Deep Learning Inter-city Roads Conditions in East Africa for Infrastructure Prioritization using Satellite Imagery and Mobile Data
Traditional survey methods for gathering information, such as questionnaires and field visits, have long been used in East Africa to evaluate road conditions and prioritize their development. These surveys are time-consuming, expensive, and vulnerable to human error. Road building and maintenance,...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
South African Institute of Electrical Engineers
2024-07-01
|
| Series: | Africa Research Journal |
| Subjects: | |
| Online Access: | https://journals.uj.ac.za/index.php/SAIEE/article/view/623 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841550106468286464 |
|---|---|
| author | Davy Uwizera Prof. Patrick McSharry Charles Ruranga |
| author_facet | Davy Uwizera Prof. Patrick McSharry Charles Ruranga |
| author_sort | Davy Uwizera |
| collection | DOAJ |
| description |
Traditional survey methods for gathering information, such as questionnaires and field visits, have long been used in East Africa to evaluate road conditions and prioritize their development. These surveys are time-consuming, expensive, and vulnerable to human error. Road building and maintenance, on the other hand, has long experienced corruption due to a lack of accountability and validation of conventional approaches to determining which areas to prioritize. With the digital revolution, a lot of data is generated daily such as call detail record (CDR), that is likely to contain useful proxy data for spatial mobility distribution across different routes. In this research we focus on satellite imagery data with applications in East Africa and Google Maps suggested inter-city roads to assess road conditions and provide an approach for infrastructure prioritization given mobility patterns between cities. With increased urban population, East African cities have been expanding in multiple directions affecting the overall distribution of residential areas and consequently likely to impact the mobility trends across cities. We introduce a novel approach for infrastructure prioritization using deep learning and big data analytics. We apply deep learning to satellite imagery, to assess roads conditions by area and big data analytics to CDR data, to rank which ones could be prioritized for construction given mobility trends. Among deep learning models considered for roads condition classification, EfficientNet-B3 outperforms them and achieves accuracy of 99\%.
|
| format | Article |
| id | doaj-art-5efcb3b93f65444695cafb52dfaad012 |
| institution | Kabale University |
| issn | 1991-1696 |
| language | English |
| publishDate | 2024-07-01 |
| publisher | South African Institute of Electrical Engineers |
| record_format | Article |
| series | Africa Research Journal |
| spelling | doaj-art-5efcb3b93f65444695cafb52dfaad0122025-01-10T08:58:38ZengSouth African Institute of Electrical EngineersAfrica Research Journal1991-16962024-07-011141Deep Learning Inter-city Roads Conditions in East Africa for Infrastructure Prioritization using Satellite Imagery and Mobile DataDavy Uwizera0https://orcid.org/0000-0003-0858-6520Prof. Patrick McSharry1https://orcid.org/0000-0003-4663-970XCharles Ruranga2https://orcid.org/0000-0002-5456-7454a:1:{s:5:"en_US";s:43:"Africa Center of Excellence in Data Science";}University of OxfordAfrica Center of Excellence in Data Science (University of Rwanda) Traditional survey methods for gathering information, such as questionnaires and field visits, have long been used in East Africa to evaluate road conditions and prioritize their development. These surveys are time-consuming, expensive, and vulnerable to human error. Road building and maintenance, on the other hand, has long experienced corruption due to a lack of accountability and validation of conventional approaches to determining which areas to prioritize. With the digital revolution, a lot of data is generated daily such as call detail record (CDR), that is likely to contain useful proxy data for spatial mobility distribution across different routes. In this research we focus on satellite imagery data with applications in East Africa and Google Maps suggested inter-city roads to assess road conditions and provide an approach for infrastructure prioritization given mobility patterns between cities. With increased urban population, East African cities have been expanding in multiple directions affecting the overall distribution of residential areas and consequently likely to impact the mobility trends across cities. We introduce a novel approach for infrastructure prioritization using deep learning and big data analytics. We apply deep learning to satellite imagery, to assess roads conditions by area and big data analytics to CDR data, to rank which ones could be prioritized for construction given mobility trends. Among deep learning models considered for roads condition classification, EfficientNet-B3 outperforms them and achieves accuracy of 99\%. https://journals.uj.ac.za/index.php/SAIEE/article/view/623Deep LearningMobile-dataClassificationVision-recognitionBig-dataSattelite-imagery |
| spellingShingle | Davy Uwizera Prof. Patrick McSharry Charles Ruranga Deep Learning Inter-city Roads Conditions in East Africa for Infrastructure Prioritization using Satellite Imagery and Mobile Data Africa Research Journal Deep Learning Mobile-data Classification Vision-recognition Big-data Sattelite-imagery |
| title | Deep Learning Inter-city Roads Conditions in East Africa for Infrastructure Prioritization using Satellite Imagery and Mobile Data |
| title_full | Deep Learning Inter-city Roads Conditions in East Africa for Infrastructure Prioritization using Satellite Imagery and Mobile Data |
| title_fullStr | Deep Learning Inter-city Roads Conditions in East Africa for Infrastructure Prioritization using Satellite Imagery and Mobile Data |
| title_full_unstemmed | Deep Learning Inter-city Roads Conditions in East Africa for Infrastructure Prioritization using Satellite Imagery and Mobile Data |
| title_short | Deep Learning Inter-city Roads Conditions in East Africa for Infrastructure Prioritization using Satellite Imagery and Mobile Data |
| title_sort | deep learning inter city roads conditions in east africa for infrastructure prioritization using satellite imagery and mobile data |
| topic | Deep Learning Mobile-data Classification Vision-recognition Big-data Sattelite-imagery |
| url | https://journals.uj.ac.za/index.php/SAIEE/article/view/623 |
| work_keys_str_mv | AT davyuwizera deeplearningintercityroadsconditionsineastafricaforinfrastructureprioritizationusingsatelliteimageryandmobiledata AT profpatrickmcsharry deeplearningintercityroadsconditionsineastafricaforinfrastructureprioritizationusingsatelliteimageryandmobiledata AT charlesruranga deeplearningintercityroadsconditionsineastafricaforinfrastructureprioritizationusingsatelliteimageryandmobiledata |