Adaptive Neuro-fuzzy Inference System Method Research Articles

Computer-Aided Neuro-fuzzy Algorithm for Prediction of Ginger(Zingiber officinale) Rhizome Drying

Neuro-fuzzy modeling technique has been used for the development of computer-based adaptive process control systems for most postharvest operations instead of convectional mechanistic modeling technique owing to its good prediction without prior knowledge of process operation. Therefore, adaptive neuro-fuzzy inference system (ANFIS) modeling and prediction of ginger (Zingiber officinale) rhizome moisture content in a forced convective tray dryer was investigated in this study. Computer codes for an exhaustive search and grid partitioning were written in the Matlab software environment and used for the analysis of experimental data obtained from the ginger rhizome drying experiment. The data were trained and checked using the grid-partitioning ANFIS method for the development of neuro-fuzzy network for ginger drying prediction. The prediction accuracy of the network was evaluated by varying input and output Membership Function (MF) types. The exhaustive search analysis shows that drying time (DT) has the highest effect on the moisture content, followed by air drying temperature (ADT), air relative humidity (ARH), and air flow velocity (AFV). Moreover, combination of DT and ADT as two interactive variables; and combination DT, ADT and ARH as three interactive variables show highest effect on ginger moisture content removal during the process. Generalized bell (gbell) MF with two MF for each input variable and constant output MF 2 type were obtained as the best ginger drying ANFIS network with corresponding R and MSE of 0.9667 and 0.0971, respectively. Therefore, this study shows the reliability of the ANFIS model for the prediction of ginger rhizome drying in a tray dryer.

Computer-Aided Neuro-fuzzy Algorithm for Prediction of Ginger(Zingiber officinale) Rhizome Drying

Neuro-fuzzy modeling technique has been used for the development of computer-based adaptive process control systems for most postharvest operations instead of convectional mechanistic modeling technique owing to its good prediction without prior knowledge of process operation. Therefore, adaptive neuro-fuzzy inference system (ANFIS) modeling and prediction of ginger (Zingiber officinale) rhizome moisture content in a forced convective tray dryer was investigated in this study. Computer codes for an exhaustive search and grid partitioning were written in the Matlab software environment and used for the analysis of experimental data obtained from the ginger rhizome drying experiment. The data were trained and checked using the grid-partitioning ANFIS method for the development of neuro-fuzzy network for ginger drying prediction. The prediction accuracy of the network was evaluated by varying input and output Membership Function (MF) types. The exhaustive search analysis shows that drying time (DT) has the highest effect on the moisture content, followed by air drying temperature (ADT), air relative humidity (ARH), and air flow velocity (AFV). Moreover, combination of DT and ADT as two interactive variables; and combination DT, ADT and ARH as three interactive variables show highest effect on ginger moisture content removal during the process. Generalized bell (gbell) MF with two MF for each input variable and constant output MF 2 type were obtained as the best ginger drying ANFIS network with corresponding R and MSE of 0.9667 and 0.0971, respectively. Therefore, this study shows the reliability of the ANFIS model for the prediction of ginger rhizome drying in a tray dryer.

A Novel Method for Accurate Pressure Drop Prediction in Horizontal and Near Horizontal Pipes using Adaptive Neuro Fuzzy Inference System Based Model

Effective flow line and piping network design depends on the accurate prediction of pressure drop in multiphase flow for horizontal and near horizontal pipes. Since early 1950, several empirical correlations and mechanistic models have been developed to predict pressure drop. All correlations used by the industry, in addition to their applicability limitations, fall short of providing the necessary precision of pressure drop predictions. However, compared to empirical correlations, the recently developed mechanistic models improved pressure drop prediction. To design and construct more dependable and economical surface piping networks and wells, it is still necessary to improve prediction accuracy. This study uses the Adaptive Neuro-Fuzzy Inference System (ANFIS) to create a model that predicts pressure drop in horizontal and near-horizontal pipelines with greater accuracy and simplicity. Using the ANFIS method, the fuzzy modelling procedure can gather knowledge about a set of data to determine the membership function parameters that will enable the associated fuzzy inference system to track input/output data most effectively. The model was created and tested using field data encompassing various variables. The model was developed using 450 different data sets that were collected from the Asian continent. 113 data sets were used for testing, and a total of 337 data sets were used for training. Trend analysis was carried out during the model development phase prior to the model's completion. This is performed to make sure the model is stable and to make sure the created model is physically sound and accurately simulates the real physical process. To determine the percentage of error between the predicted value and the actual measured data, statistical analysis was carried out. To compare the performance of the new ANFIS model to earlier empirical correlations and mechanistic models, graphical and statistical techniques were also used. The new model outperformed known correlations and the most recent mechanistic models by a significant margin in producing incredibly accurate pressure drop predictions. The Dukler empirical correlation, Beggs and Brill empirical correlation, Xiao mechanistic model, and Gomez mechanistic model had values of 25.284, 20.940, 30.122, and 20.817, respectively, while the ANFIS model had a value of 13.256 for the lowest average absolute percentage error. Additionally, the Duckler and Beggs & Brill models came in second and third, with values of 0.908 and 0.906, respectively, and the ANFIS model had the highest coefficient of determination at 0.955.

KONTROL FREKUENSI BEBAN MENGGUNAKAN METODE ADAPTIVE NEURO FUZZY INFERENCE SYSTEM (ANFIS) PADA SISTEM HYBRID WIND MIKROHIDRO DAN DIESEL

This study aims to analyze and compare the performance of three frequency load controller methods in a hybrid generator consisting of three types of energy generation, namely microhydro, diesel and wind. The controller methods being compared are the PID (Proportional Integral Derivative) method, ANFIS (Adaptive Neuro-Fuzzy Inference System), and Fuzzy. This analysis was carried out to improve the efficiency and stability of the hybrid generating system by optimizing the frequency load controller. Frequency instability can occur due to load fluctuations, changes in environmental conditions, or system disturbances. Therefore, the use of an effective and adaptive controller method is very important in maintaining the stability and reliability of the hybrid generator system. The analytical method used in this study involved data collection and computer modeling. The required data includes information on load variations, energy production, and environmental conditions. Furthermore, the PID, ANFIS, and Fuzzy methods are applied to the data to build a frequency load controller model. The results of the analysis show that the three controller methods have different performance in maintaining frequency stability in the hybrid generator system. The PID method provides a fast and accurate response to load fluctuations, but is less adaptive to environmental changes. While the ANFIS method is able to adapt well to changes in system conditions, it requires time for model training. Fuzzy methods can provide control that is more adaptive and tolerant to disturbances, but may require more complex tuning. However, in general, the use of intelligent controller methods such as ANFIS and Fuzzy can improve the performance of hybrid generators by producing more adaptive and stable controls. This research has important implications for the development of more efficient and reliable hybrid power systems. By choosing the right controller method, hybrid power plants can provide energy in a more stable and environmentally friendly manner, and reduce dependence on limited fossil resources. Therefore, this research can make a significant contribution to the development of renewable energy and sustainable development in the future.

Academic Performance Assessment Prediction Model Using the Adaptive Neuro-Fuzzy Inference System Method

Performance evaluation of Human Resources is an important part of an organization or company. One of the HR in tertiary institutions that must be evaluated is academic performance. The author conducted research on the factors of academic performance assessment. Therefore, we need a system that can classify academic performance optimally in order to improve the quality of academic performance. In this research, we construct a predictive model for academic ability evaluation using Adaptive Neuro-Fuzzy Inference System method. The ANFIS method shows a very good data accuracy of 92.20%. From each variable motivation to work appraisal show is a Good, competence to work appraisal = Good, compensation to work appraisal show is a Good, responsibility to work appraisal show is a Good, and job satisfaction to work assessment show is Good.

Leaf area estimation in lettuce: Comparison of artificial intelligence-based methods with image analysis technique

Artificial intelligence (AI) as a simulation approach is increasingly being used in precision agriculture. The current study evaluated the performance of five methods for estimating lettuce leaf area (LA), including simple linear regression (SLR), artificial neural networks (ANNs), adaptive neuro fuzzy inference system (ANFIS), support vector regression (SVR), and image analysis technique. The standardized Ranking Performance Index (sRPI) was used to determine the overall ranking of the simulation approaches. Image analysis and ANFIS methods were found to have superior performance to other methods evaluated, according to the evaluation criteria of R2 values of 0.98 and 0.92, and RRMSE values of 4.3 and 2.32, respectively. The SLR, on the other hand, was found to be the least ranked method. Overall, the results indicated that the image analysis method could be a cost-effective option, and the ANFIS method could serve as a non-destructive alternative to conventional LA determination methods.

Optimization of ultrasonic-excited double-pipe heat exchanger with machine learning and PSO

Two intelligent optimization methods, artificial neural networks (ANNs) and adaptive neuro-fuzzy inference system (ANFIS), with particle swarm optimization (PSO), were employed in this study to forecast the heat transfer rate, Nusselt number, number of transfer units (NTU), and effectiveness of a double-pipe counter-flow heat exchanger. The experiments are related to hot flow rate (113–257 l/h), hot fluid inlet temperature (40–60 °C), ultrasonic excitation power level (0 or 60 watts), and volume fraction of nanoparticle (0–0.8%). The findings of the ANN, ANFIS, ANN-PSO, and ANFIS-PSO methods were verified through experimental studies. The ANN model, the multilayer perceptron/backpropagation with three different learning algorithms, the Levenberg Marquardt (LM), the scaled conjugate gradient (SCG), the Bayesian regularization algorithm (BR), and the ANFIS model were developed with backpropagation and the optimal hybrid method. Finally, these two models were optimized using the PSO algorithm. The experimental and predicted data were compared, and both models were found to be accurate. The correlation coefficients of both models were greater than 94.84%, with the ANN-PSO model slightly outperforming the ANFIS-PSO model. Also, the maximum amount of MSE is equal to 2.592, which shows the model has good performance in predicting results.

Multi-Extremum Adaptive Fuzzy Network Method for Dynamic Reliability Estimation Method of Vectoring Exhaust Nozzle

To enhance the accuracy and efficiency of reliability analysis for an aero-engine vectoring exhaust nozzle (VEN), a multi-extremum adaptive fuzzy network (MEAFN) method is developed by absorbing an adaptive neuro-fuzzy inference system (ANFIS) into the multi-extremum surrogate model (MESM) method. In the proposed method, the MERSM is used to establish the surrogate models of many output responses for the multi-objective integrated reliability analysis of the VEN. The ANFIS method is regarded as the basis function of the MESM method and adopted to improve the modeling precision of the MESM by introducing the membership degree into the input parameters and weights to improve the approximation capability of the neural network model to the high nonlinear reliability analysis of the VEN. The mathematical model of the MEAFN method and reliability analysis thoughts of the VEN is provided in this study. Then, the proposed MEAFN method is applied to conduct the dynamic reliability analysis of the expansion sheet and the triangular connecting rod in the VEN by considering the aerodynamic loads, operation temperature, and material parameters as the random input variables and the stresses and deformations as the output responses, compared with the Monte Carlo method and the extremum response surface method. From the comparison of the methods, it is indicated that the MEAFN method is promising to improve computational efficiency while maintaining accuracy. The efforts of this study provide guidance for the optimization design of the VEN and enrich the reliability theory of the flexible mechanism.

Comparison of performances of fuzzy logic and adaptive neuro-fuzzy inference system (ANFIS) for estimating employee labor loss

As a result of artificial intelligence research that started in the 1950s, the need for human beings in all sectors and labor markets constantly decreases. The increase in the total cost of the labor force increases the productivity pressure on the labor. For this reason, the workforce participating in production is expected to be more efficient and productive. For this reason, the loss of labor is carefully monitored and tried to be reduced as much as possible. However, with each passing day, labor losses are inevitable due to personnel turnover, work accidents, dismissals, and absenteeism. Humanity is still struggling, mainly due to the contagious covid-19 virus, which has recently affected the world. Since it is a condition that affects human health, its adverse effects have been observed in many areas where people are present. Especially in this period, unpredictable workforce losses have occurred in the production and service sectors since people are mostly the primary workforce. Since there is no plan and measure for such a situation in most risk planning, it also brings labor losses and costs. In this study, In order to examine the relationship between health problems and loss of labor, the amount of lost labor due to employees who could not come to work due to health-related reasons was tried to be estimated by Fuzzy Logic and ANFIS methods. This study examined three-year absenteeism data of employees in a courier company, and twenty-eight reasons for absenteeism were determined. The amount of labor loss was estimated using Fuzzy Logic and ANFIS methods, using five factors that cause absenteeism. Estimated and actual values were statistically compared with MAD MAPE, MSE, and RMSE performance measurement values. With fuzzy logic, the MAD value is 4.76; the MAPE value is 155.7; The MSE value was calculated as 52.7, and the RMSE value as 7.26. In ANFIS, the MAD value is 3.2, the MAPE value of 86.24, MSE of 27.5; The RMSE value was calculated as 5.25. When the results are compared, it has been seen that the ANFIS method obtains closer estimations than the fuzzy logic method.

A Hybridized Machine Learning Approach for Predicting COVID-19 Using Adaptive Neuro-Fuzzy Inference System and Reptile Search Algorithm.

This research is aimed to escalate Adaptive Neuro-Fuzzy Inference System (ANFIS) functioning in order to ensure the veracity of existing time-series modeling. The COVID-19 pandemic has been a global threat for the past three years. Therefore, advanced forecasting of confirmed infection cases is extremely essential to alleviate the crisis brought out by COVID-19. An adaptive neuro-fuzzy inference system-reptile search algorithm (ANFIS-RSA) is developed to effectively anticipate COVID-19 cases. The proposed model integrates a machine-learning model (ANFIS) with a nature-inspired Reptile Search Algorithm (RSA). The RSA technique is used to modulate the parameters in order to improve the ANFIS modeling. Since the performance of the ANFIS model is dependent on optimizing parameters, the statistics of infected cases in China and India were employed through data obtained from WHO reports. To ensure the accuracy of our estimations, corresponding error indicators such as RMSE, RMSRE, MAE, and MAPE were evaluated using the coefficient of determination (R2). The recommended approach employed on the China dataset was compared with other upgraded ANFIS methods to identify the best error metrics, resulting in an R2 value of 0.9775. ANFIS-CEBAS and Flower Pollination Algorithm and Salp Swarm Algorithm (FPASSA-ANFIS) attained values of 0.9645 and 0.9763, respectively. Furthermore, the ANFIS-RSA technique was used on the India dataset to examine its efficiency and acquired the best R2 value (0.98). Consequently, the suggested technique was found to be more beneficial for high-precision forecasting of COVID-19 on time-series data.

Voice Recognition as a Mobile Robot Controller with the Adaptive Neuro-Fuzzy Inference System Method

Voice recognition or speech recognition is a biometric technology that has very wide applications, one of which is for simple robot motion control. There are three stages in this research, namely data acquisition, feature extraction, and data classification. For feature extraction, the wavelet transform method is used which can analyze non-stationary and non-linear signals, while for data classification, the Adaptive Neuro-Fuzzy Inference System (Anfis) method is used. The result of data classification is 92.25% and 7.75% error. So, based on the results of the classification accuracy, the robot can be moved via voice commands and to anticipate the error value, the ultrasonic sensor feature is added to the robot as an alternative control.

Comparison of Wavelet Artificial Neural Network, Wavelet Support Vector Machine, and Adaptive Neuro-Fuzzy Inference System Methods in Estimating Total Solar Radiation in Iraq

Estimating the amount of solar radiation is very important in evaluating the amount of energy that can be received from the sun for the construction of solar power plants. Using machine learning tools to estimate solar energy can be a helpful method. With a high number of sunny days, Iraq has a high potential for using solar energy. This study used the Wavelet Artificial Neural Network (WANN), Wavelet Support Vector Machine (WSVM), and Adaptive Neuro-Fuzzy Inference System (ANFIS) techniques to estimate solar energy at Wasit and Dhi Qar stations in Iraq. RMSE, EMA, R2, and IA criteria were used to evaluate the performance of the techniques and compare the results with the actual measured value. The results showed that the WANN and WSVM methods had similar results in solar energy modeling. However, the results of the WANN technique were slightly better than the WSVM technique. In Wasit and Dhi Qar stations, the value of R2 for the WANN and WSVM methods was 0.89 and 0.86, respectively. The value of R2 in the WANN and WSVM methods in Wasit and Dhi Qar stations was 0.88 and 0.87, respectively. The ANFIS technique also obtained acceptable results. However, compared to the other two techniques, the ANFIS results were lower, and the R2 value was 0.84 and 0.83 in Wasit and Dhi Qar stations, respectively.

Determination of qualified human resources using the ANFIS method

To improve the quality of education is very closely related to the problem of human resources. One of the main key in creating professional human resource lies in the recruitment process, workforce selection and training. Finding a professional and qualified workforce is not easy and a must in an organization or university in screening new employees or lecturers. Therefore we need a system for organizations and universities to be able to get the right people, qualified and placed according to their abilities. This research was conducted using quantitative descriptive research methods and data collection methods in the form of questionnaires and using Adaptive Neuro-Fuzzy Inference System (ANFIS). From the results of testing the data this algorithm shows a data accuracy rate of 77 percent 
 Keywords: HR, ANFIS, questionnaire, quantitative description

Application of Intelligent Adaptive Neuro Fuzzy Method for Reusability of Component Based Software System

Component Based Software System (CBSS) provides an easy and efficient way to develop new software application with the help of existing software components of similar functionalities. It increases the reusability of software components and reduce the development time, cost and effort of software developers. To select the appropriate component, it become essential to assess the reusability of software components so that suitable component can be selected to reuse in another application. For assessing the reusability of CBSS, several factors are required to be considered. In this paper, four reusability sub-factors Interface Complexity (IC), Understandability (Un), Customizability (Co) and Reliability (Re) are used as input variables and reusability is assessed using Fuzzy Inference System (FIS) and Adaptive Neuro Fuzzy Inference System (ANFIS) approach because these two approaches are commonly used approach for assessing the quality factors. For experimental work, one case study has been done where rules are generated to assess reusability using four different reusability factors by taking feedback from researchers and academicians using online survey. Reusability was assessed for ten different values of input variables. Experiment shows that results obtained from ANFIS method were closer to the original values. Root Mean Square Error (RMSE) of FIS results was 6.05% which was further reduced by the application of ANFIS approach and finally 2.20% of RMSE was achieved. This research work will be helpful for software developers and researchers to assess the reusability of software components and they will be able to take corrective decision for choosing the appropriate component to be reused in new software applications, which will reduce their effort, time and cost of development

Aquila Optimization with Machine Learning-Based Anomaly Detection Technique in Cyber-Physical Systems

Cyber-physical system (CPS) is a concept that integrates every computer-driven system interacting closely with its physical environment. Internet-of-things (IoT) is a union of devices and technologies that provide universal interconnection mechanisms between the physical and digital worlds. Since the complexity level of the CPS increases, an adversary attack becomes possible in several ways. Assuring security is a vital aspect of the CPS environment. Due to the massive surge in the data size, the design of anomaly detection techniques becomes a challenging issue, and domain-specific knowledge can be applied to resolve it. This article develops an Aquila Optimizer with Parameter Tuned Machine Learning Based Anomaly Detection (AOPTML-AD) technique in the CPS environment. The presented AOPTML-AD model intends to recognize and detect abnormal behaviour in the CPS environment. The presented AOPTML-AD framework initially pre-processes the network data by converting them into a compatible format. Besides, the improved Aquila optimization algorithm-based feature selection (IAOA-FS) algorithm is designed to choose an optimal feature subset. Along with that, the chimp optimization algorithm (ChOA) with an adaptive neuro-fuzzy inference system (ANFIS) model can be employed to recognise anomalies in the CPS environment. The ChOA is applied for optimal adjusting of the membership function (MF) indulged in the ANFIS method. The performance validation of the AOPTML-AD algorithm is carried out using the benchmark dataset. The extensive comparative study reported the better performance of the AOPTML-AD technique compared to recent models, with an accuracy of 99.37%.

A Comparative Analysis of Maximum Power Point Techniques for Solar Photovoltaic Systems

The characteristics of a PV (photovoltaic) module is non-linear and vary with nature. The tracking of maximum power point (MPP) at various atmospheric conditions is essential for the reliable operation of solar-integrated power generation units. This paper compares the most widely used maximum power point tracking (MPPT) techniques such as the perturb and observe method (P&O), incremental conductance method (INC), fuzzy logic controller method (FLC), neural network (NN) model, and adaptive neuro-fuzzy inference system method (ANFIS) with the modern approach of the hybrid method (neural network + P&O) for PV systems. The hybrid method combines the strength of the neural network and P&O in a single framework. The PV system is composed of a PV panel, converter, MPPT unit, and load modelled using MATLAB/Simulink. These methods differ in their characteristics such as convergence speed, ease of implementation, sensors used, cost, and range of efficiencies. Based on all these, performances are evaluated. In this analysis, the drawbacks of the methods are studied, and wastage of the panel’s available output energy is observed. The hybrid technique concedes a spontaneous recovery during dynamic changes in environmental conditions. The simulation results illustrate the improvements obtained by the hybrid method in comparison to other techniques.

Automatic diagnosis of schizophrenia and attention deficit hyperactivity disorder in rs-fMRI modality using convolutional autoencoder model and interval type-2 fuzzy regression.

Nowadays, many people worldwide suffer from brain disorders, and their health is in danger. So far, numerous methods have been proposed for the diagnosis of Schizophrenia (SZ) and attention deficit hyperactivity disorder (ADHD), among which functional magnetic resonance imaging (fMRI) modalities are known as a popular method among physicians. This paper presents an SZ and ADHD intelligent detection method of resting-state fMRI (rs-fMRI) modality using a new deep learning method. The University of California Los Angeles dataset, which contains the rs-fMRI modalities of SZ and ADHD patients, has been used for experiments. The FMRIB software library toolbox first performed preprocessing on rs-fMRI data. Then, a convolutional Autoencoder model with the proposed number of layers is used to extract features from rs-fMRI data. In the classification step, a new fuzzy method called interval type-2 fuzzy regression (IT2FR) is introduced and then optimized by genetic algorithm, particle swarm optimization, and gray wolf optimization (GWO) techniques. Also, the results of IT2FR methods are compared with multilayer perceptron, k-nearest neighbors, support vector machine, random forest, and decision tree, and adaptive neuro-fuzzy inference system methods. The experiment results show that the IT2FR method with the GWO optimization algorithm has achieved satisfactory results compared to other classifier methods. Finally, the proposed classification technique was able to provide 72.71% accuracy.

Improving the ANFIS Forecating Model for Time Series Based on the Fuzzy Cluster Analysis Algorithm

This paper proposes the forecasting model for the time series based on the improvement of the adaptive neuro-fuzzy inference system (ANFIS) method and the fuzzy cluster analysis (FCA) algorithm. In this model, (i) the authors firstly find the appropriate number of groups for the series. Then, (ii) this study determines the specific elements for each group based on the established fuzzy relationship. Finally, using the results of (i) and (ii) as the input variables, the authors improve the iterations of ANFIS method. Combining the above improvements, the efficient forecasting model for time series is proposed. The proposed model is illustrated step by step through a numerical example, and implemented rapidly by the established Matlab procedure. The experiment obtained from this model shows the outstanding advantages in comparison with the existing ones. This research can be applied well to forecast for many fields in reality.

Safety assessment: predicting fatality rates in methanol plant incidents

In this article, the prediction of fatality accident rate at methanol (MeOH) plant was studied using different assessment methods. The prediction method was performed and simulated using HYSYS, ALOHA, MARPLOT, and MATLAB software. Recent studies for pressure variation up to 442 bar in MeOH synthesis by carbon dioxide (CO2) hydrogenation showed that three times more MeOH was produced than in conventional plants, with 90% CO2 conversion and 95% MeOH selectivity. However, safety concerns were noted when MeOH production was operated at pressures above 76–500 bar. Therefore, a safety assessment of the pressures between 76 and 500 bar was performed to predict the fatality rate at the MeOH plant. Adaptive Neuro-Fuzzy Inference System (ANFIS) was compared with a conventional analysis by using the consequence method to predict the fatality rate. First, 26 input parameters were simulated in HYSYS, ALOHA, and MARPLOT software by using the consequence method. Then, the input parameters were reduced to six, namely, pressure, mass, volume, leakage size, wind speed, and wind direction, for prediction using ANFIS tool in MATLAB. This study aimed to highlight the accuracy of the fatality rate prediction by using the ANFIS method. In this manner, accurate prediction of fatality rate for MeOH plant incidents was achieved. The prediction values for the ANFIS method was validated using the standard error of the regression. The percent error measurement obtained the lowest regression of 0.0088 and the lowest percent error of 0.02% for Hydrogen (H2) Vapor Cloud Explosion (VCE) ident. Therefore, the ANFIS method was found to be a simpler and alternative prediction method for the fatality rate than the conventional consequence method.

A new hybrid risk assessment method based on Fine-Kinney and ANFIS methods for evaluation spatial risks in nursing homes

Today, as the elderly population in the world increases, the increase in those living in nursing homes causes their problems to be even more important. Spatial hazards cause injury and death most of the time, therefore should be evaluated risks then corrective and preventive actions should be implemented. Fine-Kinney is one of the most widely used risk assessment methods, but it has some shortcomings. One of them is that risk factors such as probability, frequency, and severity are accepted as equally important, but they can have different importance weights in real-life applications. Another is that experts assess the risk magnitudes using their opinions, who usually tend to use linguistic expressions instead of crisp numbers, in incomplete information and uncertain situations. The last is that the experts' experiences are not effectively incorporated into the automation of the risk assessment. The adaptive neuro-fuzzy inference system (ANFIS) method, which is a machine learning method, can overcome all these shortcomings.In this study, a novel hybrid risk assessment method based on Fine-Kinney and ANFIS is developed to predict the class of a new occurring risk. The hybrid method was applied to nursing homes located in Turkey. The risk classes predicted with the hybrid method were compared to ones found in the traditional Fine-Kinney method. It was determined that the prediction accuracy and Fleiss kappa value of the new hybrid method were 95.745% and 0.929 respectively. Thus, the hybrid method can be used instead of the traditional Fine-Kinney method to determine the class of a new risk, because it does not require a large number of experts and provides a faster assessment.