Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- short-paperJune 2024
WiP: Efficient LLM Prefilling with Mobile NPU
EdgeFM '24: Proceedings of the Workshop on Edge and Mobile Foundation ModelsJune 2024, Pages 33–35https://doi.org/10.1145/3662006.3662066Large language models (LLMs) play a crucial role in various Natural Language Processing (NLP) tasks, prompting their deployment on mobile devices for inference. However, a significant challenge arises due to high waiting latency, especially for long ...
- research-articleAugust 2023
A multi-metric small sphere large margin method for classification
Pattern Analysis & Applications (PAAS), Volume 26, Issue 4Nov 2023, Pages 1615–1629https://doi.org/10.1007/s10044-023-01188-2AbstractMulti-metric learning is important for improving performance of learners. For complex data, multi metric learning algorithms need intensive research. Moreover, the existing multi-metric learning methods may lead to the distance not being ...
- research-articleJuly 2023
Distance metric learning based on the class center and nearest neighbor relationship
Neural Networks (NENE), Volume 164, Issue CJul 2023, Pages 631–644https://doi.org/10.1016/j.neunet.2023.05.004AbstractDistance metric learning has been a promising technology to improve the performance of algorithms related to distance metrics. The existing distance metric learning methods are either based on the class center or the nearest neighbor ...
- research-articleApril 2023
An efficient multi-metric learning method by partitioning the metric space
Neurocomputing (NEUROC), Volume 529, Issue CApr 2023, Pages 56–79https://doi.org/10.1016/j.neucom.2023.01.074AbstractMetric learning has attracted significant attention due to its high effectiveness and efficiency for pattern recognition task. Traditional supervised metric learning algorithms attempt to seek a global distance metric with labeled samples. When ...
- research-articleApril 2023
High-order implicit RBF-based differential quadrature-finite volume method on unstructured grids: Application to inviscid and viscous compressible flows
Journal of Computational Physics (JOCP), Volume 478, Issue CApr 2023https://doi.org/10.1016/j.jcp.2023.111962AbstractThis paper exploits the potential of a high-order implicit radial basis function-based differential quadrature-finite volume (IRBFDQ-FV) method for effective simulation of inviscid and viscous compressible flows using unstructured grids. The ...
Highlights- Compressible inviscid and viscous flow problems are solved by the present high-order method on unstructured grids.
- RBFDQ meshless method is locally employed for derivative approximation.
- Convective and viscous fluxes at the cell ...
-
- research-articleMarch 2023
Classification of COVID-19 from community-acquired pneumonia: Boosting the performance with capsule network and maximum intensity projection image of CT scans
- Yanan Wu,
- Qianqian Qi,
- Shouliang Qi,
- Liming Yang,
- Hanlin Wang,
- Hui Yu,
- Jianpeng Li,
- Gang Wang,
- Ping Zhang,
- Zhenyu Liang,
- Rongchang Chen
Computers in Biology and Medicine (CBIM), Volume 154, Issue CMar 2023https://doi.org/10.1016/j.compbiomed.2023.106567Abstract BackgroundThe coronavirus disease 2019 (COVID-19) and community-acquired pneumonia (CAP) present a high degree of similarity in chest computed tomography (CT) images. Therefore, a procedure for accurately and automatically ...
Highlights- MIP can identify changes in vascular morphology and COVID-19 lesions in CT images.
- research-articleDecember 2022
Multi-metric learning by a pair of twin-metric learning framework
Applied Intelligence (KLU-APIN), Volume 52, Issue 15Dec 2022, Pages 17490–17507https://doi.org/10.1007/s10489-022-03330-9AbstractMulti-metric learning is important for improving classification performance since learning a single metric is usually insufficient for complex data. The existing multi-metric learning methods are based on the triplet constraints, and thus are with ...
- research-articleOctober 2022
A multi-birth metric learning framework based on binary constraints
Neural Networks (NENE), Volume 154, Issue COct 2022, Pages 165–178https://doi.org/10.1016/j.neunet.2022.07.004AbstractMulti-metric learning plays a significant role in improving the generalization of algorithms related to distance metrics since using a single metric is sometimes insufficient to handle complex data. Metric learning can adjust ...
- research-articleOctober 2022
A novel metric learning framework by exploiting global and local information
Neurocomputing (NEUROC), Volume 507, Issue COct 2022, Pages 84–96https://doi.org/10.1016/j.neucom.2022.08.003AbstractDistance metric learning plays a significant role in improving the generalization of algorithms related to distance metrics. In this paper, we first propose a generalized Mahalanobis metric learning framework (called GLML) to make use ...
- research-articleSeptember 2022
A Hybrid Multilayer Perceptron-Radial Basis Function (HMLP-RBF) Neural Network for Solving Hyperbolic Conservation Laws
AbstractThis paper combines the multilayer perceptron (MLP) and the radial basis function (RBF) neural networks to design a hybrid multilayer perceptron-radial basis function (HMLP-RBF) neural network for solving the hyperbolic conservation laws without ...
- research-articleSeptember 2022
Asymmetric kernel-based robust classification by ADMM
Knowledge and Information Systems (KAIS), Volume 65, Issue 1Jan 2023, Pages 89–110https://doi.org/10.1007/s10115-022-01758-6AbstractCorrentropy is a locally second-order statistical measure in kernel space. The different kernel functions induce different correntropy with different properties. In this work, we propose an asymmetric mixture kernel and the corresponding ...
- research-articleMay 2022
Large margin projection-based multi-metric learning for classification
Knowledge-Based Systems (KNBS), Volume 243, Issue CMay 2022https://doi.org/10.1016/j.knosys.2022.108481AbstractMetric learning has been a promising technology to improve classification performance, which aims to learn a data-dependent distance metric such that the similarity between samples can be more effectively evaluated. Metric plays a ...
- research-articleApril 2022
Joint learning adaptive metric and optimal classification hyperplane
Neural Networks (NENE), Volume 148, Issue CApr 2022, Pages 111–120https://doi.org/10.1016/j.neunet.2022.01.002AbstractMetric learning has attracted a lot of interest in classification tasks due to its efficient performance. Most traditional metric learning methods are based on k-nearest neighbors (kNN) classifiers to make decisions, while the choice k ...
- research-articleApril 2022
Generalized eigenvalue extreme learning machine for classification
Applied Intelligence (KLU-APIN), Volume 52, Issue 6Apr 2022, Pages 6662–6691https://doi.org/10.1007/s10489-021-02654-2AbstractExtreme learning machine (ELM) has attracted widespread attention due to its simple, quick and good performance. In this work, in order to deal with cross data quickly and efficiently, we first propose generalized eigenvalue proximal extreme ...
- research-articleMarch 2022
Analyses and reconstruction of the lattice Boltzmann flux solver
Journal of Computational Physics (JOCP), Volume 453, Issue CMar 2022https://doi.org/10.1016/j.jcp.2021.110923Highlights- The macroscopic equations with actual numerical dissipative terms of the LBFS are derived.
The lattice Boltzmann flux solver (LBFS) uses the finite volume method (FVM) to update macroscopic variables while uses the local solution of lattice Boltzmann equation (LBE) to calculate fluxes at the cell interface. It overcomes the ...
- research-articleMarch 2022
Robust metric learning based on subspace learning with l p − n o r m
Highlights- Perform simultaneously subspace learning and metric learning (psub).
- Enhance ...
Distance metric learning has been an important technique in machine learning field recently due to its high effectiveness in improving the performance of distance related methods. In order to take advantages of both subspace learning ...
- research-articleFebruary 2022
Fully automatic pipeline of convolutional neural networks and capsule networks to distinguish COVID-19 from community-acquired pneumonia via CT images
- Qianqian Qi,
- Shouliang Qi,
- Yanan Wu,
- Chen Li,
- Bin Tian,
- Shuyue Xia,
- Jigang Ren,
- Liming Yang,
- Hanlin Wang,
- Hui Yu
Computers in Biology and Medicine (CBIM), Volume 141, Issue CFeb 2022https://doi.org/10.1016/j.compbiomed.2021.105182Abstract BackgroundChest computed tomography (CT) is crucial in the diagnosis of coronavirus disease 2019 (COVID-19). However, the persistent pandemic and similar CT manifestations between COVID-19 and community-acquired pneumonia (...
Highlights- The fully automatic pipeline of deep learning can distinguish COVID-19 from CAP.
- research-articleFebruary 2022
An implicit lattice Boltzmann flux solver for simulation of compressible flows
Computers & Mathematics with Applications (CMAP), Volume 107, Issue CFeb 2022, Pages 82–94https://doi.org/10.1016/j.camwa.2021.12.014Highlights- The implicit LBFS is proposed aiming to efficiently simulate both steady and unsteady flows.
The lattice Boltzmann flux solver (LBFS) is a novel Boltzmann-typed solver under the finite volume framework, which has many advantages over traditional lattice Boltzmann equation (LBE) solvers. However, the existing versions of LBFS ...
- research-articleFebruary 2022
Laplacian Generalized Eigenvalues Extreme Learning Machine
Neural Processing Letters (NPLE), Volume 54, Issue 1Feb 2022, Pages 467–499https://doi.org/10.1007/s11063-021-10640-5AbstractSemi-supervised learning is an attractive technique for using unlabeled data in classification. In this work, an efficient semi-supervised extreme learning machine (ELM) classification framework is proposed by introducing the Laplacian ...
- research-articleJanuary 2022
Low-rank supervised and semi-supervised multi-metric learning for classification
Knowledge-Based Systems (KNBS), Volume 236, Issue CJan 2022https://doi.org/10.1016/j.knosys.2021.107787AbstractMulti-metric learning is an important technique for improving classification performance since learning a single metric is usually insufficient for complex data. Most of the existing multi-metric learning approaches have high ...