A Honey Bee Mating Optimization Based Gradient Descent Learning – FLANN (HBMO-GDL-FLANN) for Classification

2015 ◽  
pp. 211-220 ◽  
Author(s):  
Bighnaraj Naik ◽  
Janmenjoy Nayak ◽  
H. S. Behera
Keyword(s):  
Honey Bee ◽  
Gradient Descent ◽  
Honey Bee Mating Optimization

Image vector quantization algorithm via honey bee mating optimization

2011 ◽  
Vol 38 (3) ◽  
pp. 1382-1392 ◽  
Author(s):  
Ming-Huwi Horng ◽  
Ting-Wei Jiang
Keyword(s):  
Honey Bee ◽  
Vector Quantization ◽  
Honey Bee Mating Optimization

Application of Honey-Bee Mating Optimization to Naphtha Reforming Reactor

2013 ◽  
Vol 11 (1) ◽  
pp. 293-308 ◽  
Author(s):  
Somayeh Karimi ◽  
Navid Mostoufi ◽  
Rahmat Sotudeh-Gharebagh
Keyword(s):  
Objective Function ◽  
Honey Bee ◽  
Process Model ◽  
Global Optimum ◽  
Inlet Temperature ◽  
Local Optimum ◽  
Naphtha Reforming ◽  
Decision Variables ◽  
Algorithm Comparison ◽  
Honey Bee Mating Optimization

Abstract Modeling and optimization of the process of continuous catalytic reforming (CCR) of naphtha was investigated. The process model is based on a network of four main reactions which was proved to be quite effective in terms of industrial application. Temperatures of the inlet of four reactors were selected as the decision variables. The honey-bee mating optimization (HBMO) and the genetic algorithm (GA) were applied to solve the optimization problem and the results of these two methods were compared. The profit was considered as the objective function which was subject to maximization. Optimization of the CCR moving bed reactors to reach maximum profit was carried out by the HBMO algorithm and the inlet temperature reactors were considered as decision variables. The optimization results showed that an increase of 3.01% in the profit can be reached based on the results of the HBMO algorithm. Comparison of the performance of optimization by the HBMO and the GA for the naphtha reforming model showed that the HBMO is an effective and rapid converging technique which can reach a better optimum results than the GA. The results showed that the HBMO has a better performance than the GA in finding the global optimum with fewer number of objective function evaluations. Also, it was shown that the HBMO is less likely to get stuck in a local optimum.

scholarly journals Implementasi Honey Bee Mating Optimization Pada Vehicle Routing Problem With Time Windows Dalam Perencanaan Jalur Wisata Malang

Repositor ◽  
2020 ◽  
Vol 2 (4) ◽  
pp. 495
Author(s):  
M Syawaluddin Putra Jaya ◽  
Yufiz Azhar ◽  
Nur Hayatin
Keyword(s):  
Honey Bee ◽  
Royal Jelly ◽  
Time Windows ◽  
Route Planning ◽  
Routing Problem ◽  
Capacity Limit ◽  
Shortest Route ◽  
Mutation Ratio ◽  
Bee Colonies ◽  
Honey Bee Mating Optimization

Abstrak Vahicle Routing Problem adalah suatu masalah pencaian jalur yang akan dilalui dengan tujuan mencari rute yang paling cepat atau pendek. Vahicle Routing Problem with Time Windows (VRPTW) yang merupakan sebutan bagi VRP dengan kendala tambahan berupa adanya time windows pada masing-masing pelanggan yang dalam hal ini berupa destinasi wisata. Dalam penelitian ini diterapkan Honey Bee Mating Optimization (HBMO) dalam menyelesaikan VRPTW. HBMO sendiri terinspirasi oleh perilaku koloni lebah ketika bereproduksi. Algoritma tersebut bertujuan untuk mengevaluasi pencarian individu atau solusi terbaik. Tujuan dari penelitian ini adalah bagaimana mengimplementasikan Honey Bee Mating Optimization dalam menyelesaikan VRPTW pada perencanaan jalur wisata di Malang. Sehingga dapat meminimumkan waktu dan jarak tempuh perjalanan. Berdasarkan hasil pengujian, parameter yang optimal untuk optimasi VRPTW menggunakan HBMO pada kasus perencannan jalur wisata Malang yaitu dengan menggunakan 800 generasi, populasi lebah jantan sebesar 300, batas kapasitas spermatheca sejumlah 100, nilai mutation ratio (Pm) dan royal jelly masing-masing bernilai 0.5.Abstract Vahicle Routing Problem is a problem of finding the best route that will be passed with the purpose to finding the fastest or shortest route. Vahicle Routing Problem with Time Windows (VRPTW) is a part of VRP with additional obstacles in the form of time windows in each customer. In this research, Honey Bee Mating Optimization (HBMO) was applied to completing VRPTW. HBMO itself was inspired by the behavior of bee colonies when reproducing. The purpose of this algorithm is to evaluate the best individual or the best solutions. The purpose of this research is how to implement Honey Bee Mating Optimization to completing VRPTW in Malang tourism route planning. So that it can minimize travel time and distance. Based on the results of the testing, the optimal parameters for VRPTW optimization using HBMO in Malang tourism route planning case are using 800 generations, the male bee population is 300, the capacity limit of spermatheca is 100, the mutation ratio (Pm) and royal jelly are respectively 0.5.

Sign in / Sign up

Export Citation Format

Share Document