Search

Your search keyword '"Du, Jinhua"' showing total 47 results
Start Over Author "Du, Jinhua" Publisher ieee
47 results on '"Du, Jinhua"'

13. Attentive Siamese LSTM network for semantic textual similarity measure

Author

Bao, Wei, Bao, Wugedele, Du, Jinhua, Yang, Yuanyuan, Zhao, Xiaobing, Bao, Wei, Bao, Wugedele, Du, Jinhua, Yang, Yuanyuan, and Zhao, Xiaobing

Abstract

Semantic Textual Similarity (STS) is important for many applications such as Plagiarism Detection (PD), Text Paraphrasing and Information Retrieval (IR). Current methods for STS rely on statistical machine learning. Recent studies showed that neural networks for STS presented promising experimental results. In this paper, we propose an Attentive Siamese Long Short-Term Memory (LSTM) network for measuring Semantic Textual Similarity. Instead of external resources and handcraft features, raw sentence pairs and pre-trained word embedding are needed as input. Attention mechanism is utilized in LSTM network to capture high-level semantic information. We demonstrated the effectiveness of our model by applying the architecture in different tasks: three corpora and three language tasks. Experimental results on all tasks and languages show that our method with attention mechanism outperforms the baseline model with a higher correlation with human annotation.

Published
2019
Full Text
View/download PDF

14. Distributed dimensionality reduction of industrial data based on clustering

Author

Zhang, Yongyan, Xie, Guo, Wang, Wenqing, Qian, Fucai, Du, Xulong, and Du, Jinhua

Subjects
Machine translating
Abstract

Large amounts of data are produced in system operation, and how to extract effective information from these data has become an important research topic in the industrial application. Dimensionality reduction is a way to refine the data. Because of the low efficiency of the existing methods, these methods can’t discover the internal structure of the data. Regarding these problems, a distributed method of dimensionality reduction based on clustering is proposed, which includes the following steps:(1) Clustering the data into some small classes according to the similarity between the data variables; (2) reducing the dimension of data in a small class after being clustered respectively; (3) merging the data after being reduced dimension; (4) classifying the data after being merged by support vector machine (SVM). The data in the simulation is the test data, and the results show that the methods proposed in this paper are better than the existing dimensionality reduction methods.

Published
2018

30. Improved Analytical Model for Inductance Calculations of a Dual-Rotor Permanent Magnet Reluctance Machine Based on Magnetic Networks.

Author

Du, Jinhua, Xue, Yuntian, Liu, Quanwei, and Wang, Shuhong

Subjects
*MAGNETIC reluctance generators, *MAGNETIZATION, *ELECTRIC inductance, *FINITE element method, *RELUCTANCE motors
Abstract

This paper proposed a varying magnetic network modeling method of dual-rotor permanent magnet reluctance (DRPMR) machines based on magnetic circuits considering possible saturation and nonlinearity according to the physical structure, which is put forward to obtain the accurate inductance characteristics of the proposed machine. The feasibility of this analytical model is confirmed by the finite element method. Moreover, experiments are designed to validate the analytical results. It indicates that the analytical inductance characteristics of the DRPMR machine have good agreements with the experimental results. [ABSTRACT FROM AUTHOR]

Published
2018
Full Text
View/download PDF

41. Performance Analysis of a Mutually Coupled Linear Switched Reluctance Machine for Direct-Drive Wave Energy Conversions.

Author

Du, Jinhua, Liang, Deliang, and Liu, Xinzheng

Subjects
*PERFORMANCE evaluation, *SWITCHED reluctance motors, *WAVE energy, *ENERGY conversion, *COMPARATIVE studies, *ELECTROMAGNETIC forces
Abstract

The requirements of high efficiency and environment-friendly behavior for wave energy conversions (WECs) have promoted improving investigations of linear electric machines. As an alternative to these existing linear machines, a mutually coupled linear switched reluctance machine (MCLSRM) for direct-drive WECs is proposed in this paper. An extensive comparative study is carried out between the proposed machine and other two comparative machines. By analyzing the operation principles of the three machines, the flux linkage and electromagnetic force formulas are theoretically derived based on equivalent magnetic circuit models, and discussed with the aid of finite-element analysis. Due to high utilization of the electrical and magnetic circuits, it is possible to find an MCLSRM design with comparable force capability to a traditional linear permanent-magnet (LPM) machine with the same electrical loading and the similar overall volume. Furthermore, two prototypes of different machines of the proposed machine and its LPM counterpart are manufactured for experimental validation. From the comparison results, the proposed MCLSRM has a good performance to extract more power from the prime mover above the rated velocity and is highly economic. The LPM counterpart has higher efficiency due to its lower fundamental flux density. [ABSTRACT FROM PUBLISHER]

Published
2017
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results