Video white balance is to correct the scene color of video frames to the color under the standard white illumination. Due to the camera movement, video white balance usually suffers temporal instability with unnatural...
详细信息
Voronoi diagrams on triangulated surfaces based on the geodesic metric play a key role in many applications of computer *** methods of constructing such Voronoi diagrams generally depended on having an exact geodesic ...
详细信息
Voronoi diagrams on triangulated surfaces based on the geodesic metric play a key role in many applications of computer *** methods of constructing such Voronoi diagrams generally depended on having an exact geodesic ***,exact geodesic computation is time-consuming and has high memory usage,limiting wider application of geodesic Voronoi diagrams(GVDs).In order to overcome this issue,instead of using exact methods,we reformulate a graph method based on Steiner point insertion,as an effective way to obtain geodesic ***,since a bisector comprises hyperbolic and line segments,we utilize Apollonius diagrams to encode complicated structures,enabling Voronoi diagrams to encode a medial-axis surface for a dense set of boundary *** on these strategies,we present an approximation algorithm for efficient Voronoi diagram construction on triangulated *** also suggest a measure for evaluating similarity of our results to the exact *** our GVD results are constructed using approximate geodesic distances,we can get GVD results similar to exact results by inserting Steiner points on triangle *** results on many 3D models indicate the improved speed and memory requirements compared to previous leading methods.
Software defect prediction plays a critical role in software development and quality assurance processes. Effective defect prediction enables testers to accurately prioritize testing efforts and enhance defect detecti...
详细信息
Software defect prediction plays a critical role in software development and quality assurance processes. Effective defect prediction enables testers to accurately prioritize testing efforts and enhance defect detection efficiency. Additionally, this technology provides developers with a means to quickly identify errors, thereby improving software robustness and overall quality. However, current research in software defect prediction often faces challenges, such as relying on a single data source or failing to adequately account for the characteristics of multiple coexisting data sources. This approach may overlook the differences and potential value of various data sources, affecting the accuracy and generalization performance of prediction results. To address this issue, this study proposes a multivariate heterogeneous hybrid deep learning algorithm for defect prediction (DP-MHHDL). Initially, Abstract Syntax Tree (AST), Code Dependency Network (CDN), and code static quality metrics are extracted from source code files and used as inputs to ensure data diversity. Subsequently, for the three types of heterogeneous data, the study employs a graph convolutional network optimization model based on adjacency and spatial topologies, a Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) hybrid neural network model, and a TabNet model to extract data features. These features are then concatenated and processed through a fully connected neural network for defect prediction. Finally, the proposed framework is evaluated using ten promise defect repository projects, and performance is assessed with three metrics: F1, Area under the curve (AUC), and Matthews correlation coefficient (MCC). The experimental results demonstrate that the proposed algorithm outperforms existing methods, offering a novel solution for software defect prediction.
Operators(such as Conv and ReLU) play an important role in deep neural networks. Every neural network is composed of a series of differentiable operators. However, existing AI benchmarks mainly focus on accessing mode...
详细信息
Operators(such as Conv and ReLU) play an important role in deep neural networks. Every neural network is composed of a series of differentiable operators. However, existing AI benchmarks mainly focus on accessing model training and inference performance of deep learning systems on specific models. To help GPU hardware find computing bottlenecks and intuitively evaluate GPU performance on specific deep learning tasks, this paper focuses on evaluating GPU performance at the operator level. We statistically analyze the information of operators on 12 representative deep learning models from six prominent AI tasks and provide an operator dataset to show the different importance of various types of operators in different networks. An operator-level benchmark, OpBench, is proposed on the basis of this dataset, allowing users to choose from a given range of models and set the input sizes according to their demands. This benchmark offers a detailed operator-level performance report for AI and hardware developers. We also evaluate four GPU models on OpBench and find that their performances differ on various types of operators and are not fully consistent with the performance metric FLOPS(floating point operations per second).
The emergence of metalenses has impacted a wide variety of applications such as beam steering,imaging,depth sensing,and display *** distortion,an important metric among many optical design specifications,has however r...
详细信息
The emergence of metalenses has impacted a wide variety of applications such as beam steering,imaging,depth sensing,and display *** distortion,an important metric among many optical design specifications,has however rarely been discussed in the context of ***,we present a generic approach for on-demand distortion engineering using compound *** show that the extra degrees of freedom afforded by a doublet metasurface architecture allow custom-tailored angle-dependent image height relations and hence distortion control while minimizing other monochromatic *** this platform,we experimentally demonstrate a compound fisheye metalens with diffraction-limited performance across a wide field of view of 140°and a low barrel distortion of less than 2%,compared with up to 22%distortion in a reference metalens without *** design strategy and compound metalens architecture presented herein are expected to broadly impact metasurface applications in consumer electronics,automotive and robotic sensing,medical imaging,and machine vision systems.
A high-temperature superconducting(HTS)dynamo flux pump can inject DC currents into closed-loop HTS magnets without *** enables the realisation of current-lead-free or even through-wall charging systems for high-field...
详细信息
A high-temperature superconducting(HTS)dynamo flux pump can inject DC currents into closed-loop HTS magnets without *** enables the realisation of current-lead-free or even through-wall charging systems for high-field applications such as nuclear magnetic resonance/magnetic resonance imaging(MRI)magnets,fusion reactors and *** have proposed many simulation models to understand the working principle of HTS dynamos,few of which are in 3D because of converging ***,the influences of many key 3D parameters in the HTS dynamo are scarcely *** authors propose an efficient 3D modelling method of the HTS dynamo based on the T-A *** rotating magnets are modelled by a ring-shaped permanent magnet with space-time-variant remanent flux density to avoid moving ***,together with the T-A formulation,makes the 3D model efficient and *** accuracy of the model is verified by the experimental instantaneous and time-integrated dynamic *** this model,the authors present systematic case studies to thoroughly explore the influences of the key parameters of a dynamo flux pump on the dynamic voltage and *** proposed modelling method and results could significantly benefit the design and optimisation of HTS dynamos for high-field magnets.
Multiarmed bandit(MAB) models are widely used for sequential decision-making in uncertain environments, such as resource allocation in computer communication systems.A critical challenge in interactive multiagent syst...
Multiarmed bandit(MAB) models are widely used for sequential decision-making in uncertain environments, such as resource allocation in computer communication systems.A critical challenge in interactive multiagent systems with bandit feedback is to explore and understand the equilibrium state to ensure stable and tractable system performance.
In today’s era, smartphones are used in daily lives because they are ubiquitous and can be customized by installing third-party apps. As a result, the menaces because of these apps, which are potentially risky for u...
详细信息
Multimodal sentiment analysis (MSA) seeks to understand human affection by leveraging signals from multiple modalities. A core challenge in MSA is the effective extraction of sentimental relations between these signal...
详细信息
Social robot accounts controlled by artificial intelligence or humans are active in social networks,bringing negative impacts to network security and social *** social robot detection methods based on graph neural net...
详细信息
Social robot accounts controlled by artificial intelligence or humans are active in social networks,bringing negative impacts to network security and social *** social robot detection methods based on graph neural networks suffer from the problem of many social network nodes and complex relationships,which makes it difficult to accurately describe the difference between the topological relations of nodes,resulting in low detection accuracy of social *** paper proposes a social robot detection method with the use of an improved neural ***,social relationship subgraphs are constructed by leveraging the user’s social network to disentangle intricate social relationships ***,a linear modulated graph attention residual network model is devised to extract the node and network topology features of the social relation subgraph,thereby generating comprehensive social relation subgraph features,and the feature-wise linear modulation module of the model can better learn the differences between the ***,user text content and behavioral gene sequences are extracted to construct social behavioral features combined with the social relationship subgraph ***,social robots can be more accurately identified by combining user behavioral and relationship *** carrying out experimental studies based on the publicly available datasets TwiBot-20 and Cresci-15,the suggested method’s detection accuracies can achieve 86.73%and 97.86%,*** with the existing mainstream approaches,the accuracy of the proposed method is 2.2%and 1.35%higher on the two *** results show that the method proposed in this paper can effectively detect social robots and maintain a healthy ecological environment of social networks.
暂无评论