Automatic recording of rare behaviors of wild animals using video bio-loggers with on-board light-weight outlier detector

Tanigaki, Kei; Otsuka, Ryoma; Li, Aiyi; Hatano, Yota; Wei, Yuanzhou; Koyama, Shiho; Yoda, Ken; Maekawa, Takuya

doi:10.1093/pnasnexus/pgad447

Cited by 1 publication

(1 citation statement)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…prey capture) and those likely requiring consideration of temporal dependencies for classification (e.g. foraging dive of streaked shearwaters, which consists of a sequence of actions such as diving underwater, following a school of fish and ascending to the sea surface (Tanigaki et al, 2024)). In this study, we explored the effectiveness of stateof-the-art deep learning architectures and related techniques for acceleration-based behaviour classification of wild animals, which may overcome the above-mentioned challenges, using datasets from two wild seabird species.…”

Section: Challenges and Our Approachmentioning

confidence: 99%

Exploring deep learning techniques for wild animal behaviour classification using animal‐borne accelerometers

Otsuka,

Yoshimura,

Tanigaki

et al. 2024

Methods Ecol Evol

Self Cite

View full text Add to dashboard Cite

Machine learning‐based behaviour classification using acceleration data is a powerful tool in bio‐logging research. Deep learning architectures such as convolutional neural networks (CNN), long short‐term memory (LSTM) and self‐attention mechanism as well as related training techniques have been extensively studied in human activity recognition. However, they have rarely been used in wild animal studies. The main challenges of acceleration‐based wild animal behaviour classification include data shortages, class imbalance problems, various types of noise in data due to differences in individual behaviour and where the loggers were attached and complexity in data due to complex animal‐specific behaviours, which may have limited the application of deep learning techniques in this area. To overcome these challenges, we explored the effectiveness of techniques for efficient model training: data augmentation, manifold mixup and pre‐training of deep learning models with unlabelled data, using datasets from two species of wild seabirds and state‐of‐the‐art deep learning model architectures. Data augmentation improved the overall model performance when one of the various techniques (none, scaling, jittering, permutation, time‐warping and rotation) was randomly applied to each data during mini‐batch training. Manifold mixup also improved model performance, but not as much as random data augmentation. Pre‐training with unlabelled data did not improve model performance. The state‐of‐the‐art deep learning models, including a model consisting of four CNN layers, an LSTM layer and a multi‐head attention layer, as well as its modified version with shortcut connection, showed better performance among other comparative models. Using only raw acceleration data as inputs, these models outperformed classic machine learning approaches that used 119 handcrafted features. Our experiments showed that deep learning techniques are promising for acceleration‐based behaviour classification of wild animals and highlighted some challenges (e.g. effective use of unlabelled data). There is scope for greater exploration of deep learning techniques in wild animal studies (e.g. advanced data augmentation, multimodal sensor data use, transfer learning and self‐supervised learning). We hope that this study will stimulate the development of deep learning techniques for wild animal behaviour classification using time‐series sensor data.

show abstract

Section: Challenges and Our Approachmentioning

confidence: 99%