Search

Your search keyword '"Dong, Baoming"' showing total 6 results
Start Over Author "Dong, Baoming"
6 results on '"Dong, Baoming"'

1. Cross-model convolutional neural network for multiple modality data representation

Author

Wu, Yanbin, Wang, Li, Cui, Fan, Zhai, Hongbin, Dong, Baoming, and Wang, Jim Jing-Yan

Subjects
Computer Science - Learning
Abstract

A novel data representation method of convolutional neural net- work (CNN) is proposed in this paper to represent data of different modalities. We learn a CNN model for the data of each modality to map the data of differ- ent modalities to a common space, and regularize the new representations in the common space by a cross-model relevance matrix. We further impose that the class label of data points can also be predicted from the CNN representa- tions in the common space. The learning problem is modeled as a minimiza- tion problem, which is solved by an augmented Lagrange method (ALM) with updating rules of Alternating direction method of multipliers (ADMM). The experiments over benchmark of sequence data of multiple modalities show its advantage.

Published
2016

3. Dual-FBG and F-P Cavity Compound Optical Fiber Sensor for Simultaneous Measurement of Bending, Temperature and Strain

Author

Yang, Shitai, Wang, Hongye, Meng, Lingzhi, Chen, Yijian, Dong, Baoming, Yuan, Tingting, Zhang, Xiaotong, and Yuan, Libo

Abstract

A dual-FBG and F-P cavity compound optical fiber sensor based on a multi-core fiber (MCF) is proposed. A hollow core fiber (HCF) was fused between a single-mode fiber (SMF) and a MCF to form the F-P cavity. Two FBGs with different reflective wavelength were prepared on a side core (SC) and the central core (CC) of MCF respectively. An asymmetric 45° reflector was fabricated at the end of the MCF to make the optical path of the dual-FBG and the F-P cavity in series. The combination of the F-P cavity and the FBG on the CC can measure temperature and axial strain, simultaneously, while both of them are insensitive to bending. The FBG on the SC is sensitive to bending and can be used for curvature measurement, and the temperature and axial strain compensation can be achieved by the combination of the F-P cavity and FBG on the CC. Therefore, the curvature, axial strain and temperature can be measured simultaneously by the compound sensor on a single optical fiber.

Published
2023
Full Text
View/download PDF

6. Cross-model convolutional neural network for multiple modality data representation.

Author

Wu, Yanbin, Wang, Li, Cui, Fan, Zhai, Hongbin, Dong, Baoming, and Wang, Jing-Yan

Subjects
ARTIFICIAL neural networks, ARTIFICIAL intelligence, MACHINE learning, DATA mining, BIG data
Abstract

A novel data representation method of convolutional neural network (CNN) is proposed in this paper to represent data of different modalities. We learn a CNN model for the data of each modality to map the data of different modalities to a common space and regularize the new representations in the common space by a cross-model relevance matrix. We further impose that the class label of data points can also be predicted from the CNN representations in the common space. The learning problem is modeled as a minimization problem, which is solved by an augmented Lagrange method with updating rules of Alternating direction method of multipliers. The experiments over benchmark of sequence data of multiple modalities show its advantage. [ABSTRACT FROM AUTHOR]

Published
2018
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results