Search

During or after a natural disaster, obtaining accurate disaster information and swiftly rescuing lives are of paramount importance. The objective of building damage assessment (BDA) is to use pre-disaster and post-disaster satellite images to predict the extent of building damage. In recent years, as the field of artificial intelligence advances, employing deep learning methods for BDA has gradually become mainstream. However, many existing methods use only pre-disaster and post-disaster images as inputs without considering their correlation. In this paper, we propose a model called building damage assessment model based on a multi-scale fusion network. In the first stage, we use a U-Net-based segmentation network to extract building location information from pre-disaster images, and the obtained network weights are then used for subsequent assessment. In the second stage, we adopt a dual-branch U-Net as the backbone network, which inputs both pre-disaster and post-disaster images. We design the feature multi-scale fusion module to extract and integrate multi-scale features, and design the cross squeeze-and-excitation module to analyze the correlation between pre-disaster and post-disaster images. Our method is validated on the xBD and LEVIR-CD datasets, and achieving F 1 b = 0.862 for segmentation metrics and F 1 d = 0.759 for classification metrics. [ABSTRACT FROM AUTHOR]

In complex networks, contrastive learning has emerged as a crucial technique for acquiring discriminative representations from graph data. Maximizing the similarity among relevant sample pairs while minimizing that among irrelevant pairs is pivotal in contrastive learning. Therefore, careful consideration must be given to the design of sample pairs in contrastive learning. However, existing node-level self-supervised contrastive learning often treats the enhanced representation of a central node as a positive sample, while considering representations of all other nodes as negative samples. This approach can lead to conflicts in downstream tasks on some graph data, as nodes of the same class are treated as negatives during learning. Precision in sample pair design is essential for enhancing the performance of contrastive learning. To address this issue, this paper introduces a negative sample debiased sampling contrastive learning (NDSCL), specifically tailored for node classification tasks. In particular, this method integrates contrastive learning with semi-supervised learning. A trained classifier assigns pseudo-labels to unlabeled data, and debiased sampling is applied to negative samples. Unlike other methods that focus on negative sample selection, NDSCL also addresses the imbalance in pseudo-label distribution by employing debiasing techniques. Finally, in conjunction with diffusion augmentation, the model is provided with diverse views as inputs to maximize the retention of underlying semantic information. Experimental results demonstrate that the proposed model significantly outperforms baseline models in node-level classification tasks across multiple network datasets. Moreover, the model not only enhances accuracy but also improves computational speed and memory requirements for handling large-scale graph data structures. [ABSTRACT FROM AUTHOR]

In this paper, a novel neural network-based robust iterative learning fault estimation scheme is proposed to address the problem of fault modeling and estimation in nonlinear manipulator systems with disturbance and parameter uncertainties. The aim is to enhance the rapidity, efficiency, and accuracy of fault estimation. Firstly, the modeling for flexible manipulator control system is constructed as a preparation of iterative learning fault estimation observer design. Then, the neural network model is constructed to optimize the gain parameters of iterative learning fault estimator to approximate nonlinear uncertainties. Additionally, a H ∞ robust technique is used to suppress fault variation rate and disturbance, which enhances the speed of estimation and reduces the impact of disturbance. So that the estimated fault can rapidly and accurately track the actual fault over the whole time interval and iterations. Finally, numerical simulations are conducted to demonstrate the effectiveness of the proposed neural network-based robust iterative learning scheme. [ABSTRACT FROM AUTHOR]

Traditional rolling bearing fault diagnosis approaches require a large amount of fault data in advance, while some specific fault data is difficult to obtain in engineering scenarios. This imbalanced fault data problem seriously affects the accuracy of fault diagnosis. To improve the accuracy under imbalanced data conditions, we propose a novel data augmentation method of Enhanced Generative Adversarial Networks with Data Selection Module (EGAN-DSM). Firstly, a network enhancement module is designed, which quantifies antagonism between the generator and discriminator through loss value. And the module determines whether to iteratively enhance the networks with weak adversarial ability. Secondly, a Data Selected Module (DSM) is constructed using Hilbert space distance for screening generated data, and the screened data is mixed with original imbalanced data to reconstruct balanced data sets. Then, Deep Convolutional Neural Networks with Wide First-layer Kernels (WDCNN) is used for fault diagnosis. Finally, the method is verified by data measured on a rotating machine experimental platform. The results show that our method has high fault diagnosis accuracy under the condition of imbalanced data. [ABSTRACT FROM AUTHOR]

In this paper, a new method of actuator fault detection and isolation in output feedback is proposed in the multiple-input multiple-output feedback system. Under the feedback control, fault source can be covered and make the fault isolation difficult. To address such an issue, the fault space is firstly segmented and the fault feature is extracted according to the space geometry theory. By this approach, the residual generator can be constructed. Secondly, in allusion to the coupling between residuals and disturbances in the feedback system, a sufficient and necessary condition for decoupling is given. Then a threshold is set to detect the fault exists or not, and the structured residual set is built to realize the relationship between residuals and faults. Consequently, the fault isolation can be achieved. Simulation results validate the feasibility and validity of the proposed algorithm. [ABSTRACT FROM AUTHOR]

The changes in hydrothermal dynamics under different underlying conditions are the important aspect of hydrological and ecological processes, and engineering stability in permafrost regions. This study monitored the temperature and moisture of soil at a depth range from 0 to 80 cm beneath the barren, alpine steppe, and alpine meadow at the Beiluhe Basin on the Qinghai-Tibet Plateau. The freezing and thawing process and hydrothermal dynamic changes were analyzed within the test range. In a year, the freezing and thawing process controlled the pattern of hydrothermal changes. The properties of ground surface affected the hydrothermal change process in various stages. In the freeze stages, moisture and the absolute value of ground temperature showed an exponential relationship. In the thawing stages, moisture may increase, decrease, or remain stable in different temperature ranges. This process is affected by precipitation, solar radiation, and so on. At a 0-30 cm depth range, moisture increased linearly with precipitation. At 0-20 cm depth range, precipitation had a significant effect on the ground temperature changes. With the same rainfall condition, the decline of ground temperature corresponds with solar radiation flux. Results confirmed that ground properties were important factors that control the soil moisture and temperature change in the permafrost region. [ABSTRACT FROM AUTHOR]

Sensor fault cannot be converted to system equation under the condition of under- measurement system. Aiming to solve this problem, we present a new method which treats sensor fault as state variable to enforce fault diagnosis. Firstly, the system model of sensor fault is constructed by putting sensor fault into the state equation. Then, the residual generator is designed using the space projection operation to solve the relevant parameter matrices. Since the proposed algorithm satisfies one-to-one correspondence of faults and residuals, it can achieve single and multiple sensors FDI. Simulation results show the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

The design mind of SOPC (System on Programmable Chip), hardware & software co-design, will bring the system optimization with larger degree of freedom. It will establish the foundation on realizing the miniaturization and more efficient local preprocessing in smart cooperative sensor networks. In this contribution, a solution is proposed for smart multimedia sensor nodes based on the SOPC framework, aiming at improving the on-board processing capability and the degree of freedom in development. This paper mainly presents the structure and design method of the smart cooperative multimedia sensor node based on SOPC. The on-board feature extraction is realized and some correlative experimental data and results are presented as well. The experimental results evaluate the feasibility and efficiency of the proposed node design method. [ABSTRACT FROM AUTHOR]