Improved Feature Selection Based on Chaos Game Optimization for Social Internet of Things with a Novel Deep Learning Model
The Social Internet of Things (SIoT) ecosystem tends to process and analyze extensive data generated by users from both social networks and Internet of Things (IoT) systems and derives knowledge and diagnoses from all connected objects. To overcome many challenges in the SIoT system, such as big dat...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/11/4/1032 |
| _version_ | 1827756572442361856 |
|---|---|
| author | Abdelghani Dahou Samia Allaoua Chelloug Mai Alduailij Mohamed Abd Elaziz |
| author_facet | Abdelghani Dahou Samia Allaoua Chelloug Mai Alduailij Mohamed Abd Elaziz |
| author_sort | Abdelghani Dahou |
| collection | DOAJ |
| description | The Social Internet of Things (SIoT) ecosystem tends to process and analyze extensive data generated by users from both social networks and Internet of Things (IoT) systems and derives knowledge and diagnoses from all connected objects. To overcome many challenges in the SIoT system, such as big data management, analysis, and reporting, robust algorithms should be proposed and validated. Thus, in this work, we propose a framework to tackle the high dimensionality of transferred data over the SIoT system and improve the performance of several applications with different data types. The proposed framework comprises two parts: Transformer CNN (TransCNN), a deep learning model for feature extraction, and the Chaos Game Optimization (CGO) algorithm for feature selection. To validate the framework’s effectiveness, several datasets with different data types were selected, and various experiments were conducted compared to other methods. The results showed that the efficiency of the developed method is better than other models according to the performance metrics in the SIoT environment. In addition, the average of the developed method based on the accuracy, sensitivity, specificity, number of selected features, and fitness value is 88.30%, 87.20%, 92.94%, 44.375, and 0.1082, respectively. The mean rank obtained using the Friedman test is the best value overall for the competitive algorithms. |
| first_indexed | 2024-03-11T08:28:18Z |
| format | Article |
| id | doaj.art-58b8dea4d9c54dddbddb3198a32e3b1c |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-11T08:28:18Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-58b8dea4d9c54dddbddb3198a32e3b1c2023-11-16T21:57:25ZengMDPI AGMathematics2227-73902023-02-01114103210.3390/math11041032Improved Feature Selection Based on Chaos Game Optimization for Social Internet of Things with a Novel Deep Learning ModelAbdelghani Dahou0Samia Allaoua Chelloug1Mai Alduailij2Mohamed Abd Elaziz3Faculty of Computer Sciences and Mathematics, Ahmed Draia University, Adrar 01000, AlgeriaInformation Technology Department, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh 11671, Saudi ArabiaDepartment of Computer Science, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh 11671, Saudi ArabiaDepartment of Mathematics, Faculty of Science, Zagazig University, Zagazig 44519, EgyptThe Social Internet of Things (SIoT) ecosystem tends to process and analyze extensive data generated by users from both social networks and Internet of Things (IoT) systems and derives knowledge and diagnoses from all connected objects. To overcome many challenges in the SIoT system, such as big data management, analysis, and reporting, robust algorithms should be proposed and validated. Thus, in this work, we propose a framework to tackle the high dimensionality of transferred data over the SIoT system and improve the performance of several applications with different data types. The proposed framework comprises two parts: Transformer CNN (TransCNN), a deep learning model for feature extraction, and the Chaos Game Optimization (CGO) algorithm for feature selection. To validate the framework’s effectiveness, several datasets with different data types were selected, and various experiments were conducted compared to other methods. The results showed that the efficiency of the developed method is better than other models according to the performance metrics in the SIoT environment. In addition, the average of the developed method based on the accuracy, sensitivity, specificity, number of selected features, and fitness value is 88.30%, 87.20%, 92.94%, 44.375, and 0.1082, respectively. The mean rank obtained using the Friedman test is the best value overall for the competitive algorithms.https://www.mdpi.com/2227-7390/11/4/1032Social Internet of Things (SIoT)Deep Learning (DL)Chaos Game Optimization (CGO)feature selection |
| spellingShingle | Abdelghani Dahou Samia Allaoua Chelloug Mai Alduailij Mohamed Abd Elaziz Improved Feature Selection Based on Chaos Game Optimization for Social Internet of Things with a Novel Deep Learning Model Mathematics Social Internet of Things (SIoT) Deep Learning (DL) Chaos Game Optimization (CGO) feature selection |
| title | Improved Feature Selection Based on Chaos Game Optimization for Social Internet of Things with a Novel Deep Learning Model |
| title_full | Improved Feature Selection Based on Chaos Game Optimization for Social Internet of Things with a Novel Deep Learning Model |
| title_fullStr | Improved Feature Selection Based on Chaos Game Optimization for Social Internet of Things with a Novel Deep Learning Model |
| title_full_unstemmed | Improved Feature Selection Based on Chaos Game Optimization for Social Internet of Things with a Novel Deep Learning Model |
| title_short | Improved Feature Selection Based on Chaos Game Optimization for Social Internet of Things with a Novel Deep Learning Model |
| title_sort | improved feature selection based on chaos game optimization for social internet of things with a novel deep learning model |
| topic | Social Internet of Things (SIoT) Deep Learning (DL) Chaos Game Optimization (CGO) feature selection |
| url | https://www.mdpi.com/2227-7390/11/4/1032 |
| work_keys_str_mv | AT abdelghanidahou improvedfeatureselectionbasedonchaosgameoptimizationforsocialinternetofthingswithanoveldeeplearningmodel AT samiaallaouachelloug improvedfeatureselectionbasedonchaosgameoptimizationforsocialinternetofthingswithanoveldeeplearningmodel AT maialduailij improvedfeatureselectionbasedonchaosgameoptimizationforsocialinternetofthingswithanoveldeeplearningmodel AT mohamedabdelaziz improvedfeatureselectionbasedonchaosgameoptimizationforsocialinternetofthingswithanoveldeeplearningmodel |