Fingerprinting Indoor Positioning Based on Improved Sequential Deep Learning
Accurate indoor positioning is essential for many applications. However, current methods often fall short in complex environments due to signal fluctuations. We propose a new indoor positioning approach, that is, improved sequential deep learning (ISDL), to address this issue. First, we apply sequen...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/18/1/17 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589437168517120 |
|---|---|
| author | Dongfang Mao Haojie Lin Xuyang Lou |
| author_facet | Dongfang Mao Haojie Lin Xuyang Lou |
| author_sort | Dongfang Mao |
| collection | DOAJ |
| description | Accurate indoor positioning is essential for many applications. However, current methods often fall short in complex environments due to signal fluctuations. We propose a new indoor positioning approach, that is, improved sequential deep learning (ISDL), to address this issue. First, we apply sequential classification algorithms to progressively narrow the search space, reducing potential location regions into smaller neighborhoods. Next, we combine a deep neural network (DNN) with Weighted K-Nearest Neighbors (WKNN) to refine the final location prediction. Then, we validate our method using the publicly available <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>U</mi><mi>J</mi><mi>I</mi><mi>n</mi><mi>d</mi><mi>o</mi><mi>o</mi><mi>r</mi><mi>L</mi><mi>o</mi><mi>c</mi></mrow></semantics></math></inline-formula> dataset, demonstrating superior accuracy compared to existing methods. Specifically, we achieved 95% floor prediction accuracy and reduced the average positioning error to just 7.82 m. By combining sequential classification and the DNN-WKNN hybrid model, we achieve better localization in complex indoor environments. This system offers practical improvements for real-time location-based services and other applications requiring precise indoor positioning. |
| format | Article |
| id | doaj-art-e13a47af0d534b22ae2d4a87af84eda1 |
| institution | Kabale University |
| issn | 1999-4893 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj-art-e13a47af0d534b22ae2d4a87af84eda12025-01-24T13:17:29ZengMDPI AGAlgorithms1999-48932025-01-011811710.3390/a18010017Fingerprinting Indoor Positioning Based on Improved Sequential Deep LearningDongfang Mao0Haojie Lin1Xuyang Lou2College of Automation & College of Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing 210023, ChinaSchool of IoT Engineering, Jiangnan University, Wuxi 214122, ChinaSchool of IoT Engineering, Jiangnan University, Wuxi 214122, ChinaAccurate indoor positioning is essential for many applications. However, current methods often fall short in complex environments due to signal fluctuations. We propose a new indoor positioning approach, that is, improved sequential deep learning (ISDL), to address this issue. First, we apply sequential classification algorithms to progressively narrow the search space, reducing potential location regions into smaller neighborhoods. Next, we combine a deep neural network (DNN) with Weighted K-Nearest Neighbors (WKNN) to refine the final location prediction. Then, we validate our method using the publicly available <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>U</mi><mi>J</mi><mi>I</mi><mi>n</mi><mi>d</mi><mi>o</mi><mi>o</mi><mi>r</mi><mi>L</mi><mi>o</mi><mi>c</mi></mrow></semantics></math></inline-formula> dataset, demonstrating superior accuracy compared to existing methods. Specifically, we achieved 95% floor prediction accuracy and reduced the average positioning error to just 7.82 m. By combining sequential classification and the DNN-WKNN hybrid model, we achieve better localization in complex indoor environments. This system offers practical improvements for real-time location-based services and other applications requiring precise indoor positioning.https://www.mdpi.com/1999-4893/18/1/17indoor positioningsequential deep learningdeep neural networkweighted K-nearest neighbor |
| spellingShingle | Dongfang Mao Haojie Lin Xuyang Lou Fingerprinting Indoor Positioning Based on Improved Sequential Deep Learning Algorithms indoor positioning sequential deep learning deep neural network weighted K-nearest neighbor |
| title | Fingerprinting Indoor Positioning Based on Improved Sequential Deep Learning |
| title_full | Fingerprinting Indoor Positioning Based on Improved Sequential Deep Learning |
| title_fullStr | Fingerprinting Indoor Positioning Based on Improved Sequential Deep Learning |
| title_full_unstemmed | Fingerprinting Indoor Positioning Based on Improved Sequential Deep Learning |
| title_short | Fingerprinting Indoor Positioning Based on Improved Sequential Deep Learning |
| title_sort | fingerprinting indoor positioning based on improved sequential deep learning |
| topic | indoor positioning sequential deep learning deep neural network weighted K-nearest neighbor |
| url | https://www.mdpi.com/1999-4893/18/1/17 |
| work_keys_str_mv | AT dongfangmao fingerprintingindoorpositioningbasedonimprovedsequentialdeeplearning AT haojielin fingerprintingindoorpositioningbasedonimprovedsequentialdeeplearning AT xuyanglou fingerprintingindoorpositioningbasedonimprovedsequentialdeeplearning |