Comparison of adaptive neuro-fuzzy inference system (ANFIS) and Gaussian processes for machine learning (GPML) algorithms for the prediction of skin temperature in lower limb prostheses

Estimating the Physical Properties of Nanofluids Using a Connectionist Intelligent Model Known as Gaussian Process Regression Approach

This work aims to develop a robust machine learning model for the prediction of the relative viscosity of nanoparticles (NPs) including Al2O3, TiO2, SiO2, CuO, SiC, and Ag based on the most important input parameters affecting them covering the size, concentration, thickness of the interfacial layer, and intensive properties of NPs. In order to develop a comprehensive artificial intelligence model in this study, sixty-nine data samples were collected. To this end, the Gaussian process regression approach with four basic function kernels (Matern, squared exponential, exponential, and rational quadratic) was exploited. It was found that Matern outperformed other models with R2 = 0.987, MARE (%) = 6.048, RMSE = 0.0577, and STD = 0.0574. This precise yet simple model can be a good alternative to the complex thermodynamic, mathematical-analytical models of the past.

Multi-objective optimization technique for trajectory planning of multi-humanoid robots in cluttered terrain

Humanoid robots hold a decent advantage over wheeled robots because of their ability to mimic human exile. The presented paper proposes a novel strategy for trajectory planning in a cluttered terrain using the hybridized controller modeled on the basis of modified MANFIS (multiple adaptive neuro-fuzzy inference system) and MOSFO (multi-objective sunflower optimization) techniques. The controller works in a two-step mechanism. The input parameters, i.e., obstacle distances and target direction, are first fed to the MANFIS controller, which generates a steering angle in both directions of an obstacle to dodge it. The intermediate steering angles are obtained based on the training model. The final steering angle to avoid obstacles is selected based on the direction of the target and additional obstacles in the path. It is further works as input for the MOSFO technique, which provides the ultimate steering angle. Using the proposed technique, various simulations are carried out in the WEBOT simulator, which shows a deviation under 5% when the results are validated in real-time experiments, revealing the technique to be robust. To resolve the complication of providing preference to the robot during deadlock condition in multi-humanoids system, the dining philosopher controller is implemented. The efficiency of the proposed technique is examined through the comparisons with the default controller of NAO based on toques produces at various joints that present an average improvement of 6.12%, 7.05% and 15.04% in ankle, knee and hip, respectively. It is further compared against the existed navigational strategy in multiple robot systems that also displays an acceptable improvement in travel length. In comparison in reference to the existing controller, the proposed technique emerges to be a clear winner by portraying its superiority.

Technical analysis of adaptive neuron fuzzy intelligent system in tennis serve

Serving is the most important hitting technique in tennis, and a good service receiving can instantly reverse the active and passive relationship between serve and receive on the tennis court, and control the rhythm of the court. The purpose of this study is to use an adaptive neuron fuzzy intelligent system to analyze some techniques of tennis serve. In this study, eight male players from the school tennis team were selected as the experimental subjects, whose sports level was above the national tennis level II. Ten weeks before the simulation test, the training time and frequency of 8 subjects were the same. In other words, 5 times a week, 2.5 hours±0.5 hours. The work engineering of adaptive fuzzy system firstly, in the off-line modeling stage, the adaptive fuzzy system uses the rule self splitting technology to generate the initial fuzzy rules, and uses the improved adaptive neural network algorithm to optimize the calculation; then according to the error between the system input and the predicted output, the independent variable is adjusted and replaced; at the same time, the adaptive fuzzy system is further used for calculation In the process of tennis serving, the nonlinear control variables are obtained online and applied to the fuzzy system for control. Next, in the experiment, the system was used to record the body’s movement and service scores during service. The experimental results show that during the service process, the maximum trunk torsion amplitude can reach 48.26 ° and the minimum is only 5.41 ° and the service score accounts for 81.41% and 80.47% of the total scores of the two sections respectively. This shows that the fuzzy system in this study can effectively analyze the service posture and score of athletes. It is concluded that the accurate calculation and analysis of tennis serve by adaptive neuron intelligent fuzzy system in this study is conducive to improve the tennis serviceability and competition performance of players. This research has made a certain contribution to the intellectualization of sports.

Intelligent Neutrosophic Diagnostic System for Cardiotocography Data

Cardiotocography data uncertainty is a critical task for the classification in biomedical field. Constructing good and efficient classifier via machine learning algorithms is necessary to help doctors in diagnosing the state of fetus heart rate. The proposed neutrosophic diagnostic system is an Interval Neutrosophic Rough Neural Network framework based on the backpropagation algorithm. It benefits from the advantages of neutrosophic set theory not only to improve the performance of rough neural networks but also to achieve a better performance than the other algorithms. The experimental results visualize the data using the boxplot for better understanding of attribute distribution. The performance measurement of the confusion matrix for the proposed framework is 95.1, 94.95, 95.2, and 95.1 concerning accuracy rate, precision, recall, and F1-score, respectively. WEKA application is used to analyse cardiotocography data performance measurement of different algorithms, e.g., neural network, decision table, the nearest neighbor, and rough neural network. The comparison with other algorithms shows that the proposed framework is both feasible and efficient classifier. Additionally, the receiver operation characteristic curve displays the proposed framework classifications of the pathologic, normal, and suspicious states by 0.93, 0.90, and 0.85 areas that are considered high and acceptable under the curve, respectively. Improving the performance measurements of the proposed framework by removing ineffective attributes via feature selection would be suitable advancement in the future. Moreover, the proposed framework can also be used in various real-life problems such as classification of coronavirus, social media, and satellite image.

Evaluation of ANN and ANFIS modeling ability in the prediction of AISI 1050 steel machining performance

In the development of an accurate modeling technique for the design of an efficient machining process, manufacturers must be able to identify the most suitable technique capable of producing a fast and accurate performance. This study evaluates the performance of the Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) models in predicting the machining responses (metal removal rate and tool wear) in an AIS steel turning operation. With data generated from carefully designed machining experimentation, the adequacies of the ANN and ANFIS techniques in modeling and predicting the responses were carefully analyzed and compared. Both techniques displayed excellent abilities in predicting the responses of the machining process. However, a comparison of both techniques indicates that ANN is relatively superior to the ANFIS techniques, considering the accuracy of its results in terms of the prediction errors obtained for the ANN and ANFIS of 6.1% and 11.5% for the MRR and 4.1% and 7.2% for the Tool wear respectively. The coefficient of correlation (R²) obtained from the analysis further confirms the preference of the ANN with a maximum value of 92.1% recorded using the ANN compared to that of the ANFIS of 73%. The experiment further reveals that the performance of the ANN technique can yield the most ideal results when the right parameters are employed.

Comparison of Machine Learning Algorithms for Structure State Prediction in Operational Load Monitoring

The aim of operational load monitoring is to make predictions about the remaining usability time of structures, which is extremely useful in aerospace industry where in-service life of aircraft structural components can be maximized, taking into account safety. In order to make such predictions, strain sensors are mounted to the structure, from which data are acquired during operational time. This allows to determine how many load cycles has the structure withstood so far. Continuous monitoring of the strain distribution of the whole structure can be complicated due to vicissitude nature of the loads. Sensors should be mounted in places where stress and strain accumulations occur, and due to experiencing variable loads, the number of required sensors may be high. In this work, different machine learning and artificial intelligence algorithms are implemented to predict the current safety factor of the structure in its most stressed point, based on relatively low number of strain measurements. Adaptive neuro-fuzzy inference systems (ANFIS), support-vector machines (SVM) and Gaussian processes for machine learning (GPML) are trained with simulation data, and their effectiveness is measured using data obtained from experiments. The proposed methods are compared to the earlier work where artificial neural networks (ANN) were proven to be efficiently used for reduction of the number of sensors in operational load monitoring processes. A numerical comparison of accuracy and computational time (taking into account possible real-time applications) between all considered methods is provided.

Spatial prediction of landslide susceptibility using hybrid support vector regression (SVR) and the adaptive neuro-fuzzy inference system (ANFIS) with various metaheuristic algorithms

Landslides are natural and sometimes quasi-natural hazards that are destructive to natural resources and cause loss of human life every year. Hence, preparing susceptibility maps for landslide monitoring is essential to minimizing their negative effects. The main aim of the current research was to develop landslide susceptibility maps for Icheon Township, South Korea, using hybrid Machin learning and metaheuristic algorithms, that is, the bee algorithm (Bee), the adaptive neuro-fuzzy inference system (ANFIS), support vector regression (SVR), and the grey wolf optimizer (GWO), and to compare their predictive accuracy. Based on identified landslide locations, an inventory map was prepared and divided into training and validation data sets (70%/30%). the predicated model outcomes were validated with root mean square error (RMSE), and area under receiver operating characteristic curve (AUC), and pairwise comparison values for the ANFIS, ANFIS-Bee, ANFIS-GWO, SVR, SVR-Bee, and SVR-GWO models were obtained. The area under the curve was obtained with the training and validation data sets. Based on the training data sets, AUC of 80%, 83%, 83%, 69%, 81%, and 80% were obtained for the SVR, SVR-GWO, SVR-Bee, ANFIS, ANFIS-GWO, and ANFIS-Bee models, respectively. For the validation data sets, values of 79%, 82%, 82%, 68%, 79%, and 79%, respectively, were obtained. The SVR-GWO and SVR-Bee models were the most predictive models in terms of constructing the exceptionally focused landslide susceptibility map, with little spatial variation in the highly susceptible classes. Furthermore, the MSE, RMSE, and pairwise comparisons indicated that the SVR-GWO and SVR-Bee models were superior models for this study township. In addition, ANFIS individually was not superior to the ensembles of ANFIS-GWO and ANFIS-Bee for landslide assessment. These landslide susceptibility maps provide a platform for land use planning with an eye toward sustainable development of infrastructure and damage reduction for Icheon Township.

Modelling and validation of magneto-rheological fluid damper behaviour under impact loading using interpolated multiple adaptive neuro-fuzzy inference system

Purpose

The objective of this paper is to develop a fast modelling technique for predicting magneto-rheological fluid damper behaviour under impact loading applications.

Design/methodology/approach

The adaptive neuro-fuzzy inference system (ANFIS) technique was adopted to predict the behaviour of a magneto-rheological fluid (MRF) damper through experimental characterisation data. In this study, an MRF damper manufactured by Lord Corporation was used for characterisation using an impact pendulum test rig. The experimental characterisation was carried out with various impact energies and constant input currents applied to the MRF damper.

Findings

This research provided a fast modelling technique with relatively less error in predicting MRF damper behaviour for the development of control strategies. Accordingly, the ANFIS model was able to predict MRF damper behaviour under impact loading and showed better performance than the modified Bouc–Wen model.

Research limitations/implications

This study only focused on modelling technique for a single type of MRF damper used for impact loading applications. It is possible for other applications, such as cyclic loading, random loadings and system identification, to be studied in future experiments.

Original/Value

Future researchers could apply the ANFIS model as an actuator model for the development of control strategies and analyse the control performance. The model also can be replicated in other industries with minor modifications to suit different needs.

An Improved and Adaptive Approach in ANFIS to Predict Knee Diseases

Artificial intelligence is emerging as a persuasive tool in the field of medical science. This research work also primarily focuses on the development of a tool to automate the diagnosis of inflammatory diseases of the knee joint. The tool will also assist the physicians and medical practitioners for diagnosis. The diseases considered for this research under inflammatory category are osteoarthritis, rheumatoid arthritis and osteonecrosis. A five-layer adaptive neuro-fuzzy (ANFIS) architecture was used to model the system. The ANFIS system works by mapping input parameters to the input membership functions, input membership functions are mapped to the rules generated by the ANFIS model which are further mapped to the output membership function. A comparative performance analysis of fuzzy system and ANFIS system is also done and results generated shows that the ANFIS system outperformed fuzzy system in terms of testing accuracy, sensitivity and specificity.

Oil Price Forecasting Using a Time-Varying Approach

The international crude oil market plays an important role in the global economy. This paper uses a variable time window and the polynomial decomposition method to define the trend term of time series and proposes a crude oil price forecasting method based on time-varying trend decomposition to describe the changes in trends over time and forecast crude oil prices. First, to characterize the time-varying characteristics of crude oil price trends, the basic concepts of post-position intervals, pre-position intervals and time-varying windows are defined. Second, a crude oil price series is decomposed with a time-varying window to determine the best fitting results. The parameter vector is used as a time-varying trend. Then, to quantitatively describe the continuation of the time-varying trend, the concept of the trend threshold is defined, and a corresponding algorithm for selecting the trend threshold is given. Finally, through the predicted trend thresholds, the historical reference data are selected, and the time-varying trend is combined to complete the crude oil price forecast. Through empirical research, it is found that the time-varying trend prediction model proposed in this paper achieves a better prediction than several common models. These results can provide suggestions and references for investors in the international crude oil market to understand the trends of oil prices and improve their investment decisions.

Deep learning and regression modelling of cloudless downward longwave radiation

Background

Though downward longwave radiation (DLR) models curb the paucity of data, they are mostly location dependent. Therefore, there is a need to evaluate their relevance given the increasing use of machine learning techniques. In this study, cloudless DLR estimates from regression models and soft computing models of neural networks (NN), support vector regression (SVR) and adaptive neuro-fuzzy inference system (ANFIS) were compared. Clear days from September 1992 to August 1994 and July 1995 to March 1998 in Ilorin (8.50 °N, 4.55 °E), Nigeria were considered, while the predictors for the models were water vapour pressure, e and air temperature, T.

Results

A new regression model in relation to the Boltzmann constant, σ: $$ \left(1.014\left(\frac{1.0\times {10}^{30}\times e}{T^{13}}\right)+0.699\right)\sigma {T}^4 $$1.0141.0×1030×eT13+0.699σT4, was better than other regression models and applicable at another location. Between 1 and 8, the sixth degree was the best polynomial kernel function in SVR models’ estimations of cloudless DLR. Though the new regression model was comparable to expert systems, ANFIS was still the best model due to its consistent high correlations and lowest estimation errors.

Conclusions

Experience-based computational procedures that combine enough logics with neural networks respond effectively to other data. Furthermore, the analytical relationship between water vapour pressure and air temperature in DLR’s mechanism should be redefined accordingly, while the sixth polynomial should be used as the default setting in SVR systems.

Multi-hazard probability assessment and mapping in Iran

Several areas of Iran are prone to numerous natural hazards. An effective multi-hazard risk reduction requires analysis of the individual hazards and their interplay. This research develops a multi-hazard probability map for three hazards (i.e. landslides, floods, and earthquakes) for the management of hazard-prone areas in Lorestan Province, Iran, using anew ensemble model named SWARA-ANFIS-GWO. First, based on flood and landslide occurrence maps, hazard-prone areas were identified and sub-divided into two subsets.70% of these locations were randomly chosen to be used for the construction of susceptibility maps, while the remaining 30% of the instances were used to assess the accuracy of the models. Then, eleven factors relating to terrain and land use were selected for the preparation of landslide and flood susceptibility maps. An earthquake map was prepared based on a probabilistic seismic hazard analysis (PSHA). The SWARA method was implemented for weighting contributing factors and evaluating spatial relationships between the three hazards and predisposing factors. Subsequently, the ANFIS approach was used to acquire weights for each value while using a gray Wolf metaheuristic algorithm. Finally, all weight values were further assessed using the MATLAB software. The predicated results from the models were validated with ROC (rate of change) curves. The resulting AUCs (area under the curve) of the validation data indicated accuracies of 84% and 80% for floods and landslides, respectively, and 87% and 82.6%for flood and landslides based on the training data, respectively. Finally, the flood, landslide, and earthquake maps were combined to create a multi-hazard probability map of the Lorestan Province. This multi-hazard map serves as a valuable tool for land use planning and sustainable infrastructure development for the Lorestan Province.

Computational techniques applied to volume and biomass estimation of trees in Brazilian savanna

The Brazilian Savannah, known as Cerrado, has the richest flora in the world among the savannas, with a high degree of endemic species. Despite the global ecological importance of the Cerrado, there are few studies focused on the modeling of the volume and biomass of this forest formation. Volume and biomass estimation can be performed using allometric models, artificial intelligence (AI) techniques and mixed regression models. Thus, the aim of this work was to evaluate the use of AI techniques and mixed models to estimate the volume and biomass of individual trees in vegetation of Brazilian central savanna. Numerical variables (diameter at height of 1.30 m of ground, total height, volume and biomass) and categorical variables (species) were used for the training and fitting of AI techniques and mixed models, respectively. The statistical indicators used to evaluate the training and the adjustment were the correlation coefficient, bias and Root mean square error relative. In addition, graphs were elaborated as complementary analysis. The results obtained by the statistical indicators and the graphical analysis show the great potential of AI techniques and mixed models in the estimation of volume and biomass of individual trees in Brazilian savanna vegetation. In addition, the proposed methodologies can be adapted to other biomes, forest typologies and variables of interest.

Design of ANFIS for Hydrophobicity Classification of Polymeric Insulators with Two-Stage Feature Reduction Technique and Its Field Deployment

Hydrophobicity of polymeric insulator plays a vital role in determining the insulation quality in outdoor overhead electrical transmission and distribution lines. Loss of hydrophobicity increases the leakage current and leads to flashover. Monitoring hydrophobicity becomes a fundamental requirement to ensure continuity of power line operations. Hydrophobicity of polymeric insulator is classified according to STRI (Swedish Transmission Research Institute) guidelines. This paper proposes an intelligent ANFIS (Adaptive Neuro-Fuzzy Inference System) based classifier to determine the hydrophobicity quality using the digital image of the insulator. Ten statistical features are extracted from the digital images. Two stages of feature reduction are employed to reduce the number of features. Pre-design stage uses PCA (Principal Component Analysis) and reduces the number of features to six from ten and the post-design stage analyzes the accumulation effect to reduce the number of features to four. Various ANFIS classifiers are trained using these reduced features extracted from the image. The performance of these ANFIS classifiers is evaluated in both field and laboratory specimens. Results indicate classification accuracy of 96.4% and 93.3% during the training and testing phase when triangular membership function with linear output function is employed in ANFIS. A GUI (Graphical User Interface) has also been designed to facilitate the use of the proposed system by field operators.

Flood susceptibility assessment in Hengfeng area coupling adaptive neuro-fuzzy inference system with genetic algorithm and differential evolution

Floods are among Earth's most common natural hazards, and they cause major economic losses and seriously affect peoples' lives and health. This paper addresses the development of a flood susceptibility assessment that uses intelligent techniques and GIS. An adaptive neuro-fuzzy inference system (ANFIS) was coupled with a genetic algorithm and differential evolution for flood spatial modelling. The model considers thirteen hydrologic, morphologic and lithologic parameters for the flood susceptibility assessment, and Hengfeng County in China was chosen for the application of the model due to data availability and the 195 total flood events. The flood locations were randomly divided into two subsets, namely, training (70% of the total) and testing (30%). The Step-wise Weight Assessment Ratio Analysis (SWARA) approach was used to assess the relation between the floods and influencing parameters. Subsequently, two data mining techniques were combined with the ANFIS model, including the ANFIS-Genetic Algorithm and the ANFIS-Differential Evolution, to be used for flood spatial modelling and zonation. The flood susceptibility maps were produced, and their robustness was checked using the Receiver Operating Characteristic (ROC) curve. The results showed that the area under the curve (AUC) for all models was >0.80. The highest AUC value was for the ANFIS-DE model (0.852), followed by ANFIS-GA (0.849). According to the RMSE and MSE methods, the ANFIS-DE hybrid model is more suitable for flood susceptibility mapping in the study area. The proposed method is adaptable and can easily be applied in other sites for flood management and prevention.

Flood susceptibility mapping using novel ensembles of adaptive neuro fuzzy inference system and metaheuristic algorithms

Flood is one of the most destructive natural disasters which cause great financial and life losses per year. Therefore, producing susceptibility maps for flood management are necessary in order to reduce its harmful effects. The aim of the present study is to map flood hazard over the Jahrom Township in Fars Province using a combination of adaptive neuro-fuzzy inference systems (ANFIS) with different metaheuristics algorithms such as ant colony optimization (ACO), genetic algorithm (GA), and particle swarm optimization (PSO) and comparing their accuracy. A total number of 53 flood locations areas were identified, 35 locations of which were randomly selected in order to model flood susceptibility and the remaining 16 locations were used to validate the models. Learning vector quantization (LVQ), as one of the supervised neural network methods, was employed in order to estimate factors' importance. Nine flood conditioning factors namely: slope degree, plan curvature, altitude, topographic wetness index (TWI), stream power index (SPI), distance from river, land use/land cover, rainfall, and lithology were selected and the corresponding maps were prepared in ArcGIS. The frequency ratio (FR) model was used to assign weights to each class within particular controlling factor, then the weights was transferred into MATLAB software for further analyses and to combine with metaheuristic models. The ANFIS-PSO was found to be the most practical model in term of producing the highly focused flood susceptibility map with lesser spatial distribution related to highly susceptible classes. The chi-square result attests the same, where the ANFIS-PSO had the highest spatial differentiation within flood susceptibility classes over the study area. The area under the curve (AUC) obtained from ROC curve indicated the accuracy of 91.4%, 91.8%, 92.6% and 94.5% for the respective models of FR, ANFIS-ACO, ANFIS-GA, and ANFIS-PSO ensembles. So, the ensemble of ANFIS-PSO was introduced as the premier model in the study area. Furthermore, LVQ results revealed that slope degree, rainfall, and altitude were the most effective factors. As regards the premier model, a total area of 44.74% was recognized as highly susceptible to flooding. The results of this study can be used as a platform for better land use planning in order to manage the highly susceptible zones to flooding and reduce the anticipated losses.