Ruohai Di

Dr. Ruohai Di


Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
13 June 2018 in Mathematical Problems in Engineering
Verified
Journal Article
Open access
PDF file
RDRuohai Di
Ruohai Di
Xiaoguang GaoXiaoguang Gao
Xiaoguang Gao
ZGZhigao Guo
Zhigao Guo
KWKaifang Wan
Kaifang Wan
The autonomous decision-making of a UAV is based on rapid and accurate threat assessment of the target. Accordingly, modeling of threat assessment under the condition of a small data set is studied in this paper. First, the operational scenario of a manned/unmanned aerial vehicle is constructed, and feature selection and data preprocessing are performed. Second, to obtain the structure, a modeling method for threat assessment is proposed based on an improved BIC score. Finally, the obtained model is applied to compute the threat probability using the junction tree algorithm. The experimental results show that the method proposed in this paper is an available method for threat assessment under the condition of small data sets.

18 December 2025 in Entropy
Verified
Journal Article
Open access
PDF file
RDRuohai Di
Ruohai Di
HFHao Fan
Hao Fan
YMYuanzheng Ma
Yuanzheng Ma
JWJinqiang Wang
Jinqiang Wang
RQRuoyu Qian
Ruoyu Qian
Detecting low-altitude, slow-speed, small (LSS) UAVs is especially challenging in low-visibility scenes (low light, haze, motion blur), where inherent uncertainties in sensor data and object appearance dominate. We propose GAME-YOLO, a novel detector that integrates a Bayesian-inspired probabilistic reasoning framework with Global Attention and Multi-Scale Enhancement to improve small-object perception and sub-pixel-level localization. Built on YOLOv11, our framework comprises: (i) a visibility restoration front-end that probabilistically infers and enhances latent image clarity; (ii) a global-attention-augmented backbone that performs context-aware feature selection; (iii) an adaptive multi-scale fusion neck that dynamically weights feature contributions; (iv) a sub-pixel-aware small-object detection head (SOH) that leverages high-resolution feature grids to model sub-pixel offsets; and (v) a novel Shape-Aware IoU loss combined with focal loss. Extensive experiments on the LSS2025-DET dataset demonstrate that GAME-YOLO achieves state-of-the-art performance, with an AP@50 of 52.0% and AP@[0.50:0.95] of 32.0%, significantly outperforming strong baselines such as LEAF-YOLO (48.3% AP@50) and YOLOv11 (36.2% AP@50). The model maintains high efficiency, operating at 48 FPS with only 7.6 M parameters and 19.6 GFLOPs. Ablation studies confirm the complementary gains from our probabilistic design choices, including a +10.5 pp improvement in AP@50 over the baseline. Cross-dataset evaluation on VisDrone-DET2021 further validates its generalization capability, achieving 39.2% AP@50. These results indicate that GAME-YOLO offers a practical and reliable solution for vision-based UAV surveillance by effectively marrying the efficiency of deterministic detectors with the robustness principles of Bayesian inference.

1 June 2014
Verified
Conference Paper
Closed access
Guoliang LiGuoliang Li
Guoliang Li
Xiaoguang GaoXiaoguang Gao
Xiaoguang Gao
RDRuohai Di
Ruohai Di
To improve the accuracy of structure learning for Dynamic Bayesian Network (DBN), this paper proposes Mutual Information-Binary Particle Swarm Optimization (MI-BPSO) algorithm. The MI-BPSO algorithm firstly uses MI and conditional independence test to prune the search space and speed up the convergence of the searching phase, then calls BPSO algorithm to search the constrained space and get the intra-network and inter-network of DBN. Experimental results show that this algorithm performs as well as K2 while it doesn't need a given variable ordering, and performs better than MWST-GES, MWST-HC and I-BN-PSO.

24 September 2022 in Entropy
Verified
Journal Article
Open access
PDF file
ZLZhigang Lv
Zhigang Lv
YCYiwei Chen
Yiwei Chen
RDRuohai Di
Ruohai Di
HWHongxi WANG
Hongxi WANG
XSXiaojing Sun
Xiaojing Sun
XLXiaoyan Li
Xiaoyan Li
The Bayesian Network (BN) structure learning algorithm based on dynamic programming can obtain global optimal solutions. However, when the sample cannot fully contain the information of the real structure, especially when the sample size is small, the obtained structure is inaccurate. Therefore, this paper studies the planning mode and connotation of dynamic programming, restricts its process with edge and path constraints, and proposes a dynamic programming BN structure learning algorithm with double constraints under small sample conditions. The algorithm uses double constraints to limit the planning process of dynamic programming and reduces the planning space. Then, it uses double constraints to limit the selection of the optimal parent node to ensure that the optimal structure conforms to prior knowledge. Finally, the integrating prior-knowledge method and the non-integrating prior-knowledge method are simulated and compared. The simulation results verify the effectiveness of the method proposed and prove that the integrating prior knowledge can significantly improve the efficiency and accuracy of BN structure learning.

25 December 2025 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
WHWei Hong
Wei Hong
WHWei Hong
Wei Hong
RDRuohai Di
Ruohai Di
SJShoucai Jing
Shoucai Jing
CHChuchao He
Chuchao He
XZXiangmo Zhao
Xiangmo Zhao
The credibility of the perception system is a linchpin for the safety of Automated Vehicles (AVs). However, existing scenario-based testing approaches often overlook the reliability assessment of the perception system. To address this shortcoming, we propose BAGA, a Bayesian-based adaptive search method for high-value scenarios, which accelerates scenario-based simulations while identifying critical scenarios for the perception system. Concurrently, we design a sensitivity analysis method, BNSobol, based on the naive Bayes network. This method decouples the associations among selected trigger source sets and develops a mutation strategy that aligns with the physical characteristics of the perception system. Furthermore, we construct an objective function that integrates the tolerance boundaries of the credibility indicators. This function calculates the perception system's credibility within scenarios and identifies high-value scenarios. Ultimately, we develop integrated software for evaluating the credibility of the perception system, providing a universal solution for such assessments. Experimental results demonstrate that, compared to mainstream scenario generation methods and exhaustive search methods, our proposed method increases efficiency by 77.7% and 143.2%, respectively. It can effectively generate the high-value scenarios required for perception system testing, thereby facilitating the discovery and localization of credibility issues.

20 May 2022 in Scientific Programming
Verified
Journal Article
Open access
RDRuohai Di
Ruohai Di
YLYe Li
Ye Li
TLTingpeng Li
Tingpeng Li
PWPeng Wang
Peng Wang
CHChuchao He
Chuchao He
Bayesian network structure learning based on dynamic programming strategy can be used to find the optimal graph structure compared with approximate search methods. The traditional dynamic programming method for Bayesian network structure learning is a depth-first-based strategy, which is inefficient. We proposed two methods to solve this problem. First, the dependency constraints were used to prune the process of calculating redundancy scores. The constraints were obtained by the conditional independence test from the observed data sets. However, it was difficult to guarantee the accuracy of the constraints, which may have led to a decrease in the accuracy of the method. Second, we proposed a breadth-first-based strategy, which enhanced efficiency greatly while also ensuring global optimality. Experimental results showed that on the standard network data sets, compared with the dynamic programming based on depth-first search (DFSDP) algorithm, dynamic programming based on constraints (CBDP) could reduce the average running time by 57.10% and that dynamic programming based on breadth-first search (BFSDP) could reduce the average running time by 50.02%. On the UCI data sets, compared with DFSDP, CBDP reduced the average running time by 40.71%, and BFSDP reduced the average running time by 81.78%.