Author name cluster

Wenlong Wang

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.

5 papers

2 author rows

JBHI Journal 2026 Journal Article

Automatic Detection and Segmentation of Tooth Cracks Based on Improved Mask R-CNN

Yuanchang Huang
Yadong Tang
Juhao Wu
Jiayan He
Wenlong Wang

Early diagnosis and intervention of cracked teeth are crucial for preventing further dental damage. However, the detection of cracked teeth remains challenging for dental clinicians due to the subtle, complex, and irregular feature of these cracks. To address this issue, we propose an improved Mask R-CNN instance segmentation network for the automatic detection and segmentation of cracked teeth. Firstly, the backbone network was replaced with ResNeXt-50(32 × 4 d) to enhance the extraction of local features specific to cracks. Secondly, we introduced a Crack Feature Enhancement Module (CFEM), utilizing Bayesian optimization to fine-tune its hyperparameters, which leverages the pixel intensity differences between cracked and non-cracked regions to increase the sensitivity of the Feature Pyramid Network (FPN) to the complex features of cracks while suppressing irrelevant background information. Additionally, the mask head was redesigned into an encoder-decoder structure incorporating dynamic snake convolutions, which enables better capture of crack edge details and the integration of both deep and shallow feature information, with deep supervision applied to adjust the loss function weights. Extensive experiments and comprehensive evaluations demonstrate that our method outperforms the current state-of-the-art techniques. Furthermore, experiments on real intraoral images validate the effectiveness of our approach in detecting tooth cracks. Our model enables more accurate and earlier detection of cracked teeth, improving patient outcomes by allowing for timely interventions, reducing the need for invasive treatments, and preserving dental structure.

Details DOI

JBHI Journal 2026 Journal Article

MB-STFormer: A Multi-Band Spectral-Temporal Transformer with Efficient Attention for Enhanced EEG-Based Fatigue Detection

Ke Liu
Lilong Sun
Wenlong Wang
Zhenghui Gu
Zhuliang Yu
Wei Wu

Accurate detection of driver fatigue is critical for preventing traffic accidents. Although electroencephalogram (EEG) signals provide a robust physiological indicator of fatigue, effectively capturing their intricate spatiotemporal-spectral dynamics poses significant challenges. In this paper, we propose MB-STFormer, a novel deep neural network designed for EEG-based fatigue detection, which systematically integrates neurophysiological priors into deep feature learning. The proposed MB-STFormer employs a multi-branch frequency-aware module to extract spatiotemporal features from EEG signals, with each branch dedicated to a distinct frequency sub-band. By leveraging adaptive temporal convolution kernel sizes tailored to each sub-band, the model adeptly captures the inherent rhythmic patterns and temporal dynamics unique to different frequency components. Additionally, we introduce an Efficient Additive Attention mechanism to aggregate global contextual information, thereby addressing the over-smoothing of subtle yet critical features often encountered with conventional transformer self-attention mechanisms. Extensive experiments conducted on three publicly available datasets demonstrate that MB-STFormer achieves state-of-the-art performance while maintaining superior interpretability and generalizability. The proposed framework offers a promising solution for real-world fatigue monitoring systems.

Details DOI

ICLR Conference 2025 Conference Paper

Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient

Wenlong Wang
Ivana Dusparic
Yucheng Shi
Ke Zhang
Vinny Cahill

Model-based reinforcement learning (RL) offers a solution to the data inefficiency that plagues most model-free RL algorithms. However, learning a robust world model often requires complex and deep architectures, which are computationally expensive and challenging to train. Within the world model, sequence models play a critical role in accurate predictions, and various architectures have been explored, each with its own challenges. Currently, recurrent neural network (RNN)-based world models struggle with vanishing gradients and capturing long-term dependencies. Transformers, on the other hand, suffer from the quadratic memory and computational complexity of self-attention mechanisms, scaling as $O(n^2)$, where $n$ is the sequence length. To address these challenges, we propose a state space model (SSM)-based world model, Drama, specifically leveraging Mamba, that achieves $O(n)$ memory and computational complexity while effectively capturing long-term dependencies and enabling efficient training with longer sequences. We also introduce a novel sampling method to mitigate the suboptimality caused by an incorrect world model in the early training stages. Combining these techniques, Drama achieves a normalised score on the Atari100k benchmark that is competitive with other state-of-the-art (SOTA) model-based RL algorithms, using only a 7 million-parameter world model. Drama is accessible and trainable on off-the-shelf hardware, such as a standard laptop. Our code is available at https://github.com/realwenlongwang/Drama.git.

Details

IROS Conference 2024 Conference Paper

Applying Neural Monte Carlo Tree Search to Unsignalized Multi-intersection Scheduling for Autonomous Vehicles

Yucheng Shi
Wenlong Wang
Xiaowen Tao
Ivana Dusparic
Vinny Cahill

Dynamic scheduling of access to shared resources by autonomous systems is a challenging problem, characterized as being NP-hard. The complexity of this task leads to a combinatorial explosion of possibilities in highly dynamic systems where arriving requests must be continuously scheduled subject to strong safety and time constraints. An example of such a system is an unsignalized intersection, where automated vehicles’ access to potential conflict zones must be dynamically scheduled. In this paper, we apply Neural Monte Carlo Tree Search (NMCTS) to the challenging task of scheduling platoons of vehicles crossing unsignalized intersections. Crucially, we introduce a transformation model that maps successive sequences of potentially conflicting road-space reservation requests from platoons of vehicles into a series of board-game-like problems and use NMCTS to search for solutions representing optimal road-space allocation schedules in the context of past allocations. To optimize search, we incorporate a prioritized re-sampling method with parallel NMCTS (PNMCTS) to improve the quality of training data. To optimize training, a curriculum learning strategy is used to train the agent to schedule progressively more complex boards culminating in overlapping boards that represent busy intersections. In a busy single four-way unsignalized intersection simulation, PNMCTS solved 95% of unseen scenarios, reducing crossing time by 43% in light and 52% in heavy traffic versus first-in, first-out control. In a 3x3 multi-intersection network, the proposed method maintained free-flow in light traffic when all intersections are under control of PNMCTS and outperformed state-of-the-art RL-based traffic-light controllers in average travel time by 74. 5% and total throughput by 16% in heavy traffic.

Details

AAMAS Conference 2024 Conference Paper

Decision Market Based Learning for Multi-agent Contextual Bandit Problems

Wenlong Wang
Thomas Pfeiffer

Information is often stored in a distributed and proprietary form, and agents who own this information are often self-interested and require incentives to reveal it. Suitable mechanisms are required to elicit and aggregate such distributed information for decisionmaking. In this study, we use simulations to investigate the use of decision markets as mechanisms in a multi-agent learning system to aggregate distributed information for decision-making in a contextual bandit problem.

PDF