Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Large Language Models for Spatial Trajectory Patterns Mining (2310.04942v1)

Published 7 Oct 2023 in cs.LG

Abstract: Identifying anomalous human spatial trajectory patterns can indicate dynamic changes in mobility behavior with applications in domains like infectious disease monitoring and elderly care. Recent advancements in LLMs have demonstrated their ability to reason in a manner akin to humans. This presents significant potential for analyzing temporal patterns in human mobility. In this paper, we conduct empirical studies to assess the capabilities of leading LLMs like GPT-4 and Claude-2 in detecting anomalous behaviors from mobility data, by comparing to specialized methods. Our key findings demonstrate that LLMs can attain reasonable anomaly detection performance even without any specific cues. In addition, providing contextual clues about potential irregularities could further enhances their prediction efficacy. Moreover, LLMs can provide reasonable explanations for their judgments, thereby improving transparency. Our work provides insights on the strengths and limitations of LLMs for human spatial trajectory analysis.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. Staleness-alleviated distributed gnn training via online dynamic-embedding prediction. arXiv preprint arXiv:2308.13466, 2023.
  2. Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv preprint arXiv:2204.05862, 2022.
  3. Learning object motion patterns for anomaly detection and improved object detection. In 2008 IEEE conference on computer vision and pattern recognition, pages 1–8. IEEE, 2008.
  4. Jonathan Bennett. OpenStreetMap. Packt Publishing Ltd, 2010.
  5. Transportation mode-based segmentation and classification of movement trajectories. International Journal of Geographical Information Science, 27(2):385–407, 2013.
  6. Language models are few-shot learners. ArXiv, abs/2005.14165, 2020.
  7. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota, June 2019. Association for Computational Linguistics.
  8. A hierarchical autoencoder learning model for path prediction and abnormality detection. Pattern Recognition Letters, 130:216–224, 2020.
  9. Google AI. BARD: Deepmind’s conversational ai assistant. https://blog.google/products/search/introducing-bard-google-ai, 2022. Accessed: October 7, 2023.
  10. Graph neural networks: Graph transformation. Graph Neural Networks: Foundations, Frontiers, and Applications, pages 251–275, 2022.
  11. Location-based social network data generation based on patterns of life. In 2020 21st IEEE International Conference on Mobile Data Management (MDM), pages 158–167. IEEE, 2020.
  12. Large language models are zero-shot reasoners. Advances in neural information processing systems, 35:22199–22213, 2022.
  13. Trajectory outlier detection: A partition-and-detect framework. In 2008 IEEE 24th International Conference on Data Engineering, pages 140–149. IEEE, 2008.
  14. Trajectory clustering: a partition-and-group framework. In Proceedings of the 2007 ACM SIGMOD international conference on Management of data, pages 593–604, 2007.
  15. Domain specialization as the key to make large language models disruptive: A comprehensive survey. arXiv preprint arXiv:2305.18703, 2023.
  16. Metaicl: Learning to learn in context. arXiv preprint arXiv:2110.15943, 2021.
  17. Contact tracing: Beyond the apps. SIGSPATIAL Special, 12(2):15–24, 2020.
  18. Towards mobility data science (vision paper). arXiv preprint arXiv:2307.05717, 2023.
  19. Let’s speak trajectories. In Proceedings of the 30th International Conference on Advances in Geographic Information Systems, pages 1–4, 2022.
  20. OpenAI. Gpt-4 technical report. ArXiv, abs/2303.08774, 2023.
  21. Semantic trajectories modeling and analysis. ACM Computing Surveys (CSUR), 45(4):1–32, 2013.
  22. Pre-trained models for natural language processing: A survey. Science China Technological Sciences, 63(10):1872–1897, 2020.
  23. Toward accurate spatiotemporal COVID-19 risk scores using high-resolution real-world mobility data. ACM Trans. Spatial Algorithms Syst., 8(2):1–30, 2022.
  24. Deep one-class classification. In International conference on machine learning, pages 4393–4402. PMLR, 2018.
  25. Iot wearable sensors and devices in elderly care: A literature review. Sensors, 20(10):2826, 2020.
  26. Trajectory similarity measures. Sigspatial Special, 7(1):43–50, 2015.
  27. Llama: Open and efficient foundation language models. ArXiv, abs/2302.13971, 2023.
  28. Llama 2: Open foundation and fine-tuned chat models. ArXiv, abs/2307.09288, 2023.
  29. Attention is all you need. In NIPS, 2017.
  30. Where would i go next? large language models as human mobility predictors. arXiv preprint arXiv:2308.15197, 2023.
  31. Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652, 2021.
  32. Leveraging language foundation models for human mobility forecasting. In Proceedings of the 30th International Conference on Advances in Geographic Information Systems, pages 1–9, 2022.
  33. Trajectory clustering via deep representation learning. In 2017 international joint conference on neural networks (IJCNN), pages 3880–3887. IEEE, 2017.
  34. Jianting Zhang. Smarter outlier detection and deeper understanding of large-scale taxi trip records: a case study of nyc. In Proceedings of the ACM SIGKDD International Workshop on Urban Computing, pages 157–162, 2012.
  35. Representation learning on spatial networks. Advances in Neural Information Processing Systems, 34:2303–2318, 2021.
  36. Unsupervised deep subgraph anomaly detection. In 2022 IEEE International Conference on Data Mining (ICDM), pages 753–762. IEEE, 2022.
  37. A survey of large language models. arXiv preprint arXiv:2303.18223, 2023.
  38. Understanding transportation modes based on gps data for web applications. ACM Transactions on the Web (TWEB), 4(1):1–36, 2010.
  39. Geolife: A collaborative social networking service among user, location and trajectory. IEEE Data Eng. Bull., 33(2):32–39, 2010.
  40. Anomaly detection with robust deep autoencoders. In Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining, pages 665–674, 2017.
  41. Urban life: a model of people and places. Computational and Mathematical Organization Theory, 29(1):20–51, 2023.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Zheng Zhang (488 papers)
  2. Hossein Amiri (7 papers)
  3. Zhenke Liu (5 papers)
  4. Andreas Züfle (99 papers)
  5. Liang Zhao (353 papers)
Citations (14)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now