HiGISX

High Intelligence Spatial Computing Research Team

We are dedicated to utilizing advanced computational methods and artificial intelligence techniques to analyze and process spatio-temporal big data, enabling intelligent decision-making and optimization of spatial environments. Through the analysis of spatio-temporal big data, we uncover key information and trends to provide reliable foundations for decision-making.

banner-img
More info about

Latest News

05/06/2024

Paper Delivery

Congratulations to Yingqiu Long for her paper "Optimization of Shared Electric Scooter Deployment Stations Based on Distance Tolerance" accepted by ISPRS International Journal of Geo-Information!

03/21/2024

Paper Delivery

Congratulations to Dr. Yang Zhong for his paper "ReCovNet: Reinforcement learning with covering information for solving maximal coverage billboards location problem" accepted by International Journal of Applied Earth Observation and Geoinformation!

03/19/2024

Paper Delivery

Congratulations to Xiao Li for his paper "A Single Data Extraction Algorithm for Oblique Photographic Data Based on the U-Net" accepted by Remote Sensing!

01/26/2024

Paper Delivery

Congratulations to teacher Yueyi Wang for his paper "Dynamic Visual Landscape Assessment of Disused Railway in Complex Terrain: A Study of Jingmen Railway" accepted by IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing!

01/25/2024

Paper Delivery

Congratulations to Xiao Li his paper "Development of Geographic Information System Architecture Feature Analysis and Evolution Trend Research" accepted by Journal of Sustainability!

01/19/2024

Paper Delivery

Congratulations to Junyuan Zhou for his paper "A New Approach for Solving Location Routing Problems with Deep Reinforcement Learning of Emergency Medical Facility" accepted by the Geoindustry@ACM SIGSPATIAL 2023 conference!

Team Development

Achievement

HiSpot

Open-source Software

HiSpot is an open-source software package developed by the HiGISX team, aimed at solving spatial optimization problems. The software provides multiple solution methods, including mathematical planning solvers, approximate algorithm, and heuristic algorithm, mainly solving location routing problems and facility location problems.

SpoNet

Algorithm code

SpoNet is a unified deep learning model used to solve p-median, p-center, and maximal covering location problems. It offers a new approach to solving spatial optimization problems and provides a novel method for addressing large-scale spatial optimization challenges.

GCN-Greedy

Hybrid Framework

GCN-Greedy is a hybrid framework using Graph Convolutional Network and Greedy algorithm for Covering Location Problem. We use GCN network to solve location set covering problem (LSCP) and maximum covering location problem (MCLP). The optimization of the loss function takes into account the characteristics of covering location problems. This model is more accurate and more efficient than classical heuristic algorithms.