SMART OPTIMIZER SELECTION TECHNIQUE: A COMPARATIVE STUDY OF MODIFIED DENSNET201 WITH OTHER DEEP LEARNING MODELS
The rapid growth and development of AI-based applications introduce a wide range of deep and transfer learning model architectures. Selecting an optimal optimizer is still challenging to improve any classification type's performance efficiency and accuracy. This paper proposes an intelligent o...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Lublin University of Technology
2023-12-01
|
| Series: | Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska |
| Subjects: | |
| Online Access: | https://ph.pollub.pl/index.php/iapgos/article/view/5332 |
| _version_ | 1797384665251708928 |
|---|---|
| author | Kamaran Manguri Aree A. Mohammed |
| author_facet | Kamaran Manguri Aree A. Mohammed |
| author_sort | Kamaran Manguri |
| collection | DOAJ |
| description |
The rapid growth and development of AI-based applications introduce a wide range of deep and transfer learning model architectures. Selecting an optimal optimizer is still challenging to improve any classification type's performance efficiency and accuracy. This paper proposes an intelligent optimizer selection technique using a new search algorithm to overcome this difficulty. A dataset used in this work was collected and customized for controlling and monitoring roads, especially when emergency vehicles are approaching. In this regard, several deep and transfer learning models have been compared for accurate detection and classification. Furthermore, DenseNet201 layers are frizzed to choose the perfect optimizer. The main goal is to improve the performance accuracy of emergency car classification by performing the test of various optimization methods, including (Adam, Adamax, Nadam, and RMSprob). The evaluation metrics utilized for the model’s comparison with other deep learning techniques are based on classification accuracy, precision, recall, and F1-Score. Test results show that the proposed selection-based optimizer increased classification accuracy and reached 98.84%.
|
| first_indexed | 2024-03-08T21:39:14Z |
| format | Article |
| id | doaj.art-3edec2c1fcea492da7026fbb59441f4a |
| institution | Directory Open Access Journal |
| issn | 2083-0157 2391-6761 |
| language | English |
| last_indexed | 2024-03-08T21:39:14Z |
| publishDate | 2023-12-01 |
| publisher | Lublin University of Technology |
| record_format | Article |
| series | Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska |
| spelling | doaj.art-3edec2c1fcea492da7026fbb59441f4a2023-12-20T14:08:39ZengLublin University of TechnologyInformatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska2083-01572391-67612023-12-0113410.35784/iapgos.5332SMART OPTIMIZER SELECTION TECHNIQUE: A COMPARATIVE STUDY OF MODIFIED DENSNET201 WITH OTHER DEEP LEARNING MODELSKamaran Manguri0https://orcid.org/0000-0001-8567-3367Aree A. Mohammed1https://orcid.org/0000-0001-9710-45591Erbil Polytechnic University, Erbil Technical Engineering College, Department of Technical Information System Engineering, 2University of Raparin, Department of Software and Informatics EngineeringUniversity of Sulaimani, College of Science, Computer Science Department The rapid growth and development of AI-based applications introduce a wide range of deep and transfer learning model architectures. Selecting an optimal optimizer is still challenging to improve any classification type's performance efficiency and accuracy. This paper proposes an intelligent optimizer selection technique using a new search algorithm to overcome this difficulty. A dataset used in this work was collected and customized for controlling and monitoring roads, especially when emergency vehicles are approaching. In this regard, several deep and transfer learning models have been compared for accurate detection and classification. Furthermore, DenseNet201 layers are frizzed to choose the perfect optimizer. The main goal is to improve the performance accuracy of emergency car classification by performing the test of various optimization methods, including (Adam, Adamax, Nadam, and RMSprob). The evaluation metrics utilized for the model’s comparison with other deep learning techniques are based on classification accuracy, precision, recall, and F1-Score. Test results show that the proposed selection-based optimizer increased classification accuracy and reached 98.84%. https://ph.pollub.pl/index.php/iapgos/article/view/5332deep learningoptimization techniquetransfer learningcustomized datasetmodified DenseNet201 |
| spellingShingle | Kamaran Manguri Aree A. Mohammed SMART OPTIMIZER SELECTION TECHNIQUE: A COMPARATIVE STUDY OF MODIFIED DENSNET201 WITH OTHER DEEP LEARNING MODELS Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska deep learning optimization technique transfer learning customized dataset modified DenseNet201 |
| title | SMART OPTIMIZER SELECTION TECHNIQUE: A COMPARATIVE STUDY OF MODIFIED DENSNET201 WITH OTHER DEEP LEARNING MODELS |
| title_full | SMART OPTIMIZER SELECTION TECHNIQUE: A COMPARATIVE STUDY OF MODIFIED DENSNET201 WITH OTHER DEEP LEARNING MODELS |
| title_fullStr | SMART OPTIMIZER SELECTION TECHNIQUE: A COMPARATIVE STUDY OF MODIFIED DENSNET201 WITH OTHER DEEP LEARNING MODELS |
| title_full_unstemmed | SMART OPTIMIZER SELECTION TECHNIQUE: A COMPARATIVE STUDY OF MODIFIED DENSNET201 WITH OTHER DEEP LEARNING MODELS |
| title_short | SMART OPTIMIZER SELECTION TECHNIQUE: A COMPARATIVE STUDY OF MODIFIED DENSNET201 WITH OTHER DEEP LEARNING MODELS |
| title_sort | smart optimizer selection technique a comparative study of modified densnet201 with other deep learning models |
| topic | deep learning optimization technique transfer learning customized dataset modified DenseNet201 |
| url | https://ph.pollub.pl/index.php/iapgos/article/view/5332 |
| work_keys_str_mv | AT kamaranmanguri smartoptimizerselectiontechniqueacomparativestudyofmodifieddensnet201withotherdeeplearningmodels AT areeamohammed smartoptimizerselectiontechniqueacomparativestudyofmodifieddensnet201withotherdeeplearningmodels |