Deep learning-based animal activity recognition with wearable sensors: Overview, challenges, and future directions

A Mao, E Huang, X Wang, K Liu - Computers and Electronics in Agriculture, 2023 - Elsevier
Animal behavior, as one of the most crucial indicators of animal health and welfare, provides
rich insights into animal physical and mental states. Automated animal activity recognition …

Machine learning-based sensor data fusion for animal monitoring: Scoping review

CA Aguilar-Lazcano, IE Espinosa-Curiel… - Sensors, 2023 - mdpi.com
The development of technology, such as the Internet of Things and artificial intelligence, has
significantly advanced many fields of study. Animal research is no exception, as these …

Automated identification of chicken distress vocalizations using deep learning models

A Mao, CSE Giraudet, K Liu… - Journal of the …, 2022 - royalsocietypublishing.org
The annual global production of chickens exceeds 25 billion birds, which are often housed
in very large groups, numbering thousands. Distress calling triggered by various sources of …

FedAAR: A novel federated learning framework for animal activity recognition with wearable sensors

A Mao, E Huang, H Gan, K Liu - Animals, 2022 - mdpi.com
Simple Summary Automated animal activity recognition has achieved great success due to
the recent advances in deep learning, allowing staff to identify variations in the animal …

A cognitive-driven ordinal preservation for multimodal imbalanced brain disease diagnosis

Q Zhu, T Zhu, R Zhang, H Ye, K Sun… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
The multimodal imbalanced data learning problems are becoming increasingly common in
the real world, especially in brain disease diagnosis. Although multimodal data provide …

Unsupervised Domain Adaptation for Mitigating Sensor Variability and Interspecies Heterogeneity in Animal Activity Recognition

SH Ahn, S Kim, DH Jeong - Animals, 2023 - mdpi.com
Simple Summary This study aimed to improve animal activity recognition (AAR) using
wearable sensor data, which often faces challenges due to sensor variability and individual …

Time-series-based feature selection and clustering for equine activity recognition using accelerometers

T De Waele, A Shahid, D Peralta… - IEEE Sensors …, 2023 - ieeexplore.ieee.org
With over 16 million horses worldwide and nearly 60000 sport horses registered to the
International Federation for Equestrian Sports database, tracking the activities and …

A teacher-to-student information recovery method toward energy-efficient animal activity recognition at low sampling rates

A Mao, M Zhu, E Huang, X Yao, K Liu - Computers and Electronics in …, 2023 - Elsevier
Automated animal activity recognition (AAR) has advanced greatly through recent advances
in sensing technologies and deep learning, and improved livestock management efficiency …

Transformer-based Dog Behavior Classification with Motion Sensors

B Or - IEEE Sensors Journal, 2024 - ieeexplore.ieee.org
This article deals with classifying dog behavior using motion sensors, leveraging a
transformer-based deep neural network (DNN) model. Understanding dog behavior is …

CKSP: Cross-species Knowledge Sharing and Preserving for Universal Animal Activity Recognition

A Mao, M Zhu, Z Guo, Z He, T Norton, K Liu - arXiv preprint arXiv …, 2024 - arxiv.org
Deep learning techniques are dominating automated animal activity recognition (AAR) tasks
with wearable sensors due to their high performance on large-scale labelled data. However …