Machine learning enables improved runtime and precision for bio-loggers on seabirds

Korpela, Joseph; Suzuki, Hirokazu; Matsumoto, S.; Mizutani, Yuichi; Samejima, Masaki; Maekawa, Taira; Nakai, Junichi; Yoda, Ken

doi:10.1038/s42003-020-01356-8

Cited by 34 publications

(36 citation statements)

References 37 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This new tool therewith bears the promise of continuous and long-term behavioural studies, addressing a wide range of behavioural and ecological topics, including allowing precise, behaviour-triggered sampling (e.g. [ 34 ]) and interventions and experimental research. As an extension of such behavioural studies, the same data might also be used to assist in assessing energy expenditure, biomechanics and assist in track dead-reckoning.…”

Section: Discussionmentioning

confidence: 99%

“…In another on-board data processing study in juvenile southern elephant seals ( Mirounga leonine ), Cox et al [ 28 ] identified foraging behaviour by user-defined thresholds based on expert opinion and validated their method by comparison of on-board calculated foraging behaviours with foraging behaviours identified from archived raw ACC data. Korpela et al [ 34 ] used on-board behaviour classification through ACC data to detect foraging behaviour of seabirds, triggering video-loggers to record the foraging behaviour. Moreover, to our knowledge, no published behaviour classification has compared the practicability of the aforementioned more sophisticated classification methods (i.e.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An evaluation of machine learning classifiers for next-generation, continuous-ethogram smart trackers

Deng²,

Nathan

et al. 2021

Mov Ecol

View full text Add to dashboard Cite

Background Our understanding of movement patterns and behaviours of wildlife has advanced greatly through the use of improved tracking technologies, including application of accelerometry (ACC) across a wide range of taxa. However, most ACC studies either use intermittent sampling that hinders continuity or continuous data logging relying on tracker retrieval for data downloading which is not applicable for long term study. To allow long-term, fine-scale behavioural research, we evaluated a range of machine learning methods for their suitability for continuous on-board classification of ACC data into behaviour categories prior to data transmission. Methods We tested six supervised machine learning methods, including linear discriminant analysis (LDA), decision tree (DT), support vector machine (SVM), artificial neural network (ANN), random forest (RF) and extreme gradient boosting (XGBoost) to classify behaviour using ACC data from three bird species (white stork Ciconia ciconia, griffon vulture Gyps fulvus and common crane Grus grus) and two mammals (dairy cow Bos taurus and roe deer Capreolus capreolus). Results Using a range of quality criteria, SVM, ANN, RF and XGBoost performed well in determining behaviour from ACC data and their good performance appeared little affected when greatly reducing the number of input features for model training. On-board runtime and storage-requirement tests showed that notably ANN, RF and XGBoost would make suitable on-board classifiers. Conclusions Our identification of using feature reduction in combination with ANN, RF and XGBoost as suitable methods for on-board behavioural classification of continuous ACC data has considerable potential to benefit movement ecology and behavioural research, wildlife conservation and livestock husbandry.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An evaluation of machine learning classifiers for next-generation, continuous-ethogram smart trackers

Deng²,

Nathan

et al. 2021

Mov Ecol

View full text Add to dashboard Cite

show abstract

“…Furthermore, since our system cannot synchronize external event signals in deeper water and only record neuronal activity for a few hours, neuronal recordings need to be operated automatically and locally above the fish's head. A state-of-the-art AI-assisted biologger [22] can accomplish such tasks, detect interest behaviors in real time, and activate sensors such as gyroscopes, acceleration, and water depth. In a natural environment, it is desirable to run this system with an AI-assisted biologger to start recording neuronal activity at the time of interest.…”

Section: Discussionmentioning

confidence: 99%

Wireless logging of extracellular neuronal activity in the telencephalon of free-swimming salmonids

et al. 2021

Self Cite

View full text Add to dashboard Cite

Background Salmonids return to the river where they were born in a phenomenon known as mother-river migration. The underpinning of migration has been extensively examined, particularly regarding the behavioral correlations of external environmental cues such as the scent of the mother-river and geomagnetic compass. However, neuronal underpinning remains elusive, as there have been no biologging techniques suited to monitor neuronal activity in the brain of large free-swimming fish. In this study, we developed a wireless biologging system to record extracellular neuronal activity in the brains of free-swimming salmonids. Results Using this system, we recorded multiple neuronal activities from the telencephalon of trout swimming in a rectangular water tank. As proof of principle, we examined the activity statistics for extracellular spike waveforms and timing. We found cells firing maximally in response to a specific head direction, similar to the head direction cells found in the rodent brain. The results of our study suggest that the recorded signals originate from neurons. Conclusions We anticipate that our biologging system will facilitate a more detailed investigation into the neural underpinning of fish movement using internally generated information, including responses to external cues.

show abstract

“…With increasing tag capabilities and memory and battery capacities, combining fine-scale behaviour classifications with alternate analysis methods could provide novel insights into the foraging and energetic ecology of seabirds. Custom video and GPS tags [41] attached to streaked shearwaters, where video recordings were turned on when on-board processing estimated area-restricted search behaviour occurred, focussed the video recordings to periods related to foraging. Developing the method presented in this paper could allow a similar application of on-board processing of acceleration data to record foraging behaviour, increasing the sample size of recorded foraging behaviours in streaked shearwaters and other shallow-diving seabirds.…”

Section: Future Stepsmentioning

confidence: 99%

Video and acceleration records of streaked shearwaters allows detection of two foraging behaviours associated with large marine predators

et al. 2021

View full text Add to dashboard Cite

The study of seabird behaviour has largely relied on animal-borne tags to gather information, requiring interpretation to estimate at-sea behaviours. Details of shallow-diving birds’ foraging are less known than deep-diving species due to difficulty in identifying shallow dives from biologging devices. Development of smaller video loggers allow a direct view of these birds’ behaviours, at the cost of short battery capacity. However, recordings from video loggers combined with relatively low power usage accelerometers give a means to develop a reliable foraging detection method. Combined video and acceleration loggers were attached to streaked shearwaters in Funakoshi-Ohshima Island (39°24’N,141°59’E) during the breeding season in 2018. Video recordings were classified into behavioural categories (rest, transit, and foraging) and a detection method was generated from the acceleration signals. Two foraging behaviours, surface seizing and foraging dives, are reported with video recordings. Surface seizing was comprised of successive take-offs and landings (mean duration 0.6 and 1.5s, respectively), while foraging dives were shallow subsurface dives (3.2s mean duration) from the air and water surface. Birds were observed foraging close to marine predators, including dolphins and large fish. Results of the behaviour detection method were validated against video recordings, with mean true and false positive rates of 90% and 0%, 79% and 5%, and 66% and <1%, for flight, surface seizing, and foraging dives, respectively. The detection method was applied to longer duration acceleration and GPS datasets collected during the 2018 and 2019 breeding seasons. Foraging trips lasted between 1 − 8 days, with birds performing on average 16 surface seizing events and 43 foraging dives per day, comprising <1% of daily activity, while transit and rest took up 55 and 40%, respectively. This foraging detection method can address the difficulties of recording shallow-diving foraging behaviour and provides a means to measure activity budgets across shallow diving seabird species.

show abstract

Machine learning enables improved runtime and precision for bio-loggers on seabirds

Cited by 34 publications

References 37 publications

An evaluation of machine learning classifiers for next-generation, continuous-ethogram smart trackers

An evaluation of machine learning classifiers for next-generation, continuous-ethogram smart trackers

Wireless logging of extracellular neuronal activity in the telencephalon of free-swimming salmonids

Video and acceleration records of streaked shearwaters allows detection of two foraging behaviours associated with large marine predators

Contact Info

Product

Resources

About