Improved Salp Swarm Optimization Algorithm: Application in Feature Weighting for Blind Modulation Identification
In modulation identification issues, like in any other classification problem, the performance of the classification task is significantly impacted by the feature characteristics. Feature weighting boosts the performance of machine learning algorithms, particularly the class of instance-based learni...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/10/16/2002 |
| _version_ | 1797524096164036608 |
|---|---|
| author | Sarra Ben Chaabane Akram Belazi Sofiane Kharbech Ammar Bouallegue Laurent Clavier |
| author_facet | Sarra Ben Chaabane Akram Belazi Sofiane Kharbech Ammar Bouallegue Laurent Clavier |
| author_sort | Sarra Ben Chaabane |
| collection | DOAJ |
| description | In modulation identification issues, like in any other classification problem, the performance of the classification task is significantly impacted by the feature characteristics. Feature weighting boosts the performance of machine learning algorithms, particularly the class of instance-based learning algorithms such as the Minimum Distance (MD) classifier, in which the distance measure is highly sensitive to the magnitude of features. In this paper, we propose an improved version of the Salp Swarm optimization Algorithm (SSA), called ISSA, that will be applied to optimize feature weights for an MD classifier. The aim is to improve the performance of a blind digital modulation detection approach in the context of multiple-antenna systems. The improvements introduced to SSA mainly rely on the opposition-based learning technique. Computer simulations show that the ISSA outperforms the SSA as well as the algorithms that derive from it. The ISSA also exhibits the best performance once it is applied for feature weighting in the above context. |
| first_indexed | 2024-03-10T08:51:28Z |
| format | Article |
| id | doaj.art-3e0c24585b954f2092f22070d4cf7a2e |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T08:51:28Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-3e0c24585b954f2092f22070d4cf7a2e2023-11-22T07:25:45ZengMDPI AGElectronics2079-92922021-08-011016200210.3390/electronics10162002Improved Salp Swarm Optimization Algorithm: Application in Feature Weighting for Blind Modulation IdentificationSarra Ben Chaabane0Akram Belazi1Sofiane Kharbech2Ammar Bouallegue3Laurent Clavier4Laboratory Sys’Com-ENIT (LR-99-ES21), Tunis El Manar University, Tunis 1002, TunisiaLaboratory RISC-ENIT (LR-16-ES07), Tunis El Manar University, Tunis 1002, TunisiaLaboratory Sys’Com-ENIT (LR-99-ES21), Tunis El Manar University, Tunis 1002, TunisiaLaboratory Sys’Com-ENIT (LR-99-ES21), Tunis El Manar University, Tunis 1002, TunisiaCentre for Digital Systems, IMT Lille Douai, Institut Mines-Télécom, University of Lille, F-59000 Lille, FranceIn modulation identification issues, like in any other classification problem, the performance of the classification task is significantly impacted by the feature characteristics. Feature weighting boosts the performance of machine learning algorithms, particularly the class of instance-based learning algorithms such as the Minimum Distance (MD) classifier, in which the distance measure is highly sensitive to the magnitude of features. In this paper, we propose an improved version of the Salp Swarm optimization Algorithm (SSA), called ISSA, that will be applied to optimize feature weights for an MD classifier. The aim is to improve the performance of a blind digital modulation detection approach in the context of multiple-antenna systems. The improvements introduced to SSA mainly rely on the opposition-based learning technique. Computer simulations show that the ISSA outperforms the SSA as well as the algorithms that derive from it. The ISSA also exhibits the best performance once it is applied for feature weighting in the above context.https://www.mdpi.com/2079-9292/10/16/2002SSA optimization algorithmmachine learningfeature weightingmodulation identification |
| spellingShingle | Sarra Ben Chaabane Akram Belazi Sofiane Kharbech Ammar Bouallegue Laurent Clavier Improved Salp Swarm Optimization Algorithm: Application in Feature Weighting for Blind Modulation Identification Electronics SSA optimization algorithm machine learning feature weighting modulation identification |
| title | Improved Salp Swarm Optimization Algorithm: Application in Feature Weighting for Blind Modulation Identification |
| title_full | Improved Salp Swarm Optimization Algorithm: Application in Feature Weighting for Blind Modulation Identification |
| title_fullStr | Improved Salp Swarm Optimization Algorithm: Application in Feature Weighting for Blind Modulation Identification |
| title_full_unstemmed | Improved Salp Swarm Optimization Algorithm: Application in Feature Weighting for Blind Modulation Identification |
| title_short | Improved Salp Swarm Optimization Algorithm: Application in Feature Weighting for Blind Modulation Identification |
| title_sort | improved salp swarm optimization algorithm application in feature weighting for blind modulation identification |
| topic | SSA optimization algorithm machine learning feature weighting modulation identification |
| url | https://www.mdpi.com/2079-9292/10/16/2002 |
| work_keys_str_mv | AT sarrabenchaabane improvedsalpswarmoptimizationalgorithmapplicationinfeatureweightingforblindmodulationidentification AT akrambelazi improvedsalpswarmoptimizationalgorithmapplicationinfeatureweightingforblindmodulationidentification AT sofianekharbech improvedsalpswarmoptimizationalgorithmapplicationinfeatureweightingforblindmodulationidentification AT ammarbouallegue improvedsalpswarmoptimizationalgorithmapplicationinfeatureweightingforblindmodulationidentification AT laurentclavier improvedsalpswarmoptimizationalgorithmapplicationinfeatureweightingforblindmodulationidentification |