Few-Shot Learning in Wi-Fi-Based Indoor Positioning
This paper explores the use of few-shot learning in Wi-Fi-based indoor positioning, utilizing convolutional neural networks (CNNs) combined with meta-learning techniques to enhance the accuracy and efficiency of positioning systems. The focus is on addressing the challenge of limited labeled data, a...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-09-01
|
| Series: | Biomimetics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-7673/9/9/551 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850258408386592768 |
|---|---|
| author | Feng Xie Soi Hoi Lam Ming Xie Cheng Wang |
| author_facet | Feng Xie Soi Hoi Lam Ming Xie Cheng Wang |
| author_sort | Feng Xie |
| collection | DOAJ |
| description | This paper explores the use of few-shot learning in Wi-Fi-based indoor positioning, utilizing convolutional neural networks (CNNs) combined with meta-learning techniques to enhance the accuracy and efficiency of positioning systems. The focus is on addressing the challenge of limited labeled data, a prevalent issue in extensive indoor environments. The study explores various scenarios, comparing the performance of the base CNN and meta-learning models. The meta-learning approach involves few-shot learning tasks, such as three-way N-shot, five-way N-shot, etc., to enhance the model’s ability to generalize from limited data. The experiments were conducted across various scenarios, evaluating the performance of the models with different numbers of samples per class (K) after filtering by cosine similarity (FCS) during both the stages of data preprocessing and meta-learning. The scenarios included both base classes and novel classes, with and without meta-learning. The results indicated that the base CNN model achieved varying accuracy levels depending on the scenario and the number of samples per class retained after FCS. Meta-learning performed acceptably in scenarios with fewer samples, which are the distinct datasets pertaining to novel classes. With 20 samples per class, the base CNN achieved an accuracy of 0.80 during the pre-training stage, while meta-learning (three-way one-shot) achieved an accuracy of 0.78 on a new small dataset with novel classes. |
| format | Article |
| id | doaj-art-1e17f125233e422daff76213bcb68aa0 |
| institution | OA Journals |
| issn | 2313-7673 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomimetics |
| spelling | doaj-art-1e17f125233e422daff76213bcb68aa02025-08-20T01:56:10ZengMDPI AGBiomimetics2313-76732024-09-019955110.3390/biomimetics9090551Few-Shot Learning in Wi-Fi-Based Indoor PositioningFeng Xie0Soi Hoi Lam1Ming Xie2Cheng Wang3School of Information Science and Technology, Sanda University, Shanghai 201209, ChinaFaculty of Science and Technology, University of Macau, Macau 999078, ChinaSchool of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore 639798, SingaporeSchool of Information Science and Technology, Sanda University, Shanghai 201209, ChinaThis paper explores the use of few-shot learning in Wi-Fi-based indoor positioning, utilizing convolutional neural networks (CNNs) combined with meta-learning techniques to enhance the accuracy and efficiency of positioning systems. The focus is on addressing the challenge of limited labeled data, a prevalent issue in extensive indoor environments. The study explores various scenarios, comparing the performance of the base CNN and meta-learning models. The meta-learning approach involves few-shot learning tasks, such as three-way N-shot, five-way N-shot, etc., to enhance the model’s ability to generalize from limited data. The experiments were conducted across various scenarios, evaluating the performance of the models with different numbers of samples per class (K) after filtering by cosine similarity (FCS) during both the stages of data preprocessing and meta-learning. The scenarios included both base classes and novel classes, with and without meta-learning. The results indicated that the base CNN model achieved varying accuracy levels depending on the scenario and the number of samples per class retained after FCS. Meta-learning performed acceptably in scenarios with fewer samples, which are the distinct datasets pertaining to novel classes. With 20 samples per class, the base CNN achieved an accuracy of 0.80 during the pre-training stage, while meta-learning (three-way one-shot) achieved an accuracy of 0.78 on a new small dataset with novel classes.https://www.mdpi.com/2313-7673/9/9/551few-shot learningindoor positioningmeta-learningcosine similaritylimited labeled datafew-sample learning |
| spellingShingle | Feng Xie Soi Hoi Lam Ming Xie Cheng Wang Few-Shot Learning in Wi-Fi-Based Indoor Positioning Biomimetics few-shot learning indoor positioning meta-learning cosine similarity limited labeled data few-sample learning |
| title | Few-Shot Learning in Wi-Fi-Based Indoor Positioning |
| title_full | Few-Shot Learning in Wi-Fi-Based Indoor Positioning |
| title_fullStr | Few-Shot Learning in Wi-Fi-Based Indoor Positioning |
| title_full_unstemmed | Few-Shot Learning in Wi-Fi-Based Indoor Positioning |
| title_short | Few-Shot Learning in Wi-Fi-Based Indoor Positioning |
| title_sort | few shot learning in wi fi based indoor positioning |
| topic | few-shot learning indoor positioning meta-learning cosine similarity limited labeled data few-sample learning |
| url | https://www.mdpi.com/2313-7673/9/9/551 |
| work_keys_str_mv | AT fengxie fewshotlearninginwifibasedindoorpositioning AT soihoilam fewshotlearninginwifibasedindoorpositioning AT mingxie fewshotlearninginwifibasedindoorpositioning AT chengwang fewshotlearninginwifibasedindoorpositioning |