Trajectory Clustering-Based Anomaly Detection in Indoor Human Movement
Human movement anomalies in indoor spaces commonly involve urgent situations, such as security threats, accidents, and fires. This paper proposes a two-phase framework for detecting indoor human trajectory anomalies based on density-based spatial clustering of applications with noise (DBSCAN). The f...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/6/3318 |
| _version_ | 1797608969605218304 |
|---|---|
| author | Doi Thi Lan Seokhoon Yoon |
| author_facet | Doi Thi Lan Seokhoon Yoon |
| author_sort | Doi Thi Lan |
| collection | DOAJ |
| description | Human movement anomalies in indoor spaces commonly involve urgent situations, such as security threats, accidents, and fires. This paper proposes a two-phase framework for detecting indoor human trajectory anomalies based on density-based spatial clustering of applications with noise (DBSCAN). The first phase of the framework groups datasets into clusters. In the second phase, the abnormality of a new trajectory is checked. A new metric called the longest common sub-sequence using indoor walking distance and semantic label (LCSS_IS) is proposed to calculate the similarity between trajectories, extending from the longest common sub-sequence (LCSS). Moreover, a DBSCAN cluster validity index (DCVI) is proposed to improve the trajectory clustering performance. The DCVI is used to choose the epsilon parameter for DBSCAN. The proposed method is evaluated using two real trajectory datasets: MIT Badge and sCREEN. The experimental results show that the proposed method effectively detects human trajectory anomalies in indoor spaces. With the MIT Badge dataset, the proposed method achieves 89.03% in terms of F1-score for hypothesized anomalies and above 93% for all synthesized anomalies. In the sCREEN dataset, the proposed method also achieves impressive results in F1-score on synthesized anomalies: 89.92% for rare location visit anomalies (<i>τ</i> = 0.5) and 93.63% for other anomalies. |
| first_indexed | 2024-03-11T05:55:06Z |
| format | Article |
| id | doaj.art-2c07c8e3e7af42d893a6b83e0c0d281e |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T05:55:06Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-2c07c8e3e7af42d893a6b83e0c0d281e2023-11-17T13:49:02ZengMDPI AGSensors1424-82202023-03-01236331810.3390/s23063318Trajectory Clustering-Based Anomaly Detection in Indoor Human MovementDoi Thi Lan0Seokhoon Yoon1Department of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of KoreaDepartment of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of KoreaHuman movement anomalies in indoor spaces commonly involve urgent situations, such as security threats, accidents, and fires. This paper proposes a two-phase framework for detecting indoor human trajectory anomalies based on density-based spatial clustering of applications with noise (DBSCAN). The first phase of the framework groups datasets into clusters. In the second phase, the abnormality of a new trajectory is checked. A new metric called the longest common sub-sequence using indoor walking distance and semantic label (LCSS_IS) is proposed to calculate the similarity between trajectories, extending from the longest common sub-sequence (LCSS). Moreover, a DBSCAN cluster validity index (DCVI) is proposed to improve the trajectory clustering performance. The DCVI is used to choose the epsilon parameter for DBSCAN. The proposed method is evaluated using two real trajectory datasets: MIT Badge and sCREEN. The experimental results show that the proposed method effectively detects human trajectory anomalies in indoor spaces. With the MIT Badge dataset, the proposed method achieves 89.03% in terms of F1-score for hypothesized anomalies and above 93% for all synthesized anomalies. In the sCREEN dataset, the proposed method also achieves impressive results in F1-score on synthesized anomalies: 89.92% for rare location visit anomalies (<i>τ</i> = 0.5) and 93.63% for other anomalies.https://www.mdpi.com/1424-8220/23/6/3318anomaly detectionindoor human trajectoryDBSCANcluster validity indexepsilon parametersimilarity measurement |
| spellingShingle | Doi Thi Lan Seokhoon Yoon Trajectory Clustering-Based Anomaly Detection in Indoor Human Movement Sensors anomaly detection indoor human trajectory DBSCAN cluster validity index epsilon parameter similarity measurement |
| title | Trajectory Clustering-Based Anomaly Detection in Indoor Human Movement |
| title_full | Trajectory Clustering-Based Anomaly Detection in Indoor Human Movement |
| title_fullStr | Trajectory Clustering-Based Anomaly Detection in Indoor Human Movement |
| title_full_unstemmed | Trajectory Clustering-Based Anomaly Detection in Indoor Human Movement |
| title_short | Trajectory Clustering-Based Anomaly Detection in Indoor Human Movement |
| title_sort | trajectory clustering based anomaly detection in indoor human movement |
| topic | anomaly detection indoor human trajectory DBSCAN cluster validity index epsilon parameter similarity measurement |
| url | https://www.mdpi.com/1424-8220/23/6/3318 |
| work_keys_str_mv | AT doithilan trajectoryclusteringbasedanomalydetectioninindoorhumanmovement AT seokhoonyoon trajectoryclusteringbasedanomalydetectioninindoorhumanmovement |