Dataset Information

Assessment of Machine Learning Models to Identify Port Jackson Shark Behaviours Using Tri-Axial Accelerometers.

ABSTRACT: Movement ecology has traditionally focused on the movements of animals over large time scales, but, with advancements in sensor technology, the focus can become increasingly fine scale. Accelerometers are commonly applied to quantify animal behaviours and can elucidate fine-scale (<2 s) behaviours. Machine learning methods are commonly applied to animal accelerometry data; however, they require the trial of multiple methods to find an ideal solution. We used tri-axial accelerometers (10 Hz) to quantify four behaviours in Port Jackson sharks (Heterodontus portusjacksoni): two fine-scale behaviours (<2 s)-(1) vertical swimming and (2) chewing as proxy for foraging, and two broad-scale behaviours (>2 s-mins)-(3) resting and (4) swimming. We used validated data to calculate 66 summary statistics from tri-axial accelerometry and assessed the most important features that allowed for differentiation between the behaviours. One and two second epoch testing sets were created consisting of 10 and 20 samples from each behaviour event, respectively. We developed eight machine learning models to assess their overall accuracy and behaviour-specific accuracy (one classification tree, five ensemble learners and two neural networks). The support vector machine model classified the four behaviours better when using the longer 2 s time epoch (F-measure 89%; macro-averaged F-measure: 90%). Here, we show that this support vector machine (SVM) model can reliably classify both fine- and broad-scale behaviours in Port Jackson sharks.

SUBMITTER: Kadar JP

PROVIDER: S-EPMC7763149 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Assessment of Machine Learning Models to Identify Port Jackson Shark Behaviours Using Tri-Axial Accelerometers.

Kadar Julianna P JP Ladds Monique A MA Day Joanna J Lyall Brianne B Brown Culum C

Sensors (Basel, Switzerland) 20201211 24

Movement ecology has traditionally focused on the movements of animals over large time scales, but, with advancements in sensor technology, the focus can become increasingly fine scale. Accelerometers are commonly applied to quantify animal behaviours and can elucidate fine-scale (<2 s) behaviours. Machine learning methods are commonly applied to animal accelerometry data; however, they require the trial of multiple methods to find an ideal solution. We used tri-axial accelerometers (10 Hz) to q ...[more]

PMID: 33322308

Similar Datasets

Project description:Background:California horn sharks (Heterodontus francisci) are nocturnally active, non-obligate ram ventilating sharks in rocky reef habitats that play an important ecological role in regulating invertebrate communities. We predicted horn sharks would use an area restricted search (ARS) movement strategy to locate dense resource patches while minimizing energetic costs of travel and nighttime activity. As ectotherms, we predicted environmental temperature would play a significant role in driving movement and activity patterns. Methods:Continuous active acoustic tracking methods and acceleration data loggers were used to quantify the diel fine-scale spatial movements and activity patterns of horn sharks. First passage time was used to identify the scale and locations of patches indicative of ARS. Activity was assessed using overall dynamic body acceleration (ODBA) as a proxy for energy expenditure. Behavior within a patch was characterized into three activity patterns: resting, episodic burst activity, and moderate, consistent activity. Results:After resting in daytime shelters, individuals travelled to multiple reefs throughout the night, traversing through depths of 2-112?m and temperatures of 10.0-23.8?°C. All sharks exhibited area restricted search patch use and arrived at their first patch approximately 3.4?±?2.2?h (mean?±?SD) after sunset. Sharks exhibited moderate, consistent activity in 54% of the patches used, episodic burst activity in 33%, and few (13%) were identified as resting at night. ODBA peaked while sharks were swimming through relatively deeper (~?30?m), colder channels when traversing from one patch to the next. There was no consistent pattern between ODBA and temperature. Conclusions:We provide one of the largest fine-scale, high-resolution paired data sets for an elasmobranch movement ecology study. Horn sharks exhibited ARS movement patterns for various activity patterns. Individuals likely travel to reefs known to have profitable and predictable patches, potentially tolerating less suitable environmental temperatures. We demonstrate how gathering high-resolution information on the movement decisions of a community resident enhances knowledge of community structure and overall ecosystem function.

Project description:Tri-axial accelerometry has proved to be a useful technique to study animal behavior with little direct observation, and also an effective way to measure energy expenditure, allowing a refreshing revisit to optimal foraging theory. This theory predicts that individuals should gain the most energy for the lowest cost in terms of time and energy when foraging, in order to maximize their fitness. However, during a foraging trip, central-place foragers could face different trade-offs during the commuting and searching parts of the trip, influencing behavioral decisions. Using the lesser kestrel (Falco naumanni) as an example we study the time and energy costs of different behaviors during the commuting and searching parts of a foraging trip. Lesser kestrels are small insectivorous falcons that behave as central-place foragers during the breeding season. They can commute by adopting either time-saving flapping flights or energy-saving soaring-gliding flights, and capture prey by using either time-saving active hovering flights or energy-saving perch-hunting. We tracked 6 lesser kestrels using GPS and tri-axial accelerometers during the breeding season. Our results indicate that males devoted more time and energy to flight behaviors than females in agreement with being the sex responsible for food provisioning to the nest. During the commuting flights, kestrels replaced flapping with soaring-gliding flights as solar radiation increased and thermal updrafts got stronger. In the searching part, they replaced perch-hunting with hovering as wind speed increased and they experienced a stronger lift. But also, they increased the use of hovering as air temperature increased, which has a positive influence on the activity level of the preferred prey (large grasshoppers). Kestrels maintained a constant energy expenditure per foraging trip, although flight and hunting strategies changed dramatically with weather conditions, suggesting a fixed energy budget per trip to which they adjusted their commuting and searching strategies in response to weather conditions.

Project description:Background: The time adults spend sitting in front of screens is a health risk factor. In contrast, walking and cycling to and from work, also known as active commuting, could promote physical activity and improve population health. Objective: This study investigated automatic properties role in explaining active commuting and screen-based sedentary behaviours. The stable, daily conditions for carrying out active commuting and screen-based sedentary behaviour are most likely to develop automatic properties. These characteristics mean performing behaviours via external cues (i.e. lack of intentionality), with an unpleasant emotional experience of not carrying out a set routine (i.e. lack of controllability), and without paying much attention (i.e. efficiency). Method: This article describes findings of a prospective and correlational study in which 128 people participated. First, participants responded to questions assessed using the Generic Multifaceted Automaticity Scale (GMAS), which measured the automatic properties of screen-based sedentary behaviour and active commuting. The following week, both behaviours were assessed by daily logs to document active commuting and screen-based sedentary behaviour events, and by an accelerometer, worn for seven days, as an objective criterion. Confirmatory factor analyses, bivariate correlations, and multiple linear regressions were computed for the associations between the GMAS scores and objective criterion measures of screen-based sedentary behaviours and active commuting. Results: Automaticity facets displayed different relationships with screen-based sedentary behaviours and active commuting - people with higher lack of intentionality and lack of controllability for active commuting present higher levels of moderate physical activity. In contrast, the lack of controllability of screen-based sedentary behaviours was a significant predictor of sedentary screen time. Conclusions: The multidimensional approach to automaticity could be useful in determining more precisely the features that need to be addressed to promote the adoption of active commuting and limit the time spent sitting in front of screens.

Project description:In recent decades, the global incidence of dengue has increased. Affected countries have responded with more effective surveillance strategies to detect outbreaks early, monitor the trends, and implement prevention and control measures. We have applied newly developed machine learning approaches to identify laboratory-confirmed dengue cases from 4,894 emergency department patients with dengue-like illness (DLI) who received laboratory tests. Among them, 60.11% (2942 cases) were confirmed to have dengue. Using just four input variables [age, body temperature, white blood cells counts (WBCs) and platelets], not only the state-of-the-art deep neural network (DNN) prediction models but also the conventional decision tree (DT) and logistic regression (LR) models delivered performances with receiver operating characteristic (ROC) curves areas under curves (AUCs) of the ranging from 83.75% to 85.87% [for DT, DNN and LR: 84.60% ± 0.03%, 85.87% ± 0.54%, 83.75% ± 0.17%, respectively]. Subgroup analyses found all the models were very sensitive particularly in the pre-epidemic period. Pre-peak sensitivities (<35 weeks) were 92.6%, 92.9%, and 93.1% in DT, DNN, and LR respectively. Adjusted odds ratios examined with LR for low WBCs [≤ 3.2 (x103/μL)], fever (≥38°C), low platelet counts [< 100 (x103/μL)], and elderly (≥ 65 years) were 5.17 [95% confidence interval (CI): 3.96-6.76], 3.17 [95%CI: 2.74-3.66], 3.10 [95%CI: 2.44-3.94], and 1.77 [95%CI: 1.50-2.10], respectively. Our prediction models can readily be used in resource-poor countries where viral/serologic tests are inconvenient and can also be applied for real-time syndromic surveillance to monitor trends of dengue cases and even be integrated with mosquito/environment surveillance for early warning and immediate prevention/control measures. In other words, a local community hospital/clinic with an instrument of complete blood counts (including platelets) can provide a sentinel screening during outbreaks. In conclusion, the machine learning approach can facilitate medical and public health efforts to minimize the health threat of dengue epidemics. However, laboratory confirmation remains the primary goal of surveillance and outbreak investigation.

Dataset Information

Assessment of Machine Learning Models to Identify Port Jackson Shark Behaviours Using Tri-Axial Accelerometers.

Publications

Assessment of Machine Learning Models to Identify Port Jackson Shark Behaviours Using Tri-Axial Accelerometers.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets