Analysis on spatial-temporal features of taxis' emissions from big data informed travel patterns: a case of Shanghai, China

2017 ◽  
Vol 142 ◽  
pp. 926-935 ◽  
Author(s):  
Xiao Luo ◽  
Liang Dong ◽  
Yi Dou ◽  
Ning Zhang ◽  
Jingzheng Ren ◽  
...  
2020 ◽  
Vol 14 (4) ◽  
pp. 593-604
Author(s):  
Francesco Mureddu ◽  
Juliane Schmeling ◽  
Eleni Kanellou

Purpose This paper aims to present pertinent research challenges in the field of (big) data-informed policy-making based on the research, undertaken within the course of the European Union-funded project Big Policy Canvas. Technological advancements, especially in the past decade, have revolutionised the way that both every day and complex activities are conducted. It is, thus, expected that a particularly important actor such as the public sector, should constitute a successful disruption paradigm through the adoption of novel approaches and state-of-the-art information and communication technologies. Design The research challenges stem from a need, trend and asset assessment based on qualitative and quantitative research, as well as from the identification of gaps and external framework factors that hinder the rapid and effective uptake of data-driven policy-making approaches. Findings The current paper presents a set of research challenges categorised in six main clusters, namely, public governance framework, privacy, transparency, trust, data acquisition, cleaning and representativeness, data clustering, integration and fusion, modelling and analysis with big data and data visualisation. Originality/value The paper provides a holistic overview of the interdisciplinary research challenges in the field of data-informed policy-making at a glance and shall serve as a foundation for the discussion of future research directions in a broader scientific community. It, furthermore, underlines the necessity to overcome isolated scientific views and treatments because of a high complex multi-layered environment.


2021 ◽  
Vol 40 (12) ◽  
pp. 2035-2047
Author(s):  
De TONG ◽  
Xincan ZHOU ◽  
Yongxi GONG ◽  
Keyword(s):  
Big Data ◽  

2019 ◽  
Vol 120 (2) ◽  
pp. 265-279 ◽  
Author(s):  
Tingyu Weng ◽  
Wenyang Liu ◽  
Jun Xiao

Purpose The purpose of this paper is to design a model that can accurately forecast the supply chain sales. Design/methodology/approach This paper proposed a new model based on lightGBM and LSTM to forecast the supply chain sales. In order to verify the accuracy and efficiency of this model, three representative supply chain sales data sets are selected for experiments. Findings The experimental results show that the combined model can forecast supply chain sales with high accuracy, efficiency and interpretability. Practical implications With the rapid development of big data and AI, using big data analysis and algorithm technology to accurately forecast the long-term sales of goods will provide the database for the supply chain and key technical support for enterprises to establish supply chain solutions. This paper provides an effective method for supply chain sales forecasting, which can help enterprises to scientifically and reasonably forecast long-term commodity sales. Originality/value The proposed model not only inherits the ability of LSTM model to automatically mine high-level temporal features, but also has the advantages of lightGBM model, such as high efficiency, strong interpretability, which is suitable for industrial production environment.


Sign in / Sign up

Export Citation Format

Share Document