Search results
1 – 2 of 2Kuang Junwei, Hangzhou Yang, Liu Junjiang and Yan Zhijun
Previous dynamic prediction models rarely handle multi-period data with different intervals, and the large-scale patient hospital records are not effectively used to improve the…
Abstract
Purpose
Previous dynamic prediction models rarely handle multi-period data with different intervals, and the large-scale patient hospital records are not effectively used to improve the prediction performance. This paper aims to focus on the prediction of cardiovascular disease using the improved long short-term memory (LSTM) model.
Design/methodology/approach
A new model based on the traditional LSTM was proposed to predict cardiovascular disease. The irregular time interval is smoothed to obtain the time parameter vector, and it is used as the input of the forgetting gate of LSTM to overcome the prediction obstacle caused by the irregular time interval.
Findings
The experimental results show that the dynamic prediction model proposed in this paper obtained a significant better classification performance compared with the traditional LSTM model.
Originality/value
In this paper, the authors improved the LSTM by smoothing the irregular time between different medical stages of the patient to obtain the temporal feature vector.
Details
Keywords
Hongyang Li, Anjie Xue, Junwei Zheng, Martin Skitmore and Matthew Moorhead
The current booming development of smart cities poses new requirements and challenges for their internal infrastructure development. This article aims to explore the questions…
Abstract
Purpose
The current booming development of smart cities poses new requirements and challenges for their internal infrastructure development. This article aims to explore the questions of: What is the level of social sustainability of smart city infrastructure today? and What are the core contents and paths to improve this level?
Design/methodology/approach
With the theme of public participation in the social sustainability evaluation of smart city infrastructure in the context of big data, this study mainly makes a systematic literature review of the Web of Science's Science Citation Index Expanded and Social Sciences Citation Index databases. After collection and screening, 199 documents were finally obtained.
Findings
It is found that the level of social sustainability of smart city infrastructure is still low, and public participation can provide solutions to the difficulties and challenges involved in its development, while big data technology can broaden the channels for public participation and promote the development of smart city-related components in the process, including smart city infrastructure.
Originality/value
This article summarizes the internal mechanisms of smart cities at the theoretical level and analyzes the social sustainable development of smart city infrastructure. In practice, the shortcomings in this field are identified and suggestions are provided on how to carry out digital public participation, which has practical reference value.
Details