SubvectorS_Geo: A Neural-Network-Based IPv6 Geolocation Algorithm
IPv6 geolocation is necessary for many location-based Internet services. However, the accuracy of the current IPv6 geolocation methods including machine-learning-based or deep-learning-based location algorithms are unsatisfactory for users. Strong geographic correlation is observed for measurement p...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/2/754 |
| _version_ | 1827629151321849856 |
|---|---|
| author | Zhaorui Ma Xinhao Hu Shicheng Zhang Na Li Fenlin Liu Qinglei Zhou Hongjian Wang Guangwu Hu Qilin Dong |
| author_facet | Zhaorui Ma Xinhao Hu Shicheng Zhang Na Li Fenlin Liu Qinglei Zhou Hongjian Wang Guangwu Hu Qilin Dong |
| author_sort | Zhaorui Ma |
| collection | DOAJ |
| description | IPv6 geolocation is necessary for many location-based Internet services. However, the accuracy of the current IPv6 geolocation methods including machine-learning-based or deep-learning-based location algorithms are unsatisfactory for users. Strong geographic correlation is observed for measurement path features close to the target IP, so previous methods focused more on stable paths in the vicinity of the probe. Based on this, this paper proposes a new IPv6 geolocation algorithm, SubvectorS_Geo, which is mainly divided into three steps: firstly, it filters geographically relevant routing feature codes layer by layer to approximate the fine-grained trusted region of the target; secondly, it extracts delay vectors into the trusted region; thirdly, it evaluates the vector similarity to determine the final target geolocation information. The final experiments show that the median error distance range is 7.025 km to 9.709 km on three real datasets (Shanghai, New York State, and Tokyo). Compared with the advanced method, the median distance error distance is reduced by at least 6.8% and the average error distance is reduced by at least 9.2%. |
| first_indexed | 2024-03-09T13:45:37Z |
| format | Article |
| id | doaj.art-d5b588e5fb7f447e9faed0f6ca7cb714 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T13:45:37Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-d5b588e5fb7f447e9faed0f6ca7cb7142023-11-30T21:00:58ZengMDPI AGApplied Sciences2076-34172023-01-0113275410.3390/app13020754SubvectorS_Geo: A Neural-Network-Based IPv6 Geolocation AlgorithmZhaorui Ma0Xinhao Hu1Shicheng Zhang2Na Li3Fenlin Liu4Qinglei Zhou5Hongjian Wang6Guangwu Hu7Qilin Dong8State Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou 450052, ChinaSchool of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaSchool of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaState Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou 450052, ChinaState Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou 450052, ChinaState Key Laboratory of Mathematical Engineering and Advanced Computing, Zhengzhou 450052, ChinaSchool of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaShenzhen Institute of Information Technology, School of Computer Sciences, Shenzhen 518172, ChinaSchool of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, ChinaIPv6 geolocation is necessary for many location-based Internet services. However, the accuracy of the current IPv6 geolocation methods including machine-learning-based or deep-learning-based location algorithms are unsatisfactory for users. Strong geographic correlation is observed for measurement path features close to the target IP, so previous methods focused more on stable paths in the vicinity of the probe. Based on this, this paper proposes a new IPv6 geolocation algorithm, SubvectorS_Geo, which is mainly divided into three steps: firstly, it filters geographically relevant routing feature codes layer by layer to approximate the fine-grained trusted region of the target; secondly, it extracts delay vectors into the trusted region; thirdly, it evaluates the vector similarity to determine the final target geolocation information. The final experiments show that the median error distance range is 7.025 km to 9.709 km on three real datasets (Shanghai, New York State, and Tokyo). Compared with the advanced method, the median distance error distance is reduced by at least 6.8% and the average error distance is reduced by at least 9.2%.https://www.mdpi.com/2076-3417/13/2/754IPv6 geolocationnetwork mappingneural network |
| spellingShingle | Zhaorui Ma Xinhao Hu Shicheng Zhang Na Li Fenlin Liu Qinglei Zhou Hongjian Wang Guangwu Hu Qilin Dong SubvectorS_Geo: A Neural-Network-Based IPv6 Geolocation Algorithm Applied Sciences IPv6 geolocation network mapping neural network |
| title | SubvectorS_Geo: A Neural-Network-Based IPv6 Geolocation Algorithm |
| title_full | SubvectorS_Geo: A Neural-Network-Based IPv6 Geolocation Algorithm |
| title_fullStr | SubvectorS_Geo: A Neural-Network-Based IPv6 Geolocation Algorithm |
| title_full_unstemmed | SubvectorS_Geo: A Neural-Network-Based IPv6 Geolocation Algorithm |
| title_short | SubvectorS_Geo: A Neural-Network-Based IPv6 Geolocation Algorithm |
| title_sort | subvectors geo a neural network based ipv6 geolocation algorithm |
| topic | IPv6 geolocation network mapping neural network |
| url | https://www.mdpi.com/2076-3417/13/2/754 |
| work_keys_str_mv | AT zhaoruima subvectorsgeoaneuralnetworkbasedipv6geolocationalgorithm AT xinhaohu subvectorsgeoaneuralnetworkbasedipv6geolocationalgorithm AT shichengzhang subvectorsgeoaneuralnetworkbasedipv6geolocationalgorithm AT nali subvectorsgeoaneuralnetworkbasedipv6geolocationalgorithm AT fenlinliu subvectorsgeoaneuralnetworkbasedipv6geolocationalgorithm AT qingleizhou subvectorsgeoaneuralnetworkbasedipv6geolocationalgorithm AT hongjianwang subvectorsgeoaneuralnetworkbasedipv6geolocationalgorithm AT guangwuhu subvectorsgeoaneuralnetworkbasedipv6geolocationalgorithm AT qilindong subvectorsgeoaneuralnetworkbasedipv6geolocationalgorithm |