Naoya Yoshimura

Naoya Yoshimura

Auto-generated profile, based on publicly available information

Naoya Yoshimura

Graduate School of Information Science and Technology, Osaka University, Suita, Osaka, Japan

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 February 2024 in Methods in Ecology and Evolution
Verified
Journal Article
Open access
RORyoma Otsuka
Ryoma Otsuka
NYNaoya Yoshimura
Naoya Yoshimura
KTKei Tanigaki
Kei Tanigaki
SKShiho Koyama
Shiho Koyama
YMYuichi Mizutani
Yuichi Mizutani
TMTakuya Maekawa
Takuya Maekawa
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.

5 October 2024
Verified
Conference Paper
Open access
TMTakuya Maekawa
Takuya Maekawa
NYNaoya Yoshimura
Naoya Yoshimura
JMJaime Morales
Jaime Morales
Takahiro HaraTakahiro Hara
Takahiro Hara
This paper presents an overview of OpenPack, a comprehensive dataset developed for recognizing packaging work activities, and discusses an activity recognition competition using this dataset. The availability of sensor datasets for recognizing work activities in industrial settings has been limited. This limitation has restricted research and development in industrial application methods based on activity recognition. To accelerate work activity recognition studies, OpenPack provides 53.8 hours of diverse sensor data, including acceleration data, keypoints, depth images, and readings from IoT devices such as handheld barcode scanners. This paper analyzes this data and propose several research directions based on OpenPack. We organized an activity recognition competition, OpenPack Challenge 2022, based on the OpenPack dataset. This paper also shares lessons learned from organizing the competition with the UbiComp and activity recognition research community. The OpenPack dataset is available at https://open-pack.github.io/.