Zobrazeno 1 - 10
of 601
pro vyhledávání: '"Michael K Ng"'
Publikováno v:
Machine Learning with Applications, Vol 13, Iss , Pp 100479- (2023)
In this paper, we study the problem of multilinear multitask learning (MLMTL), in which all tasks are stacked into a third-order tensor for consideration. In contrast to conventional multitask learning, MLMTL can explore inherent correlations among m
Externí odkaz:
https://doaj.org/article/145c398bf3e440048934d98213b0385d
Publikováno v:
Advances in Meteorology, Vol 2022 (2022)
Windshear is a kind of microscale meteorological phenomenon which can cause danger to the landing and takeoff of aircrafts. Accurate windshear detection plays a crucial role in aviation safety. With the development of machine learning, several learni
Externí odkaz:
https://doaj.org/article/0a12d98d80cb45ff878a23c5654d29cd
Publikováno v:
Advances in Meteorology, Vol 2022 (2022)
In this article, we propose a light detection and ranging (LiDAR) data denoising scheme for wind profile observation as a part of quality control procedure for wind velocity monitoring and windshear detection. The proposed denoising scheme consists o
Externí odkaz:
https://doaj.org/article/33745a1611644d8c989ad7f3a2970efe
Autor:
Lina Zhuang, Michael K. Ng
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 13, Pp 1143-1157 (2020)
This article introduces a new hyperspectral image (HSI) denoising method that is able to cope with additive mixed noise, i.e., mixture of Gaussian noise, impulse noise, and stripes, which usually corrupt hyperspectral images in the acquisition proces
Externí odkaz:
https://doaj.org/article/255cde5519864dec83b46ec9077c0344
Publikováno v:
Neural Networks. 161:343-358
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b49291ae69a21bf600d1d7327c527f25
https://doi.org/10.1016/j.neunet.2023.01.044
https://doi.org/10.1016/j.neunet.2023.01.044
Publikováno v:
Neural Networks. 160:63-83
Deep neural networks have achieved great success in solving many machine learning and computer vision problems. In this paper, we propose a deep neural network called the Tucker network derived from the Tucker format and analyze its expressive power.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::262361efaa560bb31a2229debdc1aa66
https://doi.org/10.1016/j.neunet.2022.12.016
https://doi.org/10.1016/j.neunet.2022.12.016
Autor:
Michael K. Ng, Andy Yip
Publikováno v:
Analysis and Applications. 21:819-840
Graph Convolution Networks (GCNs) have been shown to be very effective in utilizing pair-wise relationships across samples. They have been successfully applied to solve various machine learning problems in practice. In many applications, the construc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5db21d045f4422027c968a8bb56254ce
https://doi.org/10.1142/s0219530523500021
https://doi.org/10.1142/s0219530523500021
Publikováno v:
IEEE Transactions on Geoscience and Remote Sensing. 61:1-17
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f4ec1d7cfb0784a8510a0cd14f8ec739
https://doi.org/10.1109/tgrs.2023.3236818
https://doi.org/10.1109/tgrs.2023.3236818
Publikováno v:
ACM Transactions on Information Systems. 41:1-25
This article presents a novel model named Adversarial Auto-encoder Domain Adaptation to handle the recommendation problem under cold-start settings. Specifically, we divide the hypergraph into two hypergraphs, i.e., a positive hypergraph and a negati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c7ca0678b3fd58c9d821bf56fc8d85c9
https://doi.org/10.1145/3544105
https://doi.org/10.1145/3544105
Publikováno v:
IEEE Transactions on Cybernetics. 52:13395-13410
The general tensor-based methods can recover missing values of multidimensional images by exploiting the low-rankness on the pixel level. However, especially when considerable pixels of an image are missing, the low-rankness is not reliable on the pi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bd0172e0bd75c82f0eef96f3f00d2c3f
https://doi.org/10.1109/tcyb.2021.3108847
https://doi.org/10.1109/tcyb.2021.3108847