MCMI-ANFIS: A robust multi class multiple instance Adaptive Neuro-Fuzzy Inference System

Accurate software effort estimation has a big importance for software companies for the reason that management of the project, control of the project, financial matters and timely deliveries are achieved with effort estimation. Thus, effort estimation plays vital role for software companies. In this study, software effort estimation is predicted by using Multilayer Perceptron and Adaptive Neuro Fuzzy Inference System. As a dataset, NASA 93 with 93 projects and Desharnais with 77 projects are used. The results show that Mean Magnitude Relative Error of Adaptive Neuro Fuzzy Inference System is lower than Multilayer Perceptron. In addition, it is seen that PRED(0.25) value of Adaptive Neuro Fuzzy Inference System is higher than Multilayer Perceptron. Thus, performance of Adaptive Neuro Fuzzy Inference System is better when compared to performance of Multilayer Perceptron.

In complex industrial processes (CIPs), due to technical and economic limitations, key performance indicators (KPIs), especially the chemical content-related KPIs, are often difficult to measure in real time, which hinders the propagation of advanced process control technologies. This paper presents a soft sensor-based online KPI inference scheme by a state transition algorithm (STA)-optimized adaptive pre-sparse neuro-fuzzy inference system model, called STA-APSNFIS. It introduces a pre-sparse neural network to the traditional adaptive neuro-fuzzy inference system (ANFIS) model to establish an adaptive pre-sparse neuro-fuzzy inference system (APSNFIS) model to alleviate the adverse effects of data redundancy and noise interference in the detectable process monitoring data, which can effectively reduce the complexity of neuro-fuzzy inference system (NFIS) and speed up its convergence. Successively, to avoid being trapped at a local optimum, the STA-based optimization algorithm is adopted to replace the traditional gradient-based optimization approach to achieve an optimal APSNFIS model. Extensive validation and comparative experiments on nonlinear numeric simulation systems, benchmark Tenessee Eastman (TE) process and a real industrial bauxite flotation process demonstrated that the proposed STA-APSNFIS performed favorably against traditional ANFIS model as well as its variants, e.g., PSO-ANFIS, GA-ANFIS, and some other soft sensor-based KPI inference models.

For describing nonlinear system accurately and improving adaptive neuro-fuzzy inference system model, a quantum-inspired evolutionary algorithm is presented for optimizing parameters of adaptive neuro-fuzzy inference system. In this paper, an allele real-coded quantum evolutionary algorithm is introduced to optimize the premise and consequent parameters of adaptive neuro-fuzzy inference system. The real-coding method based on allele is adopted, and variable-scale updating strategy of parameter is employed. As a result, the parameter falling into local minimum is avoided. The model accuracy of adaptive neuro-fuzzy inference system is improved. The simulation examples show the effectiveness of proposed method. The proposed improved algorithm is compared with the standard adaptive neuro-fuzzy inference system. Finally, the proposed adaptive neuro-fuzzy inference system model is applied to predict the quality index in textile slashing process.

In this paper, a hybrid meta-heuristic artificial intelligence (AI) method, named “ANFIS–PSOGA,” is developed for modeling the discharge coefficient of circular side orifices for the first time. For this purpose, the adaptive neuro fuzzy inference system (ANFIS) network is optimized by means of two robust optimization algorithms: the genetic algorithm (GA) and the particle swarm optimization (PSO) algorithm. Furthermore, the Monte Carlo simulations are utilized to enhance the performance of the AI hybrid model. Besides, the k-fold cross-validation method is employed in order to verify the numerical results. Initially, the performance of three fuzzy inference system (FIS) generations of the ANFIS model including grid partitioning, subtractive clustering and fuzzy C-means clustering are evaluated. After that, using the parameters affecting the discharge coefficient, eleven ANFIS models are defined and then the best ANFIS model and the most influencing input parameters are identified through the conduction of a sensitivity analysis. For the superior ANFIS model, mean absolute percentage error, root-mean-square error and the correlation coefficient (R) are obtained 0.021, 0.020 and 0.871, respectively. Also, the Froude number (Fr) is detected as the most effective input parameter. Moreover, the discharge coefficient of the circular side orifices and the flow field within main channels along the side orifices are simulated through the adoption of a computational fluid dynamics (CFD) model. Additionally, the flow field at three different cross sections (beginning, middle and end of orifice) along the side weir is evaluated. For instance, by advancing the flow toward the side orifice, the Froude number is reduced. Besides, at each cross section, the maximum shear stress is estimated to occur in the vicinity of the crest of the circular side orifice. According to the CFD results, the maximum lateral velocity is estimated near the circular side orifice. In addition, the results yielded by the ANFIS, ANFIS–PSO, ANFIS–PSOGA and CFD models are compared and an uncertainty analysis is carried out for the models. Based on the comparison, ANFIS–PSOGA has the best performance in simulating the discharge coefficient. Ultimately, a simple and practical computer code for the best model (ANFIS–PSOGA) is proposed which can be easily used by scholars and engineers in practical usages.

Machine learning methods such as Adaptive Network-Based Fuzzy Inference System (ANFIS) have been widely employed in intelligent urban storm water disaster warning for the purpose of smart city. However, there exists lack of research proposed for applying ANFIS and mobile application (App) to reach the purpose of smart city. In order to accomplish the goal, the study integrates ANFIS and Qt Framework to develop a Typhoon Rainfall Forecasting System to real-time typhoon rainfall forecast via a mobile device. The Service is first built by applying cluster analysis to typhoon data (Tamsui Weather Station of Taiwan) during June 1967 and November 2020 to classify the data into four groups and then applying the ANFIS to construct the Service with data in each group. The fuzzy rule of ANFIS is established by grid partition method. Both the Service and App employ Qt Framework as the cross-operating development tool, and the App is transformed to a smart mobile device App of different platforms. The simulated results show the following: (1) Taking the example of typhoon Nakri in group 1, the lowest root mean square error (7.898 mm) and the lowest computation time (178 sec) were obtained for training with 1000 steps and three membership functions. (2) Using the optimal parameters of the typhoon belonging to that group can obtain better prediction results. The developed typhoon rainfall forecasting system App in the supplementary information demonstrates that the user can use the smart mobile device for real-time typhoon forecasting at the most three hours ahead easily.

Computational intelligence (CI) tools have been successfully applied in different fields with superior performances. Neuro-fuzzy system (NFS) is one the approach which combines the benefits of two powerful CI tools known as artificial neural networks (ANN) and fuzzy logic. Although NFS has attracted researchers in many areas of study, few of its applications have been undertaken in hydrological modeling. Adaptive Network-based Fuzzy Inference System (ANFIS) is so far the most established NFS technique and this study is an application of ANFIS in river stage prediction by using rainfall and stage antecedents as inputs in the tropical catchment of Bekok River in Malaysia. To evaluate the performance of the ANFIS model, it was compared with a traditional modeling technique known as autoregressive model with exogenous inputs (ARX). The results of this study were evaluated based on several statistical measures such as coefficient of efficiency (CE), coefficient of determination (r2), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). The results showed that ANFIS can successfully predict the river stage and it outperforms ARX model significantly. ANFIS was also found better in estimating peak river stages comparing to ARX model. This study demonstrates the auspicious potential of ANFIS in river stage modeling.

ERP projects’ failing to meet user expectations is a serious problem. This research develops an Adaptive Neuro Fuzzy Inference System (ANFIS) model, to predict the key ERP outcome “User Satisfaction” using causal factors present during an implementation as predictors. Data for training and testing the models was from a cross section of firms that had implemented ERPs. ANFIS is compared with other prediction techniques, ANN and MLRA. The results establish that ANFIS is able to predict outcome well with an error (RMSE) of 0.277 and outperforms ANN and MLRA with errors of 0.85 and 0.86 respectively. This study is expected to provide guidelines to managers and academia to predict ERP outcomes ex ante, and thereby enable corrective actions to redirect ailing projects.

Multiple-instance learning (MIL) is a variant of the traditional supervised learning. In MIL training examples are bags of instances and labels are associated with bags rather than individual instances. The standard MIL assumption indicates that a bag is labeled positive if at least one of its instances is labeled positive, and otherwise labeled negative. However, many MIL problems do not satisfy this assumption but the more general one that the class of a bag is jointly determined by multiple instances of the bag. To solve such problems, the authors of MILD proposed an efficient disambiguation method to identify the most discriminative instances in training bags and then converted MIL to the standard supervised learning. Nevertheless, MILD does not consider the generalization ability of its disambiguation method, leading to inferior performance compared to other baselines. In this paper, we try to improve the performance of MILD by considering the discrimination of its disambiguation method on the validation set. We have performed extensive experiments on the drug activity prediction and region-based image categorization tasks. The experimental results demonstrate that MILD outperforms other similar MIL algorithms by taking into account the generalization capability of its disambiguation method.

Glass fiber reinforced polyester (GFRP) composite materials are widely used in various applications. The prediction of wear values for composite materials is very complex and nonlinear phenomena. Artificial intelligence methods (AI) and expert systems such as artificial neural networks (ANNs) and fuzzy inference systems (FIS) have a series of properties on modeling nonlinear systems. In some situations, ANNs are insufficient under abrupt changes in input variables. Adaptive Neuro Fuzzy Inference System (ANFIS) is capable of integrating the linguistic expressions of FIS with the adaptation and learning skills of the ANNs. The aim of this study is to determine the optimum material content and working conditions in terms of wear resistance. This study proposes an ANFIS sub-clustering based prediction model for estimation of wear behavior of GFRP composites within various concentrations of materials and under diverse loads and speeds. Proposed ANFIS model extracted optimum concentrations and operating parameters to obtain the minimum wear rate. Due to the wear rate estimation model, optimum wear rate value is reached to 25.0013 (mm3/Nm)*10−6 at CaCO3, polystyrene, glass fiber, glass bead, alumina, load and speed values of 49%, 0%, 11%, 10%, 0.8%, 10 N and 100 rpm respectively. A high estimation capability (R2 = 0.964) has been achieved using ANFIS Model.

Due to the increasing need for intelligent systems, the adaptive neuro-fuzzy inference system (ANFIS) has recently attracted the attention of researchers in various scientific and engineering areas. The purpose of this work is to present the modeling of a photovoltaic power supply (PVPS) system using an ANFIS. For the modeling of the PVPS system, it is required to find suitable models for its different components (ANFIS PV-generator, ANFIS battery and ANFIS regulator) under variable climatic conditions. A database of measured weather data (global radiation, temperature and humidity) and electrical signals (photovoltaic, battery and regulator voltage and current) of a PVPS system installed in Tahifet (south of Algeria) has been recorded for the period from 1992 to 1997 using a data acquisition system. These data have been used for the modeling and simulation of the PVPS system. The ANFIS for the PV-generator, battery and regulator have been trained by using 10 signals recorded from the different components of the PVPS system. Each signal is represented by 365*5 values (complete 5-years). A set of data for 4-years have been used for the training of the ANFIS and data for 1-year has been used for the testing of the ANFIS. In this way, the ANFIS was trained to accept and handle a number of unusual cases. The comparison between actual and estimated values obtained from the ANFIS gave satisfactory results. The correlation coefficient between measured values and those estimated by the ANFIS gave good prediction accuracy of 98%. In addition, test results show that the ANFIS performed better than the artificial neural networks (ANN). Predicted electrical signals by the ANFIS can be used for several applications in PV systems.

<p>The release of dangerous chemicals in flood crises is a common and recurring phenomenon. Because due to the breakdown of the infrastructure in the year, the possibility of release of dangerous pollutants is expected more than before [1]. The present research has chosen a chemical factory with Glycerin tanks as a case study in the city of Liberec (Czech Republic). As acute exposure to these compounds leads to effects such as headaches, dizziness, bloating, nausea, vomiting, thirst, and diarrhea [2], the control of this pollution can significantly reduce the health risk impacts especially during floods. In the first step of this study, all the physics coordinates of the reservoirs were examined and evaluated in different conditions. In the next step, according to the experimental calculations, the volume of Glycerin release from the reservoirs and in the flood flow was evaluated. Risk analysis was done using the HAZard & OPerability study (HAZOP) technique. Risk Number in the HAZOP method is computed based on two factors containing Risk Possibility (RP) and Risk Intensity (RI) [3]. Both the values are determined according to prediction of Adaptive Neuro Fuzzy Inference System (ANFIS) [4] based on previous studies in different countries. The results demonstrated that the integrated HAZOP-ANFIS model has different performance in various flood flow conditions.</p> <p>RP value is predicted abased on three parameters include; rainfall value, mass of contaminant, and flood flow. Likewise, the RI is estimated in ANFIS method according to self-assimilative factor and continuity of floods [4]. The computations demonstrated that ANFIS technique has more than 0.9 correlation coefficient for prediction of both flood risk factors (RP and RI). Likewise, the sensitivity analysis of the prediction system is examined as per all the declared physical features which effects on RP and RI. Also, it should be mentioned that in the Glycerin content is in the range of 45%- 65% in the case study. Numerical analysis illustrated the performance of designed framework has more efficiency in the higher concentrations of the contamination. The suggested structure can be used as an early qualitative framework for acute effects of hazardous material emissions.</p> <p><strong>Keywords:</strong> <em>HAZOP risk assessment; ANFIS; Flood; Glycerin emissions; Chemical plant</em></p> <p>

Currently the purchases of drugs at Instalasi Farmasi RSU (IFRS) HKBP Balige are based on the examination of the amount of drugs usage. The purchases of drugs based on the examination of the amount of drugs usage cause frequent unplanned drugs purchases that must be hastened (cito) and purchases to other pharmacies. The purchases of cito and purchases to other pharmacies will inflict a financial loss to the patients, because when IFRS makes drugs purchases of cito or to other pharmacies, the cost of the drugs will be more expensive. Therefore, in this research, a prediction of drugs stock in IFRS HKBP Balige using Adaptive Neuro Fuzzy Inference System (ANFIS) will be carried out. ANFIS is a combination of Least Square Estimator (LSE) and Error Back Propagation (EBP) algorithms. ANFIS consists of forward pass and the backward pass learning. The sample data used to predict drugs stock in this research is data of drugs sales at the IFRS HKBP Balige from 2013 to 2015. From the results of drugs stock prediction research with ANFIS, obtained that number of errors of ANFIS model is 5.52%. Based on MAPE accuracy level evaluation, number of errors have an excellent rate so that it can be concluded that the predicted results of the drugs stock are good.

Recent developments in Artificial Intelligence (AI) and computational intelligence have made it viable in the construction industry and structural analysis. This study usesthe Adaptive Network-based Fuzzy Inference System (ANFIS) as a modelling tool to predict the strain in tie section for High Strength Self Compacting Concrete (HSSCC) deep beams. 3773 experimental data were collected. The input data andits corresponding strains in tie section as output data were recorded at all loading stages. Results from ANFIS are compared with the classical linear regression (LR). The comparison shows that the ANFIS's results are highly accurate, precise and satisfactory.

On-line measurement of physical parameters of solution means a great deal in the osmotic dehydration process of food. Ternary solution with NaCl and sucrose is widely employed in this process. This study aims at reconstructing concentrations of two components and estimating density, viscosity of this ternary solution with multifunctional sensing technique in which the multifunctional sensor was previously designed by the authors. In this work, ANFIS (Adaptive Network-Based Fuzzy Inference System) is adopted to be signal reconstruction algorithm for the multifunctional sensing technique. For obtaining number of fuzzy rules and more precise initial values of premise parameters, in the process of reconstructing and estimating, subtractive clustering and fuzzy c-means clustering are used to analyze input-output space of ANFIS. Experimental results with satisfactory accuracies proved the proposed multifunctional sensing technique with ANFIS algorithm is valuable in food industry.

Foetal Electrocardiogram (FECG) monitoring is a technique for obtaining important information about the condition of the foetus during pregnancy and labour. In this study, we propose a new method of using combination of hybrid soft-computing technique called Adaptive Neuro Fuzzy Inference System (ANFIS) along with wavelets to estimate the Maternal Electrocardiogram (MECG) and to extract the FECG signal from the mother's Abdominal Electrocardiogram (AECG). Two methods have been developed wherein: using wavelets as a pre-processing tool combined with ANFIS; using wavelet as a post-processing tool combined with ANFIS. The results obtained by both the methods were analysed in terms of Signal to Noise Ratio (SNR), correlation coefficients and with performance indices. These proposed methods successfully removed the artefacts and extracted the desired FECG signal.