Shenghan Zhou

Aircraft routing networks are complex systems vulnerable to cascading delays triggered by weather disruptions and airspace constraints. This paper proposes a Distributionally Robust Aircraft Routing (DRAR) model for systemic risk assessment. Conventional robust or stochastic optimization methods often rely on specific assumptions about delay distributions (e.g., fixed probability distributions or scenario sets). However, due to the suddenness and multi-source nature of flight delays, their true distribution is difficult to accurately characterize, limiting the effectiveness of these methods in real-world uncertain conditions. By constructing a Wasserstein-metric ambiguity set, the proposed model captures distributional uncertainty without assuming fixed probabilities, thereby handling delay risks more robustly. The study incorporated chance constraints to bound extreme delay probabilities and reformulated the model as a tractable mixed-integer program. Experiments on real airline data demonstrate that DRAR outperforms traditional benchmarks, reducing propagation delays by 4–6%, volatility by 7–9%, and extreme delay risks by up to 15.7%. Thus, the model provides a practical tool for aviation decision-makers: airlines can leverage it to optimize aircraft scheduling and routing, systematically mitigate delay propagation risk, control the probability of extreme delays, and consequently reduce indirect operational costs arising from crew overtime and airport scheduling conflicts, thereby enhancing overall resource efficiency and operational resilience. These results validate DRAR as an effective tool for controlling tail risks and ensuring sustainable operations in uncertain aviation environments.

The study proposes a two-stage multi-modal fusion framework for key point detection of impacted wisdom teeth with panoramic radiographs(OPGs). It is crucial for the clinical diagnosis and surgical planning of impacted wisdom teeth to get accurate localization of anatomical key points in panoramic radiographs. However, this task continues to present a significant challenge to clinical automated systems. The existing end-to-end deep learning models often result in unreliable precision due to the large variations in tooth morphology and orientation, particularly in severely impacted cases. The proposed solution framework consists of two stages. In the initial stage, a segmentation network offers a robust region proposal, effectively eliminating background interference. Subsequently, the study introduces an innovative multi-modal input fusion strategy, where a lightweight pose estimation network is trained on a synthesized 3-channel input consisting of a grayscale image (texture), a binary segmentation mask (shape prior), and a zero-padding channel. This approach explicitly guides the model using precise shape information, encouraging it to learn rotation-invariant geometric features. The proposed method was validated on a clinical data-set with 200 patches of panoramic dental radiographs. The empirical research results demonstrate that the framework achieves state-of-the-art performance, reaching a mean Average Precision ([email protected]:.95) of 0.918 for key point estimation. This significantly outperforms standard end-to-end baselines, demonstrating the effectiveness and practicality of the proposed multi-modal, segmentation-guided approach for high-precision medical image analysis.

The high bandwidth, low latency, and extensive coverage of Sixth Generation (6G) communication technology provide robust data support and communication guarantees for intelligent road network management. This study aims to explore the application of 6G communication technology and deep reinforcement learning (DRL) algorithms in smart road network management, with the goal of enhancing the intelligence of traffic management systems. DRL algorithms are capable of handling complex traffic environments and, through self-learning and optimization, can achieve intelligent decision-making and route planning. This study proposes a DRL-based traffic signal control method leveraging 6G communication technology. The core of this method lies in its capability to manage complex and dynamically changing traffic flows, adjusting traffic signal plans based on real-time data to adapt to various traffic conditions. By learning traffic distribution patterns, the model generates appropriate traffic signals for each intersection, thereby optimizing the traffic signal plans. Simulation experiments found that, compared to the Convolutional Neural Network (CNN) algorithm, DRL not only reduced the average travel time by 28.2% but also increased the average travel speed by 26.3%, and significantly reduced the average queue length by 42.9%. These results demonstrate that the proposed DRL algorithm shows significant advantages in alleviating traffic congestion and optimizing traffic signal control. This study offers a novel solution for intelligent road network management and validates the potential of 6G communication technology and DRL algorithms in this field.

The paper proposes an anomaly detection method for UAVs based on wavelet decomposition and stacked denoising autoencoder. This method takes the negative impact of noisy data and the feature extraction capabilities of deep learning models into account. It aims to improve the accuracy of the proposed anomaly detection method with wavelet decomposition and stacked denoising autoencoder methods. Anomaly detection based on UAV flight data is an important method of UAV condition monitoring and potential abnormal state mining, which is an important means to reduce the risk of UAV flight accidents. However, the diversity of UAV mission scenarios leads to a complex and harsh environment, so the acquired data are affected by noise, which brings challenges to accurate anomaly detection based on UAV data. Firstly, we use wavelet decomposition to denoise the original data; then, we used the stacked denoising autoencoder to achieve feature extraction. Finally, the softmax classifier is used to realize the anomaly detection of UAV. The experimental results demonstrate that the proposed method still has good performance in the case of noisy data. Specifically, the Accuracy reaches 97.53%, the Precision is 97.50%, the Recall is 91.81%, and the F1-score is 94.57%. Furthermore, the proposed method outperforms the four comparison models with more outstanding performance. Therefore, it has significant potential in reducing UAV flight accidents and enhancing operational safety.

In order to address the issue of multi-information fusion, this paper proposed a method for bearing fault diagnosis based on multisource and multimodal information fusion. Existing bearing fault diagnosis methods mainly rely on single sensor information. Nevertheless, mechanical faults in bearings are intricate and subject to countless excitation disturbances, which poses a great challenge for accurate identification if only relying on feature extraction from single sensor input. In this paper, a multisource information fusion model based on auto-encoder was first established to achieve the fusion of multi-sensor signals. Based on the fused signals, multimodal feature extraction was realized by integrating image features and time-frequency statistical information. The one-dimensional vibration signals were converted into two-dimensional time-frequency images by continuous wavelet transform (CWT), and then they were fed into the Resnet network for fault diagnosis. At the same time, the time-frequency statistical features of the fused 1D signal were extracted from the integrated perspective of time and frequency domains and inputted into the improved 1D convolutional neural network model based on the residual block and attention mechanism (1DCNN-REA) model to realize fault diagnosis. Finally, the tree-structured parzen estimator (TPE) algorithm was utilized to realize the integration of two models in order to improve the diagnostic effect of a single model and obtain the final bearing fault diagnosis results. The proposed model was validated using real experimental data, and the results of the comparison and ablation experiments showed that compared with other models, the proposed model can precisely diagnosis the fault type with an accuracy rate of 98.93%.

Air quality issues are critical to daily life and public health. However, air quality data are characterized by complexity and nonlinearity due to multiple factors. Coupled with the exponentially growing data volume, this provides both opportunities and challenges for utilizing deep learning techniques to reveal complex relationships in massive knowledge from multiple sources for correct air quality prediction. This paper proposes a prediction hybrid framework for air quality integrated with W-BiLSTM(PSO)-GRU and XGBoost methods. Exploiting the potential of wavelet decomposition and PSO parameter optimization, the prediction accuracy, stability and robustness was improved. The results indicate that the R² values of PM2.5, PM10, SO₂, CO, NO₂, and O₃ predictions exceeded 0.94, and the MAE and RMSE values were lower than 0.02 and 0.03, respectively. By integrating the state-of-the-art XGBoost algorithm, meteorological data from neighboring monitoring stations were taken into account to predict air quality trends, resulting in a wider range of forecasts. This strategic merger not only enhanced the prediction accuracy, but also effectively solved the problem of sudden interruption of monitoring. Rigorous analysis and careful experiments showed that the proposed method is effective and has high application value in air quality prediction, building a solid framework for informed decision-making and sustainable development policy formulation.

This paper aims to build a Self-supervised Fault Detection Model for UAVs combined with an Auto-Encoder. With the development of data science, it is imperative to detect UAV faults and improve their safety. Many factors affect the fault of a UAV, such as the voltage of the generator, angle of attack, and position of the rudder surface. A UAV is a typical complex system, and its flight data are typical high-dimensional large sample data sets. In practical applications such as UAV fault detection, the fault data only appear in a small part of the data sets. In this study, representation learning is used to extract the normal features of the flight data and reduce the dimensions of the data. The normal data are used for the training of the Auto-Encoder, and the reconstruction loss is used as the criterion for fault detection. An Improved Auto-Encoder suitable for UAV Flight Data Sets is proposed in this paper. In the Auto-Encoder, we use wavelet analysis to extract the low-frequency signals with different frequencies from the flight data. The Auto-Encoder is used for the feature extraction and reconstruction of the low-frequency signals with different frequencies. To improve the effectiveness of the fault localization at inference, we develop a new fault factor location model, which is based on the reconstruction loss of the Auto-Encoder and edge detection operator. The UAV Flight Data Sets are used for hard-landing detection, and an average accuracy of 91.01% is obtained. Compared with other models, the results suggest that the developed Self-supervised Fault Detection Model for UAVs has better accuracy. Concluding this study, an explanation is provided concerning the proposed model’s good results.

Due to the prevalence of the order production mode, multi-variety, small-batch manufacturing enterprises frequently delay deliveries to downstream customers. To date, most existing studies on delayed delivery risk have focused on the response to the risk after it occurs, ignoring how the risk arises. For multi-variety, low-volume production companies, any part of the production process could lead to the ultimate risk of delayed delivery, and the risk is transmissible. Therefore, the path of risk transmission needs to be identified to effectively control the risk of late delivery at key production stages. In this paper, from the perspective of risk transmission, a recognition method based on association rules and the Bayesian network was proposed to identify the risk conduction path. This method firstly determined the strong association rules among the risk factors based on historical data stored in the ERP system and determined the Bayesian network topology structures of the risk transmission path by combining the business process and expert experience. Secondly, the prior and conditional probabilities of each node were determined using data statistics, and the risk transmission path of delayed delivery was identified using the forward and backward reasoning of the Bayesian network. Finally, this paper provided a case study to verify the method, and the following conclusions were obtained: (1) the delay in delivery to downstream customers is mainly due to the delayed delivery of upstream suppliers and the sudden change in customer demand, and (2) the adjustment of enterprise production plans is the key node of the delayed delivery risk transmission path. Through the research in this paper, production companies can identify the target of risk management more scientifically and mitigate the risk through the adjustment of key links.