Magnetic Anomaly Detection Method Based on Feature Fusion and Isolation Forest Algorithm
In order to improve the weak magnetic detection ability under the background of Gaussian colored magnetic environment noise, a magnetic anomaly detection method based on feature fusion and isolation forest (IForest) algorithm is proposed in this paper. The method uses different feature algorithms to...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9852660/ |
| _version_ | 1811214806211887104 |
|---|---|
| author | Ning Zhang Yifei Liu Lei Xu Pengfei Lin Heda Zhao Ming Chang |
| author_facet | Ning Zhang Yifei Liu Lei Xu Pengfei Lin Heda Zhao Ming Chang |
| author_sort | Ning Zhang |
| collection | DOAJ |
| description | In order to improve the weak magnetic detection ability under the background of Gaussian colored magnetic environment noise, a magnetic anomaly detection method based on feature fusion and isolation forest (IForest) algorithm is proposed in this paper. The method uses different feature algorithms to extract the statistical features, time-frequency features and fractal features of the signal, reduces the dimensionality of the features by principal component analysis (PCA) and generates feature fusion tensors. Finally the IForest algorithm is used to achieve target detection. The simulation and experimental results show that the method has a higher detection rate under different SNR of Gaussian color noise, which is approximately 5%-18% higher than that of the traditional feature detection algorithm. This method can train an effective detection model with only a small number of negative samples. Compared with the fully connected neural network (FCN) model trained with unbalanced samples, the detection rate increases by approximately 5%-12%, and it takes less time. |
| first_indexed | 2024-04-12T06:11:54Z |
| format | Article |
| id | doaj.art-9e11a59473e347a6b714e1a899c18dc5 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T06:11:54Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-9e11a59473e347a6b714e1a899c18dc52022-12-22T03:44:41ZengIEEEIEEE Access2169-35362022-01-0110844448445710.1109/ACCESS.2022.31976309852660Magnetic Anomaly Detection Method Based on Feature Fusion and Isolation Forest AlgorithmNing Zhang0Yifei Liu1https://orcid.org/0000-0001-9328-8493Lei Xu2Pengfei Lin3Heda Zhao4Ming Chang5College of Weapons Engineering, Naval University of Engineering, Wuhan, ChinaCollege of Weapons Engineering, Naval University of Engineering, Wuhan, ChinaUnit 92859 of PLA, Tianjin, ChinaDepartment of Hydropower and Chemical Defense, Dalian Naval Academy, Dalian, ChinaUnit 91977 of PLA, Beijing, ChinaCollege of Weapons Engineering, Naval University of Engineering, Wuhan, ChinaIn order to improve the weak magnetic detection ability under the background of Gaussian colored magnetic environment noise, a magnetic anomaly detection method based on feature fusion and isolation forest (IForest) algorithm is proposed in this paper. The method uses different feature algorithms to extract the statistical features, time-frequency features and fractal features of the signal, reduces the dimensionality of the features by principal component analysis (PCA) and generates feature fusion tensors. Finally the IForest algorithm is used to achieve target detection. The simulation and experimental results show that the method has a higher detection rate under different SNR of Gaussian color noise, which is approximately 5%-18% higher than that of the traditional feature detection algorithm. This method can train an effective detection model with only a small number of negative samples. Compared with the fully connected neural network (FCN) model trained with unbalanced samples, the detection rate increases by approximately 5%-12%, and it takes less time.https://ieeexplore.ieee.org/document/9852660/Magnetic anomaly detectionfeature fusionunsupervised learningisolation forestprincipal component analysis |
| spellingShingle | Ning Zhang Yifei Liu Lei Xu Pengfei Lin Heda Zhao Ming Chang Magnetic Anomaly Detection Method Based on Feature Fusion and Isolation Forest Algorithm IEEE Access Magnetic anomaly detection feature fusion unsupervised learning isolation forest principal component analysis |
| title | Magnetic Anomaly Detection Method Based on Feature Fusion and Isolation Forest Algorithm |
| title_full | Magnetic Anomaly Detection Method Based on Feature Fusion and Isolation Forest Algorithm |
| title_fullStr | Magnetic Anomaly Detection Method Based on Feature Fusion and Isolation Forest Algorithm |
| title_full_unstemmed | Magnetic Anomaly Detection Method Based on Feature Fusion and Isolation Forest Algorithm |
| title_short | Magnetic Anomaly Detection Method Based on Feature Fusion and Isolation Forest Algorithm |
| title_sort | magnetic anomaly detection method based on feature fusion and isolation forest algorithm |
| topic | Magnetic anomaly detection feature fusion unsupervised learning isolation forest principal component analysis |
| url | https://ieeexplore.ieee.org/document/9852660/ |
| work_keys_str_mv | AT ningzhang magneticanomalydetectionmethodbasedonfeaturefusionandisolationforestalgorithm AT yifeiliu magneticanomalydetectionmethodbasedonfeaturefusionandisolationforestalgorithm AT leixu magneticanomalydetectionmethodbasedonfeaturefusionandisolationforestalgorithm AT pengfeilin magneticanomalydetectionmethodbasedonfeaturefusionandisolationforestalgorithm AT hedazhao magneticanomalydetectionmethodbasedonfeaturefusionandisolationforestalgorithm AT mingchang magneticanomalydetectionmethodbasedonfeaturefusionandisolationforestalgorithm |