A scheme for anomalous RFID trajectory detection based on improved clustering algorithm under digital-twin-driven
| Autor: | Mengnan Cai, Xinling Shen, Siye Wang, Yijia Jin |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Scheme (programming language)
050210 logistics & transportation Computer science Anomaly (natural sciences) 020208 electrical & electronic engineering 05 social sciences Real-time computing 02 engineering and technology Track (rail transport) Rendering (computer graphics) Position (vector) 0502 economics and business 0202 electrical engineering electronic engineering information engineering Trajectory Anomaly detection Cluster analysis computer computer.programming_language |
| Zdroj: | MobiQuitous |
| DOI: | 10.1145/3360774.3360809 |
| Popis: | Anomaly analysis of trajectories is one of the means to maintain indoor safety. Effective track anomaly detection should be based on the current road network structure. However, the indoor environment usually contains many obstacles flexible to move. The changes in the positions of obstacles frequently cause the changes of the road network structure. When the road network changes, it takes time and effort to manually redraw the road network and simultaneously losses the guarantee of real-time performance. At the same time, manual drawing is forbidden in some confidential places. In our paper, the scheme of RFID track anomaly detection combined with digital-twin technology is proposed to provide a real-time actual road network for anomaly analysis. The accurate mapping and virtual simulation functions of digital-twin technology are used to achieve the dynamic real-time rendering and the maintenance of the indoor road network structure. We also improve a clustering algorithm to make it suitable for indoor RFID track clustering. In our paper, deviation thresholds and digital-twin model are used to detect anomalies. The trajectory is judged to be abnormal when it appears in the restricted areas or exceeds the deviation thresholds in any terms of position, velocity, or direction. We use an improved scan-line algorithm and F1-scores to determine the threshold values. Our proposed anomaly detection method provides more effective and intuitive results for researchers to analyze. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|