| Title |
Smart environment design planning for smart city based on deep learning |
| ID_Doc |
36851 |
| Authors |
Liu, LL; Zhang, Y |
| Title |
Smart environment design planning for smart city based on deep learning |
| Year |
2021 |
| Published |
|
| DOI |
10.1016/j.seta.2021.101425 |
| Abstract |
Machine Learning (ML) and Deep Learning (DL) methods have contributed to the progression of models in the different aspects of planning, prediction, and uncertainty analysis of urban and smart cities development in the current scenario. Most developed cities have suffered from severe air quality as population growth and industrialization grow rapidly. Government agencies and citizens are increasingly concerned about air quality, which has an impact on various areas of the human environment and human advancement. Conventional methods of air pollution forecasting primarily use low-level simulations, and these models generate disappointing results that have led us to factors that influence air pollution measurement based on a thorough design of the structure. Furthermore, in this paper, Long Short- Term Memory (LSTM) assisted Staked Auto-Encoder (SAE) (LSTM-SAE) model has been proposed for predicting the air quality in smart environment design planning in the smart cities. Long Short- Term Memory is used to evaluate air pollution quality prediction in smart cities. Staked AutoEncoder (SAE) is modeled and prepared gently to extract the intrinsic components that occur due to air pollution. Furthermore, the findings indicate that classification accuracy of 91.22% and the overall Error rate of 0.46 has been validated, and LSTM-SAE addresses the different aspects of smart city and effective method when compared to other existing methods. |
| Author Keywords |
Smart environment design planning; Smart City (SC); Deep learning; Statistical model |
| Index Keywords |
Index Keywords |
| Document Type |
Other |
| Open Access |
Open Access |
| Source |
Science Citation Index Expanded (SCI-EXPANDED) |
| EID |
WOS:000711877100001 |
| WoS Category |
Green & Sustainable Science & Technology; Energy & Fuels |
| Research Area |
Science & Technology - Other Topics; Energy & Fuels |
| PDF |
|