Dataset Information

Ambient Effect Filtering Using NLPCA-SVR in High-Rise Buildings.

ABSTRACT: The modal frequencies of a structure are affected by continuous changes in ambient factors, such as temperature, wind speed etc. This study incorporates nonlinear principal component analysis (NLPCA) with support vector regression (SVR) to build a mathematical model to reflect the correlation between ambient factors and modal frequencies. NLPCA is first used to eliminate the high correlation among different ambient factors and extract the nonlinear principal components. The extracted nonlinear principal components are input into the SVR model for training and predicting. The proposed method is verified by the measured data provided in the Guangzhou New TV Tower (GNTVT) Benchmark. The grid search method (GSM), genetic algorithm (GA) and fruit fly optimization algorithm (FOA) are applied to determine the optimal hyperparameters for the SVR model. The optimized result of FOA is most suitable for the NLPCA-SVR model. As evaluated by the hypothesis test and goodness-of-fit test, the results show that the proposed method has a high generalization performance and the correlation between the ambient factor and modal frequency can be strongly reflected. The proposed method can effectively eliminate the effects of ambient factors on modal frequencies.

SUBMITTER: Ye X

PROVIDER: S-EPMC7070861 | biostudies-literature | 2020 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Ambient Effect Filtering Using NLPCA-SVR in High-Rise Buildings.

Ye Xijun X Wu Yingfeng Y Zhang Liwen L Mei Liu L Zhou Yunlai Y

Sensors (Basel, Switzerland) 20200219 4

The modal frequencies of a structure are affected by continuous changes in ambient factors, such as temperature, wind speed etc. This study incorporates nonlinear principal component analysis (NLPCA) with support vector regression (SVR) to build a mathematical model to reflect the correlation between ambient factors and modal frequencies. NLPCA is first used to eliminate the high correlation among different ambient factors and extract the nonlinear principal components. The extracted nonlinear p ...[more]

PMID: 32093064

Similar Datasets

Project description:ObjectivesThis study aimed to investigate possible viral transmission scenarios inside a high-rise building during the Omicron phase of the COVID-19 pandemic.Study designCross-sectional study design.MethodsIn order to determine the pathogenicity of the Omicron variant of SARS-CoV-2, demographic, vaccination and clinical data were collected from COVID-19 positive cases during an outbreak in a high-rise residential building in Shenzhen, China, in early 2022. The pattern of viral transmission inside the building was determined through field investigation and engineering analysis. The results highlight the risk of Omicron infection in high-rise residential buildings.ResultsSymptoms of infection with the Omicron variant are predominantly mild. Younger age has a greater impact on the severity of disease than vaccination status. Each floor of the high-rise building investigated contained 7 apartments, numbered 01 to 07, positioned in the same layout on each floor. The drainage system included vertical pipes from the ground to the roof of the building. There were statistically significant differences in infection rates at different time points and incidence ratios between apartment numbers ending in 07 (type 07) and other apartments (P < 0.001). Households with early disease onset were concentrated in apartment type 07 and the severity of their disease was more severe. The incubation period of the outbreak was 5.21-5.31 days and the time-dependent reproduction number (Rt) was 12.08 (95% confidence interval [CI] 7.66, 18.29). Results suggest both non-contact and contact viral transmission may have contributed to the outbreak. The drainage system in the building allows aerosol regurgitation, thus indicating that the structure of the building may have led to spread of the virus from the sewage pipes. Infections in other apartments may have been as result of viral transmission in the elevators and intimate family contact.ConclusionsResults from this study suggest that Omicron transmission was likely to be via the sewage system, supplemented by contact transmission in the stairs and elevators. The environmental spread of Omicron needs to be highlighted and prevented.

Dataset Information

Ambient Effect Filtering Using NLPCA-SVR in High-Rise Buildings.

Publications

Ambient Effect Filtering Using NLPCA-SVR in High-Rise Buildings.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets