Yan Xu, Hong Qin, Jiani Huang and Yanyun Wang
Conventional learning-based visual odometry (VO) systems usually use convolutional neural networks (CNN) to extract features, where some important context-related and…
Abstract
Purpose
Conventional learning-based visual odometry (VO) systems usually use convolutional neural networks (CNN) to extract features, where some important context-related and attention-holding global features might be ignored. Without essential global features, VO system will be sensitive to various environmental perturbations. The purpose of this paper is to design a novel learning-based framework that aims to improve accuracy of learning-based VO without decreasing the generalization ability.
Design/methodology/approach
Instead of CNN, a context-gated convolution is adopted to build an end-to-end learning framework, which enables convolutional layers that dynamically capture representative local patterns and composes local features of interest under the guidance of global context. In addition, an attention mechanism module is introduced to further improve learning ability and enhance robustness and generalization ability of the VO system.
Findings
The proposed system is evaluated on the public data set KITTI and the self-collected data sets of our college building, where it shows competitive performance compared with some classical and state-of-the-art learning-based methods. Quantitative experimental results on the public data set KITTI show that compared with CNN-based VO methods, the average translational error and rotational error of all the test sequences are reduced by 45.63% and 37.22%, respectively.
Originality/value
The main contribution of this paper is that an end-to-end deep context gate convolutional VO system based on lightweight attention mechanism is proposed, which effectively improves the accuracy compared with other learning-based methods.
Details
Keywords
Innovation has become the engine of economic growth, especially with the Fourth Industrial Revolution. This paper aims at studying the association between innovation – measured by…
Abstract
Purpose
Innovation has become the engine of economic growth, especially with the Fourth Industrial Revolution. This paper aims at studying the association between innovation – measured by gross expenditure on research and development (GERD) – and economic performance – represented by real gross domestic product (GDP) – in MENA region over the period 1996-2016.
Design/methodology/approach
The paper uses the panel corrected standard error method to account for heteroskedacity and possible contemporaneous correlation across panels, and the first order autocorrelation within panel for unbalanced datasets.
Findings
The study concludes that R&D expenditure is positive and statistically significant in explaining GDP, but their relationship is weak. Specifically, a 10 per cent increase in R&D expenditure raises GDP by 4 per cent. In addition, human capital, labor force and fixed capital accumulation are found positive and statistically significant. These findings highlight on the importance of innovation and education on fostering economic growth, urging MENA governments to further invest in R&D and innovation sector.
Originality/value
To the best of the author’s knowledge, this paper is the first to investigate the relationship between GERD and GDP in MENA region within the endogenous-growth model framework.
Details
Keywords
Muhammad Muflih and Juliana Juliana
This paper aims to estimate the influence of spirituality on halal-labeled food shopping behavior both directly and through the mediating roles of image, trust and satisfaction.
Abstract
Purpose
This paper aims to estimate the influence of spirituality on halal-labeled food shopping behavior both directly and through the mediating roles of image, trust and satisfaction.
Design/methodology/approach
Using quantitative methods, this research analyzed the responses to questionnaires distributed to 212 respondents from Bandung, Indonesia. To prove the hypotheses, the collected data were analyzed by partial least square (SEM-PLS) using SmartPLS.
Findings
This research shows that the direct relationship between spirituality and halal-labeled food shopping behavior was insignificant. However, the relationship between spirituality and halal food shopping behavior became indirectly significant through the mediating roles of image, trust and satisfaction. This finding confirms that image, trust and satisfaction are influential factors in the increased shopping behavior of consumers who choose halal-labeled foods.
Practical implications
To increase the shopping behavior of Muslims for halal-labeled food, halal food companies need to expand the halal label campaign to electronic and social media. Besides, halal food companies need to develop the accountability of food quality to ensure that the halal food products meet the health and safety standards expected by the public. Spiritual education is also required to harmonize the love for God and the food choices approved by God.
Originality/value
This study is the first in testing the influence of spirituality on halal-labeled food shopping behavior both directly and through the mediating roles of image, trust and satisfaction. It successfully revealed the strengths and weaknesses of spirituality in influencing the behavior of halal food shopping.
Details
Keywords
Guoqing Lu, Peng Dai and Xia Zhang
The purpose of this paper is to test the relationship between innovation performance and innovation spillover effects, innovation inputs, innovation outputs and industrial effects.
Abstract
Purpose
The purpose of this paper is to test the relationship between innovation performance and innovation spillover effects, innovation inputs, innovation outputs and industrial effects.
Design/methodology/approach
The analysis framework including variables such as innovation spillover effect, innovation input, innovation output and industrial effect was constructed. Through the investigation and analysis of the innovation activities of China’s GEM listed companies in 2014–2016, the innovation performance and the above factors were tested.
Findings
The research shows that enterprise performance has a significant positive correlation with innovation input and innovation output, but there is no significant correlation or even negative correlation with innovation environment and industry background such as government support and innovation opportunities, and the spillover effect is significant. The negative correlation is also negatively correlated with innovative human capital investment, company age and company Q.
Originality/value
Innovation is the real source of economic growth, and industrial innovation is the system integration of technological innovation, product innovation, market innovation, etc., which is the basic determinant of national competitiveness.