Investigation of rat exploratory behavior via evolving artificial neural networks

Costa, Ariadne de Andrade; Tinós, Renato

doi:10.1016/j.jneumeth.2016.06.010

Cited by 2 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this way, comparing virtual and real rat behavior [Tarrega 2019, Campos-Cardoso et al 2021], a low-β value represents a less anxious animal. Different β values can reproduce the effects caused by different types of drugs and drug dosages (as in previous articles studying the LCE [Costa et al 2012, Costa andTinos 2016]). This is also evident for the mean of movements on the light and dark sides (not presented here).…”

Section: Resultsmentioning

confidence: 93%

“…In each generation, the virtual rats moves through the virtual apparatus for 300 time steps; experiments with real rats in the light-dark box usually last 5 minutes (i.e., 300 seconds). The fitness function used to evaluate the individuals of the GA are based on the approach/avoidance conflict model [Costa and Tinos 2016]. The fitness for individual x (vector encoding the weights of the ANN) is:…”

Section: Modelmentioning

confidence: 99%

“…The virtual rats are created by using a neuroevolution [Floreano et al 2008] approach, consisting a relevant 3R-strategy. The virtual rat for the light-dark box is based on a model originally idealized for another experimental apparatus: the elevated plus-maze (LCE) [Costa et al 2012, Costa andTinos 2016]. This approach is different from those presented in other works where real data from rats on the LCE are used to build the behavior models based on ANNs [Salum et al 2000, Miranda et al 2009, Shimo et al 2010 or Markov chains/probability models [Giddings 2002].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Simulation of Rat Behavior in a Light-Dark Box via Neuroevolution

Souza¹,

Silva²,

Tarrega³

et al. 2022

Anais Do XIX Encontro Nacional De Inteligência Artificial E Computacional (ENIAC 2022)

View full text Add to dashboard Cite

The light-dark box is a widely used test for the investigation of animal behavior commonly used to identify and study anxious-like behavioral patterns in rodents. We propose a neuroevolution model for virtual rats in a simulated light-dark box. The virtual rat is controlled by an artificial neural network (ANN) optimized by a genetic algorithm (GA). The fitness function is given by a weighed sum of two terms (punishment and reward). By changing the weight of the punishment term, we are able to simulate the effects of anxiolytic/anxiogenic drugs on rats. We also propose using GAs to optimize the number of the ANN hidden neurons and sensors for the virtual rat. According to the experiments, the best results are obtained by ANNs combining both luminosity and wall sensors.

show abstract

Section: Resultsmentioning

confidence: 93%

Section: Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Simulation of Rat Behavior in a Light-Dark Box via Neuroevolution

Souza¹,

Silva²,

Tarrega³

et al. 2022

Anais Do XIX Encontro Nacional De Inteligência Artificial E Computacional (ENIAC 2022)

View full text Add to dashboard Cite

show abstract

“…NEG is measured by tracking the first physical visit to discrete areas of the EPM. The arena is divided into a 1 cm × 1 cm grid in a similar manner to that used in previous studies (Costa & Tinós, 2016; Salum et al, 2000). The initial visit to each square is recorded, and unique visits are aggregated over time and expressed as a percentage of the total grid units of the arm type of interest or the entire maze.…”

Section: Introductionmentioning

confidence: 99%

Novel Exploration Growth Quantifies Anxiety-like Behaviour in the Elevated Plus Maze

Zelko,

Robinson,

Hill-Yardin

et al. 2024

Preprint

View full text Add to dashboard Cite

The elevated plus maze is intended to provoke anxiety-like behaviour, which is primarily measured by the degree to which the rodent explores or avoids the risker, unenclosed arms. Measures such as arm entries and total time spent within the arm are conventionally used, but their analysis often produces inconsistent inferences about the level of anxiety-like behaviour being observed. This inconsistency occurs because the measures do not correlate with one another, raising the question of how validly they capture both the exploratory and avoidance motivations that typify anxiety-like behaviour. Given this inconsistency, we propose a new measure, novel exploration growth, that captures avoidance and exploratory behaviours within the maze. The growth of novel exploration tracks the first visit to discrete areas of the maze over time. The absolute amount of novel exploration, combined with the phasic nature of the exploration, reveals behavioural phenotypes with both avoidance and exploration quantified in a single time series. By addressing both motivations evoked by the maze through a single coherent measure, we provide a superior estimation of anxiety-like behaviour and resolve inconsistencies that arise when applying conventional measures alone.

show abstract

Investigation of rat exploratory behavior via evolving artificial neural networks

Cited by 2 publications

References 32 publications

Simulation of Rat Behavior in a Light-Dark Box via Neuroevolution

Simulation of Rat Behavior in a Light-Dark Box via Neuroevolution

Novel Exploration Growth Quantifies Anxiety-like Behaviour in the Elevated Plus Maze

Contact Info

Product

Resources

About