The Use of Supervised Learning Models in Studying Agonistic Behavior and Communication in Weakly Electric Fish

Abstract

Despite considerable advances, studying electrocommunication of weakly electric fish, particularly in pulse-type species, is challenging as very short signal epochs at variable intervals from a few hertz up to more than 100 Hz need to be assigned to individuals. In this study, we show that supervised learning approaches offer a promising tool to automate or semiautomate the workflow, and thereby allowing the analysis of much longer episodes of behavior in a reasonable amount of time. We provide a detailed workflow mainly based on open resource software. We demonstrate the usefulness by applying the approach to the analysis of dyadic interactions of Gnathonemus petersii. Coupling of the proposed methods with a boundary element modeling approach, we are thereby able to model the information gained and provided during agonistic encounters. The data indicate that the passive electrosensory input, in particular, provides sufficient information to localize a contender during the pre-contest phase, fish did not use or rely on the theoretically also available sensory information of the contest outcome-determining size difference between contenders before engaging in agonistic behavior.

Mormyrid fish as models for investigating sensory‐motor integration: A behavioural perspective

“…von der Emde & Bleckmann, 1998 ; von der Emde & Zeymer, 2020 ), communication (e.g. Pedraja et al., 2021 ) and spatial navigation (e.g. Jung et al., 2019 ; Schumacher, von der Emde, et al., 2017 ).…”

“…Jun et al., 2014) and machine learning (e.g. Pedraja et al., 2021) have improved the interpretation of behaviour in laboratory conditions while reducing the need for more invasive measures. Finally, it makes sense to take a behavioural approach given that evolution ultimately acts on behaviour (see these works for discussions of behaviour in an evolutionary context: Piaget, 2006; Slater & Halliday, 1994; Stevens, 2013).…”

Tracking spatial patterns and nocturnal arousal in an undisturbed natural population of the pulse-type weakly electric fishGymnotus omarorum

“…Gymnotus omarorum is a pulse-type weakly electric fish widely distributed in the southern boundary of gymnotiform distribution in South America 17,18 . It has been extensively studied as a model system for the understanding of the anatomo-functional principles of active electroreception 19 and of the neuroendocrine mechanisms underlying intra-and inter-sexual year-round territorial aggression 20,21 .…”

“…Recent studies have succeeded in the remote tracking of wave-type electric fish in the wild based on the individual-specific EOD frequency 3,10,13,14 . However, given that the EOD rate of pulse-type electric fish is highly variable and context dependent, individual monitoring has only been achieved so far with the help of video tracking and machine learning, methods that are not feasible to implement in the wild 15,16 .Gymnotus omarorum is a pulse-type weakly electric fish widely distributed in the southern boundary of gymnotiform distribution in South America 17,18 . It has been extensively studied as a model system for the understanding of the anatomo-functional principles of active electroreception 19 and of the neuroendocrine mechanisms underlying intra-and inter-sexual year-round territorial aggression 20,21 .…”

Advances in non-invasive tracking of wave-type electric fish in natural and laboratory settings

“…For pulse-type electric fish, tracking individual EODs is rather challenging, since signal features largely overlap between individual fish, i.e., EOD frequencies are highly variable and context dependent (Hagedorn, 1988). In order to, nevertheless, track electric behaviors of pulse-type fish, additional spatiotempoal tracking using video recordings and elaborate machinelearning approaches are usually required (Jun et al, 2013;Pedraja et al, 2021). In wave-type electric fish, however, the frequency of EODs is individual specific and remarkably stable over minutes to hours (Moortgat et al, 1998), providing a characteristic biometric cue which facilitates individual signal tracking.…”