QFQiyuan Fan

Qiyuan Fan

*This is an algorithmically generated author record based on publicly available information.

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


Qiyuan Fan has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    DroneTest-Copilot: LLM-Powered Automated Detection and Repair of Flaws in Drone Autotest Suites

    by Ziyi Liang, Lei Hu, Qiyuan Fan, Bin Yuan, Qiankun Zhang, Deqing Zou, Hai Jin

    In the landscape of the low-altitude economy, ensuring the reliability of drone flight control software is of utmost importance. ArduPilot's autotest is an automated testing framework integrated into its continuous integration (CI) pipeline, which is crucial for validating autopilot functionality. However, numerous logic defects exist in its test cases, where the intended workflow doesn't match the code implementation. This paper presents DroneTest-Copilot (DTC), a novel framework that leverages large language models (LLMs) to automate the validation and correction of autotest test cases. The system consists of four components: Preprocessor, Test Case Processor, Flaw Corrector, and Vulnerability Tester. It extracts relevant context from pull requests, uses LLMs to detect flaws such as parameter mismatch, API misuse, execution order errors, and logic errors, and then generates corrected test code. We also conduct a detailed survey and comparative analysis of existing related works to highlight the novelty and positioning of DTC. Evaluations on a dataset of patched and new test case pull requests show that DTC can correctly identify 87.23% of introduced defects in the verification set and discover previously unknown vulnerabilities in the new test case set. DTC substantially reduces manual effort in maintaining autotest suites and uncovers subtle flaws in test case code, enhancing the reliability of drone flight control software.


  • BDIP: An Efficient Big Data-Driven Information Processing Framework and Its Application in DDoS Attack Detection

    by Qiyuan Fan, Xue Li, Puming Wang, Xin Jin, Shaowen Yao, Shengfa Miao, Sizhang Li, Min An, Jing Xu

    With the rapid advancement of 5G communication technology in the era of big data, massive terminal devices connected to the Internet have dramatically increased the scale of network, generating a large amount of high-dimensional and heterogeneous information. This not only enhances the difficulty of information processing in the network, but also poses a severe challenge to data storage and calculation, which has become a big data problem to be solved urgently. To cope with it, this paper proposes an efficient information processing framework and applies it to Distributed Denial of Service (DDoS) attack detection. Overall, three major highlights are made: (1) Tensor is used to represent multi-modal information in large-scale networks; (2) A novel denoising algorithm based on tensor train(TT) decomposition is proposed, focused on optimizing both computation and correlation; (3) A big data-driven information processing framework is developed, which includes information preprocessing, denoising and classification. Results in case study indicate that the framework can achieve an accuracy of 99.19%, all while maintaining the great storage advantage, well speedup ratio and strong computing capabilities under the same computational complexity. It can also be generalized to other network data processing scenarios.


  • Manganese Intoxication Recovery and the Expression Changes of Park2/Parkin in Rats

    by Yu-Min Cao, Xi-Min Fan, Jie Xu, Jie Liu, Qi-Yuan Fan

    Occupational overexposure to manganese (Mn) produces Parkinson’s disease-like manganism. Acute Mn intoxication in rats causes dopaminergic neuron loss, impairment of motor activity and reduction of the expression of Park2/Parkin. The expression of Park2/Parkin is also reduced. Whether these changes are reversible after cessation of Mn exposure is unknown, and is the goal of this investigation. Adult male rats were injected with Mn2+ at doses 1 mg/kg and 5 mg/kg in the form of MnCl2·4H2O, every other day for one-month to produce acute Mn neurotoxicity. For a half of rats Mn exposure was suspended for recovery for up to 5 months. Mn neurotoxicity was evaluated by the accumulation of Mn in blood and brain, behavioral activities, dopaminergic neuron loss, and the expression of Park2/Parkin in the blood cells and brain. Dose-dependent Mn neurotoxicity in rats was evidenced by Mn accumulation, rotarod impairments, reduction of tyrosine hydroxylase (TH)-positive neurons in the substantia nigra, decreased level of Park2 mRNA in the blood and brain, and decreased Parkin protein in the brain. After cessation of Mn exposure, the amount of Park2 mRNA in the blood started to increase one month after the recovery. After 5-month of recovery, blood and brain Mn returned to normal, rotarod activity recovered, the reduction of TH-positive dopaminergic neurons ameliorated, and the level of Park2 mRNA in the blood and Park2/Parkin in the midbrain and striatum were returned to the normal. Mn neurotoxicity in rats is reversible after cessation of Mn exposure. The level of Park2 mRNA in the blood could be used as a novel biomarker for Mn exposure and recovery. Graphical Abstract


  • Open Access

    Development of a Cumulative Exposure Index (CEI) for Manganese and Comparison with Bone Manganese and Other Biomarkers of Manganese Exposure

    by Danelle Rolle-McFarland, Yingzi Liu, Jieqiong Zhou, Farshad Mostafaei, Yuanzhong Zhou, Yan Li, Quiyan Fan, Wei Zheng, Linda H. Nie, Ellen M. Wells

    Manganese (Mn) exposure can result in parkinsonism. However, understanding of manganese neurotoxicity has been limited by the lack of a cumulative Mn biomarker. Therefore, the current goal was to develop Mn cumulative exposure indices (MnCEI), an established method to estimate cumulative exposure, and determine associations of MnCEI with blood Mn (BMn), fingernail Mn (FMn), and bone Mn (BnMn). We completed a cross-sectional study of 60 male Chinese workers. Self-reported occupational history was used to create two MnCEIs reflecting the previous 16 years (MnCEI16) and total work history (MnCEITOT). An in vivo neutron activation analysis system was used to quantify BnMn. BMn and FMn were measured using ICP-MS. Mean (standard deviation) MnCEITOT and MnCEI16 were 37.5 (22.0) and 25.0 (11.3), respectively. Median (interquartile range) BMn, FMn, and BnMn were 14.1 (4.0) μg/L, 13.5 (58.5) μg/g, and 2.6 (7.2) μg/g dry bone, respectively. MnCEI16 was significantly correlated with FMn (Spearman’s ρ = 0.44; p = 0.02), BnMn (ρ = 0.44; p < 0.01), and MnCEITOT (ρ = 0.44; p < 0.01). In adjusted regression models, MnCEI16 was significantly associated with BnMn (β = 0.03; 95% confidence interval = 0.001, 0.05); no other biomarkers were associated with MnCEI. This suggests BnMn may be a useful biomarker of the previous 16 years of Mn exposure, but larger studies are recommended.