ANFIS Approach Research Articles

Design, construction and evaluation of a miniature soil bin plus predicting the measured parameters during primary tests using ANFIS

A clear understanding of soil-machine interaction is utilised in many areas, such as rational design and performance optimisation of soil-engaging tools/implements. This research developed a new soil bin to investigate the interaction between soil-narrow tines and soil failure. The new soil bin consisted of a chassis, a bin, a variable speed carriage and a bolt and nut type power transmission system between the motor and carriage. The design criteria of the new soil bin were based on the drive system's immediate acceleration of the carriage unit. A curved chisel tine was tested to evaluate the system's capabilities. Three parameters, including lift height, failure side area and forward failure distance, were investigated at two forward speeds of 0.037 and 0.05 m/s and three rake angles of 5°, 10° and 20°. An analysis of variance (ANOVA) test revealed the effect of rake angle on the lift height, failure side area, and forward failure distance was significant (P < 0.01). However, the forward speed did not have any significant influence on parameters. Also, the lift height and failure side area increased significantly (P < 0.01) by increasing the rake angle, while the forward failure distance decreased. Regarding soil failure, the results were in harmony with Godwin and Spoor's model. The regression and ANFIS models were developed to predict the output parameters by considering input parameters. The R2 values and ANFIS models were 0.4895, 0.7264, 0.9856, and 0.9999, 1, 1, respectively, for lift height, side area, and forward distance. Therefore, ANFIS approach was more accurate for predicting soil failure parameters.

Development of Image Processing Based Line Tracking Systems for Automated Guided Vehicles with ANFIS and Fuzzy Logic

Automated Guided Vehicles (AGVs) are robotic vehicles with the ability to move using mapping and navigation technologies to perform tasks assigned to them, guided by guides. Using sensor data such as laser scanners, cameras, magnetic stripes or colored stripes, they can sense their environment and move safely according to defined routes. The basic requirement of motion planning is to follow the path and route with minimum error even under different environmental factors. The key factor here is the most successful detection of the guiding structure of a system moving on its route. The proposed system is to equip a mechanical system that can produce very fast outputs and autonomous motion as a result of combining different algorithms with different hardware structures. In the line detection process, the wide perspective image from the camera is designed to be gradually reduced and converted into image information that is more concise but representative of the problem in a narrower perspective. In this way, the desired data can be extracted with faster processing over less information. In this study, the image information is divided into two parts and planned as two different sensors. The fact that the line information was taken from two different regions of the image at a certain distance enabled the detection of not only the presence of the line but also the flow direction. With the fuzzy system, the performance of the system was increased by generating PWM values on two different hardware structures, loading image capture, image processing processes and driving the motors. In order to determine the membership function parameters of the fuzzy system for each input, the ANFIS approach was used on the data set modeling the system. The outputs produced by the ANFIS model were combined into a single fuzzy system with two outputs from the system rules framework and the system was completed. The success of the algorithms was ensured by partitioning the task distribution in the hardware structure. With its structure and success in adapting different technologies together, a system that can be recommended for similar problems has been developed.

Multi-area optimal adaptive under-frequency load shedding control based on ANFIS approach

Multi-area optimal adaptive under-frequency load shedding control based on ANFIS approach

Analysis of Markovian Retrial Queue with Double Orbits, Vacation, Orbital Search, and Disaster Using ANFIS Approach

Analysis of Markovian Retrial Queue with Double Orbits, Vacation, Orbital Search, and Disaster Using ANFIS Approach

One-hour-ahead solar radiation forecasting by MLP, LSTM, and ANFIS approaches

One-hour-ahead solar radiation forecasting by MLP, LSTM, and ANFIS approaches

Accrual and Dismemberment of Brain Tumours Using Fuzzy Interface and Grey Textures for Image Disproportion.

A neurological disorder is a problem with the neural system of the body, as a brain tumor is one of the deadliest neurological conditions and it requires an early and effective detection procedure. The existing detection and diagnosis methods for image evaluation are based on the judgment of the radiologist and neurospecialist, where a risk of human mistakes can be found. Therefore, a new flanged method and methodology for detecting brain tumors using magnetic resonance imaging and the artificial neural network (ANN) technique are applied. The research is based on an artificial neural network-based behavioral examination of neurological disorders. In this study, an artificial neural network is used to detect a brain tumor as early as possible. The current work develops an effective approach for detecting cancer from a given brain MRI and recognizing the retrieved data for further use. To obtain the desired result, the following three procedures are used: preprocessing, feature extraction, training, and detection or classification. A Gaussian filter is also incorporated to eliminate noise from the image, and for texture feature extraction, GLCM is considered in this study. Further entropy, contrast, energy, homogeneity, and other GLCM texture properties of tumor categorization are measured using the ANFIS approach, which determines if the tumor is normal, benign, or malignant. Future research will focus on applying advanced texture analysis to classify brain tumors into distinct classes in order to improve the accuracy of brain tumor diagnosis. In the future, MRI brain imaging will be used to classify metastatic brain tumors.

Improvement of Dynamic Performance in SEIG WECS by Using ANFIS Controller

A new hybrid controller for the Self-Excited Induction Generator (SEIG) driven by the Wind Energy Conversion Scheme (WECS) was proposed in this paper. The dynamic stability of the control grid is essential for both user protection and system performance. There must be a full grasp of the effects of power system volatility to research and govern power systems. The suggested control systems were examined using frequency-domain approaches that focused on the nonlinear design of a device that is subjected to severe faults on a related bus, which was tested using time-domain strategies. In this paper, a novel 3-level inverter is designed and controlled by the ANFIS control for the Dynamic Response of the system at the load side. The ANFIS approach can be used to regulate a self-excited induction generator in this study. The design incorporates wind power to give on-grid electricity access. SEIGs are used to power wind turbines in this project, which generates alternating current (AC) for the grid. The system model uses a rotor reference frame and dynamic vector control for the machine reference model. Wind power voltage and active power are controlled by an ANFIS controller in the converter. The ANFIS controller's performance is evaluated in all abnormal scenarios, including the worst-case scenario. System modeling and simulation in Simulink-Matlab allow it to be used in SEIG configurations. Wind power system quality and stability are both improved by the ANFIS control unit, according to simulation results.

New method based on neuro-fuzzy system and PSO algorithm for estimating phase equilibria properties

The subject of this work is to propose a new method based on the ANFIS system and PSO algorithm to conceive a model for estimating the solubility of solid drugs in supercritical CO2 (sc-CO2). The high nonlinear process was modeled by the neuro-fuzzy approach (NFS). The PSO algorithm was used for two purposes: replacing the standard backpropagation in training the NFS and optimizing the process. The validation strategy has been carried out using a linear regression analysis of the predicted versus experimental outputs. The ANFIS approach is compared to the ANN in terms of accuracy. Statistical analysis of the predictability of the optimized model trained with a PSO algorithm (ANFIS-PSO) shows a better agreement with the reference data than the ANN method. Furthermore, the comparison in terms of the AARD deviation (%) between the predicted results, the results predicted by the density-based models, and a set of equations of state demonstrates that the ANFIS-PSO model correlates far better with the solubility of the solid drugs in scCO2. A control strategy was also developed for the first time in the field of phase equilibrium by using the neuro-fuzzy inverse approach (ANFISi) to estimate pure component properties from the solubility data without passing through the GCM methods.

Design and Simulation of ANFIS based Brushless DC Motor Control

BLDC motor control with ANFIS control methods was investigated and analysed, in this work. The results show that the ANFIS approach is simple, efficient and achieves the desired speed and torque values. The approach was developed and used in both industrial and literary applications. The ANFIS controller was compared with Fuzzy and PI controllers. ANFIS has proved its reliability and good performance. Besides its swift execution, speed control has demonstrated its capability to maintain a minimum cost and commitment track of the target speed values. The method is a basic method with light steps and no reference processing or synchronisation is required.

FORECASTING BITCOIN PRICES WITH THE ANFIS MODEL

Recently, Bitcoin has gained great importance in the cryptocurrency market with the highest market capitalization. Investors and researchers have attempted to find out the drivers of Bitcoin prices and if they are predictable. However, there is only limited research in the literature that identifies the most effective economic and technical variables for predicting Bitcoin prices using machine learning models. Thus, in this study, the future Bitcoin prices utilizing several economic and technical factors using the ANFIS model are aimed to forecasted between 01.05.2013 - 26.02.2021 periods. The findings show that the ANFIS model produced accurate and consistent predicting results that are in line with the real data. As a result, investors who wish to make a profit by predicting future Bitcoin values might consider using the ANFIS approach as a forecasting tool.

Estimation of Los Angeles and Micro Deval abrasion values for gneiss and granite using ANFIS approach

Gneisses and granites mechanical properties knowledge such as the Los Angeles and Micro-Deval coefficients is very important for the engineer when designing and building civil engineering works. Laboratories test often performed to obtain Los Angeles and Micro-Deval values are expensive and time consuming. For this, the depths (parallel and perpendicular to the foliation planes) obtained during a rock drilling test will be used to estimate its coefficients Los Angeles and Micro-Deval. In this study, an ANFIS approach is used to estimate gneisses and granites Los Angeles and Micro-Deval that have been compared to the Multiple Linear Regression method. For this purpose, we have used a database of a sample size of 80 to determine the parameters of the ANFIS and Multiple Linear Regression models, and a second sample of size 15 used for the validation tests. The results obtained show us that we can estimate the mechanical properties (Los Angeles and Micro-Deval) of gneisses and granites with ANFIS approach.

Accurate characterization of weld appearance induced by T-joint laser stake-welding by integration of ANFIS approach and numerical simulation

Accurate characterization of weld appearance induced by T-joint laser stake-welding by integration of ANFIS approach and numerical simulation

Experimental Investigation of White Layer Thickness on EDM Processed Silicon Steel Using ANFIS Approach

Since the white layer thickness influences the surface quality of the machined specimens using electrical discharge machining process, the prediction of such parameter is highly important in the present scenario. Adaptive network based fuzzy inference system based white layer thickness prediction on machining processed silicon steel has been attempted in the present study. Three machining process parameters such as open circuit voltage, peak current and duty factor have been utilized for the training purpose owing their importance on determining white layer thickness. The accuracy of the prediction has been analyzed by comparing the predicted values from the architecture testing with the real time measured values. From the experimental results, it has been found that the developed adaptive network based fuzzy inference system can predict the average white layer thickness in an efficient way with accuracy of 96.8%. It has also been observed that the electrical process parameters have highly contributed on determining average white layer thickness.

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.

Prediction of biodiesel fuel properties from its fatty acids composition using ANFIS approach

Biodiesel is renewable fuel, environment-friendly and a potential substitute for petroleum diesel. The biodiesel properties are based on the type of used oil and its structure. The aim of this study is to model and predict biodiesel properties such as kinematic viscosity, iodine value, cloud point and pour point from fatty acids composition using ANFIS approach. The input variables were carbon number (Cn), the number of double bonds (dn), wt% of mono unsaturated fatty acids (MU), wt% of poly unsaturated fatty acids (PU), wt% of saturated fatty acids C0, temperature (T), and molar weight (Mw). The performance of developed ANFIS model was compared using statistical criteria such as coefficient of determination (R2), root mean square error (RMSE) and mean absolute percent error (MAPE). It was determined that the coefficient of determination, R2 related to kV, IV, CP, and PP were 0.989, 0.996, 0.938, and 0.981 respectively. The RMSE and MAPE criteria were ranges between 0.28 and 2.15 and 0.25–0.62 in the order already mentioned. Consequently, the results show that developed ANFIS models have a higher accuracy and predictive ability.

Reactive navigation of underwater mobile robot using ANFIS approach in a manifold manner

Learning and self-adaptation ability is highly required to be integrated in path planning algorithm for underwater robot during navigation through an unspecified underwater environment. High frequency oscillations during underwater motion are responsible for nonlinearities in dynamic behavior of underwater robot as well as uncertainties in hydrodynamic coefficients. Reactive behaviors of underwater robot are designed considering the position and orientation of both target and nearest obstacle from robot's current position. Human like reasoning power and approximation based learning skill of neural based adaptive fuzzy inference system (ANFIS) has been found to be effective for underwater multivariable motion control. More than one ANFIS models are used here for achieving goal and obstacle avoidance while avoiding local minima situation in both horizontal and vertical plane of three dimensional workspace. An error gradient approach based on input-output training patterns for learning purpose has been promoted to spawn trajectory of underwater robot optimizing path length as well as time taken. The simulation and experimental results endorse sturdiness and viability of the proposed method in comparison with other navigational methodologies to negotiate with hectic conditions during motion of underwater mobile robot.

Diagnosis and classification using ANFIS approach of stator and rotor faults in induction machine

Diagnosis and classification using ANFIS approach of stator and rotor faults in induction machine

Measurement and prediction of correction factors for very high core compressive strength by using the adaptive neuro-fuzzy techniques

In this study the relationship between the core compressive strength with respect to reference samples and different core sizes with different slenderness ratio, length to diameter (L/D) were investigated. In addition, a comparative study was carried out by a hybrid neuro-fuzzy (ANFIS) technique, the core correction factors were evaluated by statistical methods for comparing the performance of four different ANFIS approaches. The Gaussian membership functions were used for defining linguistic terms. The back propagation multi layer (BPML) and hybrid learning algorithms with grid partition were employed for the development of the ANFIS models. Experimental results showed that the core strength was increased with the decrease of slenderness ratio and have ranged between 0.95 and 1.21. The ANFIS model results showed that it could be used an efficient tool for the estimation of the core correction factor of very high strength concrete. The ANFIS model in the current study performs sufficiently in the estimation of core correction factor of high strength concrete, which particularly estimates closely following the actual values. The ANFIS model with hybrid learning algorithm of grid partition was able to produce the most accurate model outcomes for estimating the correction factor among the examined models.

ANFIS 접근방식에 의한 미래 트랜드 충격 분석

TIA(: Trend Impact Analysis)는 발생될 가능성이 있는 미래의 예기치 못한 사건들을 식별하고 분석하기 위한 고급 예측 도구에 속한다. 적응적인 뉴로-퍼지 추론 시스템은 인공신경망의 일종으로 신경망과 퍼지 로직 원리를 모두 통합하고 보편적 추정되는 것으로 간주한다. 본 논문에서는 적응적인 뉴로-퍼지 추론 시스템을 사용하여 예기치 못한 사건에 관한 심각성의 정도를 추론하고 이를 시간의 함수로서 도입하여 예기치 못한 사건들의 출현 확률에 관해 보다 타당한 추정치를 얻는데 있다. 이러한 접근방식에 대한 배후 개념은 예기치 못한 사건이 갑자기 출현되는 것이 아니라 관련 사건이 가지고 있는 속성 값에 대한 건드림 혹은 변화가 기존 속성 값의 한계를 벗어나 마치 새로운 사건인 것처럼 등장할 수 있음을 전제로 하고 있다. ANFIS 접근 방식은 이러한 사건을 식별해서 예기치 못한 사건의 심각성의 정도를 추론하는데 매우 적절한 방식이라 할 수 있다. 속성들의 변화 값들은 확률적인 동적 모델 및 Monte-Carlo 방법을 사용하여 얻을 수 있다. 제안된 모델에 관한 타당성은 강 유역의 예상치 못한 가뭄에 따른 충격 추세 곡선을 기존 연구 결과와의 비교를 통해 나타낸다. Trend Impact Analysis(: TIA) is an advanced forecasting tool used in futures studies for identifying, understanding and analyzing the consequences of unprecedented events on future trends. An adaptive neuro-fuzzy inference system is a kind of artificial neural network that integrates both neural networks and fuzzy logic principles, It is considered to be a universal estimator. In this paper, we propose an advanced mechanism to generate more justifiable estimates to the probability of occurrence of an unprecedented event as a function of time with different degrees of severity using Adaptive Neuro-Fuzzy Inference System(: ANFIS). The key idea of the paper is to enhance the generic process of reasoning with fuzzy logic and neural network by adding the additional step of attributes simulation, as unprecedented events do not occur all of a sudden but rather their occurrence is affected by change in the values of a set of attributes. An ANFIS approach is used to identify the occurrence and severity of an event, depending on the values of its trigger attributes. The trigger attributes can be calculated by a stochastic dynamic model; then different scenarios are generated using Monte-Carlo simulation. To compare the proposed method, a simple simulation is provided concerning the impact of river basin drought on the annual flow of water into a lake.

RETRACTED: Estimating unconfined compressive strength of cockle shell–cement–sand mixtures using soft computing methodologies

The accuracy of soft computing techniques was used in this research to estimate the unconfined compressive strength according to series of unconfined compressive tests for multiple mixtures of cockle shell, cement and sand under different curing periods. We developed a process for simulating the unconfined compressive strength through two techniques of soft computing, the support vector regression (SVR) and the adaptive neuro-fuzzy inference (ANFIS). The developed SVR and ANFIS networks have one neuron (UCS) in the output layer and four neurons in the input layer. The inputs were percentage of cockle shell, cement and sand content in the mixtures, and age (in days). First, the ANFIS network was used to select the most effective parameters on the UCS. The linear, polynomial, and radial basis functions were employed as the SVR’s kernel function. The simulation results proved the performance of proposed optimizers. Additionally, the results of SVR and ANFIS were compared through the Pearson correlation coefficient and the root-mean-square error. The findings show that the predictive accuracy and capability of generalization can be an improved by the ANFIS approach in comparison to the SVR estimation. The simulation results confirmed the effectiveness of the proposed optimization strategies.