Interest rate next-day variation prediction based on hybrid feedforward neural network, particle swarm optimization, and multiresolution techniques

2016 ◽  
Vol 444 ◽  
pp. 388-396 ◽  
Author(s):  
Salim Lahmiri
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Interest Rate ◽  
Particle Swarm ◽  
Feedforward Neural Network ◽  
Swarm Optimization

scholarly journals Penerapan Particle Swarm Optimization Pada Feedforward Neural Network Untuk Klasifikasi Teks Hadis Bukhari Terjemahan Bahasa Indonesia

2018 ◽  
Vol 2 (4) ◽  
pp. 165
Author(s):  
Muhammad Ghufran ◽  
Adiwijaya Adiwijaya ◽  
Said Al-Faraby
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Islamic Law ◽  
Particle Swarm ◽  
Pso Algorithm ◽  
Feedforward Neural Network ◽  
General Technique ◽  
Swarm Optimization ◽  
The Public ◽  
Speed Up

Hadith is the second source of Islamic law after Al-Qur'an and used as a guide for Muslims life. there are many hadith which has been narrated, one of them is Bukhari history. This research aims to build a model that can classify Bukhari hadith translation of Indonesian language. This topic is chosen to assist the public in understanding the meaning of the information that contained in the hadith, in the form of advocacy information, prohibitions or just information. The Backpropagation Algorithm (BP) is the general technique that used to train the Feedforward Neural Network (FNN) in classification process cause it has good accuracy for text classification. But, BP has a weakness that is relatively slow to reach convergent and stuck in local minimum. To overcome this, the Particle Swarm Optimization (PSO) algorithm is used to speed up convergence and find the minimum global value. The purpose of this test is to see the PSO's ability to train the weight and refraction of FNN. The result of this research on 1000 hadith data show that model PSO-FNN with stemming process get 88.5% accuracy while without stemming process get 88.57% accuracy. Meanwhile, the result of comparative test between PSO-FNN with BP-FNN, the result shows that  PSO-FNN get accuracy equal to 88.57% which is lower 0.93% than BP-FNN which has 89.5% accuracy.

Sign in / Sign up

Export Citation Format

Share Document