Optimization of backpropagation neural network-based models in EDM process using particle swarm optimization and simulated annealing algorithms

2020 ◽  
Vol 42 (1) ◽  
Author(s):  
Ali Saffaran ◽  
Masoud Azadi Moghaddam ◽  
Farhad Kolahan
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Simulated Annealing ◽  
Particle Swarm ◽  
Backpropagation Neural Network ◽  
Swarm Optimization ◽  
Edm Process ◽  
Annealing Algorithms

scholarly journals Hybrid backpropagation neural network-particle swarm optimization for seismic damage building prediction

2019 ◽  
Vol 14 (1) ◽  
pp. 360
Author(s):  
Marina Yusoff ◽  
Faris Mohd Najib ◽  
Rozaina Ismail
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Damage Index ◽  
Particle Swarm ◽  
Seismic Damage ◽  
Backpropagation Neural Network ◽  
Swarm Optimization ◽  
Local Optima ◽  
Damage Indices ◽  
Prediction Problems

The evaluation of the vulnerability of buildings to earthquakes is of prime importance to ensure a good plan can be generated for the disaster preparedness to civilians. Most of the attempts are directed in calculating the damage index of buildings to determine and predict the vulnerability to certain scales of earthquakes. Most of the solutions used are traditional methods which are time consuming and complex. Some of initiatives have proven that the artificial neural network methods have the potential in solving earthquakes prediction problems. However, these methods have limitations in terms of suffering from local optima, premature convergence and overfitting. To overcome this challenging issue, this paper introduces a new solution to the prediction on the seismic damage index of buildings with the application of hybrid back propagation neural network and particle swarm optimization (BPNN-PSO) method. The prediction was based on damage indices of 35 buildings around Malaysia. The BPNN-PSO demonstrated a better result of 89% accuracy compared to the traditional backpropagation neural network with only 84%. The capability of PSO supports fast convergence method has shown good effort to improve the processing time and accuracy of the results.

scholarly journals Development of Particle Swarm Optimization and Simulated Annealing Algorithms to Solve Vehicle Routing Problems with Drones

2021 ◽  
Vol 5 (1) ◽  
pp. 1-11
Author(s):  
Hasan Aji Prawira ◽  
Budi Santosa
Keyword(s):  
Particle Swarm Optimization ◽  
Simulated Annealing ◽  
Vehicle Routing ◽  
Particle Swarm ◽  
Swarm Optimization ◽  
Routing Problem ◽  
The Cost ◽  
Number Of Customers ◽  
Alternative Delivery ◽  
Annealing Algorithms

Vehicle Routing Problem with Drone (VRPD) is a problem of determining the number of routes for delivery of goods from the depot to a number of customers using trucks and drones. Drones are an alternative delivery tool besides trucks, each truck can be equipped with a support drone. Drones can be used to make a delivery while the truck is making others. By combining a truck and a drone, the truck can act as a tool for drone launch and landing so that the drones can reach long distances from the depot. The purpose of this problem is to minimize the cost of sending goods by trucks and drones. In this study, the Particle Swarm Optimization (PSO) and the Simulated Annealing (SA) are proposed to solve these problems. The Route Drone algorithm are used to help change the structure of the PSO and SA solutions into a VRPD solution. The proposed algorithm has been applied to 24 different scenarios ranging from 6 customers to 100 customers. The PSO and SA algorithms are able to find solutions that are close to optimal. The SA is able to find a better solution than the PSO.

scholarly journals PREDIKSI KEMACETAN ANGSURAN LEASING MOTOR MENGGUNAKAN ALGORITMA BACKPRPAGATION NEURAL NETWORK BERBASIS PARTICLE SWARM OPTOM

2017 ◽  
Vol 8 (4) ◽  
pp. 243
Author(s):  
Aulia Rizky Muhammad Hendrik Noor Asegaff
Keyword(s):  
Neural Network ◽  
Data Mining ◽  
Particle Swarm Optimization ◽  
Particle Swarm ◽  
Learning Rate ◽  
Backpropagation Neural Network ◽  
Swarm Optimization ◽  
Training Cycle

Sekarang ini permintaan akan kendaraan bermotor sangat banyak ditambah lagi dengan kemudahan pada proses jual-belinya, sehingga mendorong pertumbuhan perusahaan leasing. Perusahaan leasing memberikan kemudahan kepada masyarakat agar dengan mudah mendapatkan kendaraan bermotor seperti dengan uang muka yang ringan, angsuran yang rendah dan tenor yang panjang. Namun, hal itu dapat menimbulkan resiko angsuran macet yang mengkhawatirkan bagi perusahaan itu sendiri. Penanggulangan dan pembatasan angsuran macet belum menemukan cara yang paling sesuai karena selama ini analisa pengajuan kredit dilakukan hanya pendekatan personal dengan mengisi Form Data Konsumen dan survey lapangan.Algoritma klasifikasi data mining dengan model algoritma Backpropagation Neural Network menunjukan bahwa model ini mempunyai tingkat akurasi yang baik serta dapat dioptimasi Particle Swarm Optimization (PSO) dengan melakukan pengujian secara terukur melalui parameter training cycle, learning rate dan momentum, sehingga mendapatkan hasil accuracy, precision, recall dan AUC dengan bantuan Rapi Miner. Hasilnya setelah dilakukan pengujian dengan menggunakan data konsumen dan data rekap pembayaran (collection), pada BPNN mendapatkan parameter terbaik pada nilai 200 untuk training cycle, 0.1 pada learning rate dan 0.1 pada momentum menghasilkan accuracy 75.11%, precision 77.55%, recall 84.89% dan AUC 0.772. Sedangkan pada BPNN-PSO menghasilkan accuracy 76.98%, precision 77.96, recall 87.88% dan AUC 0.814. Kata kunci : angsuran, leasing, BPNN-PSO

Analysis of Feature Reduction Techniques for Online News Popularity Prediction

2018 ◽  
Vol 4 (10) ◽  
pp. 6
Author(s):  
Shivangi Bhargava ◽  
Dr. Shivnath Ghosh
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Particle Swarm Optimization ◽  
Naive Bayes ◽  
Particle Swarm ◽  
Naïve Bayes ◽  
Online News ◽  
Feature Reduction ◽  
Support Vector ◽  
Swarm Optimization

News popularity is the maximum growth of attention given for particular news article. The popularity of online news depends on various factors such as the number of social media, the number of visitor comments, the number of Likes, etc. It is therefore necessary to build an automatic decision support system to predict the popularity of the news as it will help in business intelligence too. The work presented in this study aims to find the best model to predict the popularity of online news using machine learning methods. In this work, the result analysis is performed by applying Co-relation algorithm, particle swarm optimization and principal component analysis. For performance evaluation support vector machine, naïve bayes, k-nearest neighbor and neural network classifiers are used to classify the popular and unpopular data. From the experimental results, it is observed that support vector machine and naïve bayes outperforms better with co-relation algorithm as well as k-NN and neural network outperforms better with particle swarm optimization.

Sign in / Sign up

Export Citation Format

Share Document