A Feed-Forward Neural Network Approach for Energy-Based Acoustic Source Localization
The localization of an acoustic source has attracted much attention in the scientific community, having been applied in several different real-life applications. At the same time, the use of neural networks in the acoustic source localization problem is not common; hence, this work aims to show thei...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Journal of Sensor and Actuator Networks |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2224-2708/10/2/29 |
| _version_ | 1827694510119845888 |
|---|---|
| author | Sérgio D. Correia Slavisa Tomic Marko Beko |
| author_facet | Sérgio D. Correia Slavisa Tomic Marko Beko |
| author_sort | Sérgio D. Correia |
| collection | DOAJ |
| description | The localization of an acoustic source has attracted much attention in the scientific community, having been applied in several different real-life applications. At the same time, the use of neural networks in the acoustic source localization problem is not common; hence, this work aims to show their potential use for this field of application. As such, the present work proposes a deep feed-forward neural network for solving the acoustic source localization problem based on energy measurements. Several network typologies are trained with ideal noise-free conditions, which simplifies the usual heavy training process where a low mean squared error is obtained. The networks are implemented, simulated, and compared with conventional algorithms, namely, deterministic and metaheuristic methods, and our results indicate improved performance when noise is added to the measurements. Therefore, the current developed scheme opens up a new horizon for energy-based acoustic localization, a field where machine learning algorithms have not been applied in the past. |
| first_indexed | 2024-03-10T12:06:00Z |
| format | Article |
| id | doaj.art-b634ce16b4ff40eb8c8da3aad9748522 |
| institution | Directory Open Access Journal |
| issn | 2224-2708 |
| language | English |
| last_indexed | 2024-03-10T12:06:00Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Sensor and Actuator Networks |
| spelling | doaj.art-b634ce16b4ff40eb8c8da3aad97485222023-11-21T16:36:14ZengMDPI AGJournal of Sensor and Actuator Networks2224-27082021-04-011022910.3390/jsan10020029A Feed-Forward Neural Network Approach for Energy-Based Acoustic Source LocalizationSérgio D. Correia0Slavisa Tomic1Marko Beko2COPELABS, Universidade Lusófona de Humanidades e Tecnologias, Campo Grande 376, 1749-024 Lisboa, PortugalCOPELABS, Universidade Lusófona de Humanidades e Tecnologias, Campo Grande 376, 1749-024 Lisboa, PortugalInstituto de Telecominicações, Instituto Superior Técnico, Universidade de Lisboa, 1049-001 Lisbon, PortugalThe localization of an acoustic source has attracted much attention in the scientific community, having been applied in several different real-life applications. At the same time, the use of neural networks in the acoustic source localization problem is not common; hence, this work aims to show their potential use for this field of application. As such, the present work proposes a deep feed-forward neural network for solving the acoustic source localization problem based on energy measurements. Several network typologies are trained with ideal noise-free conditions, which simplifies the usual heavy training process where a low mean squared error is obtained. The networks are implemented, simulated, and compared with conventional algorithms, namely, deterministic and metaheuristic methods, and our results indicate improved performance when noise is added to the measurements. Therefore, the current developed scheme opens up a new horizon for energy-based acoustic localization, a field where machine learning algorithms have not been applied in the past.https://www.mdpi.com/2224-2708/10/2/29acoustic localizationartificial intelligenceartificial neural networksdeep feed-forward networksdeep learningembedded computing |
| spellingShingle | Sérgio D. Correia Slavisa Tomic Marko Beko A Feed-Forward Neural Network Approach for Energy-Based Acoustic Source Localization Journal of Sensor and Actuator Networks acoustic localization artificial intelligence artificial neural networks deep feed-forward networks deep learning embedded computing |
| title | A Feed-Forward Neural Network Approach for Energy-Based Acoustic Source Localization |
| title_full | A Feed-Forward Neural Network Approach for Energy-Based Acoustic Source Localization |
| title_fullStr | A Feed-Forward Neural Network Approach for Energy-Based Acoustic Source Localization |
| title_full_unstemmed | A Feed-Forward Neural Network Approach for Energy-Based Acoustic Source Localization |
| title_short | A Feed-Forward Neural Network Approach for Energy-Based Acoustic Source Localization |
| title_sort | feed forward neural network approach for energy based acoustic source localization |
| topic | acoustic localization artificial intelligence artificial neural networks deep feed-forward networks deep learning embedded computing |
| url | https://www.mdpi.com/2224-2708/10/2/29 |
| work_keys_str_mv | AT sergiodcorreia afeedforwardneuralnetworkapproachforenergybasedacousticsourcelocalization AT slavisatomic afeedforwardneuralnetworkapproachforenergybasedacousticsourcelocalization AT markobeko afeedforwardneuralnetworkapproachforenergybasedacousticsourcelocalization AT sergiodcorreia feedforwardneuralnetworkapproachforenergybasedacousticsourcelocalization AT slavisatomic feedforwardneuralnetworkapproachforenergybasedacousticsourcelocalization AT markobeko feedforwardneuralnetworkapproachforenergybasedacousticsourcelocalization |