Hongbo Fan

Dr. Hongbo Fan


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
6 July 2023 in Processes
Verified
Journal Article
Open access
PDF file
ZWZufa Wu
Zufa Wu
HFHongbo Fan
Hongbo Fan
YSYimeng Sun
Yimeng Sun
MPManyu Peng
Manyu Peng
Previous research focuses on approaches of deep reinforcement learning (DRL) to optimize diverse types of the single-objective dynamic flexible job shop scheduling problem (DFJSP), e.g., energy consumption, earliness and tardiness penalty and machine utilization rate, which gain many improvements in terms of objective metrics in comparison with metaheuristic algorithms such as GA (genetic algorithm) and dispatching rules such as MRT (most remaining time first). However, single-objective optimization in the job shop floor cannot satisfy the requirements of modern smart manufacturing systems, and the multiple-objective DFJSP has become mainstream and the core of intelligent workshops. A complex production environment in a real-world factory causes scheduling entities to have sophisticated characteristics, e.g., a job’s non-uniform processing time, uncertainty of the operation number and restraint of the due time, avoidance of the single machine’s prolonged slack time as well as overweight load, which make a method of the combination of dispatching rules in DRL brought up to adapt to the manufacturing environment at different rescheduling points and accumulate maximum rewards for a global optimum. In our work, we apply the structure of a dual layer DDQN (DLDDQN) to solve the DFJSP in real time with new job arrivals, and two objectives are optimized simultaneously, i.e., the minimization of the delay time sum and makespan. The framework includes two layers (agents): the higher one is named as a goal selector, which utilizes DDQN as a function approximator for selecting one reward form from six proposed ones that embody the two optimization objectives, while the lower one, called an actuator, utilizes DDQN to decide on an optimal rule that has a maximum Q value. The generated benchmark instances trained in our framework converged perfectly, and the comparative experiments validated the superiority and generality of the proposed DLDDQN.

4 October 2023 in Agriculture
Verified
Journal Article
Open access
PDF file
XLXiaowu Li
Xiaowu Li
KSKun Sun
Kun Sun
HFHongbo Fan
Hongbo Fan
ZHZihan He
Zihan He
Accurate cattle pose estimation is essential for Precision Livestock Farming (PLF). Computer vision-based, non-contact cattle pose estimation technology can be applied for behaviour recognition and lameness detection. Existing methods still face challenges in achieving fast cattle pose estimation in complex scenarios. In this work, we introduce the FasterNest Block and Depth Block to enhance the performance of cattle pose estimation based on the RTMPose model. First, the accuracy of cattle pose estimation relies on the capture of high-level image features. The FasterNest Block, with its three-branch structure, effectively utilizes high-level feature map information, significantly improving accuracy without a significant decrease in inference speed. Second, large kernel convolutions can increase the computation cost of the model. Therefore, the Depth Block adopts a method based on depthwise separable convolutions to replace large kernel convolutions. This addresses the insensitivity to semantic information while reducing the model’s parameter. Additionally, the SimAM module enhances the model’s spatial learning capabilities without introducing extra parameters. We conducted tests on various datasets, including our collected complex scene dataset (cattle dataset) and the AP-10K public dataset. The results demonstrate that our model achieves the best average accuracy with the lowest model parameters and computational requirements, achieving 82.9% on the cattle test set and 72.0% on the AP-10K test set. Furthermore, in conjunction with the object detection model RTMDet-m, our model reaches a remarkable inference speed of 39FPS on an NVIDIA GTX 2080Ti GPU using the PyTorch framework, making it the fastest among all models. This work provides adequate technical support for fast and accurate cattle pose estimation in complex farm environments.

23 May 2023 in Agriculture
Verified
Journal Article
Open access
PDF file
DSDangguo Shao
Dangguo Shao
ZHZihan He
Zihan He
HFHongbo Fan
Hongbo Fan
KSKun Sun
Kun Sun
Accurate detection of key body parts of cattle is of great significance to Precision Livestock Farming (PLF), using artificial intelligence for video analysis. As the background image in cattle livestock farms is complex and the target features of the cattle are not obvious, traditional object-detection algorithms cannot detect the key parts of the image with high precision. This paper proposes the Filter_Attention attention mechanism to detect the key parts of cattle. Since the image is unstable during training and initialization, particle noise is generated in the feature graph after convolution calculation. Therefore, this paper proposes an attentional mechanism based on bilateral filtering to reduce this interference. We also designed a Pooling_Module, based on the soft pooling algorithm, which facilitates information loss relative to the initial activation graph compared to maximum pooling. Our data set contained 1723 images of cattle, in which labels of the body, head, legs, and tail were manually entered. This dataset was divided into a training set, verification set, and test set at a ratio of 7:2:1 for training the model proposed in this paper. The detection effect of our proposed module is proven by the ablation experiment from mAP, the AP value, and the F1 value. This paper also compares other mainstream object detection algorithms. The experimental results show that our model obtained 90.74% mAP, and the F1 value and AP value of the four parts were improved.

9 March 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JCJUNLIN CHEN
JUNLIN CHEN
HFHongbo Fan
Hongbo Fan
DSDangguo Shao
Dangguo Shao
SDShuting Dai
Shuting Dai
For the characterization of the kidney segmentation task, this paper proposes a self-supervised kidney segmentation method based on multi-scale feature fusion and residual full attention, named MRFA-Net. In this study, we introduce the multi-scale feature fusion module to extract multi-scale information of kidneys from abdominal CT slices; additionally, the residual full-attention convolution module is designed to handle the multi-scale information of kidneys by introducing a full-attention mechanism, thus improving the segmentation results of kidneys. The Dice coefficient on the Kits19 dataset reaches 0.972. The experimental results demonstrate that the proposed method achieves good segmentation performance compared to other algorithms, effectively enhancing the accuracy of kidney segmentation.

26 June 2023 in Information
Verified
Journal Article
Open access
PDF file
WWWeidong Wu
Weidong Wu
HFHongbo Fan
Hongbo Fan
YFYu Fan
Yu Fan
JWJian Wen
Jian Wen
The accurate segmentation of colorectal polyps is of great significance for the diagnosis and treatment of colorectal cancer. However, the segmentation of colorectal polyps faces complex problems such as low contrast in the peripheral region of salient images, blurred borders, and diverse shapes. In addition, the number of traditional UNet network parameters is large and the segmentation effect is average. To overcome these problems, an innovative nonlinear activation-free uncertainty contextual attention network is proposed in this paper. Based on the UNet network, an encoder and a decoder are added to predict the saliency map of each module in the bottom-up flow and pass it to the next module. We use Res2Net as the backbone network to extract image features, enhance image features through simple parallel axial channel attention, and obtain high-level features with global semantics and low-level features with edge details. At the same time, a nonlinear n on-activation network is introduced, which can reduce the complexity between blocks, thereby further enhancing image feature extraction. This work conducted experiments on five commonly used polyp segmentation datasets, and the experimental evaluation metrics from the mean intersection over union, mean Dice coefficient, and mean absolute error were all improved, which can show that our method has certain advantages over existing methods in terms of segmentation performance and generalization performance.