Search

Earthquake-triggered landslides (ETLs) are characterized by their extensive occurrences, having wide distributions. The conventional human–computer interaction extraction method is often time-consuming and labor-intensive, failing to meet the demands of disaster emergency response. There is a pressing need for a swift detection of ETLs. In this study, we introduce an ETLs extraction method (MAST) combining morphological analysis edge recognition with a Swin-Transformer (SWT) deep learning model, which is specifically designed for landslide extraction. The MAST model adopts a hierarchical construction approach akin to convolution neural networks, aiding in tasks such as target detection and semantic segmentation. To enhance the accuracy of landslide edge extraction, we incorporate an edge recognition algorithm based on the morphological analysis into the MAST model. This algorithm leverages morphological operations to extract the features of landslide boundaries. It effectively addresses issues such as discretization and irregularization of the extracted landslide boundaries, leading to more precise delineation of landslide boundaries. Drawing on UAV data collected from Wan Dong Village, De Tou Town, Sichuan Luding, China, during the 2022 Ms 6.8 Luding Earthquake, we conducted automated extraction of ETLs utilizing the MAST model. Experimental results demonstrate the superior performance of the MAST model compared to the traditional full convolution neural network (FCN) model and normal SWT model. The MAST model exhibits enhanced value in landslide extraction. Notably, it demonstrates a significant advantage in boundary extraction. Employing the Boundary IoU metric to evaluate the accuracy of ETLs extraction, the MAST model outperforms the SWT and FCN models at various distances. [ABSTRACT FROM AUTHOR]

High-level autonomous decision making system is one of the key technologies in intelligent transportation networks, it requires the traffic information within a certain range of vehicles in real time. When the traffic roads become congested or the roadside units (RSUs) are unaccessed beyond the communication range, the unmanned aerial vehicle (UAV)-assisted vehicular edge computing network (VECN) is considered as a potential solution. In this paper, we propose a learning based channel allocation and task offloading strategy in temporary UAV-assisted VECNs from a user perspective, in which the UAV passing temporarily can serve as the relay and edge computing node to support the decision making system. However, the limited available computation resources and time-varying communication channel states make it critical to process the received computing tasks. To address the above mentioned challenges, we design an efficient data transmission strategy combined the long-term evolution vehicle-to-everything (LTE-V2X) and time-division multiple access (TDMA) technologies firstly, then, we propose a multi-option task processing scheme, a service cost minimization problem is proposed where the integral decisions of channel allocation and task processing mode selection are jointly optimized. Under dynamic computing resources and the current data transmission conditions, the UAV selects an optimal task processing service model based on deep reinforcement learning (DRL) algorithm. Simulation results show the proposed strategy greatly improves the data transmission efficiency. [ABSTRACT FROM AUTHOR]

Electroencephalography-based Brain Computer Interfaces (BCIs) invariably have a degenerate performance due to the considerable individual variability. To address this problem, we develop a novel domain adaptation method with optimal transport and frequency mixup for cross-subject transfer learning in motor imagery BCIs. Specifically, the preprocessed EEG signals from source and target domain are mapped into latent space with an embedding module, where the representation distributions and label distributions across domains have a large discrepancy. We assume that there exists a non-linear coupling matrix between both domains, which can be utilized to estimate the distance of joint distributions for different domains. Depending on the optimal transport, the Wasserstein distance between source and target domains is minimized, yielding the alignment of joint distributions. Moreover, a new mixup strategy is also introduced to generalize the model, where the inputs trials are mixed in frequency domain rather than in raw space. The extensive experiments on three evaluation benchmarks are conducted to validate the proposed framework. All the results demonstrate that our method achieves a superior performance than previous state-of-the-art domain adaptation approaches. [ABSTRACT FROM AUTHOR]

For a stand-alone microgrid, the reliability criterion is often taken into account to guarantee the supply adequacy. This paper proposes a mixed integer linear programming (MILP) based model to determine the optimal sizing of a photovoltaic/diesel/battery stand-alone microgrid considering the reliability. Firstly, an economic-oriented microgrid planning model is developed. Subsequently, a rolling horizon based Sequential Monte Carlo method is developed to evaluate the system reliability. In particular, a multidimensional piecewise linearization method is proposed to approximate the nonlinear and implicit reliability evaluation function. Therefore the reliability criterion can be safely integrated into the microgrid planning model as an MILP problem which can be solved easily. The advantage of this method is that the costly reliability evaluation is calculated offline. Consequently, the time consumption of the online implement of the model becomes much less. The conventional techniques, however, integrate the reliability evaluation into the procedure. Thus a lot of iterations are needed to search for a solution that satisfies the reliability criterion. Finally, numerical experiments based on one microgrid test system are performed. The results indicate that larger sized DERs are deployed if a higher reliability criterion is required. Additionally, the proposed method is much faster than conventional evolutionary algorithms. [ABSTRACT FROM AUTHOR]

Hydrogen fueling stations (HFSs) will proliferate in the near future as they are prerequisites for the fast developing hydrogen-powered vehicles (HVs). The HFSs can utilize cheap renewable energy from, e.g., wind turbines (WTs), to generate and store hydrogen on site locally. Conventional studies usually ignore the independence of the WT and HFSs and perform joint operation optimization to them. This article, however, proposes a cooperative operation model for the WT and HFSs considering individual benefit. Nash bargaining theory is employed to deal with the energy trading and benefit sharing problems during the cooperation. In particular, the conditional value-at-risk (CVaR) is used to characterize the risk-preference degree of HFSs against the uncertainties of electricity price. Moreover, an improved benders decomposition (BD) algorithm is proposed to solve the energy trading problem in a distributed manner for privacy concern; while an analytical method is developed to solve the payment bargaining problem. Numerical experiments based on two case studies indicate that the cooperation can greatly reduce the hydrogen production cost for HFSs. In addition, the proposed algorithm outperforms conventional alternating direction method of multipliers (ADMM) algorithm in the case studies. [ABSTRACT FROM AUTHOR]

Complex computational models are often designed to simulate real-world physical phenomena in many scientific disciplines. However, these simulation models tend to be computationally very expensive and involve a large number of simulation input parameters, which need to be analyzed and properly calibrated before the models can be applied for real scientific studies. We propose a visual analysis system to facilitate interactive exploratory analysis of high-dimensional input parameter space for a complex yeast cell polarization simulation. The proposed system can assist the computational biologists, who designed the simulation model, to visually calibrate the input parameters by modifying the parameter values and immediately visualizing the predicted simulation outcome without having the need to run the original expensive simulation for every instance. Our proposed visual analysis system is driven by a trained neural network-based surrogate model as the backend analysis framework. In this work, we demonstrate the advantage of using neural networks as surrogate models for visual analysis by incorporating some of the recent advances in the field of uncertainty quantification, interpretability and explainability of neural network-based models. We utilize the trained network to perform interactive parameter sensitivity analysis of the original simulation as well as recommend optimal parameter configurations using the activation maximization framework of neural networks. We also facilitate detail analysis of the trained network to extract useful insights about the simulation model, learned by the network, during the training process. We performed two case studies, and discovered multiple new parameter configurations, which can trigger high cell polarization results in the original simulation model. We evaluated our results by comparing with the original simulation model outcomes as well as the findings from previous parameter analysis performed by our experts. [ABSTRACT FROM AUTHOR]