DeepFeat: Robust Large-Scale Multi-Features Outdoor Localization in LTE Networks Using Deep Learning
In today’s Telecom market, Telecom operators find a big value in introducing valuable services to users based on their location, both for emergency and ordinary situations. This drives the research for outdoor localization using different wireless technologies. Long Term Evolution (LTE) i...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9668934/ |
| _version_ | 1827288140619972608 |
|---|---|
| author | Amel Mohamed Mohamed Tharwat Mohamed Magdy Tarek Abubakr Omar Nasr Moustafa Youssef |
| author_facet | Amel Mohamed Mohamed Tharwat Mohamed Magdy Tarek Abubakr Omar Nasr Moustafa Youssef |
| author_sort | Amel Mohamed |
| collection | DOAJ |
| description | In today’s Telecom market, Telecom operators find a big value in introducing valuable services to users based on their location, both for emergency and ordinary situations. This drives the research for outdoor localization using different wireless technologies. Long Term Evolution (LTE) is the dominant wireless technology for outdoor cellular networks. This paper introduces DeepFeat: A deep-learning-based framework for outdoor localization using a rich features set in LTE networks. DeepFeat works on the mobile operator side, and it leverages many mobile network features and other metrics to achieve high localization accuracy. In order to reduce computation and complexity, we introduce a feature selection module to choose the most appropriate features as inputs to the deep learning model. This module reduces the computation and complexity by around 20.6% while enhancing the system’s accuracy. The feature selection module uses correlation and Chi-squared algorithms to reduce the feature set to 12 inputs only regardless of the area size. In order to enhance the accuracy of DeepFeat, a One-to-Many augmenter is introduced to extend the dataset and improve the system’s overall performance. The results show the impact of the proper features selection adopted by DeepFeat on the system’s performance. DeepFeat achieved median localization accuracy of 13.179m in an outdoor environment in a mid-scale area of 6.27Km<sup>2</sup>. In a large-scale area of 45Km<sup>2</sup>, the median localization accuracy is 13.7m. DeepFeat was compared to other state-of-the-art deep-learning-based localization systems that leverage a small number of features. We show that using DeepFeat’s carefully selected features set enhances the localization accuracy compared to the state-of-the-art systems by at least 286%. |
| first_indexed | 2024-04-24T11:24:44Z |
| format | Article |
| id | doaj.art-9a47275d18ae4e3080b99a9956e3e98c |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T11:24:44Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-9a47275d18ae4e3080b99a9956e3e98c2024-04-10T23:00:06ZengIEEEIEEE Access2169-35362022-01-01103400341410.1109/ACCESS.2022.31402929668934DeepFeat: Robust Large-Scale Multi-Features Outdoor Localization in LTE Networks Using Deep LearningAmel Mohamed0https://orcid.org/0000-0001-9098-3116Mohamed Tharwat1Mohamed Magdy2https://orcid.org/0000-0002-7142-8536Tarek Abubakr3Omar Nasr4Moustafa Youssef5Department of Electronics and Electrical Communications Engineering, Canadian International College, Cairo, EgyptDepartment of Technology, Vodafone Egypt, Cairo, EgyptDomestic Wholesale Business Unit, Telecom Egypt, Cairo, EgyptTechnical Department, Etisalat Misr, New Cairo, EgyptDepartment of Electronics and Electrical Communications Engineering, Cairo University, Giza, EgyptDepartment of Computer Science and Engineering, The American University in Cairo, New Cairo, EgyptIn today’s Telecom market, Telecom operators find a big value in introducing valuable services to users based on their location, both for emergency and ordinary situations. This drives the research for outdoor localization using different wireless technologies. Long Term Evolution (LTE) is the dominant wireless technology for outdoor cellular networks. This paper introduces DeepFeat: A deep-learning-based framework for outdoor localization using a rich features set in LTE networks. DeepFeat works on the mobile operator side, and it leverages many mobile network features and other metrics to achieve high localization accuracy. In order to reduce computation and complexity, we introduce a feature selection module to choose the most appropriate features as inputs to the deep learning model. This module reduces the computation and complexity by around 20.6% while enhancing the system’s accuracy. The feature selection module uses correlation and Chi-squared algorithms to reduce the feature set to 12 inputs only regardless of the area size. In order to enhance the accuracy of DeepFeat, a One-to-Many augmenter is introduced to extend the dataset and improve the system’s overall performance. The results show the impact of the proper features selection adopted by DeepFeat on the system’s performance. DeepFeat achieved median localization accuracy of 13.179m in an outdoor environment in a mid-scale area of 6.27Km<sup>2</sup>. In a large-scale area of 45Km<sup>2</sup>, the median localization accuracy is 13.7m. DeepFeat was compared to other state-of-the-art deep-learning-based localization systems that leverage a small number of features. We show that using DeepFeat’s carefully selected features set enhances the localization accuracy compared to the state-of-the-art systems by at least 286%.https://ieeexplore.ieee.org/document/9668934/Data augmentationdeep learninglong-term-evolution localizationmulti-features localizationoutdoor localization |
| spellingShingle | Amel Mohamed Mohamed Tharwat Mohamed Magdy Tarek Abubakr Omar Nasr Moustafa Youssef DeepFeat: Robust Large-Scale Multi-Features Outdoor Localization in LTE Networks Using Deep Learning IEEE Access Data augmentation deep learning long-term-evolution localization multi-features localization outdoor localization |
| title | DeepFeat: Robust Large-Scale Multi-Features Outdoor Localization in LTE Networks Using Deep Learning |
| title_full | DeepFeat: Robust Large-Scale Multi-Features Outdoor Localization in LTE Networks Using Deep Learning |
| title_fullStr | DeepFeat: Robust Large-Scale Multi-Features Outdoor Localization in LTE Networks Using Deep Learning |
| title_full_unstemmed | DeepFeat: Robust Large-Scale Multi-Features Outdoor Localization in LTE Networks Using Deep Learning |
| title_short | DeepFeat: Robust Large-Scale Multi-Features Outdoor Localization in LTE Networks Using Deep Learning |
| title_sort | deepfeat robust large scale multi features outdoor localization in lte networks using deep learning |
| topic | Data augmentation deep learning long-term-evolution localization multi-features localization outdoor localization |
| url | https://ieeexplore.ieee.org/document/9668934/ |
| work_keys_str_mv | AT amelmohamed deepfeatrobustlargescalemultifeaturesoutdoorlocalizationinltenetworksusingdeeplearning AT mohamedtharwat deepfeatrobustlargescalemultifeaturesoutdoorlocalizationinltenetworksusingdeeplearning AT mohamedmagdy deepfeatrobustlargescalemultifeaturesoutdoorlocalizationinltenetworksusingdeeplearning AT tarekabubakr deepfeatrobustlargescalemultifeaturesoutdoorlocalizationinltenetworksusingdeeplearning AT omarnasr deepfeatrobustlargescalemultifeaturesoutdoorlocalizationinltenetworksusingdeeplearning AT moustafayoussef deepfeatrobustlargescalemultifeaturesoutdoorlocalizationinltenetworksusingdeeplearning |