Wireless Sensor Networks Focusing on Predicting Average Localization Error through Machine Learning Applications
In wireless sensor networks (WSNs), effective localization is crucial for applications like target tracking, environmental monitoring, and asset management. Accurately predicting the average localization error (ALE) is essential for improving sensor performance and reliability. This study proposes u...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Bilijipub publisher
2024-09-01
|
| Series: | Journal of Artificial Intelligence and System Modelling |
| Subjects: | |
| Online Access: | https://jaism.bilijipub.com/article_206720_29909c8491193a7833b2a1a1362e37e8.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849404805534973952 |
|---|---|
| author | Ioanna Gounari Mattheos Kanzilieris |
| author_facet | Ioanna Gounari Mattheos Kanzilieris |
| author_sort | Ioanna Gounari |
| collection | DOAJ |
| description | In wireless sensor networks (WSNs), effective localization is crucial for applications like target tracking, environmental monitoring, and asset management. Accurately predicting the average localization error (ALE) is essential for improving sensor performance and reliability. This study proposes using machine learning (ML) techniques to predict ALE in WSNs and compares the performance of different models. The models evaluated include Decision Tree Regression (DTR), Histogram Gradient Boosting Regression (HGBR), and their combined versions with Random Trees Histogram (RTH), referred to as DTRT and HGRT, respectively. Extensive testing showed that the DTRT model outperformed others in predicting ALE. During training, the DTRT model achieved an R² value of 0.990, indicating its superior prediction accuracy. In comparison, the HGRT model had an R² value of 0.975, while the HGB and DTR models scored 0.969 and 0.956, respectively. These findings highlight the competitive advantage of the DTRT model in this context. This research offers valuable insights into the effectiveness of different ML algorithms for predicting ALE in WSNs. By demonstrating the superior performance of DTRT, the study guides practitioners and researchers in selecting models that enhance localization accuracy, ultimately improving the overall functionality of WSNs. |
| format | Article |
| id | doaj-art-18bfdbd7fbaf46bf9e46cebc5d5e78f0 |
| institution | Kabale University |
| issn | 3041-850X |
| language | English |
| publishDate | 2024-09-01 |
| publisher | Bilijipub publisher |
| record_format | Article |
| series | Journal of Artificial Intelligence and System Modelling |
| spelling | doaj-art-18bfdbd7fbaf46bf9e46cebc5d5e78f02025-08-20T03:36:53ZengBilijipub publisherJournal of Artificial Intelligence and System Modelling3041-850X2024-09-01020310311710.22034/jaism.2024.474005.1055206720Wireless Sensor Networks Focusing on Predicting Average Localization Error through Machine Learning ApplicationsIoanna Gounari0Mattheos Kanzilieris1Department of Computer Engineering and Informatics, University of Patras, Patras, 26504, GreeceDepartment of Informatics and Telecommunications, University Of Thessaly, Lamia, 35131, GreeceIn wireless sensor networks (WSNs), effective localization is crucial for applications like target tracking, environmental monitoring, and asset management. Accurately predicting the average localization error (ALE) is essential for improving sensor performance and reliability. This study proposes using machine learning (ML) techniques to predict ALE in WSNs and compares the performance of different models. The models evaluated include Decision Tree Regression (DTR), Histogram Gradient Boosting Regression (HGBR), and their combined versions with Random Trees Histogram (RTH), referred to as DTRT and HGRT, respectively. Extensive testing showed that the DTRT model outperformed others in predicting ALE. During training, the DTRT model achieved an R² value of 0.990, indicating its superior prediction accuracy. In comparison, the HGRT model had an R² value of 0.975, while the HGB and DTR models scored 0.969 and 0.956, respectively. These findings highlight the competitive advantage of the DTRT model in this context. This research offers valuable insights into the effectiveness of different ML algorithms for predicting ALE in WSNs. By demonstrating the superior performance of DTRT, the study guides practitioners and researchers in selecting models that enhance localization accuracy, ultimately improving the overall functionality of WSNs.https://jaism.bilijipub.com/article_206720_29909c8491193a7833b2a1a1362e37e8.pdfhistogram gradient boosting regressionwireless sensor networksdecision tree regressionred-tailed hawk algorithmmachine learning |
| spellingShingle | Ioanna Gounari Mattheos Kanzilieris Wireless Sensor Networks Focusing on Predicting Average Localization Error through Machine Learning Applications Journal of Artificial Intelligence and System Modelling histogram gradient boosting regression wireless sensor networks decision tree regression red-tailed hawk algorithm machine learning |
| title | Wireless Sensor Networks Focusing on Predicting Average Localization Error through Machine Learning Applications |
| title_full | Wireless Sensor Networks Focusing on Predicting Average Localization Error through Machine Learning Applications |
| title_fullStr | Wireless Sensor Networks Focusing on Predicting Average Localization Error through Machine Learning Applications |
| title_full_unstemmed | Wireless Sensor Networks Focusing on Predicting Average Localization Error through Machine Learning Applications |
| title_short | Wireless Sensor Networks Focusing on Predicting Average Localization Error through Machine Learning Applications |
| title_sort | wireless sensor networks focusing on predicting average localization error through machine learning applications |
| topic | histogram gradient boosting regression wireless sensor networks decision tree regression red-tailed hawk algorithm machine learning |
| url | https://jaism.bilijipub.com/article_206720_29909c8491193a7833b2a1a1362e37e8.pdf |
| work_keys_str_mv | AT ioannagounari wirelesssensornetworksfocusingonpredictingaveragelocalizationerrorthroughmachinelearningapplications AT mattheoskanzilieris wirelesssensornetworksfocusingonpredictingaveragelocalizationerrorthroughmachinelearningapplications |