Analysis of Sparse Trajectory Features Based on Mobile Device Location for User Group Classification Using Gaussian Mixture Model
Location data collected from mobile devices via global positioning system often lack semantic information and can form sparse trajectories in space and time. This study investigates whether user age groups can be accurately classified solely from such sparse spatial–temporal trajectories. We propose...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/2/982 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589176606818304 |
|---|---|
| author | Yohei Kakimoto Yuto Omae Hirotaka Takahashi |
| author_facet | Yohei Kakimoto Yuto Omae Hirotaka Takahashi |
| author_sort | Yohei Kakimoto |
| collection | DOAJ |
| description | Location data collected from mobile devices via global positioning system often lack semantic information and can form sparse trajectories in space and time. This study investigates whether user age groups can be accurately classified solely from such sparse spatial–temporal trajectories. We propose a feature extraction method based on a Gaussian mixture model (GMM), which assigns representative points (RPs) by clustering the location data and aggregating user trajectories into these RPs. We then construct three machine learning (ML) models—support vector classifier (SVC), random forest (RF), and deep neural network (DNN)—using the GMM-based features and compare their performance with that of the improved DNN (IDNN), which is an existing feature extraction approach. In our experiments, we introduced a missing value ratio <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>θ</mi><mi>th</mi></msub></semantics></math></inline-formula> to quantify trajectory sparsity and analyzed the effect of trajectory sparsity on the classification accuracy and generalizability performance of the ML models. The results indicate that GMM-based features outperform IDNN-based features in both classification accuracy and generalization performance. Notably, the RF model achieved the highest accuracy, whereas the SVC model displayed stable generalizability. As the missing value ratio <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>θ</mi><mi>th</mi></msub></semantics></math></inline-formula> increases, the IDNN becomes more susceptible to overfitting, whereas the GMM-based approach preserves accuracy and robustness. These findings suggest that sparse trajectories can still offer meaningful classification performance with appropriate feature design and model selection even without semantic information. This approach holds promise for domains where large-scale, sparse trajectory data are common, including urban planning, marketing analysis, and public policy. |
| format | Article |
| id | doaj-art-39455e76dbe848da9e4dfe5b5d7fb084 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-39455e76dbe848da9e4dfe5b5d7fb0842025-01-24T13:21:34ZengMDPI AGApplied Sciences2076-34172025-01-0115298210.3390/app15020982Analysis of Sparse Trajectory Features Based on Mobile Device Location for User Group Classification Using Gaussian Mixture ModelYohei Kakimoto0Yuto Omae1Hirotaka Takahashi2College of Industrial Technology, Nihon University, 1-2-1 Izumicho, Narashino 275-8575, JapanCollege of Industrial Technology, Nihon University, 1-2-1 Izumicho, Narashino 275-8575, JapanDepartment of Design and Data Science and Research Center for Space Science, Advanced Research Laboratories, Tokyo City University, 3-3-1 Ushikubo-Nishi, Tsuzuki-ku, Yokohama 224-8551, JapanLocation data collected from mobile devices via global positioning system often lack semantic information and can form sparse trajectories in space and time. This study investigates whether user age groups can be accurately classified solely from such sparse spatial–temporal trajectories. We propose a feature extraction method based on a Gaussian mixture model (GMM), which assigns representative points (RPs) by clustering the location data and aggregating user trajectories into these RPs. We then construct three machine learning (ML) models—support vector classifier (SVC), random forest (RF), and deep neural network (DNN)—using the GMM-based features and compare their performance with that of the improved DNN (IDNN), which is an existing feature extraction approach. In our experiments, we introduced a missing value ratio <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>θ</mi><mi>th</mi></msub></semantics></math></inline-formula> to quantify trajectory sparsity and analyzed the effect of trajectory sparsity on the classification accuracy and generalizability performance of the ML models. The results indicate that GMM-based features outperform IDNN-based features in both classification accuracy and generalization performance. Notably, the RF model achieved the highest accuracy, whereas the SVC model displayed stable generalizability. As the missing value ratio <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>θ</mi><mi>th</mi></msub></semantics></math></inline-formula> increases, the IDNN becomes more susceptible to overfitting, whereas the GMM-based approach preserves accuracy and robustness. These findings suggest that sparse trajectories can still offer meaningful classification performance with appropriate feature design and model selection even without semantic information. This approach holds promise for domains where large-scale, sparse trajectory data are common, including urban planning, marketing analysis, and public policy.https://www.mdpi.com/2076-3417/15/2/982sparse trajectory classificationmobile device locationGaussian mixture modelmachine learning |
| spellingShingle | Yohei Kakimoto Yuto Omae Hirotaka Takahashi Analysis of Sparse Trajectory Features Based on Mobile Device Location for User Group Classification Using Gaussian Mixture Model Applied Sciences sparse trajectory classification mobile device location Gaussian mixture model machine learning |
| title | Analysis of Sparse Trajectory Features Based on Mobile Device Location for User Group Classification Using Gaussian Mixture Model |
| title_full | Analysis of Sparse Trajectory Features Based on Mobile Device Location for User Group Classification Using Gaussian Mixture Model |
| title_fullStr | Analysis of Sparse Trajectory Features Based on Mobile Device Location for User Group Classification Using Gaussian Mixture Model |
| title_full_unstemmed | Analysis of Sparse Trajectory Features Based on Mobile Device Location for User Group Classification Using Gaussian Mixture Model |
| title_short | Analysis of Sparse Trajectory Features Based on Mobile Device Location for User Group Classification Using Gaussian Mixture Model |
| title_sort | analysis of sparse trajectory features based on mobile device location for user group classification using gaussian mixture model |
| topic | sparse trajectory classification mobile device location Gaussian mixture model machine learning |
| url | https://www.mdpi.com/2076-3417/15/2/982 |
| work_keys_str_mv | AT yoheikakimoto analysisofsparsetrajectoryfeaturesbasedonmobiledevicelocationforusergroupclassificationusinggaussianmixturemodel AT yutoomae analysisofsparsetrajectoryfeaturesbasedonmobiledevicelocationforusergroupclassificationusinggaussianmixturemodel AT hirotakatakahashi analysisofsparsetrajectoryfeaturesbasedonmobiledevicelocationforusergroupclassificationusinggaussianmixturemodel |