Figure - available from: Communications Biology
This content is subject to copyright. Terms and conditions apply.
Generating space-efficient trees a Our process for the weighted random selection of features. We start with a list of features along with their required programme memory sizes in bytes (first panel). Each feature is assigned a weight proportional to the inverse of its size, illustrated using a pie chart where each feature has been assigned a slice proportional to its weight (second panel). We then perform weighted random selection to choose the subset of features that will be used when creating a new node in the tree. In this example, we have randomly placed four dots along the circumference of the circle to simulate the selection of four features (second panel). The resulting subset of features will then be compared when making the next node in the decision tree (third panel). b Example decision tree built using scikit-learn’s default decision tree classifier algorithm using the black-tailed gull data described in “Methods”. Each node is coloured based on its corresponding feature’s estimated size in bytes when implemented on board the bio-logger (scale shown in the colour bar). c Several space-efficient decision trees generated using the proposed method from the same data used to create the tree in (b). d Example space-efficient tree selected from the trees shown in (c) that costs much less than the default tree in (b) while maintaining almost the same accuracy.
Source publication
Unravelling the secrets of wild animals is one of the biggest challenges in ecology, with bio-logging (i.e., the use of animal-borne loggers or bio-loggers) playing a pivotal role in tackling this challenge. Bio-logging allows us to observe many aspects of animals’ lives, including their behaviours, physiology, social interactions, and external env...
Citations
... One way to increase ecological velocity is to use artificial intelligence (AI), with machine learning algorithms processing continuous streams of data to provide inference and insights (Christin et al., 2019;Goodwin et al., 2022;Makiola et al., 2020). Early applications in this realm include real-time event identification in biologgers for tracking animal movement (Korpela et al., 2020), automatic identification and counting of animals from camera trap images (Norouzzadeh et al., 2021) and automated analysis of animal behaviour from video data (Williams & DeLeon, 2020). ...
Ecological research and monitoring need to be able to rapidly convey information that can form the basis of scientifically sound management. Automated sensor systems, especially if combined with artificial intelligence, can contribute to such rapid high resolution data retrieval. Here, we explore the prospects of automated methods to generate insights for seabirds, which are often monitored for their high conservation value and for being sentinels for marine ecosystem changes. We have developed a system of video surveillance combined with automated image processing, which we apply to common murres Uria aalge. The system uses a deep learning algorithm for object detection (YOLOv5)that has been trained on annotated images of adult birds, chicks and eggs, and outputs time, location, size and confidence level of all detections, frame-by-frame, in the supplied video material. A total of 144 million bird detections were generated from a breeding cliff over three complete breeding seasons(2019–2021). We demonstrate how object detection can be used to accurately monitor breeding phenology and chick growth. Our automated monitoring approach can also identify and quantify rare events that are easily missed in traditional monitoring, such as disturbances from predators. Further, combining automated video analysis with continuous measurements from a temperature logger allows us to study impacts of heat waves on nest attendance in high detail. Our automated system thus produces comparable, and in several cases significantly more detailed, data than those generated from observational fieldstudies. By running in real time on the camera streams, it has the potential to supply researchers and managers with high-resolution up-to-date information on seabird population status. We describe how the system can be modified to fit various types of ecological research and monitoring goals and thereby provide up-to-date support for conservation and ecosystem management.
... One way to solve this problem is to use recently developed video loggers with eventtrigger function. In marine animals, efficient recording of feeding behavior has been achieved by acceleration-triggered video loggers (Yoshino et al. 2020) and AI-assisted video loggers (Korpela et al. 2020). Such devices would be helpful in observing low-frequency predation events and examining pursuit and antipredator strategies in various animals. ...
... Usually, unsupervised approaches are used when validation data are not available, in contrast to a supervised approach making use of pre-labelled known behavioural activities recorded. While unsupervised approaches (e.g., Expectation Maximisation, k-means) independently detect behaviours and allow for the detection of unknown behaviours 20,26 , supervised approaches (e.g., Random Forest, Support Vector Machine) are fast and reliable on known behaviours 27,28 . Whilst both approaches have their strengths, they also have their individual and shared weaknesses and can be complementary. ...
... Finally, training datasets accounting for behavioural variability could be applied to increasingly larger databases and/or used for real-time processing of accelerometer data on board of bio-logging devices to facilitate transmission via satellite systems 27 . While our framework has been tested on two penguin species, it is transferable to other species and systems. ...
Animal-borne tagging (bio-logging) generates large and complex datasets. In particular, accelerometer tags, which provide information on behaviour and energy expenditure of wild animals, produce high-resolution multi-dimensional data, and can be challenging to analyse. We tested the performance of commonly used artificial intelligence tools on datasets of increasing volume and dimensionality. By collecting bio-logging data across several sampling seasons, datasets are inherently characterized by inter-individual variability. Such information should be considered when predicting behaviour. We integrated both unsupervised and supervised machine learning approaches to predict behaviours in two penguin species. The classified behaviours obtained from the unsupervised approach Expectation Maximisation were used to train the supervised approach Random Forest. We assessed agreement between the approaches, the performance of Random Forest on unknown data and the implications for the calculation of energy expenditure. Consideration of behavioural variability resulted in high agreement (> 80%) in behavioural classifications and minimal differences in energy expenditure estimates. However, some outliers with < 70% of agreement, highlighted how behaviours characterized by signal similarity are confused. We advise the broad bio-logging community, approaching these large datasets, to be cautious when upscaling predictions, as this might lead to less accurate estimates of behaviour and energy expenditure.
... Recently, intelligent biologgers, termed Logbots, have been developed. They are operated by machine learning algorithms implemented in a microcontroller that autonomously regulates the timing of logging, thereby minimizing battery consumption [45]. An intelligent Logbot-controlled neurologger is expected to unveil the neural correlate of long-distance movements in the future. ...
Simultaneous monitoring of animal behavior and neuronal activity in the brain enables us to examine the neural underpinnings of behaviors. Conventionally, the neural activity data are buffered, amplified, multiplexed, and then converted from analog to digital in the head-stage amplifier, following which they are transferred to a storage server via a cable. Such tethered recording systems, intended for indoor use, hamper the free movement of animals in three-dimensional (3D) space as well as in large spaces or underwater, making it difficult to target wild animals active under natural conditions; it also presents challenges in realizing its applications to humans, such as the Brain–Machine Interfaces (BMI). Recent advances in micromachine technology have established a wireless logging device called a neurologger, which directly stores neural activity on ultra-compact memory media. The advent of the neurologger has triggered the examination of the neural correlates of 3D flight, underwater swimming of wild animals, and translocation experiments in the wild. Examples of the use of neurologgers will provide an insight into understanding the neural underpinnings of behaviors in the natural environment and contribute to the practical application of BMI. Here we outline the monitoring of the neural underpinnings of flying and swimming behaviors using neurologgers. We then focus on neuroethological findings and end by discussing their future perspectives.
... In addition, the development of sophisticated techniques such as artificial intelligence and machine learning are emerging as cuttingedge and powerful tools to process large and complex datasets. The utilisation of the "trainingandtesting" procedure has proven to be an efficient method for classifying and quantifying behavioural modes over large datasets composed of geographical fixes, accelerometer data and video records with high precision and accuracy (Browning et al. 2018, Yoda 2019, Korpela et al. 2020). However, these methods usually require the use of programming languages and/or processing software whose interfaces are not user friendly for those starting to learn it. ...
In the past three decades scientists have been equipping free-living seabirds with biologging devices to provide information about their behaviour in unprecedented detail. However, more recently the miniaturisation of tracking devices, have enabled scientists to understand the precise distribution patterns of seabirds across a variety of scales and species. As tags have become smaller and cheaper, seabird tracking studies and number of individuals have increased exponentially. This has allowed scientists to identify the major sources of anthropogenic stressors affecting seabirds in the marine environment and for resolving marine conservation issues. The increasing volume and complexity of tracking data has lead scientists to develop effective tools for data mining and spatial analysis with further benefits for seabird conservation. However, they often require high levels of expertise and considerable computation capacities which turn their use by policy makers and managers challenging. In this book chapter we overview the recent advances in tracking devices currently used to study seabird distribution and discuss the challenges and how they can be important for resolving marine conservation issues.
... A fascinating recent study by Korpela et al. (2020) ...
Over the past two decades accelerometer (ACC) data has been increasingly used to study animal behaviours and energetics. However, the large amount of raw ACC data can be a burden to device storage and power consumption and in many cases may also require device retrieval for data collection. On‐board data processing to reduce data volume and power consumption for data transmission may hold promise to alleviate these problems and allow for next‐generation, smart trackers. We developed a tracking system processing raw ACC data on‐board of trackers into behaviours using an XGBoost machine learning model. We used this system on six free‐ranging Pacific black ducks (Anas superciliosa) to study eight behaviours every 2 seconds. The on‐board XGBoost model for behaviour classification had 92.04% overall accuracy. One day of continuous behaviour records was compressed on‐board to as little as 17.28 kB for routine transmission via the 3G network. We received behaviour data from the six ducks continuously for periods ranging between 56 days and 14 months. On‐board processing of raw ACC data and data transmission proofed highly energy efficient and came at a minimal weight cost to the trackers, providing great potential to open up new areas in ecological and behavioural research.
... Recovery of bio-loggers, few weeks later, can still be tedious work, but the development of satellite-relay data tags with on-board processing represents a promising alternative. Indeed, it is already possible to remotely transmit a summary of the tri-axial acceleration from satellite-relay data tags [36][37][38] and to implement the learning algorithm into the logger [39]. This next step would enable the researchers to remotely, and almost in real time, follow the nesting behaviors of the equipped individuals (with the estimation of the number of eggs laid) and to relate this information with their behaviors at sea over long periods (pre−nuptial migration, breeding season, post−nuptial migration). ...
During the reproduction period, female sea turtles come several times onto the beaches to lay their eggs. Monitoring of the nesting populations is therefore important to estimate the state of a popu-lation and its future. However, measuring the clutch size and frequency of sea turtles is tedious work that requires rigorous monitoring of the nesting site throughout the breeding season. In or-der to support the fieldwork, we propose an automatic method to remotely record the behavior on land of the sea turtles from animal-attached sensors; an accelerometer. The proposed method estimates, with an accuracy of 95%, the behaviors on land of sea turtles and the number of eggs laid. This automatic method should therefore help researchers monitor nesting sea turtle popula-tions and contribute to improving global knowledge on the demographic status of these threatened species.
... However, power supply and data storage and transmission limitations of bio-logging devices are driving efforts to optimize sampling protocols or pre-process data in order to conserve these resources and prolong the life of the devices. For example, on-board processing solutions can use data from low-cost sensors to identify behaviors of interest and engage resource-intensive sensors only when these behaviors are being performed 66 . Other on-board algorithms classify raw data into behavioral states to reduce the volume of data to be transmitted 67 . ...
Inexpensive and accessible sensors are accelerating data acquisition in animal ecology. These technologies hold great potential for large-scale ecological understanding, but are limited by current processing approaches which inefficiently distill data into relevant information. We argue that animal ecologists can capitalize on large datasets generated by modern sensors by combining machine learning approaches with domain knowledge. Incorporating machine learning into ecological workflows could improve inputs for ecological models and lead to integrated hybrid modeling tools. This approach will require close interdisciplinary collaboration to ensure the quality of novel approaches and train a new generation of data scientists in ecology and conservation. Animal ecologists are increasingly limited by constraints in data processing. Here, Tuia and colleagues discuss how collaboration between ecologists and data scientists can harness machine learning to capitalize on the data generated from technological advances and lead to novel modeling approaches.
... Collecting individuals' vocal activity is challenging when using stationary or handheld bioacoustic recorders, which are mainly suitable to monitor site-specific vocal activity that may integrate multiple individuals. On the other hand, animal-borne acoustic recorders are energy consuming and produce large volumes of data, requiring a high storing capacity (Brown et al., 2013;Gill et al., 2016;Greif & Yovel, 2019;Hughey et al., 2018;Korpela et al., 2020). The size, weight, and limited recording duration (~24 h, Couchoux et al., 2015; form important restrictions to their use beyond laboratory settings. ...
Abstract To acquire a fundamental understanding of animal communication, continuous observations in a natural setting and at an individual level are required. Whereas the use of animal‐borne acoustic recorders in vocal studies remains challenging, light‐weight accelerometers can potentially register individuals’ vocal output when this coincides with body vibrations. We collected one‐dimensional accelerometer data using light‐weight tags on a free‐living, crepuscular bird species, the European Nightjar (Caprimulgus europaeus). We developed a classification model to identify four behaviors (rest, sing, fly, and leap) from accelerometer data and, for the purpose of this study, validated the classification of song behavior. Male nightjars produce a distinctive “churring” song while they rest on a stationary song post. We expected churring to be associated with body vibrations (i.e., medium‐amplitude body acceleration), which we assumed would be easy to distinguish from resting (i.e., low‐amplitude body acceleration). We validated the classification of song behavior using simultaneous GPS tracking data (i.e., information on individuals’ movement and proximity to audio recorders) and vocal recordings from stationary audio recorders at known song posts of one tracked individual. Song activity was detected by the classification model with an accuracy of 92%. Beyond a threshold of 20 m from the audio recorders, only 8% of the classified song bouts were recorded. The duration of the detected song activity (i.e., acceleration data) was highly correlated with the duration of the simultaneously recorded song bouts (correlation coefficient = 0.87, N = 10, S = 21.7, p = .001). We show that accelerometer‐based identification of vocalizations could serve as a promising tool to study communication in free‐living, small‐sized birds and demonstrate possible limitations of audio recorders to investigate individual‐based variation in song behavior.
... For example, one could downsample the high resolution image-based data to determine the optimal sampling frequency for bio-logging studies, using the videos to verify that the resulting data capture the target behaviors. Recording and quantifying the behavior of instrumented animals could also aid in the development of behaviorally activated "smart" sensors (Korpela et al., 2020;Yu, 2021). ...
