator, wholesale price index and income. First, we use the stepwise regression to select most influential variables as our input variables. Then, we input the influential variables and sales in adaptive network-based fuzzy inference system (ANFIS) to obtain the forecast. Finally, we compare our model with two forecasting models: autoregressive integrated moving average model (ARIMA) and artificial neural network (ANN). Empirical results demonstrate that the application of the ANFIS model outperforms the other two models. In addition, we modified the historical and holdout periods to improve forecasting accuracy while considering the impact from the financial tsunami in 2008. [Copyright &y& Elsevier]

Abstract: This paper proposes the generalized projective synchronization (GPS) of uncertain chaotic systems with external disturbance via Gaussian radial basis adaptive sliding mode control (GRBASMC). A sliding surface is adopted to ensure the stability of the error dynamics in sliding mode control. In the neural sliding mode controller, a Gaussian radial basis function is utilized to online estimate the system dynamic function. The adaptation law of the control system is derived in the sense of Lyapunov function, thus the system can be guaranteed to be asymptotically stable. The proposed method allows us to arbitrarily adjust the desired scaling by controlling the slave system. It is not necessary to calculate the Lyapunov exponents and the eigen values of the Jacobian matrix, which makes it simple and convenient. Also, it is a systematic procedure for GPS of chaotic systems and it can be applied to a variety of chaotic systems no matter whether it contains external excitation or not. Note that it needs only one controller to realize GPS no matter how much dimensions the chaotic system contains and the controller is easy to be implemented. The proposed method is applied to three chaotic systems: Genesio system, Lur’e like system and Duffing system. [ABSTRACT FROM AUTHOR]

Abstract: The adaptive output recurrent cerebellar model articulation control (AORCMAC) is an adaptive system with simple computation, good generalization capability and fast learning property. The proposed AORCMAC has superior capability to the conventional cerebellar model articulation controller (CMAC) in efficient learning mechanism and dynamic response. In this study, an intelligent backstepping tracking control system is proposed for wheeled inverted pendulums (WIPs) with unknown system dynamics and external disturbance. In this control system, an ABORCMAC is used to copy an ideal backstepping control (IBC), and a compensated controller is designed to compensate for difference between the IBC law and AORCMAC. Moreover, all adaptation laws of the proposed system are derived based on the Lyapunov stability analysis, the Taylor linearization technique, so that the stability of the closed-loop system can be guaranteed. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a fault diagnosis system for an automotive air-conditioner blower based on a noise emission signal using a self-adaptive data analysis technique. The proposed diagnosis system consists of feature extraction using the empirical mode decomposition (EMD) method and fault classification using the artificial neural network technique. The EMD method has been developed quite recently to adaptively decompose the non-stationary and non-linear signals. It sifts the complex signal of time series without losing its original properties and then obtains some useful intrinsic mode function (IMF) components. Calculating the energy of each component can reduce the computation dimensions and enhance classification performance. These energy features of various fault conditions are used as inputs to train the artificial neural network. In the fault classification, the probabilistic neural network (PNN) is used to verify the performance of the proposed system and compare with the traditional technique, back-propagation neural network (BPNN). The experimental results indicated the proposed technique performed well for quickly and accurately estimating fault conditions. [Copyright &y& Elsevier]

Abstract: This paper introduces an adaptive neuro-fuzzy inference system (ANFIS) model to predict the tip speed ratio (TSR) and the power factor of a wind turbine. This model is based on the parameters for LS-1 and NACA4415 profile types with 3 and 4 blades. In model development, profile type, blade number, Schmitz coefficient, end loss, profile type loss, and blade number loss were taken as input variables, while the TSR and power factor were taken as output variables. After a successful learning and training process, the proposed model produced reasonable mean errors. The results indicate that the errors of ANFIS models in predicting TSR and power factor are less than those of the ANN method. [Copyright &y& Elsevier]

Abstract: Since last decade advanced data simulations help to identify hidden trends in a time series. Our purpose is to identify uncertainties during recession period using statistical analysis, econometrical analysis and Adaptive Neural-Fuzzy networks. In this paper, initially through computational analysis we are testing financial data using correlation tests, likelihood tests, heteroscedastic characteristics analysis and hypothesis tests. These statistical and econometrical tests give us exact nature of data set and relation between data points. All tests and analysis are studied on NASDAQ Stock Market over last 2-years. Then after, optimized subtractive data clustering method is used to cluster the data and create fuzzy membership functions by using Sugeno-type Fuzzy Interface System (FIS). Finally, we are using optimized hybrid learning algorithm in customized Adaptive Neural Fuzzy Interface System (ANFIS) to train the network. Hence, we got an efficient Adaptive Neural-Fuzzy network to check and test the data sets and use it for forecasting the stock market index. During this, the hybrid learning algorithm combines Least-Square method and the Back-propagation gradient descent methods for training the Fuzzy Interface System (FIS) with the help of optimized membership functions and parameters. This paper presents a state-of-art for Adaptive Neural-Fuzzy Network (ANFN) application to forecast stock market index and involved market uncertainties by combining the econometrical test to optimize the ANFIS and FIS function. [Copyright &y& Elsevier]

Abstract: A methodology has been developed to predict fatigue crack propagation life of 7020 T7 and 2024 T3 aluminum alloys under constant amplitude loading interspersed with mode-I spike overload. It has been assessed by adopting adaptive neuro-fuzzy inference system (ANFIS), a novel soft-computing approach, suitable for non-linear, noisy and complex problems like fatigue. The proposed model has proved its efficiency quite satisfactorily compared to authors’ previously proposed ‘Exponential Model’, when tested on both the alloys. [Copyright &y& Elsevier]

Abstract: Adaptive Neuro-Fuzzy Inference System (ANFIS) and Radial Basis Function Neural Network (RBF NN) have been developed for prediction of solubility of various gases in polystyrene. Solubility of butane, isobutene, carbon dioxide, 1,1,1,2-tetrafluoroethane (HFC-134a), 1-chloro-1,1-difluoroethane (HCFC-142b), 1,1-difluoroethane (HFC-l52a) and nitrogen in polystyrene is modeled by ANFIS and RBF NN in a wide range of pressure and temperature with high accuracy. The results obtained in this work indicate that ANFIS and RBF NN are effective methods for prediction of solubility of gases in polystyrene and have better accuracy and simplicity compared with the classical methods. [Copyright &y& Elsevier]

Abstract: Thermal imaging is used extensively in the detection of infrared spectrum. This principle has found great and effective use in the screening of potential SARS patients. This paper investigates the application of several novel brain-inspired softcomputing techniques in the study of the correlation of superficial thermal images against the true internal body temperature. Given some backgrounds that the existing infrared systems used at various boarder checkpoints have high false-negative rate, the novel fuzzy neural networks (FNNs) employed in the back-end of the system have a role as a thermal analysis tool with high degree of accuracy. To achieve the automation and improve the accuracy in the feature extraction process of the infrared images, some forms of image processing technique based on the novel FNNs are also proposed in this paper. Extensive experimentations are undertaken to examine such intelligent medical decision support tool. Benchmarking was carried out on the novel FNN architectures which include pseudo outer-product fuzzy neural network (POPFNN), evolving fuzzy neural network (EFuNN), fuzzy adaptive learning control network (Falcon), generic self-organizing fuzzy neural network (GenSoFNN), and fuzzy cerebellar model articulation controller (FCMAC), and their results are promising. The performance of the GenSoFNN network is the most appealing among others. In addition, the experiments are conducted on real-life data taken from the Emergency Department (A&E), Tan Tock Seng Hospital (the designated SARS center in Singapore) to confirm the validity of such design in the real time. [Copyright &y& Elsevier]

Abstract: The performance of a solar collector system using sodium carbonate decahydrate as Phase Change Material (PCM) was experimentally investigated during March and collector efficiency was compared with those of convectional system including no PCM. We also made a series of predictions by using three different soft computing techniques as Artificial Neural Networks (ANN), Adaptive-Network-Based Fuzzy Inference System (ANFIS) and Support Vector Machines (SVM). It was found that the solar collector system with PCM is more effective than convectional systems. Soft computing techniques can be used to model of a solar collector with PCM. Furthermore, analysis of soft computing showed that SVM technique gives the best results than that of ANFIS and ANN. [Copyright &y& Elsevier]

Abstract: In this paper, a wavelet network is presented to design different controllers for DC motors based on the multi-resolution analysis and the wavelet transform. One of the basic advantages of wavelet network is that training is done using the recursive least square method which is suitable for online training usually required for adaptive control. The wavelet network is used to design adaptive speed controllers for a DC motor to achieve high performance speed control even if the motor model is unknown, the load characteristics are also unknown function of speed and the load torque changes online. Simulation and experimental results are presented to validate the effectiveness of the proposed controllers. [Copyright &y& Elsevier]

Abstract: Effluent iron concentration is an important water quality criterion used for the assessment of the performance of rapid sand filters, in addition to other criteria. This study deals with the prediction of effluent iron concentrations by adaptive neuro-fuzzy (ANFIS) model with input parameters including filter hydraulic loading rate, influent iron concentration, bed porosity and operation time. With trying various types of membership functions, two rule base generation methods, namely subtractive clustering and grid partition were used for a first order Sugeno type inference system. Models were evaluated using root mean squared error (RMSE), index of agreement (IA) and R 2 as statistical performance parameters. The fit between experimental results and model outputs showed good agreement for tap water and deionized water; testing RMSE values were 36.33 and 7.66μg/L, the IA values were 0.996 and 0.971, and R 2 values were 0.99 and 0.89, respectively. It was concluded that neuro-fuzzy modeling may be successfully used to predict effluent iron concentration in sand filtration. [Copyright &y& Elsevier]

Abstract: This paper illustrates the control strategies of an Electric Arc Furnace. It involves the prediction of the control action which aids in reduction of carbon, manganese and other impurities from the in-process molten steel. Predictive models using Artificial Neural Networks (ANN) with Bayesian Regularization and Adaptive Neuro Fuzzy Inference System (ANFIS) were developed. The control action is the amount of oxygen to be lanced at different sampling instants. The predictive models were constructed based on the values of the individual chemical constituents of the collected molten samples. Two control strategies were devised: one with full sampling and the other with limited or reduced sampling. For the full sampling case two predictive models were devised separately with ANN with Bayesian Regularization and ANFIS. For the limited sampling strategy a combination of ANN with Bayesian Regularization and ANFIS were employed. For full sampling strategy, ANFIS model performs better than ANN. The application of the limited sampling strategy gave satisfactory Mean Percentage Error (MPE) thereby justifying its practical implementation. The main advantage of reduced or limited sampling is that it helps in the reduction of cost, time and manpower associated the sample collection and its subsequent analysis. [Copyright &y& Elsevier]

Abstract: In this paper, we elaborate a neural network model to predict innovation performance with fuzzy rules, as well as implement an adaptive neuro-fuzzy inference systems (ANFIS) to measure the innovation performance through technical information resource and innovation objective. Building on the findings from fuzzy neural network approach, using Sugeno ANFIS, we also compared the artificial neural network with statistical techniques. We found strong support for ANFIS method has better results than the neural network and statistical techniques with regards to forecast performance. Finally, on the basis of our analysis, our results hold an important lesson for decision makers who may clearly picture the rules and adjust the resource allocation to meet their innovation objectives. [Copyright &y& Elsevier]

Abstract: It is well-known that conventional control theories are widely suited for applications where the processes can be reasonably described in advance. However, when the plant’s dynamics are hard to characterize precisely or are subject to environmental uncertainties, one may encounter difficulties in applying the conventional controller design methodologies. In this case, an alternative design is a model-free learning adaptive control (MFLAC), based on pseudo-gradient concepts with compensation using a radial basis function neural network and optimization approach with differential evolution technique presented in this paper. Motivation for developing a new approach is to overcome the limitation of the conventional MFLAC design, which cannot guarantee satisfactory control performance when the nonlinear process has different gains for the operational range. Robustness of the MFLAC with evolutionary-neural compensation scheme is compared to the MFLAC without compensation. Simulation results for a nonlinear chemical reactor and nonlinear control valve are given to show the advantages of the proposed evolutionary-neural compensator for MFLAC design. [Copyright &y& Elsevier]

Abstract: In the above Letter, the authors proposed an adaptive CMAC neural control (ACNC) system with a PI-type learning algorithm and applied it to control the chaotic systems. However, there are a few errors in the proof of the stability. In this letter, a modified control law is proposed and the corresponding proof is given. [Copyright &y& Elsevier]