Fangqun Gao

Dr. Fangqun Gao


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 November 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
FGFangqun Gao
Fangqun Gao
SXShu Xu
Shu Xu
WHWeiyan Hao
Weiyan Hao
TLTao Lu
Tao Lu
Generative artificial intelligence (AI) and large language models (LLMs) are reshaping the landscape of intelligent educational systems; however, existing solutions often suffer from unstructured resource organization, limited interpretability, and suboptimal retrieval precision. To address these challenges, this study introduces KA-RAG, a course-oriented question answering (QA) framework that integrates a structured Knowledge Graph (KG) with an Agentic Retrieval-Augmented Generation (Agentic-RAG) workflow. The system incorporates a responsive interface, a unified agent controller (ToolPlanner), a course knowledge graph, and a vector-based retrieval subsystem. By combining symbolic graph reasoning with dense semantic retrieval, the proposed dual-retrieval strategy supports interpretable, context-aware responses to course-related queries. Experiments conducted on a graduate-level Pattern Recognition course demonstrate that KA-RAG achieves a retrieval accuracy of 91.4%, semantic consistency of 87.6%, and an average response latency of 2.8 s. User surveys further reveal significant improvements in learning efficiency and satisfaction. The results validate the feasibility of integrating KG and Agentic-RAG techniques for knowledge-grounded educational applications, offering a practical pathway toward intelligent knowledge organization and interactive learning support.

17 October 2026 in Sensors
Verified
Journal Article
Open access
PDF file
PTPan Tang
Pan Tang
HXHeyu Xiang
Heyu Xiang
FGFangqun Gao
Fangqun Gao
YWYuntao Wu
Yuntao Wu
YZYanduo Zhang
Yanduo Zhang
MSMd Zakaria Haque Sakib
Md Zakaria Haque Sakib
Reliable visual sensing is important for UAV-assisted monitoring of live-line power operations, where workers, personal protective equipment (PPE), temporary insulation, and electrical structures appear under large-scale variation, occlusion, and background clutter. This study develops a safety-oriented detector that assigns different feature transformations to different stages of the detection hierarchy. Multi-Scale Selective Fusion (MSSF) combines 3-by-3, 5-by-5, and 7-by-7 receptive-field responses through channel-wise branch weighting. Frequency-Aware Adaptive Fusion (FreqAFU) refines the real and imaginary Fourier components and fuses the reconstructed response with the spatial feature through learned channel gates. BiNet and Mamba-based blocks provide bidirectional cross-scale interaction and state-space contextual modelling. The self-collected corpus contains 8124 annotated images and 118,119 object instances across eight categories, with 6499 training images and 1625 validation images separated at the acquisition-session level. On this fixed protocol, the complete YOLOv8n-based configuration improves mAP50-95 from 0.558 to 0.635 and mAP50 from 0.900 to 0.949. Ablations, repeated training, scale- and class-level analyses, runtime profiling, and VisDrone evaluation show that the benefit of individual components is configuration dependent rather than universally additive. The detector is positioned as an object-level perception layer; final safety-compliance reasoning remains outside its scope.

9 June 2026 in Entropy
Verified
Journal Article
Open access
PDF file
FGFangqun Gao
Fangqun Gao
WHWeiyan Hao
Weiyan Hao
YWYuntao Wu
Yuntao Wu
SYShubin Yang
Shubin Yang
Advancement toward the Essential Science Indicators (ESI) Top 1‰ is an important indicator of disciplinary competitiveness, but progress near this boundary is often nonlinear because the global threshold continues to move upward. This study develops a two-layer framework combining an Exponential Decay Model (EDM) for modeling rank trajectories and a Bivariate Logarithmic Difference Decomposition Model (BLDDM) for separating institutional citation growth from external threshold pressure. Using 13 bimonthly ESI update waves from March 2024 to March 2026, we analyze Chemistry, Engineering, and Materials Science at Wuhan Institute of Technology. The results show that the EDM outperforms a linear benchmark in all three disciplines, indicating an asymptotic pattern of advancement near the Top 1‰ boundary. The BLDDM further reveals substantial disciplinary heterogeneity: Engineering faces the strongest threshold pressure, whereas Chemistry is the most favorable near-term candidate for breakthrough. These findings suggest that ESI advancement should be understood as a moving-threshold process rather than a simple accumulation of citations.