This section mainly introduces the experimental results in three parts:
-
1.
We benchmark the performance of the core algorithms used for secure and verifiable spectral…
Category: 7. Maths
-
Privacy-preserving and verifiable spectral graph analysis in the cloud
-
Autonomous air combat decision making via graph neural networks and reinforcement learning
Overview of the overall framework
In this paper, in order to solve the problems of high complexity, dimensional expansion and computational efficiency caused by multi-agents, high dynamics and high uncertainty in the 8v8 air game environment, a…
Continue Reading
-
Partial contrastive point cloud self-supervised representation learning
Datasets
We evaluate our method on ShapeNet, ModelNet40 and ScanobjectNN datasets. ShapeNet43 is a large-scale collection of 3D shapes. It contains over 57, 448 synthetic 3D models across 55 different categories with a consistent scale and…
Continue Reading
-
Enhanced adaptive sliding mode control with termination parallelism cooperative optimization for torque ripple reduction in switched reluctance motor drives
Research begins with designing an 8/6 Switched Reluctance Motor (SRM) using MATLAB\Simulink to model its electrical and mechanical characteristics. It implements an Outer Loop Adaptive Sliding Mode Control (ASMC) for speed regulation and an Inner…
Continue Reading
-
Integrating decision tools for efficient operations management through innovative approaches
Zhang, Y. L., Xie, G. Y. & Chen, J. A Review on some Significant Methods in Operations Management. Appl. Mech. Mater. 278, 2137–2142 (2013).
Google Scholar
McFarlane, D. A. The…
Continue Reading
-
Self-weighted dual contrastive multi-view clustering network
Task Statement: Given a multi-view set \(\:{\left\{{X}^{v}\right\}}_{v=1}^{M}\), which has \(\:N\) samples across \(\:M\) views, where \(\:{X}^{v}=\left\{{X}_{1}^{v};{X}_{2}^{v}; \ldots ;{X}_{N}^{v}\right\}\in\:{R}^{N\times\:{D}_{v}}\), and
Continue Reading
-
Impact of transfer learning methods and dataset characteristics on generalization in birdsong classification
The data processing, methodology, and evaluation workflow for this study are outlined in Fig. 1.
Fig. 1 Overview of the data processing, methodology, and evaluation pipeline.
Transfer learning
Transfer learning is a machine learning technique where…
Continue Reading
-
Nystromformer based cross-modality transformer for visible-infrared person re-identification
Fig. 1 Architecture diagram of NiCTRAM. The RGB-IR image pair is fed to CNN backbone which has a modality specific CNN block followed by modality shared three blocks. The feature maps are fed to Nystromformer encoder blocks (separate branches for…
Continue Reading
-
Multi-channel volume density neural radiance field for hyperspectral imaging
Experimental design
The performance of our method and the original NeRF method on hyperspectral datasets was compared under various conditions. The images were captured in advance35. The basic configuration of our method inherits from NeRF, the…
Continue Reading
-
Predicting onward care needs at admission to reduce discharge delay using explainable machine learning
Data
We used a pseudonymised version of routinely collected data on patient admissions and hospital spells at UHS between 1st January 2017 and 1st January 2023. Cohort selection is described in Fig. 2, which we briefly summarise here. Patient…
Continue Reading