Search

Your search keyword '"Guan, Xuefeng"' showing total 166 results
Start Over Author "Guan, Xuefeng"
166 results on '"Guan, Xuefeng"'

1. GeoCode-GPT: A Large Language Model for Geospatial Code Generation Tasks

Author

Hou, Shuyang, Shen, Zhangxiao, Zhao, Anqi, Liang, Jianyuan, Gui, Zhipeng, Guan, Xuefeng, Li, Rui, and Wu, Huayi

Subjects
Computer Science - Software Engineering, Computer Science - Artificial Intelligence
Abstract

The increasing demand for spatiotemporal data and modeling tasks in geosciences has made geospatial code generation technology a critical factor in enhancing productivity. Although large language models (LLMs) have demonstrated potential in code generation tasks, they often encounter issues such as refusal to code or hallucination in geospatial code generation due to a lack of domain-specific knowledge and code corpora. To address these challenges, this paper presents and open-sources the GeoCode-PT and GeoCode-SFT corpora, along with the GeoCode-Eval evaluation dataset. Additionally, by leveraging QLoRA and LoRA for pretraining and fine-tuning, we introduce GeoCode-GPT-7B, the first LLM focused on geospatial code generation, fine-tuned from Code Llama-7B. Furthermore, we establish a comprehensive geospatial code evaluation framework, incorporating option matching, expert validation, and prompt engineering scoring for LLMs, and systematically evaluate GeoCode-GPT-7B using the GeoCode-Eval dataset. Experimental results show that GeoCode-GPT outperforms other models in multiple-choice accuracy by 9.1% to 32.1%, in code summarization ability by 1.7% to 25.4%, and in code generation capability by 1.2% to 25.1%. This paper provides a solution and empirical validation for enhancing LLMs' performance in geospatial code generation, extends the boundaries of domain-specific model applications, and offers valuable insights into unlocking their potential in geospatial code generation.

Published
2024

11. Forecast Network-Wide Traffic States for Multiple Steps Ahead: A Deep Learning Approach Considering Dynamic Non-Local Spatial Correlation and Non-Stationary Temporal Dependency

Author

Wang, Xinglei, Guan, Xuefeng, Cao, Jun, Zhang, Na, and Wu, Huayi

Subjects
Computer Science - Machine Learning, Electrical Engineering and Systems Science - Signal Processing, Statistics - Machine Learning
Abstract

Obtaining accurate information about future traffic flows of all links in a traffic network is of great importance for traffic management and control applications. This research studies two particular problems in traffic forecasting: (1) capture the dynamic and non-local spatial correlation between traffic links and (2) model the dynamics of temporal dependency for accurate multiple steps ahead predictions. To address these issues, we propose a deep learning framework named Spatial-Temporal Sequence to Sequence model (STSeq2Seq). This model builds on sequence to sequence (seq2seq) architecture to capture temporal feature and relies on graph convolution for aggregating spatial information. Moreover, STSeq2Seq defines and constructs pattern-aware adjacency matrices (PAMs) based on pair-wise similarity of the recent traffic patterns on traffic links and integrate it into graph convolution operation. It also deploys a novel seq2sesq architecture which couples a convolutional encoder and a recurrent decoder with attention mechanism for dynamic modeling of long-range dependence between different time steps. We conduct extensive experiments using two publicly-available large-scale traffic datasets and compare STSeq2Seq with other baseline models. The numerical results demonstrate that the proposed model achieves state-of-the-art forecasting performance in terms of various error measures. The ablation study verifies the effectiveness of PAMs in capturing dynamic non-local spatial correlation and the superiority of proposed seq2seq architecture in modeling non-stationary temporal dependency for multiple steps ahead prediction. Furthermore, qualitative analysis is conducted on PAMs as well as the attention weights for model interpretation., Comment: 29 pages, 16 figures, 3 tables

Published
2020
Full Text
View/download PDF

12. A Hybrid Traffic Speed Forecasting Approach Integrating Wavelet Transform and Motif-based Graph Convolutional Recurrent Neural Network

Author

Zhang, Na, Guan, Xuefeng, Cao, Jun, Wang, Xinglei, and Wu, Huayi

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Signal Processing
Abstract

Traffic forecasting is crucial for urban traffic management and guidance. However, existing methods rarely exploit the time-frequency properties of traffic speed observations, and often neglect the propagation of traffic flows from upstream to downstream road segments. In this paper, we propose a hybrid approach that learns the spatio-temporal dependency in traffic flows and predicts short-term traffic speeds on a road network. Specifically, we employ wavelet transform to decompose raw traffic data into several components with different frequency sub-bands. A Motif-based Graph Convolutional Recurrent Neural Network (Motif-GCRNN) and Auto-Regressive Moving Average (ARMA) are used to train and predict low-frequency components and high-frequency components, respectively. In the Motif-GCRNN framework, we integrate Graph Convolutional Networks (GCNs) with local sub-graph structures - Motifs - to capture the spatial correlations among road segments, and apply Long Short-Term Memory (LSTM) to extract the short-term and periodic patterns in traffic speeds. Experiments on a traffic dataset collected in Chengdu, China, demonstrate that the proposed hybrid method outperforms six state-of-art prediction methods., Comment: 7 pages, IJCAI19

Published
2019

26. MicroRNA-146b negatively affects bovine embryo development and quality.

Author

Pavani, Krishna Chaitanya, Guan XueFeng, Chunduru, Jayendra, Meese, Tim, Peelman, Luc J., Van Nieuwerburgh, Filip, Deforce, Dieter, Hendrix, An, Tilleman, Kelly, Van Soom, Ann, and Smits, Katrien

Subjects
EMBRYOS, CULTURE media (Biology), GENE expression, EXTRACELLULAR vesicles, BOS, CELL differentiation
Abstract

MicroRNAs (miRNAs), which can be carried inside extracellular vesicles (EVs), play a crucial role in regulating embryo development up to the blastocyst stage. Yet, the molecular mechanisms underlying blastocyst development and quality are largely unknown. Recently, our group identified 69 differentially expressed miRNAs in extracellular vesicles (EVs) isolated from culture medium conditioned by bovine embryos that either developed to the blastocyst stage or did not (non-blastocysts). We found miR-146b to be more abundant in the EVs derived from media conditioned by non-blastocyst embryos. Using RT-qPCR, we here confirmed the upregulation of miR-146b in non-blastocyst (arrested at two- to four-cell and morula stage) embryos compared to blastocysts (P < 0.005), which coincides with the upregulation of miR-146b in EVs derived from the medium of these non-blastocysts. To evaluate a functional effect, bovine embryo culture media were supplemented with miR-146b mimics, resulting in significantly decreased embryo quality, with lower blastocyst rates at day 7 and lower total cell numbers, while the opposite was found after supplementation with miR-146b inhibitors, which resulted in reduced apoptosis rates (P < 0.01). Transcriptomic analysis of embryos treated with miR-146b mimics or inhibitors showed differential expression (P < 0.01) of genes associated with apoptosis, cell differentiation, and the RNA Pol II transcription complex, including WDR36, MBNL2, ERCC6l2, PYGO1, and SNIP1. Overall, miR-146b is overexpressed in non-blastocyst embryos and in EVs secreted by these embryos, and it regulates genes involved in embryo development and apoptosis, resulting in decreased embryo quality. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

28. Traditional Chinese medicine for frozen shoulder: An evidence‐based guideline

Author

Qin, Xiaokuan, primary, Sun, Kai, additional, Ao, Yingfang, additional, Liu, Jianping, additional, Wang, Mei, additional, Deng, Qiang, additional, Zhong, Weihong, additional, liu, Jun, additional, Sun, Shaoqiu, additional, Liu, Xiangdi, additional, Shi, Bin, additional, Guan, Xuefeng, additional, Du, Shuangqing, additional, Zou, Jun, additional, Wu, Chengliang, additional, Chen, Feng, additional, Fang, Yigong, additional, Nie, Xiaoyan, additional, Mo, Wen, additional, Guo, Jiayi, additional, Zhang, Yili, additional, Dong, Yan, additional, Wei, Xu, additional, and Zhu, Liguo, additional

Published
2023
Full Text
View/download PDF

33. Lagrangian Analysis of Moisture Sources of Precipitation in the Tianshan Mountains, Central Asia

Author

Guan, Xuefeng, Langhamer, Lukas, Schneider, Christoph, and 1 Geography Department Humboldt‐Universität zu Berlin Berlin Germany

Subjects
ddc:551.6, ddc:550, General Earth and Planetary Sciences, Environmental Science (miscellaneous), 550 Geowissenschaften
Abstract

The moisture sources of precipitation in the Tianshan Mountains, one of the regions with the highest precipitation in Central Asia during 1979–2017 are comprehensively and quantitatively summarized by using a Lagrangian moisture source detection technique. Continental sources provide about 93.2% of the moisture for precipitation in the Tianshan Mountain, while moisture directly from the ocean is very limited, averaging only 6.8%. Central Asia plays a dominant role in providing moisture for all sub‐regions of the Tianshan Mountains. For the Western Tianshan, moisture from April to October comes mainly from Central Asia (41.4%), while moisture from November to March is derived primarily from Western Asia (45.7%). Nearly 13.0% of moisture to precipitation for Eastern Tianshan in summer originates from East and South Asia, and the Siberia region. There is a significant decreasing trend in the moisture contribution of local evaporation and Central Asia in the Eastern Tianshan during winter. The contribution of moisture from Europe to summer precipitation in the Central and Eastern Tianshan and the contribution of the North Atlantic Ocean to summer precipitation in the Northern, Central, and Eastern Tianshan also exhibit a decreasing trend. The largest increase in moisture in Western Tianshan stems from West Asia during extreme winter precipitation months. Europe is also an important contributor to extreme precipitation in the Northern Tianshan. The moisture from East and South Asia and Siberia during extreme precipitation months in both winter and summer is significantly enhanced in the Eastern Tianshan., Key Points: Local evaporation and Central Asia play a leading role in providing moisture for all sub‐regions of the Tianshan Mountains. The largest moisture component during the months of extreme winter precipitation for Western Tianshan derives from western Asia. Moisture from East and South Asia and Siberia during extreme precipitation months is significantly enhanced in the Eastern Tianshan., China Scholarship Council, Humboldt‐Universität zu Berlin, https://zenodo.org/record/6451656#.YrrfbqhBwuU

Published
2022

34. Hatching is modulated by microRNA-378a-3p derived from extracellular vesicles secreted by blastocysts

Author

Pavani, Krishna Chaitanya, Meese, Tim, Pascottini, Osvaldo Bogado, Guan, XueFeng, Lin, Xiaoyuan, Peelman, Luc, Hamacher, Joachim, Van Nieuwerburgh, Filip, Deforce, Dieter, Boel, Annekatrien, Heindryckx, Björn, Tilleman, Kelly, Van Soom, Ann, Gadella, Bart M, Hendrix, An, Smits, Katrien, FAH klinische reproductie, Veterinaire biochemie, dB&C FR-RMSC FR, dES/dFAH FR, FAH klinische reproductie, Veterinaire biochemie, dB&C FR-RMSC FR, and dES/dFAH FR

Subjects
animal structures, MICRORNAS, Veterinary medicine, Mirnas, DISEASE, ACTIVATION, Embryo Culture Techniques, Hatching, Animals, General, reproductive and urinary physiology, GENE-EXPRESSION, Multidisciplinary, PROLIFERATION, Biology and Life Sciences, Extracellular vesicles, Embryo, Mammalian, CANCER, EMBRYO QUALITY, Culture Media, MicroRNAs, Blastocyst, embryonic structures, SURVIVAL, COMPLEXES, Cattle, IMPLANTATION, Engineering sciences. Technology
Abstract

Extracellular vesicles (EVs) and their cargo microRNAs (miRNAs) are important regulators of embryo development to the blastocyst stage and beyond. Before implantation can take place, hatching of blastocysts from their zona pellucida is required. However, underlying mechanisms by which blastocyst formation and hatching are initiated remain largely unknown. Here, we provide evidence that embryonic EVs containing bta-miR-378a-3p play a crucial role in blastocyst hatching, using a bovine model. A customized procedure was used to isolate EV-miRNAs from culture droplets conditioned by individual bovine embryos that either developed to the blastocyst stage or did not (nonblastocyst). RNA sequencing identified 69 differentially expressed miRNAs between EVs derived from blastocyst conditioned medium (CM) and nonblastocyst CM. Among the miRNAs up-regulated in blastocyst CM, we selected bta-miR-378a-3p for further validation by functionality testing on developing in vitro embryos by means of mimics and inhibitors. Supplementing the embryo culture medium with miR-378a-3p mimic significandy improved blastocyst quality, with higher cell numbers and reduced apoptosis, and improved hatching, while the opposite was found after supplementation with miR-378a-3p inhibitor (P < 0.01). Transcriptomic analysis of embryos treated with miR-378 mimic/inhibitor showed differential expression (P < 0.01) of genes associated with embryo development and implantation, including RAPT GAP, ARFGEF2, SLC7A6, CENPA, SP1, LDLR, PYCRJ, MYD88, TPPJ, and NCOA3. In conclusion, miR-378a-3p is up-regulated in EVs secreted by embryos that develop to the blastocyst stage, and this EV-derived miR-378a-3p increases blastocyst quality and regulates embryo hatching, which is essential for embryo implantation.

Published
2022

35. Hatching is modulated by microRNA-378a-3p derived from extracellular vesicles secreted by blastocysts

Author

FAH klinische reproductie, Veterinaire biochemie, dB&C FR-RMSC FR, dES/dFAH FR, Pavani, Krishna Chaitanya, Meese, Tim, Pascottini, Osvaldo Bogado, Guan, XueFeng, Lin, Xiaoyuan, Peelman, Luc, Hamacher, Joachim, Van Nieuwerburgh, Filip, Deforce, Dieter, Boel, Annekatrien, Heindryckx, Björn, Tilleman, Kelly, Van Soom, Ann, Gadella, Bart M, Hendrix, An, Smits, Katrien, FAH klinische reproductie, Veterinaire biochemie, dB&C FR-RMSC FR, dES/dFAH FR, Pavani, Krishna Chaitanya, Meese, Tim, Pascottini, Osvaldo Bogado, Guan, XueFeng, Lin, Xiaoyuan, Peelman, Luc, Hamacher, Joachim, Van Nieuwerburgh, Filip, Deforce, Dieter, Boel, Annekatrien, Heindryckx, Björn, Tilleman, Kelly, Van Soom, Ann, Gadella, Bart M, Hendrix, An, and Smits, Katrien

Published
2022

36. Development Process, Quantitative Models, and Future Directions in Driving Analysis of Urban Expansion.

Author

Guan, Xuefeng, Li, Jingbo, Yang, Changlan, and Xing, Weiran

Subjects
*URBAN growth, *SOCIAL dynamics, *URBAN planning, *BIG data, *URBANIZATION, *REMOTE sensing, *SOCIOECONOMIC factors, *MACHINE learning
Abstract

Driving analysis of urban expansion (DAUE) is usually implemented to identify the driving factors and their corresponding driving effects/mechanisms for the expansion processes of urban land, aiming to provide scientific guidance for urban planning and management. Based on a thorough analysis and summarization of the development process and quantitative models, four major limitations in existing DAUE studies have been uncovered: (1) the interactions in hierarchical urban systems have not been fully explored; (2) the employed data cannot fully depict urban dynamic through finer social perspectives; (3) the employed models cannot deal with high-level feature correlations; and (4) the simulation and analysis models are still not intrinsically integrated. Four future directions are thus proposed: (1) to pay attention to the hierarchical characteristics of urban systems and conduct multi-scale research on the complex interactions within them to capture dynamic features; (2) to leverage remote sensing data so as to obtain diverse urban expansion data and assimilate multi-source spatiotemporal big data to supplement novel socio-economic driving factors; (3) to integrate with interpretable data-driven machine learning techniques to bolster the performance and reliability of DAUE models; and (4) to construct mechanism-coupled urban simulation to achieve a complementary enhancement and facilitate theory development and testing for urban land systems. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

47. HistSFC: Optimization for nD massive spatial points querying

Author

Liu, H. (author), van Oosterom, P.J.M. (author), Meijers, B.M. (author), Guan, Xuefeng (author), Verbree, E. (author), Horhammer, Mike (author), Liu, H. (author), van Oosterom, P.J.M. (author), Meijers, B.M. (author), Guan, Xuefeng (author), Verbree, E. (author), and Horhammer, Mike (author)

Abstract

Space Filling Curve (SFC) mapping-based clustering and indexing works effectively for point clouds management and querying. It maps both points and queries into a one-dimensional SFC space so that B+- tree could be utilized. Based on the basic structure, this paper develops a generic HistSFC approach which utilizes a histogram tree recording point distribution for efficient querying. The goal is to resolve the issue of skewed data querying. Besides, the paper proposes an agile method to compute a continuous Level of Detail (cLoD), and integrates it into HistSFC to support smooth rendering of massive points. Results indicate that for range queries, HistSFC decreases the False Positive Rate (FPR) of selection by maximally 80%, compared to previous approaches. It also performs significantly faster than the state-of- the-art Oracle SDO_PC solution. With improved performance on visualization and k Nearest Neighbour (kNN) search, HistSFC can therefore be used as a new standard solution., GIS Technologie

Published
2020
Full Text
View/download PDF

48. Deformation mechanisms of spherical cell porous aluminum under quasi-static compression

Author

Guan Xuefeng, Bingbing Zhang, Peng Xu, Yubo Gao, and Fan Zhiqiang

Subjects
010302 applied physics, Digital image correlation, Materials science, Mechanical Engineering, Metals and Alloys, 02 engineering and technology, Bending, Deformation (meteorology), 021001 nanoscience & nanotechnology, Condensed Matter Physics, 01 natural sciences, Shear (sheet metal), Deformation mechanism, Mechanics of Materials, 0103 physical sciences, Tearing, General Materials Science, Deformation bands, Composite material, 0210 nano-technology, Quasistatic process
Abstract

Quasi-static compression tests for a novel type of spherical cell porous aluminum prepared by the space-holder method were conducted. Formation and evolution mechanisms of deformation bands on the macro and micro scale were monitored and discussed by using a digital image correlation procedure. Effect of micro strain concentrations on the formation process and morphology of deformation bands at the macro level was analyzed in detail. In total three deformation modes of spherical cells and four failure modes of cell membranes including bending, shear, combined compression-shear, and eventually tearing were identified.

Published
2018

Catalog

Books, media, physical & digital resources
See catalog results