Deep learning models have shown their potential in recent years for several applications. However, most of the models are opaque in nature and difficult to trust due to their complex reasoning - commonly known as the ...
详细信息
Image registration is the process of bringing different images into a common coordinate system - a technique widely used in various applications of computer vision, such as remote sensing, image retrieval, and most co...
详细信息
Point cloud-based large scale place recognition is an important but challenging task for many applications such as Simultaneous Localization and Mapping (SLAM). Taking the task as a point cloud retrieval problem, prev...
详细信息
Stable consumer electronic systems can assist traffic better. Good traffic consumer electronic systems require collaborative work between traffic algorithms and hardware. However, performance of popular traffic algori...
详细信息
The matrix-based Rényi’s entropy allows us to directly quantify information measures from given data, without explicit estimation of the underlying probability distribution. This intriguing property makes it wid...
详细信息
The two-dimensional spreading under gravity of a thin fluid film with suction (fluid leak-off) or blowing (fluid injection) at the base is considered. The thin fluid film approximation is imposed. The height of the th...
详细信息
The two-dimensional spreading under gravity of a thin fluid film with suction (fluid leak-off) or blowing (fluid injection) at the base is considered. The thin fluid film approximation is imposed. The height of the thin film satisfies a nonlinear diffusion equation with a source/sink term. The Lie point symmetries of the nonlinear diffusion equation are derived and exist, which provided the fluid velocity at the base, vn satisfies a first order linear partial differential equation. The general form has algebraic time dependence while a special case has exponential time dependence. The solution in which vn is proportional to the height of the thin film is studied. The width of the base always increases with time even for suction while the height decreases with time for sufficiently weak blowing. The streamlines of the fluid flow inside the thin film are plotted by first solving a cubic equation. For sufficiently weak blowing there is a dividing streamline, emanating from the stagnation point on the centre line which separates the fluid flow into two regions, a lower region consisting of rising fluid and dominated by fluid injection at the base and an upper region consisting of descending fluid and dominated by spreading due to gravity. For sufficiently strong blowing the lower region expands to completely fill the whole thin film.
Motion artefacts in magnetic resonance brain images can have a strong impact on diagnostic confidence. The assessment of MR image quality is fundamental before proceeding with the clinical diagnosis. Motion artefacts ...
详细信息
Deep learning on graphs has attracted tremendous attention from the graph learning community in recent years. It has been widely adopted in various real-world applications from diverse domains, such as social and info...
详细信息
The emergence of novel the dummy data injection attack (DDIA) poses a severe threat to the secure and stable operation of power systems. These attacks are particularly perilous due to the minimal Euclidean spatial sep...
详细信息
The emergence of novel the dummy data injection attack (DDIA) poses a severe threat to the secure and stable operation of power systems. These attacks are particularly perilous due to the minimal Euclidean spatial separation between the injected malicious data and legitimate data, rendering their precise detection challenging using conventional distance-based methods. Furthermore, existing research predominantly focuses on various machine learning techniques, often analyzing the temporal data sequences post-attack or relying solely on Euclidean spatial characteristics. Unfortunately, this approach tends to overlook the inherent topological correlations within the non-Euclidean spatial attributes of power grid data, consequently leading to diminished accuracy in attack localization. To address this issue, this study takes a comprehensive approach. Initially, it examines the underlying principles of these new DDIAs on power systems. Here, an intricate mathematical model of the DDIA is designed, accounting for incomplete topological knowledge and alternating current (AC) state estimation from an attacker's perspective. This model aims to mitigate the vulnerabilities associated with direct current (DC) flow-based attack data generation methods that can be readily detected. Subsequently, by integrating a priori knowledge of grid topology and considering the temporal correlations within measurement data and the topology-dependent attributes of the power grid, this study introduces temporal and spatial attention matrices. These matrices adaptively capture the spatio-temporal correlations within the attacks. Leveraging gated stacked causal convolution and graph wavelet sparse convolution, the study jointly extracts spatio-temporal DDIA features. This methodology significantly enhances the dynamic correlation mining capability while improving computational efficiency in the neighborhood. Finally, the research proposes a DDIA localization method based on spatio-temporal graph
Computational Pathology (CPATH) offers the possibility for highly accurate and low-cost automated pathological diagnosis. However, the high time cost of model inference is one of the main issues limiting the applicati...
详细信息
ISBN:
(数字)9781665468190
ISBN:
(纸本)9781665468206
Computational Pathology (CPATH) offers the possibility for highly accurate and low-cost automated pathological diagnosis. However, the high time cost of model inference is one of the main issues limiting the application of CPATH methods. Due to the large size of Whole-Slide Image (WSI), commonly used CPATH methods divided a WSI into a large number of image patches at relatively high magnification, then predicted each image patch individually, which is time-consuming. In this paper, we propose a novel Uncertainty-based Model Acceleration (UMA) method for reducing the time cost of model inference, thereby relieving the deployment burden of CPATH applications. Enlightened by the slide-viewing process of pathologists, only a few high-uncertain regions are regarded as “suspicious” regions that need to be predicted at high magnification, and most of the regions in WSI are predicted at low magnification, thereby reducing the times of image patch extraction and prediction. Meanwhile, uncertainty estimation ensures prediction accuracy at low magnification. We take two fundamental CPATH classification tasks (i.e., cancer region detection and subtyping) as examples. Extensive experiments on two large-scale renal cell carcinoma classification datasets demonstrate that our UMA can significantly reduce the time cost of model inference while maintaining competitive classification performance.
暂无评论