Impact of missing data on the prediction of random fields

Hamaz, Abdelghani; Arezki, Ouerdia

doi:10.1080/02664763.2019.1633286

Cited by 5 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2) When the outlier is carbon emission data, completing the data is equivalent to making an inaccurate prediction, but it will reduce the accuracy of the model, so we choose to delete the data point [18].…”

Section: Definition 5 (Local Outlier Factor)mentioning

confidence: 99%

Correlation Analysis and Monitoring Method of Carbon Emissions in the Steel Industry Based on Big Data

Yang,

Yi,

Zhiyu

et al. 2023

SPEE

View full text Add to dashboard Cite

Excessive carbon emissions will lead to catastrophic consequences such as global warming and rising oceans and will also have a serious negative impact on the human food supply and living environment. The steel industry is characterized by high pollution, and about 18% of China’s carbon emissions come from the steel industry. The ‘double carbon’ strategy has brought important tasks and severe challenges to China’s steel industry. With a view to evaluating the achievements of carbon emission control, carbon emission monitoring systems at home and abroad have been continuously established and improved. For the steel industry, accurate and efficient carbon monitoring technology has a guiding role in guiding energy conservation and carbon reduction. Traditional carbon emission accounting methods have some problems, such as long cycles and poor data quality, which restrict the improvement of the lean level of carbon emission monitoring management. Firstly, this paper investigates and analyzes the productive process and carbon emission process of the steel industry and constructs an entropy weight-grey correlation -TOPSIS analysis method for the correlation between carbon emissions and influencing factors. Based on the above content, a carbon emission monitoring method based on multiple influencing factors is put forward, and the high monitoring accuracy of the model is proved by taking the Tianjin steel industry as an example. The results show that information mining of relevant data can strikingly increase the accuracy of carbon emission monitoring in the steel industry.

show abstract

Section: Definition 5 (Local Outlier Factor)mentioning

confidence: 99%