Guoxi Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Guoxi Liu has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Federico Iuricich
Clemson University
5 shared publications - Leila De Floriani
Department of Geographical Sciences, University of Maryland, College Park, MD, USA
2 shared publications - Biao Du
The 54th Research Institute of China Electronics Technology Group Corporation, Shijiazhuang 050081, China
1 shared publication - Fan Feng
College of Energy and Mining Engineering, Shandong University of Science and Technology, Qingdao 266590, China
1 shared publication - Fei Song
Sichuan University
1 shared publication - Hongliang Qian
School of Ocean Engineering, Harbin Institute of Technology at Weihai, Weihai 264209, China
1 shared publication
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (10) , 8211-8225
Distributed Topological Data Analysis of Tetrahedral Meshes With Apache Spark
Tetrahedral meshes are essential for scientific computing due to their flexibility in capturing complex geometries, yet their irregular structure imposes significant memory and performance challenges when applied at scale. Distributed processing can alleviate these limitations, but traditional MPI-based solutions often require substantial redesign of algorithms to manage communication and data distribution. In this work, we introduce Tetra-Spark, a framework for distributed representation and analysis of large tetrahedral meshes built on Apache Spark. Leveraging Spark's implicit data parallelism and in-memory execution model, Tetra-Spark enables scalable mesh encoding, connectivity computation, and topological analysis without the need for low-level distributed programming. To prove the effectiveness and scalability of such a framework, we conduct a comprehensive comparison against a vanilla Spark implementation and an MPI-supported implementation. Our experimental evaluation shows that Tetra-Spark achieves up to a 78× speedup and reduces memory usage by up to 80% when retrieving connectivity relations. This optimized design further accelerates subsequent morphology computations, resulting in up to a 55.6× speedup for computing local topological features, and from 15.2× to 173.6× for extracting global topological descriptors.
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (10) , 8211-8225
Distributed Topological Data Analysis of Tetrahedral Meshes With Apache Spark
Tetrahedral meshes are essential for scientific computing due to their flexibility in capturing complex geometries, yet their irregular structure imposes significant memory and performance challenges when applied at scale. Distributed processing can alleviate these limitations, but traditional MPI-based solutions often require substantial redesign of algorithms to manage communication and data distribution. In this work, we introduce Tetra-Spark, a framework for distributed representation and analysis of large tetrahedral meshes built on Apache Spark. Leveraging Spark's implicit data parallelism and in-memory execution model, Tetra-Spark enables scalable mesh encoding, connectivity computation, and topological analysis without the need for low-level distributed programming. To prove the effectiveness and scalability of such a framework, we conduct a comprehensive comparison against a vanilla Spark implementation and an MPI-supported implementation. Our experimental evaluation shows that Tetra-Spark achieves up to a 78× speedup and reduces memory usage by up to 80% when retrieving connectivity relations. This optimized design further accelerates subsequent morphology computations, resulting in up to a 55.6× speedup for computing local topological features, and from 15.2× to 173.6× for extracting global topological descriptors.
- 5 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (1) , 1010-1020
GALE: Leveraging Heterogeneous Systems for Efficient Unstructured Mesh Data Analysis
Unstructured meshes present challenges in scientific data analysis due to irregular distribution and complex connectivity. Computing and storing connectivity information is a major bottleneck for visualization algorithms, affecting both time and memory performance. Recent task-parallel data structures address this by precomputing connectivity information at runtime while the analysis algorithm executes, effectively hiding computation costs and improving performance. However, existing approaches are CPU-bound, forcing the data structure and analysis algorithm to compete for the same computational resources, limiting potential speedups. To overcome this limitation, we introduce a novel task-parallel approach optimized for heterogeneous CPU-GPU systems. Specifically, we offload the computation of mesh connectivity information to GPU threads, enabling CPU threads to focus on executing the visualization algorithm. Following this paradigm, we propose GPU-Aided Localized data structurE (GALE), the first open-source CUDA-based data structure designed for heterogeneous task parallelism. Experiments on two 20-core CPUs and an NVIDIA V100 GPU show that GALE achieves up to 2.7× speedup over state-of-the-art localized data structures while maintaining memory efficiency
- 5 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 32 (1) , 1010-1020
GALE: Leveraging Heterogeneous Systems for Efficient Unstructured Mesh Data Analysis
Unstructured meshes present challenges in scientific data analysis due to irregular distribution and complex connectivity. Computing and storing connectivity information is a major bottleneck for visualization algorithms, affecting both time and memory performance. Recent task-parallel data structures address this by precomputing connectivity information at runtime while the analysis algorithm executes, effectively hiding computation costs and improving performance. However, existing approaches are CPU-bound, forcing the data structure and analysis algorithm to compete for the same computational resources, limiting potential speedups. To overcome this limitation, we introduce a novel task-parallel approach optimized for heterogeneous CPU-GPU systems. Specifically, we offload the computation of mesh connectivity information to GPU threads, enabling CPU threads to focus on executing the visualization algorithm. Following this paradigm, we propose GPU-Aided Localized data structurE (GALE), the first open-source CUDA-based data structure designed for heterogeneous task parallelism. Experiments on two 20-core CPUs and an NVIDIA V100 GPU show that GALE achieves up to 2.7× speedup over state-of-the-art localized data structures while maintaining memory efficiency
- Open Access
- 31 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. PP (10772626) , 1-11
A Task-Parallel Approach for Localized Topological Data Structures
Unstructured meshes are characterized by data points irregularly distributed in the Euclidian space. Due to the irregular nature of these data, computing connectivity information between the mesh elements requires much more time and memory than on uniformly distributed data. To lower storage costs, dynamic data structures have been proposed. These data structures compute connectivity information on the fly and discard them when no longer needed. However, on-the-fly computation slows down algorithms and results in a negative impact on the time performance. To address this issue, we propose a new task-parallel approach to proactively compute mesh connectivity. Unlike previous approaches implementing data-parallel models, where all threads run the same type of instructions, our task-parallel approach allows threads to run different functions. Specifically, some threads run the algorithm of choice while other threads compute connectivity information before they are actually needed. The approach was implemented in the new Accelerated Clustered TOPOlogical (ACTOPO) data structure, which can support any processing algorithm requiring mesh connectivity information. Our experiments show that ACTOPO combines the benefits of state-of-the-art memory-efficient (TTK CompactTriangulation) and time-efficient (TTK ExplicitTriangulation) topological data structures. It occupies a similar amount of memory as TTK CompactTriangulation while providing up to 5x speedup. Moreover, it achieves comparable time performance as TTK ExplicitTriangulation while using only half of the memory space.
- 31 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. PP (10772626) , 1-11
Open AccessA Task-Parallel Approach for Localized Topological Data Structures
Unstructured meshes are characterized by data points irregularly distributed in the Euclidian space. Due to the irregular nature of these data, computing connectivity information between the mesh elements requires much more time and memory than on uniformly distributed data. To lower storage costs, dynamic data structures have been proposed. These data structures compute connectivity information on the fly and discard them when no longer needed. However, on-the-fly computation slows down algorithms and results in a negative impact on the time performance. To address this issue, we propose a new task-parallel approach to proactively compute mesh connectivity. Unlike previous approaches implementing data-parallel models, where all threads run the same type of instructions, our task-parallel approach allows threads to run different functions. Specifically, some threads run the algorithm of choice while other threads compute connectivity information before they are actually needed. The approach was implemented in the new Accelerated Clustered TOPOlogical (ACTOPO) data structure, which can support any processing algorithm requiring mesh connectivity information. Our experiments show that ACTOPO combines the benefits of state-of-the-art memory-efficient (TTK CompactTriangulation) and time-efficient (TTK ExplicitTriangulation) topological data structures. It occupies a similar amount of memory as TTK CompactTriangulation while providing up to 5x speedup. Moreover, it achieves comparable time performance as TTK ExplicitTriangulation while using only half of the memory space.
- Open Access
A Task-Parallel Approach for Localized Topological Data Structures
Unstructured meshes are characterized by data points irregularly distributed in the Euclidian space. Due to the irregular nature of these data, computing connectivity information between the mesh elements requires much more time and memory than on uniformly distributed data. To lower storage costs, dynamic data structures have been proposed. These data structures compute connectivity information on the fly and discard them when no longer needed. However, on-the-fly computation slows down algorithms and results in a negative impact on the time performance. To address this issue, we propose a new task-parallel approach to proactively compute mesh connectivity. Unlike previous approaches implementing data-parallel models, where all threads run the same type of instructions, our task-parallel approach allows threads to run different functions. Specifically, some threads run the algorithm of choice while other threads compute connectivity information before they are actually needed. The approach was implemented in the new Accelerated Clustered TOPOlogical (ACTOPO) data structure, which can support any processing algorithm requiring mesh connectivity information. Our experiments show that ACTOPO combines the benefits of state-of-the-art memory-efficient (TTK CompactTriangulation) and time-efficient (TTK ExplicitTriangulation) topological data structures. It occupies a similar amount of memory as TTK CompactTriangulation while providing up to 5x speedup. Moreover, it achieves comparable time performance as TTK ExplicitTriangulation while using only half of the memory space.
Open AccessA Task-Parallel Approach for Localized Topological Data Structures
Unstructured meshes are characterized by data points irregularly distributed in the Euclidian space. Due to the irregular nature of these data, computing connectivity information between the mesh elements requires much more time and memory than on uniformly distributed data. To lower storage costs, dynamic data structures have been proposed. These data structures compute connectivity information on the fly and discard them when no longer needed. However, on-the-fly computation slows down algorithms and results in a negative impact on the time performance. To address this issue, we propose a new task-parallel approach to proactively compute mesh connectivity. Unlike previous approaches implementing data-parallel models, where all threads run the same type of instructions, our task-parallel approach allows threads to run different functions. Specifically, some threads run the algorithm of choice while other threads compute connectivity information before they are actually needed. The approach was implemented in the new Accelerated Clustered TOPOlogical (ACTOPO) data structure, which can support any processing algorithm requiring mesh connectivity information. Our experiments show that ACTOPO combines the benefits of state-of-the-art memory-efficient (TTK CompactTriangulation) and time-efficient (TTK ExplicitTriangulation) topological data structures. It occupies a similar amount of memory as TTK CompactTriangulation while providing up to 5x speedup. Moreover, it achieves comparable time performance as TTK ExplicitTriangulation while using only half of the memory space.
- Open Access
Simulation of Video Streaming Over Wireless Networks with NS-3
The combination of video streaming services and wireless networks plays an important role in many fields. In this paper, we present an NS-3-based simulation platform for evaluating and optimizing the performance of the video streaming application over wireless networks. The simulation is designed to provide real-time measurements, and thus it saves the high costs for real equipment. The developed platform consists of the video streaming server, video streaming client, and wireless network environment, where the video streaming operation is implemented under UDP protocol and is equipped with an application-level adaptive rate controller. We use the platform to simulate different use cases of sharing a wireless multi-access channel among multiple video streams.
Open AccessSimulation of Video Streaming Over Wireless Networks with NS-3
The combination of video streaming services and wireless networks plays an important role in many fields. In this paper, we present an NS-3-based simulation platform for evaluating and optimizing the performance of the video streaming application over wireless networks. The simulation is designed to provide real-time measurements, and thus it saves the high costs for real equipment. The developed platform consists of the video streaming server, video streaming client, and wireless network environment, where the video streaming operation is implemented under UDP protocol and is equipped with an application-level adaptive rate controller. We use the platform to simulate different use cases of sharing a wireless multi-access channel among multiple video streams.
- Open Access
- 1 April 2022
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 2217 (1) , 012085
Research on the application of ADN propulsion module for satellites
The novel technology of the liquid Ammonium Dinitramide(ADN) propulsion is researched for its higher working performance and safer characteristics. Based on the safe performance, the design of ADN propulsion system for satellites is also presented in this paper. At the same time, the research on ADN propulsion system module is presented in this paper, including the developing processes method, the interface analysis, and the assemblage in satellites. Two examples are described here besides an ADN propulsion module applied in orbit. From the research we can know that ADN propulsion technology is fit for satellites, and the modularization of ADN propulsion system is a better developing mode for small satellites, which can simplify the developing process of propulsion system and crafts. In the end, the further application object and further work of ADN propulsion module for satellites is stated.
- 1 April 2022
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 2217 (1) , 012085
Open AccessResearch on the application of ADN propulsion module for satellites
The novel technology of the liquid Ammonium Dinitramide(ADN) propulsion is researched for its higher working performance and safer characteristics. Based on the safe performance, the design of ADN propulsion system for satellites is also presented in this paper. At the same time, the research on ADN propulsion system module is presented in this paper, including the developing processes method, the interface analysis, and the assemblage in satellites. Two examples are described here besides an ADN propulsion module applied in orbit. From the research we can know that ADN propulsion technology is fit for satellites, and the modularization of ADN propulsion system is a better developing mode for small satellites, which can simplify the developing process of propulsion system and crafts. In the end, the further application object and further work of ADN propulsion module for satellites is stated.
- 21 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 29 (2) , 1506-1517
TopoCluster: A Localized Data Structure for Topology-Based Visualization
Unstructured data are collections of points with irregular topology, often represented through simplicial meshes, such as triangle and tetrahedral meshes. Whenever possible such representations are avoided in visualization since they are computationally demanding if compared with regular grids. In this work, we aim at simplifying the encoding and processing of simplicial meshes. The article proposes TopoCluster , a new localized data structure for tetrahedral meshes. TopoCluster provides efficient computation of the connectivity of the mesh elements with a low memory footprint. The key idea of TopoCluster is to subdivide the simplicial mesh into clusters. Then, the connectivity information is computed locally for each cluster and discarded when it is no longer needed. We define two instances of TopoCluster. The first instance prioritizes time efficiency and provides only a modest savings in memory, while the second instance drastically reduces memory consumption up to an order of magnitude with respect to comparable data structures. Thanks to the simple interface provided by TopoCluster, we have been able to integrate both data structures into the existing Topological Toolkit (TTK) framework. As a result, users can run any plugin of TTK using TopoCluster without changing a single line of code.
- 21 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Visualization and Computer Graphics
- Vol. 29 (2) , 1506-1517
TopoCluster: A Localized Data Structure for Topology-Based Visualization
Unstructured data are collections of points with irregular topology, often represented through simplicial meshes, such as triangle and tetrahedral meshes. Whenever possible such representations are avoided in visualization since they are computationally demanding if compared with regular grids. In this work, we aim at simplifying the encoding and processing of simplicial meshes. The article proposes TopoCluster , a new localized data structure for tetrahedral meshes. TopoCluster provides efficient computation of the connectivity of the mesh elements with a low memory footprint. The key idea of TopoCluster is to subdivide the simplicial mesh into clusters. Then, the connectivity information is computed locally for each cluster and discarded when it is no longer needed. We define two instances of TopoCluster. The first instance prioritizes time efficiency and provides only a modest savings in memory, while the second instance drastically reduces memory consumption up to an order of magnitude with respect to comparable data structures. Thanks to the simple interface provided by TopoCluster, we have been able to integrate both data structures into the existing Topological Toolkit (TTK) framework. As a result, users can run any plugin of TTK using TopoCluster without changing a single line of code.
- 1 October 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 45, 1-3
Performance analysis of SKA dish
This paper focuses on SKA dish requirements, a new structure design is briefly described for the SKA dish, and its structural and electrical performance is analyzed and calculated. The calculated results satisfy the SKA requirements.
- 1 October 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 45, 1-3
Performance analysis of SKA dish
This paper focuses on SKA dish requirements, a new structure design is briefly described for the SKA dish, and its structural and electrical performance is analyzed and calculated. The calculated results satisfy the SKA requirements.
- 7 March 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control
- Vol. 60 (3) , 446-450
High-temperature actuation performance of BiScO3–PbTiO3 ceramics and their multilayer configuration
Electric-field-induced strains of BiScO 3 -PbTiO 3 (BS-PT) ceramics and actuation performance in multilayer configuration were investigated in the temperature range from 25°C to 250°C. Experimental results confirmed that BS-PT ceramics showed better piezoelectric temperature stability than PZT-5H ceramics, and larger strain than PZT-4 and PZT-8 ceramics at temperatures above 50°C. The strain of a BSPT multilayer actuator prepared by the silicate-cement-glue method was comparable to that of a single-layer BS-PT ceramic. Under ±7.5 kV/cm electric field, the strain of a BS-PT multilayer actuator reached 0.115% at 200°C. Our work shows that BS-PT ceramics are suitable for high-temperature actuation applications.
- 7 March 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control
- Vol. 60 (3) , 446-450
High-temperature actuation performance of BiScO3–PbTiO3 ceramics and their multilayer configuration
Electric-field-induced strains of BiScO 3 -PbTiO 3 (BS-PT) ceramics and actuation performance in multilayer configuration were investigated in the temperature range from 25°C to 250°C. Experimental results confirmed that BS-PT ceramics showed better piezoelectric temperature stability than PZT-5H ceramics, and larger strain than PZT-4 and PZT-8 ceramics at temperatures above 50°C. The strain of a BSPT multilayer actuator prepared by the silicate-cement-glue method was comparable to that of a single-layer BS-PT ceramic. Under ±7.5 kV/cm electric field, the strain of a BS-PT multilayer actuator reached 0.115% at 200°C. Our work shows that BS-PT ceramics are suitable for high-temperature actuation applications.
- 1 March 2013
- Published by SAGE Publications in International Journal of Space Structures
- Vol. 28 (1) , 15-26
Analysis of the Precision of the Structural Performance of the 65 m-Antenna Reflector
To investigate the effect of various loads on the reflector surface, provide reference for actuator adjustment, and guarantee the excellent performance of giant radio telescopes, a detailed study on the surface accuracy of the main reflector of the Shanghai 65 m-antenna structure is completed. This paper introduces the method for seeking a best-fitted paraboloid, the method for calculating the surface precision and the method for figuring out the optimum pitch angle to install and adjust the main reflector. Taking different pitch angles, wind velocities, non-uniform temperature field and reflective panel stiffness into consideration, the effects of gravity, wind loads and temperature on surface precision are systematically analyzed. The result shows that the optimum adjustment angle for installing the main reflector is 48.9°, and the corresponding maximum value of precision under gravity is 0.73 mm, with a pitch angle of 5°; the effect of non-uniform temperature field on surface precision approximates that of the gravity load, to which due attention needs to pay. Moreover, in contrast with gravity load, the effects of working wind speed and uniform temperature field on surface precision are much smaller, in a lower order of magnitude. The methods proposed and the results obtained in this paper provide reference for structural design and surface precision analysis of this kind of all-movable antennae.
- 1 March 2013
- Published by SAGE Publications in International Journal of Space Structures
- Vol. 28 (1) , 15-26
Analysis of the Precision of the Structural Performance of the 65 m-Antenna Reflector
To investigate the effect of various loads on the reflector surface, provide reference for actuator adjustment, and guarantee the excellent performance of giant radio telescopes, a detailed study on the surface accuracy of the main reflector of the Shanghai 65 m-antenna structure is completed. This paper introduces the method for seeking a best-fitted paraboloid, the method for calculating the surface precision and the method for figuring out the optimum pitch angle to install and adjust the main reflector. Taking different pitch angles, wind velocities, non-uniform temperature field and reflective panel stiffness into consideration, the effects of gravity, wind loads and temperature on surface precision are systematically analyzed. The result shows that the optimum adjustment angle for installing the main reflector is 48.9°, and the corresponding maximum value of precision under gravity is 0.73 mm, with a pitch angle of 5°; the effect of non-uniform temperature field on surface precision approximates that of the gravity load, to which due attention needs to pay. Moreover, in contrast with gravity load, the effects of working wind speed and uniform temperature field on surface precision are much smaller, in a lower order of magnitude. The methods proposed and the results obtained in this paper provide reference for structural design and surface precision analysis of this kind of all-movable antennae.