Search

Your search keyword '"Liu, Xiliang"' showing total 416 results
Start Over Author "Liu, Xiliang"
416 results on '"Liu, Xiliang"'

4. HPO-LGBM-DRI: Dynamic Recognition Interval Estimation for Imbalanced Fraud Call via HPO-LGBM

Author

Liu, Xiliang, Zhi, Xiaoying, Mei, Qiang, Wang, Peng, Su, Haoru, Wang, Jiayi, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Meng, Xiaofeng, editor, Zhang, Xueying, editor, Guo, Danhuai, editor, Hu, Di, editor, Zheng, Bolong, editor, and Zhang, Chunju, editor

Published
2024
Full Text
View/download PDF

5. An Improved DBSCAN Clustering Method for AIS Trajectories Incorporating DP Compression and Discrete Fréchet Distance

Author

Liu, Xiliang, Zhi, Xiaoying, Wang, Peng, Mei, Qiang, Su, Haoru, He, Zhixiang, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Meng, Xiaofeng, editor, Zhang, Xueying, editor, Guo, Danhuai, editor, Hu, Di, editor, Zheng, Bolong, editor, and Zhang, Chunju, editor

Published
2024
Full Text
View/download PDF

29. Mechanical characteristics of high-performance hybrid fiber concrete shaft lining in drainage settlement ground

Author

LI Shuo, LUO Yunjun, QIN Bendong, LIU Shaofeng, GUO Jiaqi, and LIU Xiliang

Subjects
concrete shaft lining, fiber reinforced concrete, numerical calculation, deep topsoil layer, shaft linings rupture, Mining engineering. Metallurgy, TN1-997
Abstract

In order to solve the problem of concrete shaft support in deep topsoil layer, ANSYS finite element software was used to compare and analyze the deformation and stress of hybrid fiber high-strength concrete shaft and ordinary high-strength concrete shaft when the thickness of topsoil layer varied from 200 m to 600 m. The calculation results show that: the strain of mixed fiber concrete shaft is greater than that of ordinary concrete shaft under the same stress, and the fiber can improve the brittleness of shaft; the maximum circumferential stress on shaft increases with the increase of topsoil layer thickness, and increases gradually from outside to inside along the shaft radial direction, and the circumferential strain is always compressive strain and the inner surface is greater than the outer surface. As the burial depth increases, the deformation of shaft changes from mainly axial deformation to mainly radial deformation; finally, the regression equation of the relationship between stress-strain and thickness of topsoil layer is given, which can guide the engineering practice.

Published
2022
Full Text
View/download PDF

42. Dynamic Characteristics and Storage Potential of Water-Alternating-CO2in Low Permeability Reservoirs

Author

Wang, Zhilin, Ge, Zhengjun, Lin, Bo, Zhao, Hongyan, Liu, Haipeng, Ni, Mingcheng, Liu, Xiliang, Zhou, Xianmin, and Chen, Hao

Abstract

Oil reservoirs in China, largely characterized by low permeability and heterogeneity, face challenges with conventional water flooding, such as rising water cuts and declining recovery rates. Over 60% of reserves are in low and ultralow permeability reservoirs. To improve oil recovery and CO2storage after water flooding, water-alternating-gas (WAG) injection is gaining attention. However, uncertainties remain regarding the effects of water cuts on minimum miscibility pressure (MMP) and the influence of slug ratios and sizes on oil recovery and storage efficiency during WACO2 injection. This study addresses these issues in the L block of the Jiangsu oilfield through slim tube tests, long-core flooding, and online NMR experiments. Key findings include: water cuts had minimal impact on MMP but affected oil recovery under nonmiscible conditions. The optimal CO2displacement and storage synergy occurred with a slug size of 0.1 PV and a slug ratio of 1:1, though a 1.5:1 ratio was also viable. Online NMR results showed that most recoverable oil can be extracted under miscible conditions, while some oil migrated under immiscible conditions, recoverable with increased pressure. CO2override and gravity separation were absent during WACO2but observed in continuous CO2injection. This research provides valuable insights into the feasibility of CO2flooding, the impact of water cuts on miscibility, and the recovery mechanisms during WACO2injection, offering guidance for enhanced oil recovery in low-permeability reservoirs.

Published
2024
Full Text
View/download PDF

47. ConvFormer-KDE: A Long-Term Point–Interval Prediction Framework for PM 2.5 Based on Multi-Source Spatial and Temporal Data.

Author

Lin, Shaofu, Zhang, Yuying, Fei, Xingjia, Liu, Xiliang, and Mei, Qiang

Subjects
CONVOLUTIONAL neural networks, TRANSFORMER models, PROBABILITY density function, ADAPTIVE natural resource management, FEATURE selection
Abstract

Accurate long-term PM2.5 prediction is crucial for environmental management and public health. However, previous studies have mainly focused on short-term air quality point predictions, neglecting the importance of accurately predicting the long-term trends of PM2.5 and studying the uncertainty of PM2.5 concentration changes. The traditional approaches have limitations in capturing nonlinear relationships and complex dynamic patterns in time series, and they often overlook the credibility of prediction results in practical applications. Therefore, there is still much room for improvement in long-term prediction of PM2.5. This study proposes a novel long-term point and interval prediction framework for urban air quality based on multi-source spatial and temporal data, which further quantifies the uncertainty and volatility of the prediction based on the accurate PM2.5 point prediction. In this model, firstly, multi-source datasets from multiple monitoring stations are preprocessed. Subsequently, spatial clustering of stations based on POI data is performed to filter out strongly correlated stations, and feature selection is performed to eliminate redundant features. In this paper, the ConvFormer-KDE model is presented, whereby local patterns and short-term dependencies among multivariate variables are mined through a convolutional neural network (CNN), long-term dependencies among time-series data are extracted using the Transformer model, and a direct multi-output strategy is employed to realize the long-term point prediction of PM2.5 concentration. KDE is utilized to derive prediction intervals for PM2.5 concentration at confidence levels of 85%, 90%, and 95%, respectively, reflecting the uncertainty inherent in long-term trends of PM2.5. The performance of ConvFormer-KDE was compared with a list of advanced models. Experimental results showed that ConvFormer-KDE outperformed baseline models in long-term point- and interval-prediction tasks for PM2.5. The ConvFormer-KDE can provide a valuable early warning basis for future PM2.5 changes from the aspects of point and interval prediction. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results