Forecasting of the Urban Area State Using Convolutional Neural Networks
Active development of modern cities requires not only efficient monitoring systems but furthermore forecasting systems that can predict future state of the urban area with high accuracy. In this work we present a method for urban area prediction based on geospatial activity of users in social network...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
FRUCT
2018-11-01
|
| Series: | Proceedings of the XXth Conference of Open Innovations Association FRUCT |
| Subjects: | |
| Online Access: | https://fruct.org/publications/fruct23/files/Muk2.pdf
|
| _version_ | 1818294029957201920 |
|---|---|
| author | Ksenia D. Mukhina Alexander A. Visheratin Gali-Ketema Mbogo Denis Nasonov |
| author_facet | Ksenia D. Mukhina Alexander A. Visheratin Gali-Ketema Mbogo Denis Nasonov |
| author_sort | Ksenia D. Mukhina |
| collection | DOAJ |
| description | Active development of modern cities requires not only efficient monitoring systems but furthermore forecasting systems that can predict future state of the urban area with high accuracy. In this work we present a method for urban area prediction based on geospatial activity of users in social network. One of the most popular social networks, Instagram, was taken as a source for spatial data and two large cities with different peculiarities of online activity – New York City, USA, and Saint Petersburg, Russia – were taken as target cities. We propose three different deep learning architectures that are able to solve a target problem and show that convolutional neural network based on three-dimensional convolution layers provides the best results with accuracy of 99%. |
| first_indexed | 2024-12-13T03:25:16Z |
| format | Article |
| id | doaj.art-e3060f8feb074de7a75010b338b85a03 |
| institution | Directory Open Access Journal |
| issn | 2305-7254 2343-0737 |
| language | English |
| last_indexed | 2024-12-13T03:25:16Z |
| publishDate | 2018-11-01 |
| publisher | FRUCT |
| record_format | Article |
| series | Proceedings of the XXth Conference of Open Innovations Association FRUCT |
| spelling | doaj.art-e3060f8feb074de7a75010b338b85a032022-12-22T00:01:16ZengFRUCTProceedings of the XXth Conference of Open Innovations Association FRUCT2305-72542343-07372018-11-0160223268275Forecasting of the Urban Area State Using Convolutional Neural NetworksKsenia D. Mukhina0Alexander A. Visheratin1Gali-Ketema Mbogo2Denis Nasonov3ITMO University, Saint Petersburg, RussiaITMO University, Saint Petersburg, RussiaITMO University, Saint Petersburg, RussiaITMO University, Saint Petersburg, RussiaActive development of modern cities requires not only efficient monitoring systems but furthermore forecasting systems that can predict future state of the urban area with high accuracy. In this work we present a method for urban area prediction based on geospatial activity of users in social network. One of the most popular social networks, Instagram, was taken as a source for spatial data and two large cities with different peculiarities of online activity – New York City, USA, and Saint Petersburg, Russia – were taken as target cities. We propose three different deep learning architectures that are able to solve a target problem and show that convolutional neural network based on three-dimensional convolution layers provides the best results with accuracy of 99%.https://fruct.org/publications/fruct23/files/Muk2.pdf convolutional neural networksocial networkInstagrampredictive modelurban forecasting |
| spellingShingle | Ksenia D. Mukhina Alexander A. Visheratin Gali-Ketema Mbogo Denis Nasonov Forecasting of the Urban Area State Using Convolutional Neural Networks Proceedings of the XXth Conference of Open Innovations Association FRUCT convolutional neural network social network predictive model urban forecasting |
| title | Forecasting of the Urban Area State Using Convolutional Neural Networks |
| title_full | Forecasting of the Urban Area State Using Convolutional Neural Networks |
| title_fullStr | Forecasting of the Urban Area State Using Convolutional Neural Networks |
| title_full_unstemmed | Forecasting of the Urban Area State Using Convolutional Neural Networks |
| title_short | Forecasting of the Urban Area State Using Convolutional Neural Networks |
| title_sort | forecasting of the urban area state using convolutional neural networks |
| topic | convolutional neural network social network predictive model urban forecasting |
| url | https://fruct.org/publications/fruct23/files/Muk2.pdf
|
| work_keys_str_mv | AT kseniadmukhina forecastingoftheurbanareastateusingconvolutionalneuralnetworks AT alexanderavisheratin forecastingoftheurbanareastateusingconvolutionalneuralnetworks AT galiketemambogo forecastingoftheurbanareastateusingconvolutionalneuralnetworks AT denisnasonov forecastingoftheurbanareastateusingconvolutionalneuralnetworks |