Selected work

Representative Papers

A QUBO-Inspired Computational Framework for Airport Landside Bottleneck Diagnosis and Dynamic Dispatch Optimization

Aug 09, 2026

This study addresses the multi-stage coordination bottlenecks arising from the coupling of passenger and vehicle flows during peak periods in airport landside operations. The authors develop a five-minute-resolution state evolution model that integrates passenger arrivals, vehicle supply, shuttle services, storage capacity, and roadway capacity. They introduce novel diagnostic dimensions—including a composite congestion severity index and shadow price-based levers—and, for the first time, apply QUBO (Quadratic Unconstrained Binary Optimization) modeling to landside scheduling. A hybrid approach combining finite-action model predictive control with a QUBO-inspired simulated annealing algorithm enables differentiated, bottleneck-targeted dynamic scheduling strategies. Evaluated under intense peak scenarios at Shanghai Pudong and Hangzhou Xiaoshan airports, the method reduces passenger queue lengths from 3,445 to 2,477 and from 2,053 to 1,482, respectively, while maintaining robust congestion mitigation under various disturbances.

0 citationsRead paper

Quantum-Inspired Evolutionary Neighborhood Search for Arrival-Departure Track Utilization Adjustment under Short-Term Disturbances

Jul 27, 2026

This study addresses the scheduling disruptions in large passenger railway stations caused by short-term perturbations that alter train arrival/departure times and the sequence of station resource releases. To tackle this challenge, the authors propose an optimization framework integrating a quantum-inspired evolutionary algorithm (QEA) with neighborhood search (NS). The approach models station resources as zone-level occupancy intervals and formulates a track reassignment model that enforces resource compatibility constraints while jointly minimizing total train delay and resource reallocation costs. Experimental results on perturbation scenarios derived from GTFS timetables demonstrate that, within a unified feasible solution space, the proposed method consistently outperforms the CP-SAT solver across ten test instances, reducing average total delay from 673.8 to 390.5 minutes (a 42% improvement) and decreasing per-train average delay from 4.99 to 3.73 minutes, thereby significantly enhancing disruption recovery performance.

0 citationsRead paper

Edge-Constrained UAV Small-Object Detection with P2 Enhancement and Quantum-Inspired Lightweight Structure Search

Jun 08, 2026

This work addresses the challenges in lightweight small-object detection on drone edge devices, where conventional models often lose shallow spatial details and struggle to balance accuracy with computational cost through manual design. To overcome these limitations, the authors propose a lightweight architecture search method that integrates a high-resolution P2 detection branch with a quantum-inspired evolutionary algorithm (QIEA). Built upon the YOLOX-Nano framework, the approach establishes a P2-centric pathway for enhanced small-object detection and jointly optimizes multiple objectives—including accuracy, FLOPs, latency, memory usage, and recall—within a tailored search space. Evaluated on the VisDrone dataset, the resulting YOLOX-Nano+-P2 model outperforms NanoDet-Plus by 17.5% in AP₀.₅ and achieves a remarkable 44.9% improvement in APₛₘₐₗₗ, demonstrating the efficacy and superiority of the proposed method.

0 citationsRead paper

Coordinated optimization of departure sequencing and section-track allocation in railway short-term concentrated departure scenarios based on qubo and hybrid quantum algorithms

Jun 04, 2026

This study addresses the joint optimization of train departure sequencing and track allocation in short-term, high-frequency railway dispatching scenarios. A unified QUBO (Quadratic Unconstrained Binary Optimization) model is developed to simultaneously represent departure position assignment and en-route track selection. Innovatively, a simulation-based evaluation layer is integrated to account for dynamic operational factors—including block occupancy, intermediate station dwell times, platform congestion, service variability, and delay propagation. The proposed framework uniquely combines QUBO modeling with simulation-driven assessment, enabling fair benchmarking of classical heuristics, quantum-inspired methods, and hybrid algorithms—such as QPSO-QAOA—within a common platform. Experimental results demonstrate that, under dynamic conditions, quantum-enhanced algorithms achieve 4.28%–26.26% lower composite costs and reduce total delays by 4.37%–24.25% compared to classical approaches, confirming their superiority in complex railway scheduling environments.

0 citationsRead paper

Polygon-mamba: Retinal vessel segmentation using polygon scanning mamba and space-frequency collaborative attention

May 11, 2026

This study addresses the challenge of segmenting fine-scale retinal vessels, which are difficult to delineate due to their delicate structure and fragile topology prone to disconnection. To enhance spatial continuity of small vessels, the authors propose a hybrid CNN-Mamba architecture featuring a novel Polygon Scan Visual State Space (PS-VSS) module. Additionally, a Spatial-Frequency Collaborative Attention Mechanism (SFCAM) is introduced to effectively fuse spatial and frequency-domain features. Evaluated on the DRIVE, STARE, and CHASE_DB1 datasets, the method achieves F1 scores of 0.8283, 0.8282, and 0.8251; AUC values of 0.9806, 0.9840, and 0.9866; and sensitivities of 0.8268, 0.8314, and 0.8484, respectively, demonstrating significant improvements in small vessel segmentation accuracy.

0 citationsRead paper

Recent publications

Latest Papers

A QUBO-Inspired Computational Framework for Airport Landside Bottleneck Diagnosis and Dynamic Dispatch Optimization

Aug 09, 2026

This study addresses the multi-stage coordination bottlenecks arising from the coupling of passenger and vehicle flows during peak periods in airport landside operations. The authors develop a five-minute-resolution state evolution model that integrates passenger arrivals, vehicle supply, shuttle services, storage capacity, and roadway capacity. They introduce novel diagnostic dimensions—including a composite congestion severity index and shadow price-based levers—and, for the first time, apply QUBO (Quadratic Unconstrained Binary Optimization) modeling to landside scheduling. A hybrid approach combining finite-action model predictive control with a QUBO-inspired simulated annealing algorithm enables differentiated, bottleneck-targeted dynamic scheduling strategies. Evaluated under intense peak scenarios at Shanghai Pudong and Hangzhou Xiaoshan airports, the method reduces passenger queue lengths from 3,445 to 2,477 and from 2,053 to 1,482, respectively, while maintaining robust congestion mitigation under various disturbances.

0 citationsRead paper

Quantum-Inspired Evolutionary Neighborhood Search for Arrival-Departure Track Utilization Adjustment under Short-Term Disturbances

Jul 27, 2026

This study addresses the scheduling disruptions in large passenger railway stations caused by short-term perturbations that alter train arrival/departure times and the sequence of station resource releases. To tackle this challenge, the authors propose an optimization framework integrating a quantum-inspired evolutionary algorithm (QEA) with neighborhood search (NS). The approach models station resources as zone-level occupancy intervals and formulates a track reassignment model that enforces resource compatibility constraints while jointly minimizing total train delay and resource reallocation costs. Experimental results on perturbation scenarios derived from GTFS timetables demonstrate that, within a unified feasible solution space, the proposed method consistently outperforms the CP-SAT solver across ten test instances, reducing average total delay from 673.8 to 390.5 minutes (a 42% improvement) and decreasing per-train average delay from 4.99 to 3.73 minutes, thereby significantly enhancing disruption recovery performance.

0 citationsRead paper

Edge-Constrained UAV Small-Object Detection with P2 Enhancement and Quantum-Inspired Lightweight Structure Search

Jun 08, 2026

This work addresses the challenges in lightweight small-object detection on drone edge devices, where conventional models often lose shallow spatial details and struggle to balance accuracy with computational cost through manual design. To overcome these limitations, the authors propose a lightweight architecture search method that integrates a high-resolution P2 detection branch with a quantum-inspired evolutionary algorithm (QIEA). Built upon the YOLOX-Nano framework, the approach establishes a P2-centric pathway for enhanced small-object detection and jointly optimizes multiple objectives—including accuracy, FLOPs, latency, memory usage, and recall—within a tailored search space. Evaluated on the VisDrone dataset, the resulting YOLOX-Nano+-P2 model outperforms NanoDet-Plus by 17.5% in AP₀.₅ and achieves a remarkable 44.9% improvement in APₛₘₐₗₗ, demonstrating the efficacy and superiority of the proposed method.

0 citationsRead paper

Coordinated optimization of departure sequencing and section-track allocation in railway short-term concentrated departure scenarios based on qubo and hybrid quantum algorithms

Jun 04, 2026

This study addresses the joint optimization of train departure sequencing and track allocation in short-term, high-frequency railway dispatching scenarios. A unified QUBO (Quadratic Unconstrained Binary Optimization) model is developed to simultaneously represent departure position assignment and en-route track selection. Innovatively, a simulation-based evaluation layer is integrated to account for dynamic operational factors—including block occupancy, intermediate station dwell times, platform congestion, service variability, and delay propagation. The proposed framework uniquely combines QUBO modeling with simulation-driven assessment, enabling fair benchmarking of classical heuristics, quantum-inspired methods, and hybrid algorithms—such as QPSO-QAOA—within a common platform. Experimental results demonstrate that, under dynamic conditions, quantum-enhanced algorithms achieve 4.28%–26.26% lower composite costs and reduce total delays by 4.37%–24.25% compared to classical approaches, confirming their superiority in complex railway scheduling environments.

0 citationsRead paper

Polygon-mamba: Retinal vessel segmentation using polygon scanning mamba and space-frequency collaborative attention

May 11, 2026

This study addresses the challenge of segmenting fine-scale retinal vessels, which are difficult to delineate due to their delicate structure and fragile topology prone to disconnection. To enhance spatial continuity of small vessels, the authors propose a hybrid CNN-Mamba architecture featuring a novel Polygon Scan Visual State Space (PS-VSS) module. Additionally, a Spatial-Frequency Collaborative Attention Mechanism (SFCAM) is introduced to effectively fuse spatial and frequency-domain features. Evaluated on the DRIVE, STARE, and CHASE_DB1 datasets, the method achieves F1 scores of 0.8283, 0.8282, and 0.8251; AUC values of 0.9806, 0.9840, and 0.9866; and sensitivities of 0.8268, 0.8314, and 0.8484, respectively, demonstrating significant improvements in small vessel segmentation accuracy.

0 citationsRead paper