Author name cluster

Bing Chen

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

JBHI Journal 2026 Journal Article

MPAExpo-LM: Fine-Tuned Large Language Model for Mycophenolic Acid Exposure Estimation After Renal Transplantation

Dehua Chen
Huilin Liu
Qingyuan Ge
Ming Zuo
Huimin An
Quan Zhou
Shangxi Fu
Peijun Zhou

An accurate estimation of mycophenolic acid (MPA) exposure after renal transplantation is important for reducing acute rejection in patients treated with mycophenolate mofetil (MMF) or enteric-coated mycophenolate sodium (MPS). We propose MPAExpo-LM, a fine-tuned large language model with a differential attention denoising module for this task. Experiments on real-world datasets demonstrate that MPAExpo-LM achieves superior results compared to existing methods in the task, offering a new pathway for precise immunosuppressive therapy. It attains an RMSE of 8. 78 mg·h/L using three sampling points (C 2, C 4, C 8 ) and 7. 43 mg·h/L with four points (C 0. 5, C 2, C 6, C 8 ). Furthermore, we conducted additional fine-tuning by incorporating a limited amount of data from external data source from another hospital. In the subsequent multi-center validation, the model demonstrated robust generalization, achieving RMSEs of 7. 342 mg·h/L (three points) and 7. 281 mg·h/L (four points). Via reinforcement fine-tuning, the model demonstrates strong generalization capability in cross-hospital tests.

Details DOI

EAAI Journal 2026 Journal Article

Occlusion-aware fruit segmentation and quantitative visibility estimation for robotic harvesting of navel oranges

Mingyue Zhang
Juntao Xiong
Bing Chen
Yanggang Ou
Zhixian Wu
Jinlong Zeng

Navel orange (Citrus sinensis) detection plays a critical role in intelligent orchard management and robotic harvesting. However, severe occlusion from foliage and overlapping fruits remains a major challenge that limits segmentation accuracy. To address this, we propose an Occlusion-Aware Fruit Segmentation Network that enhances fruit visibility modeling and robustness under single-view conditions. The network integrates three key structural innovations: a multi-scale edge-aware module that strengthens boundary detail modeling and alleviates edge blurring, a spatial-aware downsampling module that preserves essential spatial structures and occlusion cues during feature compression, and a cross-stage token statistics attention with dynamic tanh module that adaptively enhances salient fruit features across network layers while suppressing background interference. In addition, an occlusion-rate estimation method based on the minimum enclosing circle is introduced to quantitatively describe fruit visibility and enable ranking. Experimental results demonstrate that the proposed network achieves 92. 90% average precision for bounding boxes and 90. 32% for segmentation at an intersection over union threshold of 0. 5, outperforming the baseline model by 3. 56% and 3. 79%, respectively, while maintaining lower computational cost. Furthermore, the predicted occlusion rates show strong correlations with human ratings (Spearman's rank correlation coefficient of 0. 932 and Kendall's tau of 0. 808) and achieve an area under the receiver operating characteristic curve of 0. 885 in a binary occlusion classification task, confirming their effectiveness in both ranking and discrimination. Overall, this work establishes an end-to-end perception pipeline from occlusion modeling to decision support, providing a practical framework for future autonomous fruit harvesting systems.

Details DOI

EAAI Journal 2025 Journal Article

Cooperative reconnaissance coverage for heterogeneous unmanned aerial vehicle swarm in unknown communication interference environments

Yongjian Fan
Bing Chen
Yunlong Zhao
Feng Hu
Chunyan Liu
Yang Li

In complex environments with uncertain communication interference, heterogeneous unmanned aerial vehicle (HUAV) swarm often encounter the challenge of communication disruptions while collaboratively executing reconnaissance and coverage missions, hindering efficient information sharing and subsequently leading to substantial issues of redundant coverage. Given that existing research overlooks the impact of communication interference, this paper proposes a Coverage-Oriented Multi-Agent Cooperative Artificial Potential Field (MACAPF) algorithm. Firstly, a communication model for HUAV swarm under communication interference is considered to accurately reflect real-time communication status. Secondly, an autonomous collaborative distributed-concentrated architecture is devised, which dynamically adjusts the distributed-concentrated state of the swarm based on varying communication conditions, providing support for resolving communication disruptions faced by the HUAV swarm. Lastly, addressing the limitations of traditional artificial potential field (APF) algorithm in unknown communication interference environments, individualized definitions of the HUAV potential field are introduced, and the MACAPF algorithm is designed based on the autonomous collaborative distributed-concentrated architecture. This algorithm effectively guides HUAVs experiencing communication disruptions to restore communication, enhancing the communication efficiency and cooperative operation capabilities of the HUAV swarm. Simulation results demonstrate that the proposed MACAPF algorithm exhibits significant advantages over other state of the art (SOTA) algorithms across multiple dimensions under various signal interference intensities.

Details DOI

AAAI Conference 2022 Conference Paper

Deconvolutional Density Network: Modeling Free-Form Conditional Distributions

Bing Chen
Mazharul Islam
Jisuo Gao
Lin Wang

Conditional density estimation (CDE) is the task of estimating the probability of an event conditioned on some inputs. A neural network (NN) can also be used to compute the output distribution for continuous-domain, which can be viewed as an extension of regression task. Nevertheless, it is difficult to explicitly approximate a distribution without knowing the information of its general form a priori. In order to fit an arbitrary conditional distribution, discretizing the continuous domain into bins is an effective strategy, as long as we have sufficiently narrow bins and very large data. However, collecting enough data is often hard to reach and falls far short of that ideal in many circumstances, especially in multivariate CDE for the curse of dimensionality. In this paper, we demonstrate the benefits of modeling free-form conditional distributions using a deconvolution-based neural net framework, coping with data deficiency problems in discretization. It has the advantage of being flexible but also takes advantage of the hierarchical smoothness offered by the deconvolution layers. We compare our method to a number of other density-estimation approaches and show that our Deconvolutional Density Network (DDN) outperforms the competing methods on many univariate and multivariate tasks. The code of DDN is available at https: //github. com/NBICLAB/DDN

PDF Details