Deep learning-based state estimation of lithium batteries is widely used in battery management system (BMS) design. However, due to the limitation of on-board computing resources, multiple single-state estimation models are more difficult to deploy in practice. Therefore, this paper proposes a multi-task learning network (MTL) combining a multi-layer feature extraction structure with separated expert layers for the joint estimation of the state of charge (SOC) and state of energy (SOE) of Li-ion batteries. MTL uses a multi-layer network to extract features, separating task sharing from task-specific parameters. The underlying LSTM initially extracts time-series features. The separated expert layer, consisting of task-specific and shared experts, extracts features specific to different tasks and shared features for multiple tasks. The information extracted by different experts is fused through a gate structure. Tasks are processed based on specific and shared information. Multiple tasks are trained simultaneously to improve performance by sharing the learned knowledge with each other. SOC and SOE are estimated on the Panasonic dataset, and the model is tested for generalization performance on the LG dataset. The Mean Absolute Error (MAE) values for the two tasks are 1.01% and 0.59%, and the Root Mean Square Error (RMSE) values are 1.29% and 0.77%, respectively. For SOE estimation tasks, the MAE and RMSE values are reduced by 0.096% and 0.087%, respectively, when compared with single-task learning models. The MTL model also achieves reductions of up to 0.818% and 0.938% in MAE and RMSE values, respectively, compared to other multi-task learning models. For SOC estimation tasks, the MAE and RMSE values are reduced by 0.051% and 0.078%, respectively, compared to single-task learning models. The MTL model also outperforms other multi-task learning models, achieving reductions of up to 0.398% and 0.578% in MAE and RMSE values, respectively. In the process of simulating online prediction, the MTL model consumes 4.93 ms, which is less than the combined time of multiple single-task learning models and almost the same as that of other multi-task learning models. The results show the effectiveness and superiority of this method.
Automated segmentation of liver tumors on CT scans is essential for aiding diagnosis and assessing treatment. Computer-aided diagnosis can reduce the costs and errors associated with manual processes and ensure the provision of accurate and reliable clinical assessments. However, liver tumors in CT images vary significantly in size and have fuzzy boundaries, making it difficult for existing methods to achieve accurate segmentation. Therefore, this paper proposes MAEG-Net, a multi-scale adaptive feature fusion liver tumor segmentation network based on edge guidance. Specifically, we design a multi-scale adaptive feature fusion module that effectively incorporates multi-scale information to better guide the segmentation of tumors of different sizes. Additionally, to address the problem of blurred tumor boundaries in images, we introduce an edge-aware guidance module to improve the model's feature learning ability under these conditions. Evaluation results on the liver tumor dataset (LiTS2017) show that our method achieves a Dice coefficient of 71.84% and a VOE of 38.64%, demonstrating the best performance for liver tumor segmentation in CT images.
Background: There is a large amount of occlusion in dairy farms and changes in daytime and nighttime lighting seriously affect the accuracy of traditional dairy cow identification. Methods: This paper proposed a method to dairy cow identification in dairy farm. Firstly, Resnet50 was used to extract the pattern features of dairy cows and this paper fused the fourth and fifth scale features with semantic information. Secondly, on the basis of the triplet loss, it added label smoothing loss instead of softmax cross-entropy loss to further avoid over-fitting and reduced the intra-class distance with the center loss, which improved the mean average precision (mAP) by 8.9% compared with the initial Re-identification(Reid) and the joint optimized distance calculation formula was improved the single distance measurement in the triplet loss, using two distance measurement methods to effectively improve the recognition accuracy. Finally, it was combined with pruning operation to reduce the redundant parameters of the model. Result: The experiment proves that the identification mAP of dairy cows reaches 81.2%, which is an improvement 10.9% compared to the baseline model mAP, providing a strong technical support for the subsequent dairy cow identification and target tracking system.