The purpose of this research is to compare several machine learning techniques on the task of Asian language text classification, such as Chinese and Japanese where no word…
Abstract
Purpose
The purpose of this research is to compare several machine learning techniques on the task of Asian language text classification, such as Chinese and Japanese where no word boundary information is available in written text. The paper advocates a simple language modeling based approach for this task.
Design/methodology/approach
Naïve Bayes, maximum entropy model, support vector machines, and language modeling approaches were implemented and were applied to Chinese and Japanese text classification. To investigate the influence of word segmentation, different word segmentation approaches were investigated and applied to Chinese text. A segmentation‐based approach was compared with the non‐segmentation‐based approach.
Findings
There were two findings: the experiments show that statistical language modeling can significantly outperform standard techniques, given the same set of features; and it was found that classification with word level features normally yields improved classification performance, but that classification performance is not monotonically related to segmentation accuracy. In particular, classification performance may initially improve with increased segmentation accuracy, but eventually classification performance stops improving, and can in fact even decrease, after a certain level of segmentation accuracy.
Practical implications
Apply the findings to real web text classification is ongoing work.
Originality/value
The paper is very relevant to Chinese and Japanese information processing, e.g. webpage classification, web search.
Details
Keywords
Fuchun Jia, Xianghuan Liu and Yao Fu
The purposes of this paper are optimization of high speed reducer in electric vehicles based on the analysis of lubrication and verification of simulation accuracy and…
Abstract
Purpose
The purposes of this paper are optimization of high speed reducer in electric vehicles based on the analysis of lubrication and verification of simulation accuracy and optimization results.
Design/methodology/approach
The traditional CFD method presents poor applicability to complex geometric problems due to grid deformity. Therefore, moving particle semi-implicit (MPS) method is applied in this study to simulate lubrication of the reducer and analyze the influence of input speed and lubrication system design on the distribution. According to the results, the reducer is optimized. Meanwhile, the experiments for lubrication and churning power loss is carried out to verify the accuracy of simulation and optimization effects.
Findings
The flow field of lubricant inside the reducer is obtained. The lubrication system of reducer needs to be improved. Simulation and experiment show that the optimization is sufficient and efficient.
Originality/value
According to the simulation of lubrication, the reducer is optimized. The lubrication experimental setup is established. The conclusion of paper can provide the method and tool for reducer in electric vehicle.
Peer review
The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-04-2024-0123/
Details
Keywords
Shuhuan Wen, Xueheng Hu, Zhen Li, Hak Keung Lam, Fuchun Sun and Bin Fang
This paper aims to propose a novel active SLAM framework to realize avoid obstacles and finish the autonomous navigation in indoor environment.
Abstract
Purpose
This paper aims to propose a novel active SLAM framework to realize avoid obstacles and finish the autonomous navigation in indoor environment.
Design/methodology/approach
The improved fuzzy optimized Q-Learning (FOQL) algorithm is used to solve the avoidance obstacles problem of the robot in the environment. To reduce the motion deviation of the robot, fractional controller is designed. The localization of the robot is based on FastSLAM algorithm.
Findings
Simulation results of avoiding obstacles using traditional Q-learning algorithm, optimized Q-learning algorithm and FOQL algorithm are compared. The simulation results show that the improved FOQL algorithm has a faster learning speed than other two algorithms. To verify the simulation result, the FOQL algorithm is implemented on a NAO robot and the experimental results demonstrate that the improved fuzzy optimized Q-Learning obstacle avoidance algorithm is feasible and effective.
Originality/value
The improved fuzzy optimized Q-Learning (FOQL) algorithm is used to solve the avoidance obstacles problem of the robot in the environment. To reduce the motion deviation of the robot, fractional controller is designed. To verify the simulation result, the FOQL algorithm is implemented on a NAO robot and the experimental results demonstrate that the improved fuzzy optimized Q-Learning obstacle avoidance algorithm is feasible and effective.
Details
Keywords
Liang Guo, Clive Smallman and Jack Radford
This paper aims to offer a critique of corporate governance in China.
Abstract
Purpose
This paper aims to offer a critique of corporate governance in China.
Design/methodology/approach
The critique is based upon a literature review and secondary data sources.
Findings
The Chinese Government has made efforts to strengthen the effectiveness of corporate governance in state‐owned enterprises. However, existing research shows that some governance mechanisms that are effective in Western countries have no significant or negative impacts on firm performance in China. An apparent reason for this is the strong relationship between state‐owned enterprises and the government.
Originality/value
Policy implications are offered as a means to improve corporate governance in China.
Details
Keywords
Wengang Chen, Xueyuan Liu and Lili Zheng
This paper aims to clarify the friction properties of 304 steel surface modification. The surface modification includes laser texturing processing and nitriding treatment on 304…
Abstract
Purpose
This paper aims to clarify the friction properties of 304 steel surface modification. The surface modification includes laser texturing processing and nitriding treatment on 304 steel surface, and then the friction properties’ test was conducted on different friction directions and different upper test samples by using microfriction and wear testing machine.
Design/methodology/approach
The diameter and spacing of 100-, 150-, 200-, 300-μm pit array on the surface of 304 steel were calculated using a M-DPSS-50 semiconductor laser device. Then, the textured surface was nitriding-treated using a nitriding salt bath device. The chemical composition, surface morphology and surface microhardness of the composite-modified surface were measured by X-ray diffraction and by using an optical microscope and a microhardness tester. The tribological characteristics of the composite-modified surface were tested by MRTR microcomputer-controlled multifunctional friction and wear testing machine.
Findings
The result showed that a rule pit texture surface was obtained by the texture processing. The microhardness of nitriding treatment surface reached 574.27HV0.1, which significantly higher than 222.58HV0.1 of 304 steel. The composite-modified surface has excellent anti-friction and wear resistance properties when the upper specimen was GCr15 steel and ZrO2, respectively. The composite-modified surface has excellent anti-friction and anti-wear properties after long time friction under different angles. However, the friction coefficient and wear morphology of the friction pairs are not affected by the friction angle.
Research limitations/implications
Because of the chosen research approach, the research results may lack generalizability. Therefore, researchers are encouraged to test the proposed propositions further.
Practical implications
The paper conducted a systematic study of the tribological characteristics of 304 steel composite modification surface and provided a good basis for the extensive application of 304 steel.
Social implications
The study provides a good basis for the extensive application of 304 steel.
Originality/value
This paper fulfils an identified need to study the extensive application of 304 steel.