FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3215971971> ?p ?o ?g. }

• W3215971971 endingPage "129660" @default.
• W3215971971 startingPage "129660" @default.
• W3215971971 abstract "Deep learning models address air quality forecasting problems far more effectively and efficiently than the traditional machine learning models. Specifically, Long Short-Term Memory networks (LSTMs) constitute a significant breakthrough in understanding the complex sequential behavioral dependencies of the time series. Further, LSTM models justify well with the speed–accuracy tradeoff, among other deep learning models. However, there are several limitations of such deep learning models. Firstly, the addition of multiple hidden layers, on the one hand, improves the performance but, on the other hand, requires extensive hardware and computation capabilities. Secondly, most of the previous works that utilized LSTMs for air quality forecasting do not consider the issue of optimal hyperparameter calibration. While deciding the gradient, network learning parameters should be so fixed such that the model does not underfit or overfit. To address these issues, a stochastic optimization algorithm, mimicking the pattern of flocking birds, is utilized to find the most fitting solution in the parameter search space. Particle swarm optimization setup primarily models varying particles representing parameters to reach an optimum state. Furthermore, the Spatio-temporal instabilities of LSTM models are addressed in this work using preprocessing, segmentation and feature engineering to understand seasonal and trend characteristics along with the Spatio-temporal correlation of the time series. The proposed model is employed on the air quality dataset of 15 locations in India. A variety of experiments are performed to prove the superiority of the proposed method. Firstly, a comparison with traditional sequential models and deep learning models is done. Secondly, results are further evaluated over several existing benchmark dataset samples. Results suggest that the proposed method outperforms existing forecasting models when evaluated over a variety of performance metrics." @default.
• W3215971971 created "2021-12-06" @default.
• W3215971971 creator A5003636226 @default.
• W3215971971 creator A5082753354 @default.
• W3215971971 date "2021-12-01" @default.
• W3215971971 modified "2023-10-17" @default.
• W3215971971 title "A hybrid deep learning framework for urban air quality forecasting" @default.
• W3215971971 cites W1968727354 @default.
• W3215971971 cites W1974540239 @default.
• W3215971971 cites W1976007775 @default.
• W3215971971 cites W1999842331 @default.
• W3215971971 cites W2004353783 @default.
• W3215971971 cites W2041092292 @default.
• W3215971971 cites W2041178263 @default.
• W3215971971 cites W2064675550 @default.
• W3215971971 cites W2076230528 @default.
• W3215971971 cites W2076551542 @default.
• W3215971971 cites W2077215180 @default.
• W3215971971 cites W2080841555 @default.
• W3215971971 cites W2089202914 @default.
• W3215971971 cites W2107346417 @default.
• W3215971971 cites W2121029939 @default.
• W3215971971 cites W2136915828 @default.
• W3215971971 cites W2143451729 @default.
• W3215971971 cites W2146848957 @default.
• W3215971971 cites W2615551724 @default.
• W3215971971 cites W2760506659 @default.
• W3215971971 cites W2767894694 @default.
• W3215971971 cites W2803892188 @default.
• W3215971971 cites W2809533013 @default.
• W3215971971 cites W2810586154 @default.
• W3215971971 cites W2884704880 @default.
• W3215971971 cites W2886875452 @default.
• W3215971971 cites W2898461917 @default.
• W3215971971 cites W2905241670 @default.
• W3215971971 cites W2928323670 @default.
• W3215971971 cites W2982277720 @default.
• W3215971971 cites W3122775348 @default.
• W3215971971 cites W956374238 @default.
• W3215971971 doi "https://doi.org/10.1016/j.jclepro.2021.129660" @default.
• W3215971971 hasPublicationYear "2021" @default.
• W3215971971 type Work @default.
• W3215971971 sameAs 3215971971 @default.
• W3215971971 citedByCount "15" @default.
• W3215971971 countsByYear W32159719712022 @default.
• W3215971971 countsByYear W32159719712023 @default.
• W3215971971 crossrefType "journal-article" @default.
• W3215971971 hasAuthorship W3215971971A5003636226 @default.
• W3215971971 hasAuthorship W3215971971A5082753354 @default.
• W3215971971 hasConcept C108583219 @default.
• W3215971971 hasConcept C11413529 @default.
• W3215971971 hasConcept C119857082 @default.
• W3215971971 hasConcept C121332964 @default.
• W3215971971 hasConcept C126314574 @default.
• W3215971971 hasConcept C153294291 @default.
• W3215971971 hasConcept C154945302 @default.
• W3215971971 hasConcept C22019652 @default.
• W3215971971 hasConcept C2778827112 @default.
• W3215971971 hasConcept C34736171 @default.
• W3215971971 hasConcept C41008148 @default.
• W3215971971 hasConcept C45374587 @default.
• W3215971971 hasConcept C50644808 @default.
• W3215971971 hasConcept C85617194 @default.
• W3215971971 hasConcept C8642999 @default.
• W3215971971 hasConceptScore W3215971971C108583219 @default.
• W3215971971 hasConceptScore W3215971971C11413529 @default.
• W3215971971 hasConceptScore W3215971971C119857082 @default.
• W3215971971 hasConceptScore W3215971971C121332964 @default.
• W3215971971 hasConceptScore W3215971971C126314574 @default.
• W3215971971 hasConceptScore W3215971971C153294291 @default.
• W3215971971 hasConceptScore W3215971971C154945302 @default.
• W3215971971 hasConceptScore W3215971971C22019652 @default.
• W3215971971 hasConceptScore W3215971971C2778827112 @default.
• W3215971971 hasConceptScore W3215971971C34736171 @default.
• W3215971971 hasConceptScore W3215971971C41008148 @default.
• W3215971971 hasConceptScore W3215971971C45374587 @default.
• W3215971971 hasConceptScore W3215971971C50644808 @default.
• W3215971971 hasConceptScore W3215971971C85617194 @default.
• W3215971971 hasConceptScore W3215971971C8642999 @default.
• W3215971971 hasFunder F4320325255 @default.
• W3215971971 hasLocation W32159719711 @default.
• W3215971971 hasOpenAccess W3215971971 @default.
• W3215971971 hasPrimaryLocation W32159719711 @default.
• W3215971971 hasRelatedWork W2942650110 @default.
• W3215971971 hasRelatedWork W2968586400 @default.
• W3215971971 hasRelatedWork W2989932438 @default.
• W3215971971 hasRelatedWork W3099765033 @default.
• W3215971971 hasRelatedWork W4200250512 @default.
• W3215971971 hasRelatedWork W4210794429 @default.
• W3215971971 hasRelatedWork W4281986673 @default.
• W3215971971 hasRelatedWork W4312706017 @default.
• W3215971971 hasRelatedWork W4361732492 @default.
• W3215971971 hasRelatedWork W4385700958 @default.
• W3215971971 hasVolume "329" @default.
• W3215971971 isParatext "false" @default.
• W3215971971 isRetracted "false" @default.
• W3215971971 magId "3215971971" @default.
• W3215971971 workType "article" @default.