FraudMove: Fraud Drivers Discovery Using Real-Time Trajectory Outlier Detection
Taxicabs and rideshare cars nowadays are equipped with GPS devices that enable capturing a large volume of traces. These GPS traces represent the moving behavior of the car drivers. Indeed, the real-time discovery of fraud drivers earlier is a demand for saving the passenger’s life and money. For th...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/10/11/767 |
| _version_ | 1797510042617905152 |
|---|---|
| author | Eman O. Eldawy Abdeltawab Hendawi Mohammed Abdalla Hoda M. O. Mokhtar |
| author_facet | Eman O. Eldawy Abdeltawab Hendawi Mohammed Abdalla Hoda M. O. Mokhtar |
| author_sort | Eman O. Eldawy |
| collection | DOAJ |
| description | Taxicabs and rideshare cars nowadays are equipped with GPS devices that enable capturing a large volume of traces. These GPS traces represent the moving behavior of the car drivers. Indeed, the real-time discovery of fraud drivers earlier is a demand for saving the passenger’s life and money. For this purpose, this paper proposes a novel time-based system, namely <i>FraudMove</i>, to discover fraud drivers in real-time by identifying outlier active trips. Mainly, the proposed <i>FraudMove</i> system computes the time of the most probable path of a trip. For trajectory outlier detection, a trajectory is considered an outlier trajectory if its time exceeds the time of this computed path by a specified threshold. <i>FraudMove</i> employs a tunable time window parameter to control the number of checks for detecting outlier trips. This parameter allows <i>FraudMove</i> to trade responsiveness with efficiency. Unlike other related works that wait until the end of a trip to indicate that it was an outlier, <i>FraudMove</i> discovers outlier trips instantly during the trip. Extensive experiments conducted on a real dataset confirm the efficiency and effectiveness of <i>FraudMove</i> in detecting outlier trajectories. The experimental results prove that <i>FraudMove</i> saves the response time of the outlier check process by up to 65% compared to the state-of-the-art systems. |
| first_indexed | 2024-03-10T05:26:18Z |
| format | Article |
| id | doaj.art-1d28c8c23fcc450391917d475996d8f4 |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-03-10T05:26:18Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-1d28c8c23fcc450391917d475996d8f42023-11-22T23:36:32ZengMDPI AGISPRS International Journal of Geo-Information2220-99642021-11-01101176710.3390/ijgi10110767FraudMove: Fraud Drivers Discovery Using Real-Time Trajectory Outlier DetectionEman O. Eldawy0Abdeltawab Hendawi1Mohammed Abdalla2Hoda M. O. Mokhtar3Faculty of Computers and Information, Minia University, Minia 61511, EgyptDepartment of Computer Science and Statistics, University of Rhode Island, Kingston, NY 02881, USAFaculty of Computers and Artificial Intelligence, Beni-Suef University, Giza 8655, EgyptFaculty of Computers and Artificial Intelligence, Cairo University, Cairo 11311, EgyptTaxicabs and rideshare cars nowadays are equipped with GPS devices that enable capturing a large volume of traces. These GPS traces represent the moving behavior of the car drivers. Indeed, the real-time discovery of fraud drivers earlier is a demand for saving the passenger’s life and money. For this purpose, this paper proposes a novel time-based system, namely <i>FraudMove</i>, to discover fraud drivers in real-time by identifying outlier active trips. Mainly, the proposed <i>FraudMove</i> system computes the time of the most probable path of a trip. For trajectory outlier detection, a trajectory is considered an outlier trajectory if its time exceeds the time of this computed path by a specified threshold. <i>FraudMove</i> employs a tunable time window parameter to control the number of checks for detecting outlier trips. This parameter allows <i>FraudMove</i> to trade responsiveness with efficiency. Unlike other related works that wait until the end of a trip to indicate that it was an outlier, <i>FraudMove</i> discovers outlier trips instantly during the trip. Extensive experiments conducted on a real dataset confirm the efficiency and effectiveness of <i>FraudMove</i> in detecting outlier trajectories. The experimental results prove that <i>FraudMove</i> saves the response time of the outlier check process by up to 65% compared to the state-of-the-art systems.https://www.mdpi.com/2220-9964/10/11/767mining driving behaviormoving objects databasesoutlier detectiontraffic condition |
| spellingShingle | Eman O. Eldawy Abdeltawab Hendawi Mohammed Abdalla Hoda M. O. Mokhtar FraudMove: Fraud Drivers Discovery Using Real-Time Trajectory Outlier Detection ISPRS International Journal of Geo-Information mining driving behavior moving objects databases outlier detection traffic condition |
| title | FraudMove: Fraud Drivers Discovery Using Real-Time Trajectory Outlier Detection |
| title_full | FraudMove: Fraud Drivers Discovery Using Real-Time Trajectory Outlier Detection |
| title_fullStr | FraudMove: Fraud Drivers Discovery Using Real-Time Trajectory Outlier Detection |
| title_full_unstemmed | FraudMove: Fraud Drivers Discovery Using Real-Time Trajectory Outlier Detection |
| title_short | FraudMove: Fraud Drivers Discovery Using Real-Time Trajectory Outlier Detection |
| title_sort | fraudmove fraud drivers discovery using real time trajectory outlier detection |
| topic | mining driving behavior moving objects databases outlier detection traffic condition |
| url | https://www.mdpi.com/2220-9964/10/11/767 |
| work_keys_str_mv | AT emanoeldawy fraudmovefrauddriversdiscoveryusingrealtimetrajectoryoutlierdetection AT abdeltawabhendawi fraudmovefrauddriversdiscoveryusingrealtimetrajectoryoutlierdetection AT mohammedabdalla fraudmovefrauddriversdiscoveryusingrealtimetrajectoryoutlierdetection AT hodamomokhtar fraudmovefrauddriversdiscoveryusingrealtimetrajectoryoutlierdetection |