PredLife: Predicting Fine-Grained Future Activity PatternsShow others and affiliations
2023 (English)In: IEEE Transactions on Big Data, E-ISSN 2332-7790, Vol. 9, no 6, p. 1658-1669Article in journal (Refereed) Published
Abstract [en]
Activity pattern prediction is a critical part of urban computing, urban planning, intelligent transportation, and so on. Based on a dataset with more than 10 million GPS trajectory records collected by mobile sensors, this research proposed a CNN-BiLSTM-VAE-ATT-based encoder-decoder model for fine-grained individual activity sequence prediction. The model combines the long-term and short-term dependencies crosswise and also considers randomness, diversity, and uncertainty of individual activity patterns. The proposed results show higher accuracy compared to the ten baselines. The model can generate high diversity results while approximating the original activity patterns distribution. Moreover, the model also has interpretability in revealing the time dependency importance of the activity pattern prediction.
Place, publisher, year, edition, pages
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC , 2023. Vol. 9, no 6, p. 1658-1669
Keywords [en]
Activity pattern prediction, Human mobility, Big GPS data, Variational autoencoder, LSTM
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:mdh:diva-65131DOI: 10.1109/TBDATA.2023.3310241ISI: 001107490500009Scopus ID: 2-s2.0-85169689406OAI: oai:DiVA.org:mdh-65131DiVA, id: diva2:1821375
2023-12-202023-12-202024-01-23Bibliographically approved