A Transfer Learning and Optimized CNN Based Maritime Vessel Classification System
Deep learning has been used to improve intelligent transportation systems (ITS) by classifying ship targets in interior waterways. Researchers have created numerous classification methods, but they have low accuracy and misclassify other ship targets. As a result, more research into ship classificat...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/3/1912 |
| _version_ | 1797625142928474112 |
|---|---|
| author | Mostafa Hamdy Salem Yujian Li Zhaoying Liu Ahmed M. AbdelTawab |
| author_facet | Mostafa Hamdy Salem Yujian Li Zhaoying Liu Ahmed M. AbdelTawab |
| author_sort | Mostafa Hamdy Salem |
| collection | DOAJ |
| description | Deep learning has been used to improve intelligent transportation systems (ITS) by classifying ship targets in interior waterways. Researchers have created numerous classification methods, but they have low accuracy and misclassify other ship targets. As a result, more research into ship classification is required to avoid inland waterway collisions. We present a new convolutional neural network classification method for inland waterways that can classify the five major ship types: cargo, military, carrier, cruise, and tanker. This method can also be used for other ship classes. The proposed method consists of four phases for the boosting of classification accuracy for Intelligent Transport Systems (ITS) based on convolutional neural networks (CNNs); efficient augmentation method, the hyper-parameter optimization (HPO) technique for optimum CNN model parameter selection, transfer learning, and ensemble learning are suggested. All experiments used Kaggle’s public Game of Deep Learning Ship dataset. In addition, the proposed ship classification achieved 98.38% detection rates and 97.43% F1 scores. Our suggested classification technique was also evaluated on the MARVEL dataset. This dataset includes 10,000 image samples for each class and 26 types of ships for generalization. The suggested method also delivered an excellent performance compared to other algorithms, with performance metrics with an accuracy of 97.04%, a precision of 96.1%, a recall of 95.92%, a specificity of 96.55%, and a 96.31% F1 score. |
| first_indexed | 2024-03-11T09:52:36Z |
| format | Article |
| id | doaj.art-fcaae7d677804fedb5c92b7f14f2ba10 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T09:52:36Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-fcaae7d677804fedb5c92b7f14f2ba102023-11-16T16:12:08ZengMDPI AGApplied Sciences2076-34172023-02-01133191210.3390/app13031912A Transfer Learning and Optimized CNN Based Maritime Vessel Classification SystemMostafa Hamdy Salem0Yujian Li1Zhaoying Liu2Ahmed M. AbdelTawab3Faculty of Information Technology, Beijing University of Technology, Beijing 100124, ChinaSchool of Artificial Intelligence, Guilin University of Electronic Technology, Guilin 541004, ChinaFaculty of Information Technology, Beijing University of Technology, Beijing 100124, ChinaElectronics and Communications Department, Faculty of Engineering, Misr University for Science & Technology MUST, Giza 12566, EgyptDeep learning has been used to improve intelligent transportation systems (ITS) by classifying ship targets in interior waterways. Researchers have created numerous classification methods, but they have low accuracy and misclassify other ship targets. As a result, more research into ship classification is required to avoid inland waterway collisions. We present a new convolutional neural network classification method for inland waterways that can classify the five major ship types: cargo, military, carrier, cruise, and tanker. This method can also be used for other ship classes. The proposed method consists of four phases for the boosting of classification accuracy for Intelligent Transport Systems (ITS) based on convolutional neural networks (CNNs); efficient augmentation method, the hyper-parameter optimization (HPO) technique for optimum CNN model parameter selection, transfer learning, and ensemble learning are suggested. All experiments used Kaggle’s public Game of Deep Learning Ship dataset. In addition, the proposed ship classification achieved 98.38% detection rates and 97.43% F1 scores. Our suggested classification technique was also evaluated on the MARVEL dataset. This dataset includes 10,000 image samples for each class and 26 types of ships for generalization. The suggested method also delivered an excellent performance compared to other algorithms, with performance metrics with an accuracy of 97.04%, a precision of 96.1%, a recall of 95.92%, a specificity of 96.55%, and a 96.31% F1 score.https://www.mdpi.com/2076-3417/13/3/1912transfer learningconvolutional neural networkdeep learningensemble learningparticle swarm optimization |
| spellingShingle | Mostafa Hamdy Salem Yujian Li Zhaoying Liu Ahmed M. AbdelTawab A Transfer Learning and Optimized CNN Based Maritime Vessel Classification System Applied Sciences transfer learning convolutional neural network deep learning ensemble learning particle swarm optimization |
| title | A Transfer Learning and Optimized CNN Based Maritime Vessel Classification System |
| title_full | A Transfer Learning and Optimized CNN Based Maritime Vessel Classification System |
| title_fullStr | A Transfer Learning and Optimized CNN Based Maritime Vessel Classification System |
| title_full_unstemmed | A Transfer Learning and Optimized CNN Based Maritime Vessel Classification System |
| title_short | A Transfer Learning and Optimized CNN Based Maritime Vessel Classification System |
| title_sort | transfer learning and optimized cnn based maritime vessel classification system |
| topic | transfer learning convolutional neural network deep learning ensemble learning particle swarm optimization |
| url | https://www.mdpi.com/2076-3417/13/3/1912 |
| work_keys_str_mv | AT mostafahamdysalem atransferlearningandoptimizedcnnbasedmaritimevesselclassificationsystem AT yujianli atransferlearningandoptimizedcnnbasedmaritimevesselclassificationsystem AT zhaoyingliu atransferlearningandoptimizedcnnbasedmaritimevesselclassificationsystem AT ahmedmabdeltawab atransferlearningandoptimizedcnnbasedmaritimevesselclassificationsystem AT mostafahamdysalem transferlearningandoptimizedcnnbasedmaritimevesselclassificationsystem AT yujianli transferlearningandoptimizedcnnbasedmaritimevesselclassificationsystem AT zhaoyingliu transferlearningandoptimizedcnnbasedmaritimevesselclassificationsystem AT ahmedmabdeltawab transferlearningandoptimizedcnnbasedmaritimevesselclassificationsystem |