2026
Predictability-Aware Compression and Decompression Framework for Multichannel Time Series Data with Latent Seasonality
Ziqi Liu, Peng Zeng, Yi Ding
Proceedings of the ACM Web Conference (WWW) 2026 WWW
Proposes a predictability-aware framework for compressing and decompressing multichannel time series data by leveraging latent seasonality, improving efficiency while preserving essential temporal patterns.
Predictability-Aware Compression and Decompression Framework for Multichannel Time Series Data with Latent Seasonality
Ziqi Liu, Peng Zeng, Yi Ding
Proceedings of the ACM Web Conference (WWW) 2026 WWW
Proposes a predictability-aware framework for compressing and decompressing multichannel time series data by leveraging latent seasonality, improving efficiency while preserving essential temporal patterns.
2023
IFRN: Insensitive Feature Removal Network for Zero-Shot Mechanical Fault Diagnosis Across Fault Severity
Ziqi Liu, Rui Yang, Weibo Liu, Xiaohui Liu
Neurocomputing 2023
Proposes an Insensitive Feature Removal Network (IFRN) for zero-shot mechanical fault diagnosis across varying fault severities. The method leverages an attention-based module and a denoising autoencoder to hierarchically eliminate insensitive features, reducing prototype shift and improving classification accuracy.
IFRN: Insensitive Feature Removal Network for Zero-Shot Mechanical Fault Diagnosis Across Fault Severity
Ziqi Liu, Rui Yang, Weibo Liu, Xiaohui Liu
Neurocomputing 2023
Proposes an Insensitive Feature Removal Network (IFRN) for zero-shot mechanical fault diagnosis across varying fault severities. The method leverages an attention-based module and a denoising autoencoder to hierarchically eliminate insensitive features, reducing prototype shift and improving classification accuracy.
2022
Weighted Multi-view Zero-shot Learning Prototype Shift Model in Fault Diagnosis
Ziqi Liu, Rui Yang, Xiaohan Chen, Yihao Xue
China Automation Congress (CAC) 2022 CAC
Proposes a weighted multi-view zero-shot learning model to address prototype shift issues in fault diagnosis. The approach integrates multi-view feature information to improve robustness and accuracy under unseen fault conditions.
Weighted Multi-view Zero-shot Learning Prototype Shift Model in Fault Diagnosis
Ziqi Liu, Rui Yang, Xiaohan Chen, Yihao Xue
China Automation Congress (CAC) 2022 CAC
Proposes a weighted multi-view zero-shot learning model to address prototype shift issues in fault diagnosis. The approach integrates multi-view feature information to improve robustness and accuracy under unseen fault conditions.