Genetic Optimization of Artificial Neural Networks to Forecast Virioplankton Abundance from Cytometric Data

Pereira, G. C.; Oliveira, Marilia Mitidieri Fernandes de; Ebecken, Nelson F. F.

doi:10.4236/jilsa.2013.51007

Cited by 6 publications

(4 citation statements)

References 68 publications

(67 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 1 shows a typical GA as described in [27]. The common problem-dependent constituents of genetic algorithm include the following: the encoding and the evaluation functions.…”

Section: Review Of Ga Representationsmentioning

confidence: 99%

Choosing Mutation and Crossover Ratios for Genetic Algorithms—A Review with a New Dynamic Approach

et al. 2019

View full text Add to dashboard Cite

Genetic algorithm (GA) is an artificial intelligence search method that uses the process of evolution and natural selection theory and is under the umbrella of evolutionary computing algorithm. It is an efficient tool for solving optimization problems. Integration among (GA) parameters is vital for successful (GA) search. Such parameters include mutation and crossover rates in addition to population that are important issues in (GA). However, each operator of GA has a special and different influence. The impact of these factors is influenced by their probabilities; it is difficult to predefine specific ratios for each parameter, particularly, mutation and crossover operators. This paper reviews various methods for choosing mutation and crossover ratios in GAs. Next, we define new deterministic control approaches for crossover and mutation rates, namely Dynamic Decreasing of high mutation ratio/dynamic increasing of low crossover ratio (DHM/ILC), and Dynamic Increasing of Low Mutation/Dynamic Decreasing of High Crossover (ILM/DHC). The dynamic nature of the proposed methods allows the ratios of both crossover and mutation operators to be changed linearly during the search progress, where (DHM/ILC) starts with 100% ratio for mutations, and 0% for crossovers. Both mutation and crossover ratios start to decrease and increase, respectively. By the end of the search process, the ratios will be 0% for mutations and 100% for crossovers. (ILM/DHC) worked the same but the other way around. The proposed approach was compared with two parameters tuning methods (predefined), namely fifty-fifty crossover/mutation ratios, and the most common approach that uses static ratios such as (0.03) mutation rates and (0.9) crossover rates. The experiments were conducted on ten Traveling Salesman Problems (TSP). The experiments showed the effectiveness of the proposed (DHM/ILC) when dealing with small population size, while the proposed (ILM/DHC) was found to be more effective when using large population size. In fact, both proposed dynamic methods outperformed the predefined methods compared in most cases tested.

show abstract

“…Figure 1 shows a typical GA as described in [27]. The common problem-dependent constituents of genetic algorithm include the following: the encoding and the evaluation functions.…”

Section: Review Of Ga Representationsmentioning

confidence: 99%

Choosing Mutation and Crossover Ratios for Genetic Algorithms—A Review with a New Dynamic Approach

et al. 2019

View full text Add to dashboard Cite

show abstract

“…For real time data acquisition the CytoSense flow cytometry (CytoBuoy bv, Worden, The Netherlands) was used with the same configurations of [15]. This device is connected to the computer by Wi-Fi connection and data transferred by the Internet for remote operation.…”

Section: Data Acquisition and In Situ Flow Cytometrymentioning

confidence: 99%

“…The CytoSense is equipped with a solid blue laser providing 20 mW at 488 nm, one frontal sensor named forward scatter (FWS) which measures the light deviation angle according to the passage of the particle through the laser, one side scatter (SWS, 446/500 nm) detector measuring the reflected light that has interacted with structures within the cells giving a sense of its granularity, and three others sensors to detect the red fluorescence produced by the amount of chlorophyll-a (FLR, 669/725 nm); one orange/yellow (FLO, 601/651) sensor and a green/yellow (FLY, 515/585 nm) sensor that measure the amount of phycocyanin and phycoerythrin fluorescences respectively [15].…”

Section: Data Acquisition and In Situ Flow Cytometrymentioning

confidence: 99%

Structural Analysis and Static Simulation of Coastal Planktonic Networks

Pereira

Andrade²,

Espíndola³

et al. 2014

JILSA

Self Cite

View full text Add to dashboard Cite

The coastal marine habitats are often characterized by high biological activity. Therefore, monitoring programs and conservation plans of coastal environments are needed. So, in order to contribute to decision making process of the Brazilian Information System of Coastal Management, this paper presents a preliminary analysis of the effects of simulated deletions of individual organisms within a planktonic network as knowledge acquisition platform. An in situ scanning flow cytometer was used to data acquisition. A static and undirected food web is generated and represented by a fuzzy graph structure. Our results show through a series of indices the main changes of these networks. It was also verified similar traits and properties with other food webs found in the literature.

show abstract

“…This characteristic has been extensively explored in the field of artificial intelligence, particularly with regard to neural networks (NNs), which are well suited for addressing this issue and have relevant applications in the airdrop field. Compared to previous methods, deep learning methods [31] and backpropagation neural network (BPNN) approaches avoid complex model derivation and significantly reduce modeling difficulty [32]. L.W.…”

Section: Introductionmentioning

confidence: 99%

Modeling and Application of Out-of-Cabin and Extra-Vehicular Dynamics of Airdrop System Based on Kane Equation

Wang,

Yang

2023

Aerospace

View full text Add to dashboard Cite

The application of the Kane equation in analyzing airdrop dynamics problems is rare. The main objective of this paper is to apply the Kane equation dynamics model to the analysis of the status continuity problem during the out-of-cabin process and the line sail phenomenon during the extra-vehicular process. In the out-of-cabin process, an analysis of off-aircraft security and traction ratio impact was conducted. Furthermore, the BP neural network model was trained to predict the status transition of the payload for a multiple airdrop mission. In the extra-vehicular process, the spring network method was used together with the Kane equation to analyze the form and overload of the parachute line. The modeling avoids complex equations and derivations. The results suggest significant potential applications of the Kane equation in precision airdrop missions during out-of-cabin and extra-vehicular processes without heavy reliance on experimental data.

show abstract

Genetic Optimization of Artificial Neural Networks to Forecast Virioplankton Abundance from Cytometric Data

Cited by 6 publications

References 68 publications

Choosing Mutation and Crossover Ratios for Genetic Algorithms—A Review with a New Dynamic Approach

Choosing Mutation and Crossover Ratios for Genetic Algorithms—A Review with a New Dynamic Approach

Structural Analysis and Static Simulation of Coastal Planktonic Networks

Modeling and Application of Out-of-Cabin and Extra-Vehicular Dynamics of Airdrop System Based on Kane Equation

Contact Info

Product

Resources

About