Editorial for pattern recognition letters special issue on face-based emotion understanding

Li, Jingting; Yap, Moi Hoon; Cheng, Wen-Huang; See, John; Xiao, Hong; Li, Xiaobai; Wang, Sujing

doi:10.1016/j.patrec.2023.02.022

Cited by 3 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the context of various applications, Self-Attention has been used to improve model performance. Li et al [23] addressed the problem of poor generalization in emotion recognition models based on EEG by combining Convolutional Networks and Bidirectional LSTM models with Self-Attention. The Self-Attention mechanism helped extract important information by changing the weights of different channels, addressing the significance of different channels and samples when feature extraction is involved.…”

Section: Proposed Methods a Mgts-attentionmentioning

confidence: 99%

Load Energy Decomposition Algorithm Based on Improved Bidirectional Transformer Combined With Time-Sensing Self-Attention

Xuan,

Pang,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Non-Intrusive Load Monitoring (NILM) is a technique capable of extracting the quantity, type and operational status from overall power data in a specific area. Through energy disaggregation, the total power consumption can be decomposed into device-level power consumption. In recent years, with the advancement of deep learning techniques, numerous improvements have been made in energy disaggregation technologies. However, for NILM tasks, significant variations in device switching can result in data imbalance, and devices in different operating states can impact the model's prediction accuracy. To address these issues, this paper proposes a method based on Bidirectional Transformer and GRU, combined with time-aware self-attention for load prediction(CTA-BERT). In this model, We leverage the bidirectional transformer of BERT to learn features at different positions in the power sequence. Simultaneously, GRU is added to capture long-term sequence dependencies. Device time-state variables and dilated convolutional layers are introduced in the Transformer section to effectively capture long sequence dependencies and global features. We also enhance the masking strategy to adapt the appliances in different states. Finally, on the REDD and UK-DALE datasets, we tested and compared the proposed method with several state-ofthe-art NILM algorithms. The results indicate that the model's average absolute error (MAE) is reduced by an average of 25% across all devices, F1-Score is improved by approximately 20%, and prediction accuracy is significantly enhanced.

show abstract

Section: Proposed Methods a Mgts-attentionmentioning

confidence: 99%