HMM-Based Map Matching and Spatiotemporal Analysis for Matching Errors with Taxi Trajectories
Abstract
:1. Introduction
2. Data Description and Pre-Processing
3. Methodology
3.1. Hidden Markov Model
Algorithm 1: HMM-based Map Matching |
Input |
Output: |
1: Initialize Viterbi path viterbi[], path probability v[], and state sequence y[] |
2: For each point p in P |
3: Calculate observation probabilities o[] for R based on the HMM |
4: For each state s in R |
5: Calculate v[s] = max{s’}(v[s’] * transition(s’, s) * o[s]) |
6: viterbi[s] = argmax{s’}(v[s’] * transition(s’, s)) |
7: y.append(viterbi[argmax_s(v[s])]) |
8: For i = N − 1 down to 1 |
9: ] |
10: return y |
3.2. Matching Error Trajectory Recognition Method
- (i)
- Off-Road Error (ORE) refers to a trajectory point or two/three adjacent points (e.g., P5 in Figure 4a) that fall outside of a buffer of a 15-meter radius, while its adjacent GPS points are captured;
- (ii)
- Wrong-match on Road Error (WRE) indicates that a trajectory point or two/three adjacent points (P5 in Figure 4b) are incorrectly matched to a nearby road segment, instead of the road that contains its upstream and downstream trajectory points;
- (iii)
- Off-Junction Error (OJE) means a trajectory point or two/three adjacent points (P5 in Figure 4c) that ought to be located within an intersection, but the point is not captured within the 15-meter radius buffer;
- (iv)
- Wrong-match in Junction Error (WJE) represents a trajectory point or two/three adjacent points (P5 in Figure 4d), which are supposed to be located within an intersection, but it is incorrectly matched to a nearby road segment.
- Select the GPS trajectories of a vehicle from the matched Taxi GPS points database based on the plate number and the timestamps.
- Examine the matched road ID of each five or seven adjacent GPS points and check the sequence of the road ID.
- For the errors on road segments, if the first two/three points and the last two/three points share the same road ID, while no road ID is matched to the middle point, i.e., out of the 15-meter buffer zone, it is classified as an “Off Road Error” (ORE). However, if the middle point is matched to a road segment, the road ID of which is different to that of the former two/three and latter two/three points, it is classified as a “Wrong Road Error” (WRE).
- For the errors occurring on intersections, if the former two/three points have the same road ID, and the latter two/three points share another road ID, while no road ID is matched to the middle point, it is classified as an “Off Junction Error” (OJE). However, if the middle point is matched to a road segment, the road ID of which is different to that of the former two/three and latter two/three points, it is classified as a “Wrong Junction Error” (WJE).
- Select the trajectories of another vehicle and repeat steps 1 to 4.
3.3. Spatial–Temporal Characteristics for Trajectory Errors
3.4. Exploration of the Spatial–Temporal Factors
4. Results
4.1. Outputs of Map Matching
4.2. Temporal and Spatial Distribution of Trajectory Errors
4.3. Contributing Factors of Map-Matching Errors
5. Discussion
6. Conclusions
- The spatial patterns of ORE, WRE, OJE, and WJE overtly vary across the time scales (e.g., time of day and weekday/weekends), signifying that the map-matching errors are not consistently located in the study area.
- Compared to ORE, the probability of WRE and OJE is higher on weekdays, while the probability of WJE is higher on weekends. It is noted that OREs and WJEs are more likely to occur during peak hours and at night.
- WREs, OJEs, and WJEs are more likely to be observed at intersections, especially on a flyover, an X-junction, and a T-junction.
- WREs tend to occur on the road where previous and latter roads simultaneously have bicycle dividers, median dividers, one-way control, and roadside parking, while these factors have mixed impacts on OJEs and WJEs. Also, higher resident and public service density on the latter road could increase the probability of WRE, OJE, and WJE.
- WREs are likely to occur on roads with low-speed limits. OJEs tend to occur when vehicles switch from a low speed limit to a high speed limit road, while the occurrence of WJE has the opposite trend.
Author Contributions
Funding
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Li, L.; Jiang, R.; He, Z.; Chen, X.; Zhou, X. Trajectory Data-Based Traffic Flow Studies: A Revisit. Transp. Res. Part C Emerg. Technol. 2020, 114, 225–240. [Google Scholar] [CrossRef]
- Wang, Y.; Chen, Y.; Li, G.; Lu, Y.; He, Z.; Yu, Z.; Sun, W. City-Scale Holographic Traffic Flow Data Based on Vehicular Trajectory Resampling. Sci. Data 2023, 10, 57. [Google Scholar] [CrossRef]
- Fan, J.; Li, Y.; Liu, Y.; Zhang, Y.; Ma, C. Analysis of Taxi Driving Behavior and Driving Risk Based on Trajectory Data. IEEE Intell. Veh. Symp. 2019, 2019, 220–225. [Google Scholar] [CrossRef]
- Dong, X.; Zhang, M.; Zhang, S.; Shen, X.; Hu, B. The Analysis of Urban Taxi Operation Efficiency Based on GPS Trajectory Big Data. Phys. A Stat. Mech. Its Appl. 2019, 528, 121456. [Google Scholar] [CrossRef]
- Shahverdy, M.; Fathy, M.; Berangi, R.; Sabokrou, M. Driver Behavior Detection and Classification Using Deep Convolutional Neural Networks. Expert Syst. Appl. 2020, 149, 113240. [Google Scholar] [CrossRef]
- Lin, Y.; Li, W.; Qiu, F.; Xu, H. Research on Optimization of Vehicle Routing Problem for Ride-Sharing Taxi. Procedia Soc. Behav. Sci. 2012, 43, 494–502. [Google Scholar] [CrossRef] [Green Version]
- Wang, R.; Alazzam, M.B.; Alassery, F.; Almulihi, A.; White, M. Innovative Research of Trajectory Prediction Algorithm Based on Deep Learning in Car Network Collision Detection and Early Warning System. Mob. Inf. Syst. 2021, 2021, 3773688. [Google Scholar] [CrossRef]
- Kan, Z.; Tang, L.; Kwan, M.P.; Ren, C.; Liu, D.; Li, Q. Traffic Congestion Analysis at the Turn Level Using Taxis’ GPS Trajectory Data. Comput. Environ. Urban Syst. 2019, 74, 229–243. [Google Scholar] [CrossRef]
- Kong, X.; Xu, Z.; Shen, G.; Wang, J.; Yang, Q.; Zhang, B. Urban Traffic Congestion Estimation and Prediction Based on Floating Car Trajectory Data. Futur. Gener. Comput. Syst. 2016, 61, 97–107. [Google Scholar] [CrossRef]
- Keler, A.; Krisp, J.M.; Ding, L. Detecting Vehicle Traffic Patterns in Urban Environments Using Taxi Trajectory Intersection Points. Geo-Spatial Inf. Sci. 2017, 20, 333–344. [Google Scholar] [CrossRef] [Green Version]
- Qin, J.; Mei, G.; Xiao, L. Building the Traffic Flow Network with Taxi GPS Trajectories and Its Application to Identify Urban Congestion Areas for Traffic Planning. Sustainability 2021, 13, 266. [Google Scholar] [CrossRef]
- Qin, H.; Peng, Y.; Zhang, W. Vehicles on RFID: Error-Cognitive Vehicle Localization in GPS-Less Environments. IEEE Trans. Veh. Technol. 2017, 66, 9943–9957. [Google Scholar] [CrossRef]
- Zhang, Z.; Hu, H.; Yu, Y.; Qian, W.; Shu, K. Dependency Preserved Raft for Transactions; Lecture Notes in Computer Science; Springer: Cham, Germany, 2020; Volume 12112, ISBN 978-3-030-59409-1. [Google Scholar]
- Gunn, L.; Smet, P.; Arbon, E.; McDonnell, M.D. Anomaly Detection in Satellite Communications Systems Using LSTM Networks. In Proceedings of the 2018 Military Communications and Information Systems Conference (MilCIS), Canberra, ACT, Australia, 13–15 November 2018. [Google Scholar] [CrossRef] [Green Version]
- Koetsier, C.; Fiosina, J.; Gremmel, J.N.; Müller, J.P.; Woisetschläger, D.M.; Sester, M. Detection of Anomalous Vehicle Trajectories Using Federated Learning. ISPRS Open J. Photogramm. Remote Sens. 2022, 4, 100013. [Google Scholar] [CrossRef]
- Ranacher, P.; Brunauer, R.; Trutschnig, W.; Van der Spek, S.; Reich, S. GPS Error and Its Effects on Movement Analysis. Int. J. Geogr. Inf. Sci. 2015, 30, 316–333. [Google Scholar] [CrossRef] [Green Version]
- Dey, S.; Tomko, M.; Winter, S. Map-Matching Error Identification in the Absence of Ground Truth. ISPRS Int. J. Geo-Information 2022, 11, 538. [Google Scholar] [CrossRef]
- Quddus, M.A.; Ochieng, W.Y.; Noland, R.B. Current Map-Matching Algorithms for Transport Applications: State-of-the Art and Future Research Directions. Transp. Res. Part C Emerg. Technol. 2007, 15, 312–328. [Google Scholar] [CrossRef] [Green Version]
- Liu, Z.; Wang, X.D.; Yan, X.Y. Map-Matching Algorithm for GPS Trajectories in Complex Urban Road Networks. Dianzi Keji Daxue Xuebao J. Univ. Electron. Sci. Technol. China 2016, 45, 1008–1013. [Google Scholar] [CrossRef]
- Sharma, K.P.; Poonia, R.C.; Sunda, S. A Novel Map Matching Algorithm for Real-Time Location Using Low Frequency Floating Trajectory Data. Intell. Paradig. 2023, 24, 442–455. [Google Scholar] [CrossRef]
- Li, W.; Wang, Y.; Li, D.; Xu, X. A Robust Map Matching Method by Considering Memorized Multiple Matching Candidates. Theor. Comput. Sci. 2023, 941, 104–120. [Google Scholar] [CrossRef]
- Yu, Q.; Hu, F.; Ye, Z.; Chen, C.; Sun, L.; Luo, Y. High-Frequency Trajectory Map Matching Algorithm Based on Road Network Topology. IEEE Trans. Intell. Transp. Syst. 2022, 23, 17530–17545. [Google Scholar] [CrossRef]
- Hu, H.; Qian, S.; Ouyang, J.; Cao, J.; Han, H.; Wang, J.; Chen, Y. AMM: An Adaptive Online Map Matching Algorithm. IEEE Trans. Intell. Transp. Syst. 2023, 24, 5039–5051. [Google Scholar] [CrossRef]
- Jiang, L.; Chen, C.X.; Chen, C. L2MM: Learning to Map Matching with Deep Models for Low-Quality GPS Trajectory Data. ACM Trans. Knowl. Discov. Data 2023, 17, 39. [Google Scholar] [CrossRef]
- Feng, J.; Li, Y.; Zhao, K.; Xu, Z.; Xia, T.; Zhang, J.; Jin, D. DeepMM: Deep Learning Based Map Matching With Data Augmentation. IEEE Trans. Mob. Comput. 2022, 21, 2372–2384. [Google Scholar] [CrossRef]
- Tortora, M.; Cordelli, E.; Soda, P. PyTrack: A Map-Matching-Based Python Toolbox for Vehicle Trajectory Reconstruction. IEEE Access 2022, 10, 112713–112720. [Google Scholar] [CrossRef]
- Saki, S.; Hagen, T. A Practical Guide to an Open-Source Map-Matching Approach for Big GPS Data. SN Comput. Sci. 2022, 3, 415. [Google Scholar] [CrossRef]
- Ma, S.; Lee, H. A Practical HMM-Based Map-Matching Method for Pedestrian Navigation. Int. Conf. Inf. Netw. 2023, 2023, 806–811. [Google Scholar] [CrossRef]
- Jiang, L.; Chen, C.; Chen, C.; Huang, H.; Guo, B. From Driving Trajectories to Driving Paths: A Survey on Map—Matching Algorithms. CCF Trans. Pervasive Comput. Interact. 2022, 4, 252–267. [Google Scholar] [CrossRef]
- Member, R.S.; Wang, G.; Cheng, Q.; Fu, L.; Chiang, K.; Hsu, L.-T.; Ochieng, W.Y. Improving GPS Code Phase Positioning Accuracy in Urban Environments Using Machine Learning. IEEE Internet Things J. 2020, 8, 7065–7078. [Google Scholar] [CrossRef]
- Chao, P.; Xu, Y.; Hua, W.; Zhou, X. A Survey on Map-Matching Algorithms. In Databases Theory and Applications, Proceedings of the 31st Australasian Database Conference, ADC 2020, Melbourne, VIC, Australia, 3–7 February 2020; Lecture Notes in Computer Science; Springer: Cham, Germany, 2020; Volume 12008, pp. 121–133. [Google Scholar] [CrossRef] [Green Version]
- Luo, S.; Gu, F.; Xu, F.; Shang, J. Effect Evaluation of Spatial Characteristics on Map Matching-Based Indoor Positioning. Sensors 2020, 20, 6698. [Google Scholar] [CrossRef]
- Wang, J.; Yuan, Y.; Ni, T.; Ma, Y.; Liu, M.; Xu, G. Anomalous Trajectory Detection and Classification Based on Difference and Intersection Set Distance. IEEE Trans. Veh. Technol. 2020, 69, 2487–2500. [Google Scholar] [CrossRef]
- Cervantes, J.; Garcia-lamont, F.; Rodríguez-mazahua, L.; Lopez, A. Neurocomputing A Comprehensive Survey on Support Vector Machine Classification: Applications, Challenges and Trends. Neurocomputing 2020, 408, 189–215. [Google Scholar] [CrossRef]
- Talebi, H.; Peeters, L.J.M.; Otto, A. A Truly Spatial Random Forests Algorithm for Geoscience Data Analysis and Modelling. Math. Geosci. 2022, 54, 1–22. [Google Scholar] [CrossRef]
- Singh, J.; Singh, S.; Singh, S.; Singh, H. Evaluating the Performance of Map Matching Algorithms for Navigation Systems: An Empirical Study. Spat. Inf. Res. 2019, 27, 63–74. [Google Scholar] [CrossRef]
- Santi, P.; Resta, G.; Szell, M.; Sobolevsky, S.; Strogatz, S.H.; Ratti, C. Quantifying the Benefits of Vehicle Pooling with Shareability Networks. Proc. Natl. Acad. Sci. USA 2014, 111, 13290–13294. [Google Scholar] [CrossRef]
- Brühwiler, L.; Fu, C.; Huang, H.; Longhi, L.; Weibel, R. Computers, Environment and Urban Systems Predicting Individuals’ Car Accident Risk by Trajectory, Driving Events, and Geographical Context. Comput. Environ. Urban Syst. 2022, 93, 101760. [Google Scholar] [CrossRef]
- Fu, X.; Zhang, J.; Zhang, Y. An Online Map Matching Algorithm Based on Second-Order Hidden Markov Model. J. Adv. Transp. 2021, 2021, 9993860. [Google Scholar] [CrossRef]
- Hsueh, Y.L.; Chen, H.C. Map Matching for Low-Sampling-Rate GPS Trajectories by Exploring Real-Time Moving Directions. Inf. Sci. 2018, 433–434, 55–69. [Google Scholar] [CrossRef]
- Xue, T.; Zhong, M.; Luo, L.; Li, L.; Ding, S.X. Distributionally Robust Fault Detection by Using Kernel Density Estimation. IFAC Pap. 2020, 53, 652–657. [Google Scholar] [CrossRef]
- Çelik, A.K.; Oktay, E. A Multinomial Logit Analysis of Risk Factors Influencing Road Traffic Injury Severities in the Erzurum and Kars Provinces of Turkey. Accid. Anal. Prev. 2014, 72, 66–77. [Google Scholar] [CrossRef] [PubMed]
- O’Brien, R.M. A Caution Regarding Rules of Thumb for Variance Inflation Factors. Qual. Quant. 2007, 41, 673–690. [Google Scholar] [CrossRef]
- Wong, R.C.P.; Szeto, W.Y. An Alternative Methodology for Evaluating the Service Quality of Urban Taxis. Transp. Policy 2018, 69, 132–140. [Google Scholar] [CrossRef]
- Dong, Y.; Xu, J.; Liu, X.; Gao, C.; Ru, H.; Duan, Z. Carbon Emissions and Expressway Traffic Flow Patterns in China. Sustainability 2019, 11, 2824. [Google Scholar] [CrossRef] [Green Version]
- Ulak, M.B.; Yazici, A.; Aljarrah, M. Value of Convenience for Taxi Trips in New York City. Transp. Res. Part A Policy Pract. 2020, 142, 85–100. [Google Scholar] [CrossRef]
- Schneider, R.J.; Diogenes, M.C.; Arnold, L.S.; Attaset, V.; Griswold, J.; Ragland, D.R. Association between Roadway Intersection Characteristics and Pedestrian Crash Risk in Alameda County, California. Transp. Res. Rec. 2010, 2198, 41–51. [Google Scholar] [CrossRef] [Green Version]
- Guo, F.; Wang, X.; Abdel-Aty, M.A. Modeling Signalized Intersection Safety with Corridor-Level Spatial Correlations. Accid. Anal. Prev. 2010, 42, 84–92. [Google Scholar] [CrossRef]
- Liu, X.; Sun, L.; Sun, Q.; Gao, G. Spatial Variation of Taxi Demand Using GPS Trajectories and POI Data. J. Adv. Transp. 2020, 2020, 7621576. [Google Scholar] [CrossRef]
- Zhou, Y.; Fang, Z.; Thill, J.; Li, Q.; Li, Y. Computers, Environment and Urban Systems Functionally Critical Locations in an Urban Transportation Network: Identification and Space—Time Analysis Using Taxi Trajectories. Comput. Environ. Urban Syst. 2015, 52, 34–47. [Google Scholar] [CrossRef]
- Hannover, L.U.; Braunschweig, T.U. Vehicle-to-Vehicle IEEE 802.11p Performance Measurements at Urban Intersections. In Proceedings of the 2012 IEEE International Conference on Communications (ICC), Ottawa, ON, Canada, 10–15 June 2022; pp. 7131–7135. [Google Scholar]
- Deep, S.; Raghavendra, S.; Bharath, B.D. RESEARCH PAPER GPS SNR Prediction in Urban Environment. Egypt. J. Remote Sens. Sp. Sci. 2018, 21, 83–85. [Google Scholar] [CrossRef] [Green Version]
Field Name | Data Type | Description | Example |
---|---|---|---|
plate_number | string | License plate number | 川ADT9088 |
plate_color | bigint | Plate color indicates whether the taxi is an electric vehicle | 0 |
alarm | bigint | Alarm status indicates occasions on which the vehicle loses connection | 0 |
state | bigint | Vehicle status indicates whether the vehicle is occupied by passengers | 0 |
lat | double | Latitude | 30.66301 |
lng | double | Longitude | 104.0812 |
direction | bigint | Direction | 214 |
speed | double | Instant speed | 300 |
position time | bigint | Satellite time | 1600457268000 |
crton | bigint | Creation time | 1600457271250 |
crt_by | string | Time creator | 10012 |
Type | Variables | Descriptions | Mean | Standard Deviation |
---|---|---|---|---|
Time | Time-weekend | If the error occurs at the weekend, define it as “1”; otherwise, define it as “0”. | 0.26 | 0.439 |
Time-peak hours | If the error occurs in peak hours, define it as “1”; otherwise, define it as “0”. | 0.28 | 0.448 | |
Time-night | If the error occurs at night, define it as “1”; otherwise, define it as “0”. | 0.37 | 0.483 | |
Intersection type | Int-flyover | If the error occurs near the flyover, define it as “1”; otherwise, define it as “0”. | 0.00 | 0.046 |
Int-crossroad | If the error occurs near the crossroad, define it as “1”; otherwise, define it as “0”. | 0.25 | 0.432 | |
Int-X-junction | If the error occurs near the X-junction, define it as “1”; otherwise, define it as “0”. | 0.02 | 0.141 | |
Int-T-junction | If the error occurs near the T-junction, define it as “1”; otherwise, define it as “0”. | 0.37 | 0.482 | |
Whether it is a large intersection | If the error occurs near a large intersection, define it as “1”; otherwise, define it as “0”. | 0.12 | 0.323 | |
Whether it is a medium-sized intersection | If the error occurs near a medium-sized intersection, define it as “1”; otherwise, define it as “0”. | 0.20 | 0.397 | |
Whether it is a small intersection | If the error occurs near a small intersection, define it as “1”; otherwise, define it as “0”. | 0.25 | 0.435 | |
Previous road’s characteristics | PreRoad-speed limit | If the previous road speed limit is <30 km/h, define it as “1”; If the previous road speed limit is 30–50 km/h, define it as “2”; if the previous road speed limit is >50 km/h, define as “3”. | 0.55 | 0.497 |
PreRoad-bicycle divider | If the error occurs on the previous road with the bicycle divider, define it as “1”; otherwise, define it as “0”. | 0.45 | 0.497 | |
PreRoad-median divider | If the error occurs on the previous road with the median divider, define it as “1”; otherwise, define it as “0”. | 0.09 | 0.287 | |
PreRoad-roadside parking | If the error occurs on the previous road with roadside parking, define it as “1”; otherwise, define it as “0”. | 1.96 | 0.202 | |
PreRoad-one way | If the error occurs on the previous road that is one way, define it as “1”; if the error occurs on the previous road that is two way, define it as “2”. | 0.60724981355 | 4.633130389169 | |
PreRoad-commercial density | The 20-meter buffer radius POI point commercial density of the previous road. | 1.06788664028 | 2.503877913297 | |
PreRoad-public service density | The 20-meter buffer radius POI point public service density of the previous road. | 3.93085171376 | 4.339859341936 | |
PreRoad-resident density | The 20-meter buffer radius POI point resident density of the previous road. | 0.26 | 0.439 | |
Latter road’s characteristics | LatRoad-speed limit | If the latter road speed limit is <30 km/h, define as “1”; if the latter road speed limit is 30–50 km/h, define as “2”; if the latter road speed limit is >50 km/h, define it as “3” | 0.28 | 0.448 |
LatRoad-bicycle divider | If the error occurs on the latter road with the bicycle divider, define it as “1”; otherwise, define it as “0”. | 0.37 | 0.483 | |
LatRoad-median divider | If the error occurs on the latter road with the median divider, define it as “1”; otherwise, define it as “0”. | 0.00 | 0.046 | |
LatRoad-roadside parking | If the error occurs on the latter road with roadside parking, define it as “1”; otherwise, define it as “0”. | 0.25 | 0.432 | |
LatRoad-one way | If the error occurs on the latter road that is one way, define it as “1”; if the error occurs on the latter road that is two way, define it as “2”. | 0.02 | 0.141 | |
LatRoad-commercial density | The 20-meter buffer radius POI point commercial density of the latter road. | 0.37 | 0.482 | |
LatRoad-public service density | The 20-meter buffer radius POI point public service density of the latter road. | 0.12 | 0.323 | |
LatRoad-resident density | The 20-meter buffer radius POI point resident density of the latter road. | 0.20 | 0.397 |
Stages of Calculations | Field Name | Data Type | Description | Example |
---|---|---|---|---|
Raw Data Stage | Plate number | string | License plate number | 川ADT9088 |
lat | double | Latitude | 30.67455 | |
lng | double | Longitude | 104.08496 | |
Position time | bigint | Satellite time | 1600457268000 | |
Shape | string | Road segment type | Line | |
0BJECTID | number | The ID of the road | 1980 | |
Name | string | Road name | Section 3 South of First Ring Road | |
Shape Leng | string | Road length | 0.00751 | |
Data Pre-Processing Stage | plate_number | string | License plate number | 川ADT9088 |
lat | double | Latitude | 30.6746432 | |
lng | double | Longitude | 104.0850109 | |
position time | bigint | Satellite time | 20200919 03:27:48 | |
Shape | string | Road segment type | Line | |
0BJECTID | number | The ID of the road | 1980 | |
Name | string | Road name | Section 3 South of First Ring Road | |
Shape Leng | string | Road length | 0.00751 | |
Map Matching Completed Stage | plate_number | string | License plate number | 川ADT9088 |
lat | string | Latitude | 3395261.8989394824 | |
lng | string | Longitude | 35412317.51912209 | |
Position time | string | Satellite time | 20200919 03:27:48 | |
Shape | string | Road segment type | Line | |
0BJECTID | number | The ID of the road | 1980 | |
Name | string | Road name | Section 3 South of First Ring Road | |
Shape Leng | string | Road length | 0.00751 |
Error Matching Trajectory Type | Meaning | Number of Cases | Percentage |
---|---|---|---|
ORE | Road Segment Off | 24,702 | 14.1% |
WRE | Road Segment Error | 113,349 | 64.6% |
OJE | Intersection Off | 18,904 | 10.8% |
WJE | Intersection Error | 18,557 | 10.6% |
Variables | WRE | OJE | WJE | |||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|
Mean | S.D. | Sig. | OR | Mean | S.D. | Sig. | OR | Mean | S.D. | Sig. | OR | |
Intercept | −0.078 | 0.027 | 0.004 | −0.852 | 0.035 | <0.001 | −0.873 | 0.036 | <0.001 | |||
Time-weekend | −0.054 | 0.018 | 0.002 | 0.948 | −0.049 | 0.023 | 0.030 | 0.952 | 0.042 | 0.022 | 0.063 | 1.042 |
Time-peak hours | −0.041 | 0.020 | 0.035 | 0.960 | −0.060 | 0.025 | 0.015 | 0.942 | −0.027 | 0.026 | 0.284 | 0.973 |
Time-night | −0.092 | 0.018 | <0.001 | 0.912 | −0.154 | 0.023 | <0.001 | 0.857 | 0.294 | 0.023 | <0.001 | 1.342 |
Time-daytime (set as base) | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- |
Int-close to a flyover | 1.179 | 0.193 | <0.001 | 3.252 | 0.703 | 0.245 | 0.004 | 2.021 | −2.516 | 1.017 | 0.013 | 0.081 |
Int road-close to a crossroad | 1.543 | 0.025 | <0.001 | 4.678 | 0.780 | 0.030 | <0.001 | 2.181 | 0.826 | 0.030 | <0.001 | 2.285 |
Int-close to an X-junction | 0.736 | 0.063 | <0.001 | 2.087 | 0.117 | 0.080 | 0.146 | 1.124 | 0.336 | 0.082 | <0.001 | 1.399 |
Int-close to a T-junction | 1.447 | 0.019 | <0.001 | 4.251 | 0.055 | 0.024 | 0.024 | 1.057 | 0.287 | 0.024 | <0.001 | 1.333 |
Int-close to a large intersection | −0.044 | 0.028 | 0.117 | 0.957 | 0.445 | 0.036 | <0.001 | 1.560 | 0.434 | 0.036 | <0.001 | 1.543 |
Int-close to a medium-sized intersection | 0.932 | 0.027 | <0.001 | 2.540 | 0.613 | 0.035 | <0.001 | 1.846 | 0.425 | 0.036 | <0.001 | 1.529 |
Int-close to a small intersection | 0.985 | 0.021 | <0.001 | 2.678 | 0.353 | 0.027 | <0.001 | 1.423 | 0.242 | 0.027 | <0.001 | 1.274 |
Int-beyond the intersection range (set as base) | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- |
PreRoad-speed limit <30 km/h | −1.027 | 0.032 | <0.001 | 0.358 | 0.431 | 0.038 | <0.001 | 1.539 | −0.360 | 0.037 | <0.001 | 0.698 |
PreRoad-speed limit 40–50 km/h | −0.108 | 0.035 | 0.002 | 0.897 | 0.408 | 0.046 | <0.001 | 1.503 | −0.388 | 0.047 | <0.001 | 0.678 |
PreRoad-speed limit ≥60 km/h (set as base) | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- |
PreRoad-bicycle divider | 0.096 | 0.029 | 0.001 | 1.101 | −0.545 | 0.037 | <0.001 | 0.580 | −0.001 | 0.036 | 0.983 | 0.999 |
PreRoad-median divider | 0.429 | 0.032 | <0.001 | 1.535 | 0.073 | 0.041 | 0.079 | 1.076 | −0.437 | 0.040 | <0.001 | 0.646 |
PreRoad-roadside parking | 0.246 | 0.032 | <0.001 | 1.279 | 0.179 | 0.035 | <0.001 | 1.196 | −0.020 | 0.035 | 0.573 | 0.980 |
PreRoad-one way | 0.245 | 0.041 | <0.001 | 1.278 | 0.430 | 0.043 | <0.001 | 1.538 | 0.211 | 0.046 | <0.001 | 1.235 |
PreRoad-commercial density | −0.027 | 0.002 | <0.001 | 0.973 | −0.008 | 0.002 | <0.001 | 0.992 | 0.004 | 0.001 | 0.005 | 1.004 |
PreRoad-public service density | 0.019 | 0.004 | <0.001 | 1.019 | −0.033 | 0.005 | <0.001 | 0.967 | −0.015 | 0.005 | 0.002 | 0.985 |
PreRoad-resident density | 0.045 | 0.002 | <0.001 | 1.046 | −0.002 | 0.003 | 0.466 | 0.998 | −0.011 | 0.003 | <0.001 | 0.989 |
LatRoad-speed limit <30 km/h | −1.051 | 0.032 | <0.001 | 0.349 | −0.263 | 0.038 | <0.001 | 0.769 | 0.851 | 0.038 | <0.001 | 2.342 |
LatRoad-speed limit 40–50 km/h | −0.168 | 0.035 | <0.001 | 0.845 | −0.212 | 0.045 | <0.001 | 0.809 | 0.066 | 0.049 | 0.174 | 1.068 |
LatRoad-speed limit ≥60 km/h (set as base) | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- |
LatRoad-bicycle divider | 0.492 | 0.029 | <0.001 | 1.636 | 0.283 | 0.036 | <0.001 | 1.328 | −0.351 | 0.037 | <0.001 | 0.704 |
LatRoad-median divider | 0.145 | 0.032 | <0.001 | 1.156 | 0.390 | 0.040 | <0.001 | 1.477 | 0.530 | 0.042 | <0.001 | 1.699 |
LatRoad-roadside parking | 0.118 | 0.032 | <0.001 | 1.125 | −0.110 | 0.037 | 0.003 | 0.896 | −0.153 | 0.034 | <0.001 | 0.858 |
LatRoad-one way | 0.049 | 0.041 | 0.233 | 1.051 | −0.018 | 0.048 | 0.704 | 0.982 | 0.015 | 0.044 | 0.738 | 1.015 |
LatRoad-commercial density | −0.020 | 0.002 | <0.001 | 0.980 | −0.001 | 0.002 | 0.429 | 0.999 | <0.001 | 0.001 | 0.748 | 1.000 |
LatRoad-public service density | 0.040 | 0.004 | <0.001 | 1.041 | 0.050 | 0.005 | <0.001 | 1.052 | 0.012 | 0.005 | 0.026 | 1.012 |
LatRoad-resident density | 0.052 | 0.002 | <0.001 | 1.053 | 0.030 | 0.003 | <0.001 | 1.031 | 0.011 | 0.003 | <0.001 | 1.011 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Qu, L.; Zhou, Y.; Li, J.; Yu, Q.; Jiang, X. HMM-Based Map Matching and Spatiotemporal Analysis for Matching Errors with Taxi Trajectories. ISPRS Int. J. Geo-Inf. 2023, 12, 330. https://doi.org/10.3390/ijgi12080330
Qu L, Zhou Y, Li J, Yu Q, Jiang X. HMM-Based Map Matching and Spatiotemporal Analysis for Matching Errors with Taxi Trajectories. ISPRS International Journal of Geo-Information. 2023; 12(8):330. https://doi.org/10.3390/ijgi12080330
Chicago/Turabian StyleQu, Lin, Yue Zhou, Jiangxin Li, Qiong Yu, and Xinguo Jiang. 2023. "HMM-Based Map Matching and Spatiotemporal Analysis for Matching Errors with Taxi Trajectories" ISPRS International Journal of Geo-Information 12, no. 8: 330. https://doi.org/10.3390/ijgi12080330
APA StyleQu, L., Zhou, Y., Li, J., Yu, Q., & Jiang, X. (2023). HMM-Based Map Matching and Spatiotemporal Analysis for Matching Errors with Taxi Trajectories. ISPRS International Journal of Geo-Information, 12(8), 330. https://doi.org/10.3390/ijgi12080330