Heterogeneity is a fundamental and challenging issue in federated learning, especially for the graph data due to the complex relationships among the graph nodes. To deal with the heterogeneity, lots of existing method...
详细信息
Estimating the Ratio of Edge-Users (REU) is an important issue in mobile networks, as it helps the subsequent adjustment of loads in different cells. However, existing approaches usually determine the REU manually, wh...
详细信息
Estimating the Ratio of Edge-Users (REU) is an important issue in mobile networks, as it helps the subsequent adjustment of loads in different cells. However, existing approaches usually determine the REU manually, which are experience-dependent and labor-intensive, and thus the estimated REU might be imprecise. Considering the inherited graph structure of mobile networks, in this paper, we utilize a graph-based deep learning method for automatic REU estimation, where the practical cells are deemed as nodes and the load switchings among them constitute edges. Concretely, Graph Attention Network (GAT) is employed as the backbone of our method due to its impressive generalizability in dealing with networked data. Nevertheless, conventional GAT cannot make full use of the information in mobile networks, since it only incorporates node features to infer the pairwise importance and conduct graph convolutions, while the edge features that are actually critical in our problem are disregarded. To accommodate this issue, we propose an Edge-Aware Graph Attention Network (EAGAT), which is able to fuse the node features and edge features for REU estimation. Extensive experimental results on two real-world mobile network datasets demonstrate the superiority of our EAGAT approach to several state-of-the-art methods.
In this paper, we consider the `q−regularized kernel regression with 0 q−penalty term over a linear span of features generated by a kernel function. We study the asymptotic behavior of the algorithm under the framewor...
详细信息
Interactive medical image segmentation methods have become increasingly popular in recent years. These methods combine manual labeling and automatic segmentation, reducing the workload of annotation while maintaining ...
Interactive medical image segmentation methods have become increasingly popular in recent years. These methods combine manual labeling and automatic segmentation, reducing the workload of annotation while maintaining high accuracy. However, most current interactive segmentation frameworks are limited to 2D image data, and are not suitable for 3D image data due to the large size and high complexity of 3D data, as well as the challenges posed by information asymmetry and sparse annotation. In this paper, we propose SliceProp, an interactive segmentation framework that implements slice-wise Label Bidirectional Propagation (LBP) for 3D medical image segmentation. SliceProp extends the interactive 2D image segmentation algorithm to 3D image segmentation, and can handle 3D data with large size and high complexity. Moreover, equipped with a Backtracking Feedback Check (BFC) module, SliceProp effectively addresses the issues of information asymmetry and spatial sparse annotation in 3D medical image segmentation. Additionally, we adopt an uncertainty-based criterion to pri-oritize the slices to be refined interactively, which enhances the efficiency of the interaction process by enabling the model to focus on the regions with the most unreliable predictions. SliceProp is evaluated on two datasets and achieves promising results compared to state-of-the-art methods.
A C64x-based multi-DSP real-time imageprocessing system is introduced, which uses high performance TMS320C6414 DSP to process image and FPGA device to realize LINK port to transport image data with LVDS signal. Requi...
详细信息
A C64x-based multi-DSP real-time imageprocessing system is introduced, which uses high performance TMS320C6414 DSP to process image and FPGA device to realize LINK port to transport image data with LVDS signal. Requirements of imageprocessing performance and image data communication of image fusion are met. Based on the hardware system, a real time microkernel based distributed operating system is designed and implemented. At the end, its real-time performance is analyzed from three aspects. It's shown that the real time imageprocessing system can reach the requirements of real time imageprocessing.
Contextual information plays an important role in action recognition. Local operations have difficulty to model the relation between two elements with a long-distance interval. However, directly modeling the contextua...
详细信息
Since the DC-coupled interface between the driver and the laser diode makes it impossible for the conventional drivers to work with low power supply, an output stage has been proposed. A novel APC can suppress the out...
详细信息
Since the DC-coupled interface between the driver and the laser diode makes it impossible for the conventional drivers to work with low power supply, an output stage has been proposed. A novel APC can suppress the output average optical power and extinction ratio within ±0.3 dBm and ±0.4 dB(-40°C to 100°C), respectively. The initialization time is not more than 0.6 μs because the fast binary search algorithm is incorporated into the APC. The burst-on delay and burst-off delay are less than 5 ns and meet the requirement of PON system. The chip is fabricated in TSMC 0.8 μm BiCMOS process and occupies an area of 1.56 mm × 1.67 mm with a power consumption of 105 mW.
Background: Segment prostates from transrectal ultrasound (TRUS) images plays an essential role in the diagnosis and treatment of prostate cancer. However, traditional segmentation methods are time-consuming and labor...
详细信息
Background: Segment prostates from transrectal ultrasound (TRUS) images plays an essential role in the diagnosis and treatment of prostate cancer. However, traditional segmentation methods are time-consuming and laborious. To address this issue, there is an urgent need to develop computer algorithms that can automatically segment prostates from TRUS images, which makes it become the direction and form of future development. Purpose: Automatic prostate segmentation in TRUS images has always been a challenging problem, since prostates in TRUS images have ambiguous boundaries and inhomogeneous intensity distribution. Although many prostate segmentation methods have been proposed, they still need to be improved due to the lack of sensibility to edge information. Consequently, the objective of this study is to devise a highly effective prostate segmentation method that overcomes these limitations and achieves accurate segmentation of prostates in TRUS images. Methods: A 3D edge-aware attention generative adversarial network (3D EAGAN)-based prostate segmentation method is proposed in this paper, which consists of an edge-aware segmentation network (EASNet) that performs the prostate segmentation and a discriminator network that distinguishes predicted prostates from real prostates. The proposed EASNet is composed of an encoder-decoder-based U-Net backbone network, a detail compensation module, four 3D spatial and channel attention modules, an edge enhance module, and a global feature extractor. The detail compensation module is proposed to compensate for the loss of detailed information caused by the down-sampling process of the encoder. The features of the detail compensation module are selectively enhanced by the 3D spatial and channel attention module. Furthermore, an edge enhance module is proposed to guide shallow layers in the EASNet to focus on contour and edge information in prostates. Finally, features from shallow layers and hierarchical features from the decod
Moving cast shadow causes serious problem while segmenting and extracting foreground from image sequences, due to the misclassification of moving shadow as foreground. This paper proposes a Boosting discriminative mod...
详细信息
Moving cast shadow causes serious problem while segmenting and extracting foreground from image sequences, due to the misclassification of moving shadow as foreground. This paper proposes a Boosting discriminative model to eliminate cast shadow on Discriminative Random Fields (DRFs). The method combines different features for Boosting to discriminate cast shadow from moving objects, then temporal and spatial coherence of shadow and foreground are incorporated on Discriminative Random Fields and the problem can be solved by graph cut. Firstly, moving objects are obtained by background subtraction;secondly, shadow candidates can be derived through pre-processing moving objects, in terms of the shadow physical property;thirdly, color information and texture information is derived by comparing shadow and foreground points in current image with corresponding points in background image, which are selected as features for Boosting;finally, temporal and spatial coherence of shadow and foreground is employed on Discriminative Random Fields and discriminate shadow and foreground by graph cut accurately.
Sparse canonical correlation analysis (CCA) is a useful statistical tool to detect latent information with sparse structures. However, sparse CCA works only for two datasets, i.e., there are only two views or two dist...
详细信息
暂无评论