FedAAR: A Novel Federated Learning Framework for Animal Activity Recognition with Wearable Sensors.

Deep learning dominates automated animal activity recognition (AAR) tasks due to high performance on large-scale datasets. However, constructing centralised data across diverse farms raises data privacy issues. Federated learning (FL) provides a distributed learning solution to train a shared model by coordinating multiple farms (clients) without sharing their private data, whereas directly applying FL to AAR tasks often faces two challenges: client-drift during local training and local gradient conflicts during global aggregation. In this study, we develop a novel FL framework called FedAAR to achieve AAR with wearable sensors. Specifically, we devise a prototype-guided local update module to alleviate the client-drift issue, which introduces a global prototype as shared knowledge to force clients to learn consistent features. To reduce gradient conflicts between clients, we design a gradient-refinement-based aggregation module to eliminate conflicting components between local gradients during global aggregation, thereby improving agreement between clients. Experiments are conducted on a public dataset to verify FedAAR's effectiveness, which consists of 87,621 two-second accelerometer and gyroscope data. The results demonstrate that FedAAR outperforms the state-of-the-art, on precision (75.23%), recall (75.17%), F1-score (74.70%), and accuracy (88.88%), respectively. The ablation experiments show FedAAR's robustness against various factors (i.e., data sizes, communication frequency, and client numbers).

Cross-Modality Interaction Network for Equine Activity Recognition Using Imbalanced Multi-Modal Data.

With the recent advances in deep learning, wearable sensors have increasingly been used in automated animal activity recognition. However, there are two major challenges in improving recognition performance-multi-modal feature fusion and imbalanced data modeling. In this study, to improve classification performance for equine activities while tackling these two challenges, we developed a cross-modality interaction network (CMI-Net) involving a dual convolution neural network architecture and a cross-modality interaction module (CMIM). The CMIM adaptively recalibrated the temporal- and axis-wise features in each modality by leveraging multi-modal information to achieve deep intermodality interaction. A class-balanced (CB) focal loss was adopted to supervise the training of CMI-Net to alleviate the class imbalance problem. Motion data was acquired from six neck-attached inertial measurement units from six horses. The CMI-Net was trained and verified with leave-one-out cross-validation. The results demonstrated that our CMI-Net outperformed the existing algorithms with high precision (79.74%), recall (79.57%), F1-score (79.02%), and accuracy (93.37%). The adoption of CB focal loss improved the performance of CMI-Net, with increases of 2.76%, 4.16%, and 3.92% in precision, recall, and F1-score, respectively. In conclusion, CMI-Net and CB focal loss effectively enhanced the equine activity classification performance using imbalanced multi-modal sensor data.

[Performance of desulfurizing absorbent of roasted navajoite].

An innovative flue gas desulfurization (FGD) coupling process was proposed in this study to overcome the problems in wet-type limestone/lime processes which include fouling, clogging, and difficulty of selling the by-products and the problems in traditional process for vanadium extraction from navajoite ore such as excessive consumption of sulfuric acid and emissions of pollutants. The performance of a jet bubbling reactor (JBR) at pilot-scale was evaluated using navajoite ore produced in the process of extracting vanadium pentoxide as desulfurization absorbent. Results showed that navajoite ore slurry achieved better desulfurization performance than limestone slurry. When the inlet flue gas pressure drop was 3.0 kPa, the gas flow was about 2350 m3 x h(-1) and the pH of the navajoite ore slurry was higher than 4.5, the desulfurization efficiency was stable about 90%. The SO2 removal efficiency appeared to increase along with the increasing of absorbent cycle-index. The efficiency of the second circulation was improved 3.5% compared to the first circulation. After an operating duration of 40 minutes, the leaching rate of vanadium pentoxide was about 20%, and reached 60% when the by-products were leached with 5% dilute sulfuric acid for 10 hours. The by-product from this process not only could be used to produce vanadium pentoxide which is a valuable industrial product, but also could significantly overcome the pollution problem existing in the traditional refining process of vanadium pentoxide when navajoite ore is used as the feed material. This FGD process using roasted navajoite slurry as absorbent is environmental sound and cost-effective, and shows the potential for application in the field of flue gas desulfurization as well as hydrometallurgy.