Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385485584> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4385485584 abstract "Radio base stations are quite crucial to the quality of mobile communication services. The path loss of the mobile signal is mainly affected by the physical parameters of the base station itself and the geographical structure within the service area. Efficiently optimizing the number and assignment of radio base stations by predicting the path loss of radio signals within the service range is of great significance for improving signal quality and saving costs. The traditional modeling method based on the physical parameters of the base station and wireless signal propagation mechanism cannot consider geographical structure information, and the prediction accuracy is low. Another method based on simulation software can improve prediction accuracy, but it requires professional knowledge to guide the experiment, and the cost is very high. In this work, based on the massive geographical data and the path loss data within the service range of the base station including real data and simulation data, our approach uses the deep transfer learning method to construct a data-driven model for predicting the signal path loss of the base station. Moreover, the polar coordinate transformation is used to enhance the capacity of extracting the features of radio propagation, and a two-stream model is constructed to decouple geographic information and physical parameters of the base station for improving prediction accuracy. Using the prediction accuracy obtained between the measured and the model outputs as a measure of performance, the experimental results show that compared with the baseline model, our method significantly improves the accuracy of predicting signal path loss on testing data, which verifies the effectiveness of our method." @default.
- W4385485584 created "2023-08-03" @default.
- W4385485584 creator A5041442529 @default.
- W4385485584 creator A5054429473 @default.
- W4385485584 date "2023-03-17" @default.
- W4385485584 modified "2023-09-23" @default.
- W4385485584 title "A Big Data-Driven Deep Transfer Learning Approach for Path Loss Prediction in Mobile Communications" @default.
- W4385485584 cites W2085165892 @default.
- W4385485584 cites W2100005771 @default.
- W4385485584 cites W2171345554 @default.
- W4385485584 cites W2194775991 @default.
- W4385485584 cites W2767585020 @default.
- W4385485584 cites W2810482148 @default.
- W4385485584 cites W2892035503 @default.
- W4385485584 cites W2901008672 @default.
- W4385485584 cites W2902952649 @default.
- W4385485584 cites W2980441388 @default.
- W4385485584 cites W3000408141 @default.
- W4385485584 cites W3007943565 @default.
- W4385485584 cites W3011010806 @default.
- W4385485584 cites W3081154744 @default.
- W4385485584 doi "https://doi.org/10.1145/3594315.3594375" @default.
- W4385485584 hasPublicationYear "2023" @default.
- W4385485584 type Work @default.
- W4385485584 citedByCount "0" @default.
- W4385485584 crossrefType "proceedings-article" @default.
- W4385485584 hasAuthorship W4385485584A5041442529 @default.
- W4385485584 hasAuthorship W4385485584A5054429473 @default.
- W4385485584 hasConcept C124101348 @default.
- W4385485584 hasConcept C127413603 @default.
- W4385485584 hasConcept C146978453 @default.
- W4385485584 hasConcept C194273485 @default.
- W4385485584 hasConcept C199360897 @default.
- W4385485584 hasConcept C202311505 @default.
- W4385485584 hasConcept C204323151 @default.
- W4385485584 hasConcept C2777735758 @default.
- W4385485584 hasConcept C2779843651 @default.
- W4385485584 hasConcept C31258907 @default.
- W4385485584 hasConcept C41008148 @default.
- W4385485584 hasConcept C555944384 @default.
- W4385485584 hasConcept C68649174 @default.
- W4385485584 hasConcept C76155785 @default.
- W4385485584 hasConcept C76843793 @default.
- W4385485584 hasConcept C79403827 @default.
- W4385485584 hasConceptScore W4385485584C124101348 @default.
- W4385485584 hasConceptScore W4385485584C127413603 @default.
- W4385485584 hasConceptScore W4385485584C146978453 @default.
- W4385485584 hasConceptScore W4385485584C194273485 @default.
- W4385485584 hasConceptScore W4385485584C199360897 @default.
- W4385485584 hasConceptScore W4385485584C202311505 @default.
- W4385485584 hasConceptScore W4385485584C204323151 @default.
- W4385485584 hasConceptScore W4385485584C2777735758 @default.
- W4385485584 hasConceptScore W4385485584C2779843651 @default.
- W4385485584 hasConceptScore W4385485584C31258907 @default.
- W4385485584 hasConceptScore W4385485584C41008148 @default.
- W4385485584 hasConceptScore W4385485584C555944384 @default.
- W4385485584 hasConceptScore W4385485584C68649174 @default.
- W4385485584 hasConceptScore W4385485584C76155785 @default.
- W4385485584 hasConceptScore W4385485584C76843793 @default.
- W4385485584 hasConceptScore W4385485584C79403827 @default.
- W4385485584 hasLocation W43854855841 @default.
- W4385485584 hasOpenAccess W4385485584 @default.
- W4385485584 hasPrimaryLocation W43854855841 @default.
- W4385485584 hasRelatedWork W1640609104 @default.
- W4385485584 hasRelatedWork W2093048387 @default.
- W4385485584 hasRelatedWork W2100021775 @default.
- W4385485584 hasRelatedWork W2119404501 @default.
- W4385485584 hasRelatedWork W2154582320 @default.
- W4385485584 hasRelatedWork W2182682900 @default.
- W4385485584 hasRelatedWork W2763989852 @default.
- W4385485584 hasRelatedWork W2905361432 @default.
- W4385485584 hasRelatedWork W3203000479 @default.
- W4385485584 hasRelatedWork W2624760132 @default.
- W4385485584 isParatext "false" @default.
- W4385485584 isRetracted "false" @default.
- W4385485584 workType "article" @default.