China
Africa
Explore chapters and articles related to this topic
Recent Trends in 5G and Machine Learning, Challenges, and Opportunities
Published in Uzzal Sharma, Parmanand Astya, Anupam Baliyan, Salah-ddine Krit, Vishal Jain, Mohammad Zubair Khan, Advancing Computational Intelligence Techniques for Security Systems Design, 2023
S. Kannadhasan, R. Nagarajan, M. Shanmuganantham
We investigated the application of deep learning in applied EM. Advances in machine-learning algorithms might aid other fields, such as engineering. Since there has been no visible progress in the radar image classification, the use of the radar image classification in the antenna design field is intended to enable non-experienced engineers by aiding in the design of conventional antennas or discovering innovative antenna designs. In order to get high numerical performance, the optimization of architectural parameters is currently the most significant problem, as shown in Figure 5.2. The literature has suggested genetic algorithms (GA), particle swarm optimization (PSO), Biogeography Based Optimization (BBO), neural networks, and other approaches for design optimization. The optimization methodology is a method for determining the minimum and maximum of a cost function-defined operator. The optimizers alter the vector equations before the lowest has a firm hold on anything. The error function (EF) or search methods (SM) formulas identify the optimizers. The majority of the above-mentioned optimization techniques may be applied in simulation applications. The electromagnetic simulation software HFSS and CST employ one or more of the mathematical optimizers listed below to obtain a broad variety of capabilities: Non-linear programming approaches include ANN (MATLAB compatible), Quasi Newton, Sequential Non-linear Programming (SNLP), Sequential Mixed Integer Non-linear Programming (SMINLP), and GA. ANN allows you to customize antenna characteristics including return loss, bandwidth, scale, and gain. To increase energy economy while preserving users' quality of service (QoS) needs, a collaborative architecture for antenna selection and power delivery for multi-user multi-antenna downlinks was developed.
Hybrid Cartesian Genetic Programming Algorithms: A Review
Published in Siddhartha Bhattacharyya, Václav Snášel, Indrajit Pan, Debashis De, Hybrid Computational Intelligence, 2019
Johnathan Melo Neto, Heder S. Bernardino, Helio J.C. Barbosa
Biogeography-Based Optimization (BBO) [69] is an evolutive algorithm that has the science of biogeography as inspiration. The individuals, also called habitats, represent candidate solutions and they are composed of solution features. Those features are called Suitability Index Variables (SIVs), and each individuals fitness is described by its corresponding Habitat Suitability Index (HSI). Therefore, high-HSI solutions are good individuals, whereas the low-HSI individuals represent the poor ones. The migration and mutation are the main BBO operators.
Dialectics of Nature: Inspiration for Computing
Published in Nazmul Siddique, Hojjat Adeli, Nature-Inspired Computing, 2017
MacArthur and Wilson (1967) developed mathematical models of biogeography that describe how species migrate from one island to another, how new species arise, and how species become extinct. Since the 1960s, biogeography has become a major area of research that studies the geographical distribution of biological species. On the basis of the concept of biogeography, Simon (2008) derived a new family of algorithms for optimization called biogeography-based optimization (BBO).
Optimization research on load dispatch in gas-steam combined cycle units
Published in Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 2020
Hui Gu, Hongxia Zhu, Fengqi Si
The basic biogeography-based optimization (BBO) algorithm, first proposed by D. Simon, including a population of potential solutions, called islands or habitats (Roy & Ghosh, 2017). This algorithm designs a probability-based individual move operation, so that the information exchanging between individuals can be completed by adjusting the immigration rate and the emigration rate . Moreover, the mutation operation is introduced to increase the diversity of the population, and the mutation probability of each individual has its own characteristics (Yadav & Banka, 2016). With the migration and variation of individuals, the algorithm gradually approaches the habitat with the highest adaptability, and the final habitat is the optimal solution of the problem.
Biogeography-based Optimization of Artificial Neural Network (BBO-ANN) for Solar Radiation Forecasting
Published in Applied Artificial Intelligence, 2023
Ajay Kumar Bansal, Virendra Swaroop Sangtani, Pankaj Dadheech, Nagender Aneja, Umar Yahya
A biogeography-based optimization method was developed by (Simon 2008). Biogeography-based optimization (BBO) is a blend of bio-inspired optimization and population-based evolutionary algorithm (EA) (Bansal and Garg 2021). Biogeography is the study of species’ behavior in nature concerning time and distance, as well as the movement of species across environments. The population combines tentative solutions generated by the BBO algorithm, represented as a vector of numbers (Mandal et al. 2011). The BBO algorithm uses the migration operator to facilitate the transfer of information across solutions. The adaptable qualities of the BBO algorithm promote its use for resolving complicated optimum sizing problems involving hybrid energy systems.
Optimization of water distribution networks using hybrid BBO-IWO algorithm
Published in Urban Water Journal, 2023
Biogeography-based optimization (BBO) algorithm is a population-based heuristic algorithm developed by Simon (2008) that deals with the emergence of new species as a result of the interaction between living things in different habitats. In terms of mathematical point of view, BBO is an algorithm that explains how species migrate from one island to another, how new species emerge, and how existing species disappear. In this algorithm, each name represents the possible sets of solutions for the problem. In the BBO algorithm, each habitat has a habitat fitness index (HSI), which depends on values such as precipitation, vegetation, temperature, amount of nutrients, etc. HSI corresponds to the fitness value calculated in other population-based algorithms. Suitability index variable ( refers to the independent variables of habitats. In the BBO algorithm, a random habitat is created at the beginning (). It then proceeds with migration and mutation processes to achieve the goal. The migration rate and the immigration rate information is shared between living environments. Each individual has μ immigration rate and immigration rate , and each solution is modified depending on the pmutate probability parameter defined by the user. The Immigration rate () and the migration rate () are calculated using Equations (4) and (5), respectively, (Haiping and Simon 2011).