Deep learning accurately predicts white shark locomotor activity from depth data
Deep learning accurately predicts white shark locomotor activity from depth data
复制标题
深度学习根据深度数据准确预测白鲨运动活动
DOI：
--
复制
发表时间：
2019
影响因子：
2.7
通讯作者：
S. Jorgensen
中科院分区：
文献类型：
--
作者：
Zac Yung;J. Moxley;P. Kanive;A. Gleiss;T. Maughan;L. Bird;O. J. Jewell;T. Chapple;Tyler O. Gagné;C. White;S. Jorgensen
背景自由放养动物的生物能量学、运动学和行为的研究已经随着越来越多的生物记录设备的使用而发生变化，这些设备利用高分辨率传感器对运动进行密集采样。来自生物记录标签的整体动态身体加速度(ODBA)已被验证为运动能量消耗的替代指标，已在一系列陆地和水生生物中进行了校准。然而，识别精细过程和推断能源支出所需的时间分辨率提高，与电力和内存需求增加以及从档案仪器恢复数据的后勤挑战有关。这限制了研究的持续时间和空间范围，潜在地排除了发生在更大规模上的相关生态过程。方法在这里，我们提出了一种使用深度学习来仅从垂直运动模式估计运动活动的过程。我们训练人工神经网络(ANN)从两条自由游动的白鲨(Carcharodon Carcharas)的单变量深度(压力)数据中预测ODBA。结果根据一条鲨鱼1h的训练数据，ANN能够从多个时间尺度上的1 GHz压力传感器数据中稳健地预测ODBA。这些预测始终优于零中心趋势模型，而且广义预测比其他测试的机器学习技术更准确。对于同一条鲨鱼，ODBA综合加班周期 ≥ 10分钟的ANN预测精度始终很高(~ 90%的准确率， >； 比零提高10%)，并且同样可以在个体之间推广(>； 75%的准确率)。瞬时ODBA估计的变异性更大(鲨鱼1的R2 = 为0.54，鲨鱼2的R2为0.24)。预测精度不受训练数据量的影响，在超过1-3小时的训练后，预测6小时的测试数据没有取得明显的收益。结论从相对较短的高分辨率数据集中使用能量和运动学信息来增强简单的深度度量，极大地扩展了可以从更常见和更广泛应用的时间深度记录器(TDR)数据集中得出的潜在推断。未来的研究工作将集中在建立一个广泛的通用模型，该模型利用全运动传感器生物记录数据集的档案，包含最多的个体，包括不同的栖息地、行为和依恋方法。
BackgroundThe study of bioenergetics, kinematics, and behavior in free-ranging animals has been transformed through the increasing use of biologging devices that sample motion intensively with high-resolution sensors. Overall dynamic body acceleration (ODBA) derived from biologging tags has been validated as a proxy of locomotor energy expenditure has been calibrated in a range of terrestrial and aquatic taxa. The increased temporal resolution required to discern fine-scale processes and infer energetic expenditure, however, is associated with increased power and memory requirements, as well as the logistical challenges of recovering data from archival instruments. This limits the duration and spatial extent of studies, potentially excluding relevant ecological processes that occur over larger scales.MethodHere, we present a procedure that uses deep learning to estimate locomotor activity solely from vertical movement patterns. We trained artificial neural networks (ANNs) to predict ODBA from univariate depth (pressure) data from two free-swimming white sharks (Carcharodon carcharias).ResultsFollowing 1 h of training data from an individual shark, ANN enabled robust predictions of ODBA from 1 Hz pressure sensor data at multiple temporal scales. These predictions consistently out-performed a null central-tendency model and generalized predictions more accurately than other machine learning techniques tested. The ANN prediction accuracy of ODBA integrated overtime periods ≥ 10 min was consistently high (~ 90% accuracy, > 10% improvement over null) for the same shark and equivalently generalizable across individuals (> 75% accuracy). Instantaneous ODBA estimates were more variable (R2 = 0.54 for shark 1, 0.24 for shark 2). Prediction accuracy was insensitive to the volume of training data, no observable gains were achieved in predicting 6 h of test data beyond 1–3 h of training.ConclusionsAugmenting simple depth metrics with energetic and kinematic information from comparatively short-lived, high-resolution datasets greatly expands the potential inference that can be drawn from more common and widely deployed time-depth recorder (TDR) datasets. Future research efforts will focus on building a broadly generalized model that leverages archives of full motion sensor biologging data sets with the greatest number of individuals encompassing diverse habitats, behaviors, and attachment methods.
影响因子：
16.6
作者：
Gleiss, Adrian C.;Jorgensen, Salvador J.;Wilson, Rory P.
通讯作者：
Wilson, Rory P.