Adaptive Network-based Inference System Research Articles

Application of an ANFIS to Estimate Kansai International Airport’s International Air Passenger Demand

This study presents an Adaptive Network Based Inference System (ANFIS) model to forecast international passenger demand at Osaka’s Kansai International Airport. The study covered the period 1994 to 2018. The study used nine determinants of air travel demand and three dummy variables as input variables. The results reveal that the model successfully forecasts Kansai International Airport’s international passenger demand. The coefficient of determination (R2) was high, being around 0.9776%. The overall MAPE of Kansai International Airport’s international air passenger demand model was 7.40%.

Modeling and analysis of effects of precipitation and vegetation coverage on runoff and sediment yield in Jinsha River Basin

This paper focuses on the effects of precipitation and vegetation coverage on runoff and sediment yield in the Jinsha River Basin. Results of regression analysis were taken as input variables to investigate the applicability of the adaptive network-based fuzzy inference system (ANFIS) to simulating annual runoff and sediment yield. Correlation analysis indicates that runoff and sediment yield are positively correlated with the precipitation indices, while negatively correlated with the vegetation indices. Furthermore, the results of stepwise regression show that annual precipitation is the most important factor influencing the variation of runoff, followed by forest coverage, and their contributions to the variation of runoff are 69.8% and 17.3%, respectively. For sediment yield, rainfall erosivity is the most important factor, followed by forest coverage, and their contributions to the variation of sediment yield are 49.3% and 24.2%, respectively. The ANFIS model is of high precision in runoff forecasting, with a relative error of less than 5%, but of poor precision in sediment yield forecasting, indicating that precipitation and vegetation coverage can explain only part of the variation of sediment yield, and that other impact factors, such as human activities, should be sufficiently considered as well.

Detection of hypochromic anemia in blood sample microscopic images using adaptive network-based fuzzy inference system

Volume of red blood cell is an important factor in distinguishing its abnormalities. Mean corpuscular volume MCV of red blood cells contributes much to differentiation of several blood diseases lik...

Prediction of building energy needs in early stage of design by using ANFIS

Studies performed on the prediction of building energy consumption are increasingly important for selecting the best control strategies against the excessive energy consumptions. This paper presents Adaptive Network Based Inference System (ANFIS) model to forecast building energy consumption in a cold region. The objective of this paper is to examine the feasibility and applicability of ANFIS in building energy load forecasting area. Different combinations of building samples formed by using three different form factors (FF 1/2, FF 1/1 and FF 2/1), nine azimuth angles varied 0o–80o, three transparency ratios of 15%, 20%, 25% and five insulation thicknesses of 0, 2.5, 5, 10 and 15cm. Finally, it is observed that ANFIS can be a strong tool with the 96.5 and 83.8% for heating and cooling energy prediction in pre-design stage of energy efficient buildings for choosing the best combinations.

Seed-Based Region Growing (SBRG) vs Adaptive Network-Based Inference System (ANFIS) vs Fuzzyc-Means (FCM): Brain Abnormalities Segmentation

Segmentation of Magnetic Resonance Imaging (MRI) images is the most challenging problems in medical imaging. This paper compares the performances of Seed-Based Region Growing (SBRG), Adaptive Network-Based Fuzzy Inference System (ANFIS) and Fuzzy c-Means (FCM) in brain abnormalities segmentation. Controlled experimental data is used, which designed in such a way that prior knowledge of the size of the abnormalities are known. This is done by cutting various sizes of abnormalities and pasting it onto normal brain tissues. The normal tissues or the background are divided into three different categories. The segmentation is done with fifty seven data of each category. The knowledge of the size of the abnormalities by the number of pixels are then compared with segmentation results of three techniques proposed. It was proven that the ANFIS returns the best segmentation performances in light abnormalities, whereas the SBRG on the other hand performed well in dark abnormalities segmentation. Keywords—Seed-Based Region Growing (SBRG), Adaptive Network-Based Fuzzy Inference System (ANFIS), Fuzzy c-Means (FCM), Brain segmentation.

Forecasting the Performance of the Asian Currency Unit and the Causes of Contagion of the Asian Financial Crisis

This study analyses the prediction performance of the Asian Currency Unit (ACU) by employing variant methods including the Back-Propagation Neural Networks (BPN), Recurrent Neural Network (RNN), Time-Delay Recurrent Neural Network (TDRNN), General Autoregressive Conditional Heteroscedasticity (GARCH), and random walk models. The results show that Artificial Neural Network models outperform GARCH and random walk models. The BPN model presents prominent forecasting performance in most division conditions. The study further verifies the causes of contagion of the Asian financial crisis using the Adaptive Network-Based Fuzzy Inference System (ANFIS). The empirical results indicate that the contagion effect would most likely be influenced by tight financial linkage and conditions of macroeconomic similarity as well.

Adaptive network based inference system for estimation of flank wear in end-milling

The focus of this paper is to develop a reliable method to predict flank wear during end-milling process. A neural-fuzzy scheme is applied to perform the prediction of flank wear from cutting force signals. In this contribution we also discussed the construction of a ANFIS system that seeks to provide a linguistic model for the estimation of tool wear from the knowledge embedded in the neural network. Machining experiments conducted using the proposed method indicate that using an appropriate maximum force signals, the flank wear can be predicted within 4% of the actual wear for various end-milling conditions.

Adaptive fuzzy control for wind-diesel weak power systems

This work is concerned with the development of an adaptive fuzzy logic controller for a wind-diesel system composed of a stall regulated wind turbine with an induction generator connected to an AC busbar in parallel with a diesel generator set having a synchronous generator. In this work we propose to use an adaptive network based inference system (ANFIS) in order to generate fuzzy membership functions and control rules for the controller. A feedback linearized proportional integral controller is used to provide the required expert knowledge. A controller design process is identified; it consists of generating input-output data pairs to identify the control variables range and initial fuzzy memberships, and then to tune or adapt them using an ANFIS network structure. The controller inputs are the frequency error and its integral for the governor part of the controller, and the voltage and frequency errors for the automatic voltage regulator. These are readily measurable quantities leading to a simple controller which can be easily implemented.