Trip Purpose Imputation Using GPS Trajectories with Machine Learning
We studied trip purpose imputation using data mining and machine learning techniques based on a dataset of GPS-based trajectories gathered in Switzerland. With a large number of labeled activities in eight categories, we explored location information using hierarchical clustering and achieved a clas...
| 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/2220-9964/10/11/775 |
| _version_ | 1797510068666630144 |
|---|---|
| author | Qinggang Gao Joseph Molloy Kay W. Axhausen |
| author_facet | Qinggang Gao Joseph Molloy Kay W. Axhausen |
| author_sort | Qinggang Gao |
| collection | DOAJ |
| description | We studied trip purpose imputation using data mining and machine learning techniques based on a dataset of GPS-based trajectories gathered in Switzerland. With a large number of labeled activities in eight categories, we explored location information using hierarchical clustering and achieved a classification accuracy of 86.7% using a random forest approach as a baseline. The contribution of this study is summarized below. Firstly, using information from GPS trajectories exclusively without personal information shows a negligible decrease in accuracy (0.9%), which indicates the good performance of our data mining steps and the wide applicability of our imputation scheme in case of limited information availability. Secondly, the dependence of model performance on the geographical location, the number of participants, and the duration of the survey is investigated to provide a reference when comparing classification accuracy. Furthermore, we show the ensemble filter to be an excellent tool in this research field not only because of the increased accuracy (93.6%), especially for minority classes, but also the reduced uncertainties in blindly trusting the labeling of activities by participants, which is vulnerable to class noise due to the large survey response burden. Finally, the trip purpose derivation accuracy across participants reaches 74.8%, which is significant and suggests the possibility of effectively applying a model trained on GPS trajectories of a small subset of citizens to a larger GPS trajectory sample. |
| first_indexed | 2024-03-10T05:26:31Z |
| format | Article |
| id | doaj.art-5b45681ef4ff4326aacb528c01cb781d |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-03-10T05:26:31Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-5b45681ef4ff4326aacb528c01cb781d2023-11-22T23:36:40ZengMDPI AGISPRS International Journal of Geo-Information2220-99642021-11-01101177510.3390/ijgi10110775Trip Purpose Imputation Using GPS Trajectories with Machine LearningQinggang Gao0Joseph Molloy1Kay W. Axhausen2Institute for Transport Planning and Systems, ETH Zurich, 8093 Zurich, SwitzerlandInstitute for Transport Planning and Systems, ETH Zurich, 8093 Zurich, SwitzerlandInstitute for Transport Planning and Systems, ETH Zurich, 8093 Zurich, SwitzerlandWe studied trip purpose imputation using data mining and machine learning techniques based on a dataset of GPS-based trajectories gathered in Switzerland. With a large number of labeled activities in eight categories, we explored location information using hierarchical clustering and achieved a classification accuracy of 86.7% using a random forest approach as a baseline. The contribution of this study is summarized below. Firstly, using information from GPS trajectories exclusively without personal information shows a negligible decrease in accuracy (0.9%), which indicates the good performance of our data mining steps and the wide applicability of our imputation scheme in case of limited information availability. Secondly, the dependence of model performance on the geographical location, the number of participants, and the duration of the survey is investigated to provide a reference when comparing classification accuracy. Furthermore, we show the ensemble filter to be an excellent tool in this research field not only because of the increased accuracy (93.6%), especially for minority classes, but also the reduced uncertainties in blindly trusting the labeling of activities by participants, which is vulnerable to class noise due to the large survey response burden. Finally, the trip purpose derivation accuracy across participants reaches 74.8%, which is significant and suggests the possibility of effectively applying a model trained on GPS trajectories of a small subset of citizens to a larger GPS trajectory sample.https://www.mdpi.com/2220-9964/10/11/775class noisedata miningensemble filterhierarchical clusteringmachine learningrandom forest |
| spellingShingle | Qinggang Gao Joseph Molloy Kay W. Axhausen Trip Purpose Imputation Using GPS Trajectories with Machine Learning ISPRS International Journal of Geo-Information class noise data mining ensemble filter hierarchical clustering machine learning random forest |
| title | Trip Purpose Imputation Using GPS Trajectories with Machine Learning |
| title_full | Trip Purpose Imputation Using GPS Trajectories with Machine Learning |
| title_fullStr | Trip Purpose Imputation Using GPS Trajectories with Machine Learning |
| title_full_unstemmed | Trip Purpose Imputation Using GPS Trajectories with Machine Learning |
| title_short | Trip Purpose Imputation Using GPS Trajectories with Machine Learning |
| title_sort | trip purpose imputation using gps trajectories with machine learning |
| topic | class noise data mining ensemble filter hierarchical clustering machine learning random forest |
| url | https://www.mdpi.com/2220-9964/10/11/775 |
| work_keys_str_mv | AT qingganggao trippurposeimputationusinggpstrajectorieswithmachinelearning AT josephmolloy trippurposeimputationusinggpstrajectorieswithmachinelearning AT kaywaxhausen trippurposeimputationusinggpstrajectorieswithmachinelearning |