Search bioRxiv⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.64898/2026.09.30.755682

BettaAI: a machine-learning object detection model for the quantification of aggressive displays in the Siamese fighting fish Betta splendens

Cardoso, S. D.·Fusani, B.·Ramos, A.·Maria, J. M.·Goncalves, D. M.
View original source ↗Export metadata ↓

Abstract

The Siamese fighting fish (Betta splendens) is well-known for its high levels of aggression and complex, stereotyped displays, making it an ideal model for testing deep learning-based tools for high-throughput, unbiased quantification of aggressive behaviour. A deep-learning object recognition model (BettaAI) was developed to detect the species' aggressive displays, including threat (opercula opening and fin distension), attack (bites) behaviours, as well as surface air breathing, a behaviour correlated with the frequency and intensity of aggression. Videos of males confronting their mirror image were acquired simultaneously with synchronised top and side cameras. Two separate models were trained, with some behaviours identified from top-view frames and others from side-view frames; outputs from both models were combined and post-processed for final quantification. BettaAI performed with high accuracy: F1 scores were 0.99 for the top-view model and 0.93 for the side-view model. Average Precision (AP) at 0.5 IoU exceeded 0.98 for all categories except bites, a rare behaviour in the dataset, which reached 0.865. Comparisons with a manually curated "ground-truth" dataset from videos of 10 males showed strong concordance between automated quantification and manual annotations by expert observers across all behaviours. A case study on 461 males reacting either to a mirror or to a video playback of a conspecific demonstrated the high-throughput and unbiased advantages of BettaAI, with threat displays being more frequent toward the mirror image and attack rates not differing between treatments. This work underscores the potential of BettaAI for automated, bias-free quantification of aggressive displays in B. splendens.

Explore related subjects

animal behavior and cognitionPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Cardoso, S. D., Fusani, B., Ramos, A., Maria, J. M., Goncalves, D. M.. 2026-10-06. BettaAI: a machine-learning object detection model for the quantification of aggressive displays in the Siamese fighting fish Betta splendens. https://doi.org/10.64898/2026.09.30.755682

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

Behavioral divergence across replicated predation regimes is species-specific in two sympatric poeciliid fishes

Predation is a potent driver of behavioral divergence across prey populations, yet whether shared predation regimes generate similar responses in coexisting prey species remains unclear. Species differences in reproductive and foraging traits may alter vulnerability to predators, generating species-specific responses. We compared behavior and cognition of two poeciliid fishes (Gambusia affinis and Poecilia latipinna) that differ in body size, the presence of male ornamentation, and mating tactics. We sampled both species across replicate high- and low-predation regimes and measured exploration, shyness, boldness, social motivation, and detour solve latency (N = 509). Multivariate behavior and cognition differed between predation regimes, and the magnitude of divergence varied with species but not body size. Consistent with the multivariate pattern, the more conspicuous P. latipinna exhibited higher boldness and overall lower exploration under high-predation, while high- and low-predation populations of G. affinis did not differ. These findings suggest either that the more conspicuous species experiences greater predation risk or that the less conspicuous species reduces its predation risk through alternative phenotypic responses. More broadly, species differences in reproductive phenotypes associated with sexual selection may help explain why shared predation regimes generate variable patterns of behavioral divergence across taxa.

animal behavior and cognition↗
bioRxiv2026

Capturing the rhythm: methodological choices shape inference from circadian activity data

Abstract 1. Statistical tools and analytical decisions for analysing animal activity data are often limited and poorly justified, particularly with respect to model choice, sampling design and temporal aggregation. These shortcomings can constrain our ability to draw accurate and biologically meaningful inferences about behaviour. 2. We interrogated 24 h activity data taken from individual males and females derived from five Drosophila melanogaster populations to generate a general framework for collecting and analysing activity data that systematically compares common model classes, continuous verses fragmented sampling strategies, and alternative temporal aggregation choices (time-bin sizes). 3. Our analyses identified generalised additive mixed models (GAMMs) applied to high-frequency continuous data with small-moderate bin sizes (1-5 minutes) as providing the most robust and interpretable inference for our complex, high-frequency activity data. 4. However, our interrogation of the data set confirmed that analytical and sampling decisions need to be tailored to the study species, the timing of activities and the nature of the behaviour of interest. Accordingly, polynomial and cosinor generalised linear models, increased but biologically targeted snapshot sampling, and bin sizes smaller than one hour yielded adequate analyses with similar biological conclusions when appropriately matched to the system. 5. Our approach provides an accessible decision-making framework for activity analyses that allows researchers across behavioural, ecological and evolutionary studies to justify and optimise choices about data collection and modelling. Such an approach improves the biological relevance of inference and supporting the use of modern tracking and analytical technologies.

animal behavior and cognition↗
bioRxiv2026

Greylag geese (Anser anser) initiate group flight based on the number and identities of callers

Social animals need to maintain cohesion when they move, and movement decisions are influenced by social organization and ecological or individual needs. To maintain synchrony during collective movement, the use of signals, including vocal signals, is often necessary. Greylag geese are gregarious and vocal before and during flight. We observed instances of naturally occurring flight initiation attempts in a free-living population of greylag geese -n = 133 birds- to investigate the decision-making process in this species, including the role vocalisations play in flight decisions. We recorded the number of participants in flight-initiation attempts, their vocal behaviour -using two call types specific to flight initiation signalling: Locomotion and Pre-flight calls-, the outcome of those attempts, in addition to the resulting flying group size and composition. We found that the identities and number of flock members joining in the calling chorus predicted both the probability of successful flight and the resulting flying group size. The number of Locomotion callers was associated with an increased probability of success, as well as larger flying group size, including both family and non-family fliers. The number of Pre-flight callers was also associated with a higher probability of successful flight, but its effect on the increase in flying group size was marginal. Successful departures were more probable when the family members of the initiator responded vocally. Overall, our findings are consistent with a system where the decision to fly is made individually using two distinct vocal signals to estimate the number of voters and at least the identities of social partners and progeny. In species where temporal and spatial group cohesion varies both seasonally and diurnally, individuals priorities appear to be maintaining proximity to mates and family members, followed by maximizing the size of flight groups.

animal behavior and cognition↗