Lili Guo

Lili Guo

Auto-generated profile, based on publicly available information

Lili Guo

Tsinghua University, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
15 October 2022 in Carbon Letters
Verified
Journal Article
Closed access
PDF file
YSYang Su
Yang Su
NCNa Chen
Na Chen
HRHai-Lin Ren
Hai-Lin Ren
CLChengwei Li
Chengwei Li
LGLi-Li Guo
Li-Li Guo
XWxiaomin wang
xiaomin wang

29 March 2023 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
LXLele Xu
Lele Xu
YLYe Li
Ye Li
JXJinzhong Xu
Jinzhong Xu
YZYue Zhang
Yue Zhang
LGLili Guo
Lili Guo
Building footprint extraction in remote sensing remains challenging due to the diverse appearances of buildings and confusing scenarios. Recently, researchers have revealed that both the globality and locality are vitally important in building footprint extraction tasks and proposed to incorporate the local context and global long-range dependency in the segmentation models. However, the inadequate integration of the globality and locality still leads to incomplete, fake or missing extraction results. To alleviate these problems, a novel segmentation method named Bi-branch Cross-fusion Transformer Network (BCTNet) is proposed in this study. Two parallel branches of the convolutional encoder branch (CB) and the transformer encoder branch (TB) are designed to extract multi-scale feature maps. A concatenation-then-cross-fusion transformer block (CCTB) is put forward to integrate the locality from the CB and globality from the TB in a cross-fusion way at each stage of the encoding process. Then, an adaptive gating module (AGM) is proposed to gate the feature maps from the CCTB to strengthen the important features while suppressing the irrelevant interference information. After that, the segmentation results can be obtained through a simple decoding process. Comprehensive experiments on two benchmark datasets demonstrate that the proposed BCTNet can achieve superior performance compared to the current state-of-the-art (SOTA) segmentation methods.

30 December 2021 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
HLHaoran Liang
Haoran Liang
Lei SongLei Song
Lei Song
JDJun-Rong Du
Jun-Rong Du
XLXuzhi Li
Xuzhi Li
LGLili Guo
Lili Guo
Multivariate time series is widely derived from industrial facilities, such as power plants, manufacturing machines, spacecraft, digital devices etc., and anomaly detection and location is of great importance to industrial preventive maintenance. However, anomalies in multivariate time series always result from their unusual change of temporal or correlative features, and it is challenging to capture these complex characteristics. Besides, achieving consistent anomaly detection and location performance is also a tricky issue. In this article, a novel anomaly detection and location framework that combines generative adversarial networks and autoencoder is proposed to capture time dependent and correlation features of multivariate time series with on need of anomalous sequences. Firstly, multi-time scale correlation computation is utilized to encode multivariate time series into multiple cross-correlation graphs, which can be fed into the proposed deep architecture for extracting more distinguishable features. On this basis, a robust cost function with multiple loss issues is designed, and reconstruction matrix deviation from original space of encoder-encoder structure is utilized to detect and locate abnormal time series, ensuring the consistency of detection and location tasks and the framework reliability. Extensive experiments on five industrial datasets are conducted to indicate our model is a generic and excellent framework for anomaly detection and location of multivariate time series.

1 September 2020 in Agricultural and Forest Meteorology
Verified
Journal Article
Closed access
YZYunpu Zheng
Yunpu Zheng
CHChunlin He
Chunlin He
LGLili Guo
Lili Guo
LHLihua Hao
Lihua Hao
DCDongjuan Cheng
Dongjuan Cheng
MXMing Xu
Ming Xu

28 May 2020
Verified
Conference Paper
Open access
JDJun-Rong Du
Jun-Rong Du
LGLili Guo
Lili Guo
Lei SongLei Song
Lei Song
HLHaoran Liang
Haoran Liang
TCTianyuan Chen
Tianyuan Chen

26 April 2024
Verified
Conference Paper
Open access
LGLili Guo
Lili Guo
JWJianmin Wang
Jianmin Wang
HYHe Yu
He Yu
Lei SongLei Song
Lei Song
XQXin Qin
Xin Qin
Xu ChengXu Cheng
Xu Cheng
This study introduces an innovative imputation-free framework for time series classification amidst missing values, challenging traditional imputation-based approaches. By integrating GRU-based imputation with a noisy-robust feature learning module, our model adeptly navigates the complexities of incomplete data, reducing reliance on assumptions and harnessing the informational essence of missingness. Tested across 20 univariate time series datasets and one multivariate time series data under various missing ratios, the proposed framework not only outperforms conventional methods but also marks a paradigm shift in handling missing data, illustrating the potential for imputation-free strategies to enhance analysis accuracy and reliability in critical data-intensive applications.