Search results

1 – 3 of 3
To view the access options for this content please click here
Article
Publication date: 4 April 2016

Yang Lu, Shujuan Yi, Yurong Liu and Yuling Ji

This paper aims to design a multi-layer convolutional neural network (CNN) to solve biomimetic robot path planning problem.

Abstract

Purpose

This paper aims to design a multi-layer convolutional neural network (CNN) to solve biomimetic robot path planning problem.

Design/methodology/approach

At first, the convolution kernel with different scales can be obtained by using the sparse auto encoder training algorithm; the parameter of the hidden layer is a series of convolutional kernel, and the authors use these kernels to extract first-layer features. Then, the authors get the second-layer features through the max-pooling operators, which improve the invariance of the features. Finally, the authors use fully connected layers of neural networks to accomplish the path planning task.

Findings

The NAO biomimetic robot respond quickly and correctly to the dynamic environment. The simulation experiments show that the deep neural network outperforms in dynamic and static environment than the conventional method.

Originality/value

A new method of deep learning based biomimetic robot path planning is proposed. The authors designed a multi-layer CNN which includes max-pooling layer and convolutional kernel. Then, the first and second layers features can be extracted by these kernels. Finally, the authors use the sparse auto encoder training algorithm to train the CNN so as to accomplish the path planning task of NAO robot.

Details

Assembly Automation, vol. 36 no. 2
Type: Research Article
ISSN: 0144-5154

Keywords

To view the access options for this content please click here
Article
Publication date: 26 August 2014

Zhifeng Huang, Xiaoyang Ma, Zemin Qiao, Shujuan Wang and Xinli Jing

This paper aims to disclose the evolution of pendulum hardness of two-component acrylic polyurethane coatings during the cure process and attempts to describe the…

Abstract

Purpose

This paper aims to disclose the evolution of pendulum hardness of two-component acrylic polyurethane coatings during the cure process and attempts to describe the quantitative relationship between pendulum hardness and curing time. These findings are helpful for the study of fast curing acrylic polyurethane coatings.

Design/methodology/approach

The pendulum hardness method was used to monitor the hardness of two-component acrylic polyurethane coatings during curing. The quantitative relationship between pendulum hardness and curing time can be obtained with Avrami equation.

Findings

The evolution of coating pendulum hardness can be divided into three stages. By using the Avrami equation that explained the influence of both the acid value and the curing temperature on the drying speed of hydroxyl acrylic resin, the evolution of coating pendulum hardness during curing can also be accurately described.

Research limitations/implications

It should be noted that the physical meaning of the Avrami exponent, n, is not yet clear.

Practical implications

The results are of great significance for the development of fast-curing hydroxyl-functional acrylic resins, with the potential to improve the drying speed of the coatings used in automotive refinish.

Originality/value

It is novel to divide the pendulum hardness into three stages, and, for the first time, the Avrami equation is utilized to describe the evolution of coating pendulum hardness during curing.

Details

Pigment & Resin Technology, vol. 43 no. 5
Type: Research Article
ISSN: 0369-9420

Keywords

To view the access options for this content please click here
Article
Publication date: 1 January 2011

Jun Xie and Xiaotao Zeng

The purpose of this paper is to examine whether the shareholding of the largest shareholder and other large shareholders could exert a good stimulating effect within a…

Abstract

Purpose

The purpose of this paper is to examine whether the shareholding of the largest shareholder and other large shareholders could exert a good stimulating effect within a firm's corporate governance structure and what impact the balance of power among large shareholders could have on top management turnover.

Design/methodology/approach

This paper has investigated 787 firms publicly listed in the Shanghai Stock Exchange and checked the relation between power balance of firms' block shareholders and their top management turnover.

Findings

The paper's empirical results show that there is a U‐shaped relationship between the proportions of shareholding of a firm's largest shareholder and its top management turnover, that is, the controlling shareholder could impose either negative or positive effect for different types of equity ownership. We also find that the proportion of shares held by other block shareholders is significantly and positively related to the turnover of management and the monitoring effect of other large shareholders is strong. Furthermore, duality of chairman and CEO shows a significant negative effect on firms's top management turnover.

Originality/value

The paper usefully shows that under the institutional background of relatively weak legal protection for medium and small investors in China, centralized shareholding by large shareholders in listed firms, or the so‐called mechanism of power balance among block shareholders, has the ability to effectively supervise and restrain the corporate governance of a firm, replace ineffective managers and thus improve its whole management performance.

Details

China Finance Review International, vol. 1 no. 1
Type: Research Article
ISSN: 2044-1398

Keywords

1 – 3 of 3