A Two-Stage Semi-Supervised High Maneuvering Target Trajectory Data Classification Algorithm
Labeled data in insufficient amounts and missing categories are two observable features for high maneuvering target trajectory data. However, the existing research achievements are insufficient for solving these two problems simultaneously during data classification. This study proposed a two-stage...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/21/10979 |
| _version_ | 1797469178710458368 |
|---|---|
| author | Qing Li Xintai He Kun Chen Qicheng Ouyang |
| author_facet | Qing Li Xintai He Kun Chen Qicheng Ouyang |
| author_sort | Qing Li |
| collection | DOAJ |
| description | Labeled data in insufficient amounts and missing categories are two observable features for high maneuvering target trajectory data. However, the existing research achievements are insufficient for solving these two problems simultaneously during data classification. This study proposed a two-stage semi-supervised trajectory data classification algorithm. By pre-training the autoencoder and combining it with the Siamese network, a two-stage joint training was formed, which enabled the model to deal with missing categories by clustering and maintaining the classification ability under the missing label categories. The experimental simulation results showed that the performance of this algorithm was better than the classical semi-supervised algorithm label propagation and transferred learning when the amount of various labeled data was as low as 1–5. The two-stage training model also had a good effect on the problem of missing categories. When 75% of the types were missing, the purity could still reach 82%, which was about eight percentage points higher than the directly trained network. When two problems appeared simultaneously, compared with the directly trained network, the performance improved by about three percentage points on average, and the purity was consistently higher than the clustering results. In summary, this algorithm was more tolerant of the problems of labeled datasets, so it was more practical. |
| first_indexed | 2024-03-09T19:17:46Z |
| format | Article |
| id | doaj.art-13d45744376e41ddb37d432de88cb987 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T19:17:46Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-13d45744376e41ddb37d432de88cb9872023-11-24T03:35:59ZengMDPI AGApplied Sciences2076-34172022-10-0112211097910.3390/app122110979A Two-Stage Semi-Supervised High Maneuvering Target Trajectory Data Classification AlgorithmQing Li0Xintai He1Kun Chen2Qicheng Ouyang3Department of Information System Engineering, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaDepartment of Information System Engineering, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaDepartment of Information System Engineering, PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, ChinaChina Communications Construction Fourth Engineering Bureau Co., Ltd., Zhengzhou 450001, ChinaLabeled data in insufficient amounts and missing categories are two observable features for high maneuvering target trajectory data. However, the existing research achievements are insufficient for solving these two problems simultaneously during data classification. This study proposed a two-stage semi-supervised trajectory data classification algorithm. By pre-training the autoencoder and combining it with the Siamese network, a two-stage joint training was formed, which enabled the model to deal with missing categories by clustering and maintaining the classification ability under the missing label categories. The experimental simulation results showed that the performance of this algorithm was better than the classical semi-supervised algorithm label propagation and transferred learning when the amount of various labeled data was as low as 1–5. The two-stage training model also had a good effect on the problem of missing categories. When 75% of the types were missing, the purity could still reach 82%, which was about eight percentage points higher than the directly trained network. When two problems appeared simultaneously, compared with the directly trained network, the performance improved by about three percentage points on average, and the purity was consistently higher than the clustering results. In summary, this algorithm was more tolerant of the problems of labeled datasets, so it was more practical.https://www.mdpi.com/2076-3417/12/21/10979trajectory clusteringSiamese neural networkautoencoderjoint training |
| spellingShingle | Qing Li Xintai He Kun Chen Qicheng Ouyang A Two-Stage Semi-Supervised High Maneuvering Target Trajectory Data Classification Algorithm Applied Sciences trajectory clustering Siamese neural network autoencoder joint training |
| title | A Two-Stage Semi-Supervised High Maneuvering Target Trajectory Data Classification Algorithm |
| title_full | A Two-Stage Semi-Supervised High Maneuvering Target Trajectory Data Classification Algorithm |
| title_fullStr | A Two-Stage Semi-Supervised High Maneuvering Target Trajectory Data Classification Algorithm |
| title_full_unstemmed | A Two-Stage Semi-Supervised High Maneuvering Target Trajectory Data Classification Algorithm |
| title_short | A Two-Stage Semi-Supervised High Maneuvering Target Trajectory Data Classification Algorithm |
| title_sort | two stage semi supervised high maneuvering target trajectory data classification algorithm |
| topic | trajectory clustering Siamese neural network autoencoder joint training |
| url | https://www.mdpi.com/2076-3417/12/21/10979 |
| work_keys_str_mv | AT qingli atwostagesemisupervisedhighmaneuveringtargettrajectorydataclassificationalgorithm AT xintaihe atwostagesemisupervisedhighmaneuveringtargettrajectorydataclassificationalgorithm AT kunchen atwostagesemisupervisedhighmaneuveringtargettrajectorydataclassificationalgorithm AT qichengouyang atwostagesemisupervisedhighmaneuveringtargettrajectorydataclassificationalgorithm AT qingli twostagesemisupervisedhighmaneuveringtargettrajectorydataclassificationalgorithm AT xintaihe twostagesemisupervisedhighmaneuveringtargettrajectorydataclassificationalgorithm AT kunchen twostagesemisupervisedhighmaneuveringtargettrajectorydataclassificationalgorithm AT qichengouyang twostagesemisupervisedhighmaneuveringtargettrajectorydataclassificationalgorithm |