Data prediction model in wireless sensor networks based on bidirectional LSTM
Abstract The data collected by the wireless sensor nodes often has some spatial or temporal redundancy, and the redundant data impose unnecessary burdens on both the nodes and networks. Data prediction is helpful to improve data quality and reduce the unnecessary data transmission. However, the curr...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2019-08-01
|
| Series: | EURASIP Journal on Wireless Communications and Networking |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s13638-019-1511-4 |
| _version_ | 1818160002704080896 |
|---|---|
| author | Hongju Cheng Zhe Xie Leihuo Wu Zhiyong Yu Ruixing Li |
| author_facet | Hongju Cheng Zhe Xie Leihuo Wu Zhiyong Yu Ruixing Li |
| author_sort | Hongju Cheng |
| collection | DOAJ |
| description | Abstract The data collected by the wireless sensor nodes often has some spatial or temporal redundancy, and the redundant data impose unnecessary burdens on both the nodes and networks. Data prediction is helpful to improve data quality and reduce the unnecessary data transmission. However, the current data prediction methods of wireless sensor networks seldom consider how to utilize the spatial-temporal correlation among the sensory data. This paper has proposed a new data prediction method multi-node multi-feature (MNMF) based on bidirectional long short-term memory (LSTM) network. Firstly, the data quality is improved by quartile method and wavelet threshold denoising. Then, the bidirectional LSTM network is used to extract and learn the abstract features of sensory data. Finally, the abstract features are used in the data prediction by adopting the merge layer of the neural network. The experimental results show that the proposed MNMF model has better performance compared with the other methods in many evaluation indicators. |
| first_indexed | 2024-12-11T15:54:57Z |
| format | Article |
| id | doaj.art-172b45c06c7d4b938811e536e1d8b4d0 |
| institution | Directory Open Access Journal |
| issn | 1687-1499 |
| language | English |
| last_indexed | 2024-12-11T15:54:57Z |
| publishDate | 2019-08-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Wireless Communications and Networking |
| spelling | doaj.art-172b45c06c7d4b938811e536e1d8b4d02022-12-22T00:59:28ZengSpringerOpenEURASIP Journal on Wireless Communications and Networking1687-14992019-08-012019111210.1186/s13638-019-1511-4Data prediction model in wireless sensor networks based on bidirectional LSTMHongju Cheng0Zhe Xie1Leihuo Wu2Zhiyong Yu3Ruixing Li4College of Mathematics and Computer Science, Fuzhou UniversityCollege of Mathematics and Computer Science, Fuzhou UniversityCollege of Mathematics and Computer Science, Fuzhou UniversityCollege of Mathematics and Computer Science, Fuzhou UniversityFujian College Applied Engineering Centre of Internet of Things, Minjiang Teachers CollegeAbstract The data collected by the wireless sensor nodes often has some spatial or temporal redundancy, and the redundant data impose unnecessary burdens on both the nodes and networks. Data prediction is helpful to improve data quality and reduce the unnecessary data transmission. However, the current data prediction methods of wireless sensor networks seldom consider how to utilize the spatial-temporal correlation among the sensory data. This paper has proposed a new data prediction method multi-node multi-feature (MNMF) based on bidirectional long short-term memory (LSTM) network. Firstly, the data quality is improved by quartile method and wavelet threshold denoising. Then, the bidirectional LSTM network is used to extract and learn the abstract features of sensory data. Finally, the abstract features are used in the data prediction by adopting the merge layer of the neural network. The experimental results show that the proposed MNMF model has better performance compared with the other methods in many evaluation indicators.http://link.springer.com/article/10.1186/s13638-019-1511-4Wireless sensor networksData predictionSpatial-temporal correlationLSTM |
| spellingShingle | Hongju Cheng Zhe Xie Leihuo Wu Zhiyong Yu Ruixing Li Data prediction model in wireless sensor networks based on bidirectional LSTM EURASIP Journal on Wireless Communications and Networking Wireless sensor networks Data prediction Spatial-temporal correlation LSTM |
| title | Data prediction model in wireless sensor networks based on bidirectional LSTM |
| title_full | Data prediction model in wireless sensor networks based on bidirectional LSTM |
| title_fullStr | Data prediction model in wireless sensor networks based on bidirectional LSTM |
| title_full_unstemmed | Data prediction model in wireless sensor networks based on bidirectional LSTM |
| title_short | Data prediction model in wireless sensor networks based on bidirectional LSTM |
| title_sort | data prediction model in wireless sensor networks based on bidirectional lstm |
| topic | Wireless sensor networks Data prediction Spatial-temporal correlation LSTM |
| url | http://link.springer.com/article/10.1186/s13638-019-1511-4 |
| work_keys_str_mv | AT hongjucheng datapredictionmodelinwirelesssensornetworksbasedonbidirectionallstm AT zhexie datapredictionmodelinwirelesssensornetworksbasedonbidirectionallstm AT leihuowu datapredictionmodelinwirelesssensornetworksbasedonbidirectionallstm AT zhiyongyu datapredictionmodelinwirelesssensornetworksbasedonbidirectionallstm AT ruixingli datapredictionmodelinwirelesssensornetworksbasedonbidirectionallstm |