Adaptive Neuro-fuzzy Inference System For Modeling Research Articles

PENERAPAN METODE ANFIS UNTUK MEMPREDIKSI NILAI TUKAR DOLAR AS (USD) TERHADAP RUPIAH

The purpose of this study is to explain the prediction of the exchange rate of the United States Dollar (USD) on the Indonesia Rupiah (IDR) using the Adaptive Neuro Fuzzy Inference System (ANFIS) method. ANFIS is a combination of functions contained in fuzzy logic and neural networks. The data used is data with daily period of the USD exchange rate against the rupiah. The input to the daily prediction is a combination of the exchange rates on the previous days for the prediction of the selling rate of the United States Dollar (USD) for the next one day. The results of this study, the best model ANFIS uses a membership function Gaussian with model 3 consisting of 4 inputs and 1 output with a combination of training data and test data 80:20 or 202 data training and 51 data testing resulting MAPE is 3.74% and from the MAPE value it can be concluded that predictions using the ANFIS can be categorized as very accurate.

Estimation of tool wear and optimization of cutting parameters based on novel ANFIS-PSO method toward intelligent machining

Compacted graphite iron (CGI) plays an important role in contemporary manufacturing of automobile engine, and coated tool is the best choice for milling of CGI. But studies about the estimation of the wear of coated tool are still rare and incomplete. As tool wear is the main factor that affects the quality of machined surface, in this study, we proposed an intelligent model-adaptive neuro fuzzy inference system (ANFIS) to estimate the tool wear, and ANFIS was learned by the improved particle swarm optimization (PSO) algorithm. As the PSO algorithm is easy to fall into the local minimum, the vibration and communication particle swarm optimization (VCPSO) algorithm was proposed by introducing the self-random vibration and inter-particle communication mechanisms. Besides that, to obtain the optimal combination of milling parameters, the multi-objective optimization based on minimum cutting power, surface roughness and maximum material removal rate (MRR) was studied using VCPSO algorithm. The experimental results showed that the ANFIS learned by VCPSO algorithm (ANFIS-VCPSO) has better performance for the estimation of tool wear compared with other intelligent models. The VCPSO algorithm was tested using Benchmark functions, and the results showed VCPSO algorithm has the global optimization ability. Meantime, the best combinations of milling parameters under different tool wear status were obtained through VCPSO algorithm. The proposed ANFIS-VCPSO model as a new intelligent model can be applied for real-time tool wear monitoring, which can improve the machining efficiency and prolong tool life. In order to meet the requirements of green and intelligent manufacturing, the best combination of milling parameters was also obtained in this work.

Landslide Susceptibility Mapping by Neuro-Fuzzy Approach in a Landslide-Prone Area (Cameron Highlands, Malaysia)

This paper presents the results of the neuro-fuzzy model using remote-sensing data and geographic information system for landslide susceptibility analysis in a part of the Cameron Highlands areas in Malaysia. Landslide locations in the study area were identified by interpreting aerial photographs and satellite images, supported by extensive field surveys. Landsat TM satellite imagery was used to map the vegetation index. Maps of the topography, lineaments, Normalized Difference Vegetation Index (NDVI), and land cover were constructed from the spatial data sets. Eight landslide conditioning factors such as altitude, slope gradient, curvature, distance from the drainage, distance from the road, lithology, distance from the faults, and NDVI were extracted from the spatial database. These factors were analyzed using a neuro-fuzzy model adaptive neuro-fuzzy inference system to produce the landslide susceptibility maps. During the model development works, a total of five landslide susceptibility models were constructed. For verification, the results of the analyses were then compared with the field-verified landslide locations. Additionally, the receiver operating characteristic curves for all landslide susceptibility models were drawn, and the area under curve values were calculated. Landslide locations were used to validate the results of the landslide susceptibility map, and the verification results showed a 97% accuracy for model 5, employing all parameters produced in the present study as the landslide conditioning factors. The validation results showed a sufficient agreement between the obtained susceptibility map and the existing data on the landslide areas. Qualitatively, the model yields reasonable results, which can be used for preliminary land-use planning purposes.