Combat effectiveness of unmanned aerial vehicle(UAV)formations can be severely affected by the mission execution *** the practical execution phase,there are inevitable risks where UAVs being destroyed or targets faile...
详细信息
Combat effectiveness of unmanned aerial vehicle(UAV)formations can be severely affected by the mission execution *** the practical execution phase,there are inevitable risks where UAVs being destroyed or targets failed to be *** improve the mission reliability,a resilient mission planning framework integrates task pre-and re-assignment modules is developed in this *** the task pre-assignment phase,to guarantee the mission reliability,probability constraints regarding the minimum mission success rate are imposed to establish a multi-objective optimization *** an improved genetic algorithm with the multi-population mechanism and specifically designed evolutionary operators is used for efficient *** in the task-reassignment phase,possible trigger events are first analyzed.A real-time contract net protocol-based algorithm is then proposed to address the corresponding emergency *** the dual objective used in the former phase is adapted into a single objective to keep a consistent combat *** cases of different scales demonstrate that the two modules cooperate well with each *** the one hand,the pre-assignment module can generate high-reliability mission schedules as an elaborate mathematical model is *** the other hand,the re-assignment module can efficiently respond to various emergencies and adjust the original schedule within a *** corresponding animation is accessible at ***/video/BV12t421w7EE for better illustration.
Recently, cross-domain named entity recognition (cross-domain NER), which can reduce the high data annotation costs faced by fully-supervised methods, has drawn attention. Most competitive approaches mainly rely on pr...
详细信息
Web services have been integrated with all walks of life in society. Abnormalities in the network and services seriously affect user experience and company revenue. The system log records various information of the sy...
详细信息
Multi-exposure image fusion is a cost-effective method to improve the dynamic range of images. For the problems of inadequate detail extraction in bright and dark areas and the over simplicity of existing fusion rules...
详细信息
ISBN:
(数字)9789887581581
ISBN:
(纸本)9798350366907
Multi-exposure image fusion is a cost-effective method to improve the dynamic range of images. For the problems of inadequate detail extraction in bright and dark areas and the over simplicity of existing fusion rules by current deep learning multi-exposure image fusion algorithms, we propose a DenseNet-based framework using adaptive Gabor convolution. Building on the Dense network architecture, we design an adaptive Gabor convolution module, which the parameters of the Gabor filter can be updated along with the network, enhancing the ability of Gabor to extract image features. Additionally, a cross-domain aggregation attention module is proposed, which effectively aggregates and enhances information. Comparing our method with seven advanced methods on the multi-exposure image fusion benchmark dataset, the subjective and objective evaluations outperform the other methods, proving the effectiveness and superiority of our method. The experiments of different exposure images fusion demonstrate the good generalization performance of our method.
The core of recommendation models is estimating the probability that a user will like an item based on historical interactions. Existing collaborative filtering(CF) algorithms compute the likelihood by utilizing simpl...
详细信息
The core of recommendation models is estimating the probability that a user will like an item based on historical interactions. Existing collaborative filtering(CF) algorithms compute the likelihood by utilizing simple relationships between objects, e.g., user-item, item-item, or user-user. They always rely on a single type of object-object relationship, ignoring other useful relationship information in data. In this paper, we model an interaction between user and item as an edge and propose a novel CF framework, called learnable edge collaborative filtering(LECF). LECF predicts the existence probability of an edge based on the connections among edges and is able to capture the complex relationship in data. Specifically, we first adopt the concept of line graph where each node represents an interaction edge; then calculate a weighted sum of similarity between the query edge and the observed edges(i.e., historical interactions) that are selected from the neighborhood of query edge in the line graph for a recommendation. In addition, we design an efficient propagation algorithm to speed up the training and inference of LECF. Extensive experiments on four public datasets demonstrate LECF can achieve better performance than the state-of-the-art methods.
Increasingly complex systems contain large numbers of devices that generate great number of multivariate time series that are monitored and recorded. For anomaly detection of these complex time series, deep learning t...
详细信息
In the past few years, latency-sensitive task computing over the industrial internet of things (IIoT) has played a key role in an increasing number of intelligent applications, such as intelligent self-driving vehicle...
详细信息
In order to promote the evaluation performance of deep learning infrared automatic target recognition (ATR) algorithms in the complex environment of air-to-air missile research, we proposed an analytic hierarchy proce...
详细信息
Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many ...
Fine-grained visual categorization is challenged by limited training data by localizing discriminative regions and learning diverse features. We propose an effective regularization method that simultaneously imposes s...
详细信息
暂无评论