Narrow Results

Today, with real-life problems, modeling is a primary step in organizing, analyzing and optimizing them. Queueing theory is a particular approach used to model this category of issues. Space constraints, feedback, service dependency, etc. are often inseparable from the issues they create. In light of this objective, this research presents a model and analysis of the steady-state behavior of an $M/G/1$ feedback retrial queue with two dependent phases of service under a Bernoulli vacation policy. The service times for the two stages are often independent in normal queueing frameworks. We presume that they are dependent random variables in this case. Indeed, this dependence is one-way (i.e., the service time of the second phase has no effect on the service time of the first phase). Yet, the first phase service time has an impact on the second phase service time. In order to determine the steady-state probabilities and probability-generating functions (PGF) for the different states, the supplementary variable technique (SVT) was utilized. Furthermore, a broad range of performance metrics had been established. The generated metrics are then envisioned and validated with the aid of graphs and tables. Additionally, a nonlinear cost function is constructed, which is subsequently minimized by distinct approaches like particle swarm optimization (PSO), artificial bee colony (ABC) and genetic algorithm (GA). Furthermore, we used certain figures to examine the convergence of these optimization methods. Finally, validation outcomes are compared with neuro-fuzzy results generated with the “adaptive neuro-fuzzy inference system” (ANFIS).

Drug synergy prediction plays a significant role in the medical field for inhibiting specific cancer agents. It can be developed as a pre-processing tool for therapeutic successes. Examination of different drug–drug interaction can be done by drug synergy score. It needs efficient regression-based machine learning approaches to minimize the prediction errors. Numerous machine learning techniques such as neural networks, support vector machines, random forests, LASSO, Elastic Nets, etc., have been used in the past to realize requirement as mentioned above. However, these techniques individually do not provide significant accuracy in drug synergy score. Therefore, the primary objective of this paper is to design a neuro-fuzzy-based ensembling approach. To achieve this, nine well-known machine learning techniques have been implemented by considering the drug synergy data. Based on the accuracy of each model, four techniques with high accuracy are selected to develop ensemble-based machine learning model. These models are Random forest, Fuzzy Rules Using Genetic Cooperative-Competitive Learning method (GFS.GCCL), Adaptive-Network-Based Fuzzy Inference System (ANFIS) and Dynamic Evolving Neural-Fuzzy Inference System method (DENFIS). Ensembling is achieved by evaluating the biased weighted aggregation (i.e. adding more weights to the model with a higher prediction score) of predicted data by selected models. The proposed and existing machine learning techniques have been evaluated on drug synergy score data. The comparative analysis reveals that the proposed method outperforms others in terms of accuracy, root mean square error and coefficient of correlation.

This paper proposed an adaptive neuro-fuzzy model (ANFIS) to multilevel inverter (MLI) for grid connected photovoltaic (PV) system. The purpose of the proposed controller is that it is not requiring any optimal pulse width modulated (PWM) switching-angle generator and proportional–integral controller. The proposed method strictly prohibits the variations present in the output voltage of the cascaded H-bridge MLI. In this method, the ANFIS have the input which is grid voltage, the difference voltage and the output target is control voltage. By using these parameters, the ANFIS makes the rules and has been tuned perfectly. During the testing time, the ANFIS gives the control voltage according to the different inputs. The resultant control voltage equivalent gate pulses are utilized for controlling the insulated gate bi-polar switches (IGBT) of MLI. Then the ANFIS based MLI for grid connected PV system is implemented in the MATLAB/simulink platform and the effectiveness of the proposed control technique is analyzed by comparing with the neural network (NN), fuzzy logic control, etc. The comparison results demonstrate the superiority of the proposed approach and confirm its potential to solve the problem. A prototype of three-phase grid connected cascaded H-bridge inverter has been developed using field-programmable gate array (FPGA) and results are analyzed.

In this study, the effectiveness of an SPAD-502 portable chlorophyll (Chl) meter was evaluated for estimating the Chl contents in leaves of some medicinal and aromatic plants. To predict the individual chlorophyll concentration indexes of St. John’s wort (Hypericum perforatum L.), mint (Mentha angustifolia L.), melissa (Melissa officinalis L.), thyme (Thymus sp.), and echinacea (Echinacea purpurea L.), models were developed using SPAD value. Multi-layer perceptron (MLP), adaptive neuro fuzzy inference system (ANFIS), and general regression neural network (GRNN) were used for determining the chlorophyll concentration indexes.

In this paper, the hybrid direct torque control (DTC) technique is proposed for controlling the speed of the induction motor (IM). The hybrid technique is the combination of an enhanced firefly algorithm (FA) and the adaptive neuro fuzzy inference system (ANFIS) technique. The performance of the FA is improved by updating the randomized parameter. Here, the genetic algorithm (GA) is utilized for updating the parameter and improved the performance of the FA. Initially, the actual torque and the change of toque are applied to the input of the enhanced FA and form the electromagnetic torque as a dataset. The output of the enhanced FA is given to the input of the ANFIS which is determined from the output of interference system. The dynamic behavior of the IM is analyzed in terms of the parameters such as the speed, torque, flux, etc. Based on the parameters, the motor speed is controlled by utilizing the proposed technique. Then the output of the ANFIS is translated into the stator voltage which is given to the input of the support vector machine (SVM). After that, the control signal is generated for controlling the speed of the IM. The proposed hybrid technique is implemented in the Matlab/Simulink platform. The performance analysis of the proposed method is demonstrated and contrasted with the existing techniques such as without controller, particle swarm optimization (PSO)-based ANFIS and FA-ANFIS controller.

The development of bidirectional DC–DC converters has become important because of their requirement in energy-storage systems. The simple structure of nonisolated bidirectional DC–DC converter types includes multilevel, switched-capacitor, buck-boost, and coupled inductor type. In multilevel and switched-capacitor types, if large voltage gain must be provided, more switches and capacitors are required. Since the leakage inductor energy cannot be recycled, voltage stresses on the switches are present. Therefore, the control strategy is easily implemented in the system operation. This paper presents a cascaded nonisolated dc–dc switched coupled converter for enhancement of the switching operation. For the optimal switching performances, an Artificial Intelligence (AI) technique is utilized. The AI technique is the Adaptive Neuro-Fuzzy Inference System (ANFIS) for generating the optimal control pulses to enhance the performance of boost and buck switch. In addition, the proposed technique is utilized in cascaded nonisolated DC–DC switched coupled converter to reduce the losses. In the ANFIS technique, the error voltage and change in error voltage are given as inputs. At the same time, the ANFIS controller is employed to reduce the error value and produce the optimized gain pulses. In the buck and boost switch mode of operation, it is enhanced with the help of the proposed technique. Moreover, the operating principle and voltage conversion ratio are discussed. It is seen that the implementation of the proposed controller improves the efficiency of the system and also reduces the voltage drop across the switching operation. Then the proposed ANFIS technique with bidirectional converter topology was implemented in MATLAB/Simulink working platform and the output performance is analyzed. Then the proposed circuit performance is compared to the existing circuit such as proportional integral derivative (PID), artificial neural network (ANN) and Fuzzy, respectively.

Inertial navigation system (INS) is often integrated with satellite navigation systems to achieve the required precision at high-speed applications. In global navigation system (GPS)/INS integration systems, GPS outages are unavoidable and a severe challenge. Moreover, because of the usage of low-cost microelectromechanical sensors (MEMS) with noisy outputs, the INS will get diverged during GPS outages, and that is why navigation precision severely decreases in commercial applications. In this paper, we improve GPS/INS integration system during GPS outages using extended Kalman filter (EKF) and artificial intelligence (AI) together. In this integration algorithm, the AI receives the angular rates and specific forces from the inertial measurement unit (IMU) and velocity from the INS at $t$ and $t-1$. Therefore, the AI has positioning and timing data of the INS. While the GPS signals are available, the output of the AI is compared with the GPS increment; so that the AI is trained. During GPS outages, the AI will practically play the GPS role. Thus, it can prevent the divergence of the GPS/INS integration system in GPS-denied environments. Furthermore, we utilize neural networks (NNs) as an AI module in five different types: multi-layer perceptron (MLP) NN, radial basis function (RBF) NN, wavelet NN, support vector regression (SVR) and adaptive neuro-fuzzy inference system (ANFIS). To evaluate the proposed approach, we utilize a real dataset that has been gathered by a mini-airplane. The results demonstrate that the proposed approach outperforms the INS and GPS/INS integration systems with the EKF during GPS outages. Meanwhile, the ANFIS also reached more than 47.77% precision compared to the traditional method.

This research attempts to explore the utilization of Gas-Assisted Electrical Discharge Machining (GAEDM) of die steel. High pressure inert gas (argon) in conventional electric discharge machining with constraint state was utilized to assess the surface roughness (SR). Analysis of Variance (ANOVA) was used to find out the process parameters that notably affected the SR. In this study, a mathematical model has been investigated to know the SR by using Buckingham pie-theorem. The fit summary confirmed that the quadratic model is statistically appropriate and the lack of fit is insignificant. Root mean square error and absolute standard deviation, obtained through response surface method (RSM), were also used for developing the model and for predicting its abilities through ANN, ANFIS. The experiment and anticipated estimates of SR during the process, obtained by RSM, dimensional analysis, ANN and ANFIS, were found to be in accord with each other. However, the ANFIS technique proved to be more fitting to the response as compared to the ANN, dimensional analysis and the RSM.

Intelligent and adaptive control systems are naturally suitable to deal with dynamic uncertain systems with non-smooth nonlinearities; they constitute an important advantage over conventional control approaches. This control technology can be used to design powerful and robust controllers for complex vibration engineering problems such as vibration control of civil structures. Fuzzy logic based controllers are simple and robust systems that are rapidly becoming a viable alternative for classical controllers. Furthermore, new control devices such as magnetorheological (MR) dampers have been widely studied for structural control applications. In this paper, we design a semi-active fuzzy controller for MR dampers using an adaptive neuro-fuzzy inference system (ANFIS). The objective is to verify the effectiveness of a neuro-fuzzy controller in reducing the response of a building structure equipped with a MR damper operating in passive and semi-active control modes. The uncontrolled and controlled responses are compared to assess the performance of the fuzzy logic based controller.

A hemispherical model equipped with a three component accelerometer force balance has been tested in a shock tunnel at Mach 8.0 freestream conditions. A novel technique has been devised using the Artificial Neuro-Fuzzy Inference System (ANFIS) for recovering the forces experienced by the model during the experiments. Implementation of this methodology in calibration of the force balance showed encouraging agreement with the impulse forces recovered from the calibration tests. The same recovery procedure is then adopted to obtain the time history of the forces for 0${}^{\circ }$ and 15${}^{\circ }$ angle of attack experiments. The drag recovered in steady state is found to agree well with the conventional methods with minor discrimination for the lift and pitching moment. In light of the limitation of the accelerometer force balance theory due to the unaccountability of model dynamics, the force recovery technique proposed herein is found simple to implement and can be opted as a tool for prediction of the aerodynamic coefficients and force time histories.

In cardiopulmonary resuscitation (CPR), in practice, the rescuer usually uses two hands to perform the action of chest compressions. During chest compressions action, the two arms of the rescuer actually constitute a parallel mechanism. Inspired by this performance, this paper presents a novel structure of parallel manipulators from Delta robot family for chest compressions in rescuing a patient. Also, two new control methodologies are applied to track the desired trajectory. Based on one supervisory approach and another one based upon adaptive neuro-fuzzy inference system (ANFIS) approach. Inverse dynamic modeling is performed based on principle of virtual work and the results are verified using MSC.Adams© software. The proportional derivative (PD) controllers of computed torque (C-T) method usually need manual retuning to make a successful task, particularly in the presence of disturbance. In the present paper, we study and compare the feasibility of applying supervisory controller and ANFIS instead of conventional controller used in C-T method to cope with the above mentioned problem. Several computer simulations imply that the proposed method is encouraging compared with C-T method implemented with conventional controller.

The estimation of knee joint torque is important for the development of powered exoskeletons to achieve ideal gait characteristics. In this study, we proposed three different models to predict the required torque for performing sit-to-stand (STS) and back-to-sit (BTS) movements. The surface electromyography (sEMG) signals were extracted from the biceps femoris and rectus femoris muscles during STS and BTS movements. The time-domain features selected as input to the models for torque prediction are integrated EMG (iEMG), root mean square (RMS), and mean absolute value (MAV). Two-way ANOVA analysis identifies the significance of NN models and EMG features of the muscles in predicting the knee joint torque requirement. The artificial neural network models selected for prediction are the feed-forward back-propagation algorithm, ANFIS, and NARX. The theoretical value of knee joint torque calculated using the Lagrange method was compared with the torque output for each model based on root mean square error (RMSE). The desired torque predicted using the NARX model confirms to have the least average error ($0.9\pm 0.4$Nm), which indicates that NARX can estimate knee joint torque more accurately from sEMG than other models.

Adaptive Neuro Fuzzy Inference System (ANFIS) used to be applied to finance, engineering, material design, and decision-making management in past research, but seldom to predict educational learning performance. In recent research, gamification learning material design is often applied to reinforce learning performance, while the prediction of gamification learning performance is seldom discussed. This study therefore applies Rough set theory to extract Core Set and generating rule, ANFIS for learning achievement predication. In order to evaluate the performance of proposed model, the VCCSEGLS dataset are collected as experimental dataset and compared with other models. The results show that the proposed method outperforms the listing models in accuracy. The three key factors are extract, (G7) Time spent on game-based learning, (L1) Examination, normal drugs and treatment, and (L2) Integration ability (time scoring, stability scoring, strain capacity, completeness scoring).The proposed model also can offer accurate predictions and provide some simple decision rules, which can be accurately used by decision-makers and game designers.

Higher accuracy and meticulousness are highly demandable in modern industrial field during micro-machining performances by electrochemical discharge machining (ECDM) process. The paper deals with the experimental fuzzy logic control (FLC) analysis as well as artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) analysis during micro-channel fabrication on silica glass. A comparative analysis of FLC, ANN as well as ANFIS has been performed and experimental error prediction has been propounded to estimate minimum error possibilities such as mean absolute error (MAE), root mean square error (RMSE) and regression value (R). Computational time training dataset, minimum sample size and prediction time are also illustrated in this paper. In this paper, ANN, FLC and ANFIS models are analyzed for tool wear rate (TWR) and heat-affected zone (HAZ). 3D Rule Viewer and regression analysis as well as validation of test results and characteristics graph between performances with number of epochs of ANN model also are included in this paper for TWR and HAZ. Influence of process parameters like voltage, duty ratio, pulse frequency and electrolyte concentration on Surface Viewer of TWR and HAZ is also illustrated. It is found that ANFIS has great effectiveness of prediction of error during micro-ECDM process.

Due to the expanded industrialization, the necessity of variable speed machines/drives keeps on expanding. The vast majority of computerized Brushless Direct Current (BLDC) motor frame-works are utilized because of their speedier reaction and high stablity. In this paper, an innovative technique, i.e. Adaptive Neuro-Fuzzy Inference System (ANFIS) with Fractional-Order PID (FOPID) controllers for controlling a portion of the parameters, for example, speed, and torque of the BLDC motor are exhibited. With a specific end goal being the performance of the proposed controller under outrageous working conditions, for example, varying load and set speed conditions, simulation results are taken for deliberation. An Opposition-based Elephant Herding Optimization (OEHO) optimization algorithm is utilized to improve the tuning parameters of FOPID controller. At that point, the ANFIS is gladly proposed to adequately control the speed and torque of the motor. The simulation result exhibited that the composed FOPID controller understands a decent dynamic behavior of the BLDC, an immaculate speed tracking with less ascent and gives better execution. The performance investigation of the proposed strategy lessened the error signal contrasted with the existing strategies, for example, FOPID-based Elephant Herding Optimization (EHO), Proportional–Integral–Derivative BAT (PID-BAT), and PID-ANFIS.

The detection and diagnosis of faults in technical systems are of great practical significance and paramount importance for the safe operation of the plant. The early detection of fault can help avoid system shutdown, breakdown and even catastrophe involving human fatalities and material damage. Since the operator cannot monitor all the variables simultaneously, an automated approach is needed for the real time monitoring and diagnosis of the system. This paper presents the design and development of adaptive neuro-fuzzy inference system (ANFIS) model based for the fault detection of pneumatic valve in cooler water spray system in cement industry. The fault detection model is developed by using two different approaches, namely, ANFIS and feed forward network with back propagation algorithm (BPN). The training and testing data required are developed for the ANFIS model and BPN model that were generated at different operating conditions by operating the pneumatic valve and by creating various faults in real time in a laboratory experimental model. The performance of the developed ANFIS model and back propagation were tested and also compared for a total of 19 faults in pneumatic valve used in cooler water spray system. Obtained results of the ANFIS performed better than BPN.

This paper introduces a novel approach for tuning the parameters of the adaptive network-based fuzzy inference system (ANFIS). In the commonly used training methods, the antecedent and consequent parameters of ANFIS are trained by gradient-based algorithms and recursive least square method, respectively. In this study, a new swarm-based meta-heuristic optimization algorithm, so-called "Cat Swarm Optimization", is used in order to train the antecedent part parameters and gradient descent algorithm is applied for training the consequent part parameters. Experimental results for prediction of Mackey–Glass model and identification of two nonlinear dynamic systems reveal that the performance of proposed algorithm is much better and it shows quite satisfactory results.

With lower operational costs, many small and medium-sized enterprises (SMEs) trade via e-commerce, but without the abilities to develop the expensive payment system. Therefore, a cash flow service provider plays critical roles to complete the online transactions. A cash flow service provider must precisely predict those outsourcing customers to serve the customers well under the correctly prepared facilities. Since the adaptive neuro-fuzzy inference systems (ANFIS) have demonstrated prediction efficiency for fuzzy circumstances in many fields, this study attempts to innovate deploying the ANFIS model on the time series predictions for e-commerce cash flow service customers. Moreover, this study takes an e-commerce cash flow service provider in Taiwan for numerical analysis. For the ANFIS predictions, an acceptable prediction error rate of 5.6% is achieved. The results show that fashion industry tops the highest customers share for outsourcing the cash flow services; and the credit cards top the highest share in the payment media choices.

Communities globally experience devastating effects, high monetary loss and loss of lives due to incidents of flood and other hazards. Inadequate information and awareness of flood hazard make the management of flood risks arduous and challenging. This paper proposes a hybridized analytic approach via unsupervised and supervised learning methodologies, for the discovery of pieces of knowledge, clustering and prediction of flood severity levels (FSL). A two-staged unsupervised learning based on $k$-means and self-organizing maps (SOM) was performed on the unlabeled flood dataset. $K$-means based on silhouette criterion discovered top three representatives of the optimal numbers of clusters inherent in the flood dataset. Experts’ judgment favored four clusters, while Squared Euclidean distance was the best performing distance measure. SOM provided cluster visuals of the input attributes within the four different groups and transformed the dataset into a labeled one. A 5-layered Adaptive Neuro Fuzzy Inference System (ANFIS) driven by hybrid learning algorithm was applied to classify and predict FSL. ANFIS optimized by Genetic Algorithm (GA) produced root mean squared error (RMSE) of 0.323 and Error Standard Deviation of 0.408 while Particle Swarm Optimized ANFIS model produced 0.288 as the RMSE, depicting 11% improvement when compared with GA optimized model. The result shows significant improvement in the classification and prediction of flood risks using single ML tool.

Thin-film deposition processes have gained much popularity due to their unique capability to enhance the physical and chemical properties of various materials. Identification of the best parametric combination for a deposition process to achieve desired coating quality is often considered to be challenging due to the involvement of a large number of input process parameters and conflicting responses. This study discusses the development of adaptive neuro-fuzzy inference system-based models for the prediction of quality measures of two thin-film deposition processes, i.e., SiCN thin-film coating using thermal chemical vapor deposition (CVD) process and Ni–Cr alloy thin-film coating using direct current magnetron sputtering process. The predicted response values obtained from the developed models are validated and compared based on actual experimental results which exhibit a very close match between both the values. The corresponding surface plots obtained from the developed models illustrate the effect of each process parameter on the considered responses. These plots will help the operator in selecting the best parametric mix to achieve enhanced coating quality. Also, analysis of variance results identifies the importance of each process parameter in the determination of response values. The proposed approach can be applied to various deposition processes for modeling and prediction of observed response values. It will also assist as an operator in selecting the best parametric mix for achieving desired response values.