A Neoteric Approach to Rough Neuro Fuzzy Methods

Author(s):  
S. Chandana ◽  
R.V. Mayorga
Keyword(s):  
2019 ◽  
Vol 3 (1) ◽  
pp. 58
Author(s):  
Aenul Muhajirah ◽  
Eka Safitri ◽  
Titin Mardiana ◽  
Hartina Hartina ◽  
Andi Setiawan

Abstrak: Penelitian ini dilakukan untuk menganalisis proses forecasting dalam menentukan tipe terbaik yang digunakan pada sistem peramalan (forecast). Pada penelitian ini data yang digunakan yaitu data IPM Provinsi Nusa Tengara Barat (NTB) tahun 2008-2018 untuk memprediksi data Indeks Pembangunan Manusia (IPM) tahun 2019. Penelitian ini menggunakan metode Artificial Intelligence Neuro Fuzzy yaitu Fuzzy Mamdani dan ANFIS Sugeno yang diterapkan pada Matlab. Adapun tipe yang diuji adalah Trimf, Trapmf, Gbellmf, Gaussmf, Gauss2mf, Sigmf, Dsigmf, Psigmf, dan Primf. Tipe tersebut bertujuan untuk melihat tingkat akurasi berdasarkan hasil error. Hasil peramalan terbaik didapatkan pada tipe Gauss2mf karena menghasilkan prediksi sebesar 69.5 dengan error sebesar 0.95947 dan MAD sebesar 0.530.354, MSE sebesar 1.570035, MAPE sebesar 0.049273. Abstract: This research was conducted to analyze the forecasting process in determining the best type used in the forecasting system. In this study the data used were the data of West Nusa Tenggara Province (HDI) HDI for the years 2008-2018 to predict the 2019 Human Development Index (HDI) data. This study uses Artificial Intelligence Neuro Fuzzy methods namely Fuzzy Mamdani and ANFIS Sugeno applied to Matlab . The types tested were Trimf, Trapmf, Gbellmf, Gaussmf, Gauss2mf, Sigmf, Dsigmf, Psigmf, and Primf. This type aims to see the level of accuracy based on the results of the error. The best forecasting results were obtained on the Gauss2mf type because it produced a prediction of 69.5 with an error of 0.95947 and MAD of 0.530.354, MSE of 1.570035, MAPE of 0.049273.


Author(s):  
Dimitris C. Dracopoulos ◽  
Dimitrios Effraimidis

Computational intelligence techniques such as neural networks, fuzzy logic, and hybrid neuroevolutionary and neuro-fuzzy methods have been successfully applied to complex control problems in the last two decades. Genetic programming, a field under the umbrella of evolutionary computation, has not been applied to a sufficiently large number of challenging and difficult control problems, in order to check its viability as a general methodology to such problems. Helicopter hovering control is considered a challenging control problem in the literature and has been included in the set of benchmarks of recent reinforcement learning competitions for deriving new intelligent controllers. This chapter shows how genetic programming can be applied for the derivation of controllers in this nonlinear, high dimensional, complex control system. The evolved controllers are compared with a neuroevolutionary approach that won the first position in the 2008 helicopter hovering reinforcement learning competition. The two approaches perform similarly (and in some cases GP performs better than the winner of the competition), even in the case where unknown wind is added to the dynamic system and control is based on structures evolved previously, that is, the evolved controllers have good generalization capability.


2006 ◽  
Vol 6 (9) ◽  
pp. 2020-2030 ◽  
Author(s):  
L. Mehennaoui ◽  
N. Debbache . ◽  
M.L. Benloucif .

Sign in / Sign up

Export Citation Format

Share Document