Learning Heterogeneous Spatial-Temporal Representation for Bike-Sharing Demand Prediction

Li, Youru; Zhu, Zhongkui; Kong, Deqiang; Xu, Meixiang; Zhao, Yao

doi:10.1609/aaai.v33i01.33011004

Cited by 68 publications

(40 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Batch time means the runtime of each batch in the model testing. Method Accuracy Precision Sensitivity Specificity F1-score AUC Model size Batch time DyHAN [113] 0.9008 0.9368 0.9479 0.9258 0.9312 0.8918 184.5M 2.10 s CE-LSTM [114] 0.9161 0.9458 0.9585 0.9287 0.9372 0.9035 273.6M 2.12 s Ours 0.9810 0.9889 0.9861 0.9859 0.9875 0.9908 76.4M 1.14 s …”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Pay attention to doctor–patient dialogues: Multi-modal knowledge graph attention image-text embedding for COVID-19 diagnosis

et al. 2021

View full text Add to dashboard Cite

The sudden increase in coronavirus disease 2019 (COVID-19) cases puts high pressure on healthcare services worldwide. At this stage, fast, accurate, and early clinical assessment of the disease severity is vital. In general, there are two issues to overcome: (1) Current deep learning-based works suffer from multimodal data adequacy issues; (2) In this scenario, multimodal (e.g., text, image) information should be taken into account together to make accurate inferences. To address these challenges, we propose a multi-modal knowledge graph attention embedding for COVID-19 diagnosis. Our method not only learns the relational embedding from nodes in a constituted knowledge graph but also has access to medical knowledge, aiming at improving the performance of the classifier through the mechanism of medical knowledge attention. The experimental results show that our approach significantly improves classification performance compared to other state-of-the-art techniques and possesses robustness for each modality from multi-modal data. Moreover, we construct a new COVID-19 multi-modal dataset based on text mining, consisting of 1393 doctor-patient dialogues and their 3706 images (347 X-ray 2598 CT 761 ultrasound) about COVID-19 patients and 607 non-COVID-19 patient dialogues and their 10754 images (9658 X-ray 494 CT 761 ultrasound), and the fine-grained labels of all. We hope this work can provide insights to the researchers working in this area to shift the attention from only medical images to the doctor-patient dialogue and its corresponding medical images.

show abstract

Section: Resultsmentioning

confidence: 99%

“…

CE-LSTM [114] is an event-flow serializing method to learn the representation from heterogeneous spatial–temporal graph through encoding the evolution of dynamic heterogeneous graph into a special language pattern such as word sequence in a corpus.…”

Section: Resultsmentioning

confidence: 99%

Pay attention to doctor–patient dialogues: Multi-modal knowledge graph attention image-text embedding for COVID-19 diagnosis

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The taxi demand forecasting method proposed by Geng et al [21] can help taxi companies to better allocate vehicles. Li et al [22] proposed a method for forecasting the demand for shared bicycles, which can optimize resource scheduling.…”

Section: Introductionmentioning

confidence: 99%

A Road Network Enhanced Gate Recurrent Unit Model for Gather Prediction in Smart Cities

Yuan

Tian

Yan

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Gather prediction is an indispensable part of smart city projects. The city government can respond in advance based on gather predictions and greatly reduce the loss and risks caused by vicious gatherings. Compared with other trajectory prediction tasks (i.e., the recommendation of point of interest), gather prediction pay more attention to real-time trajectory data and requests stronger spatial-temporal dependence. At the same time, gather prediction is more focused on scenes with multiple types of trajectories. And the existing methods majorly rely on the trajectory data and ignore the great influence of geographical environment (i.e., road network structure). Therefore, this paper transforms the gather prediction into the trajectory prediction task with strong real-time condition in a certain city and conducts the gathering situations by predicting users’ aggregated movements in next minutes or hours. A novel Spatiotemporal Gate Recurrent Unit (STGRU) model is proposed, where spatiotemporal gates and road network gate are introduced to capture the spatiotemporal relationships between trajectories. Compared with existing methods, we improve the performance of the model by adding road network structure and external knowledges, as well as time and distance gates to reduce model parameters. The proposed STGRU is evaluated on three real-world trajectory datasets, and the experimental results demonstrate the effectiveness of the proposed model.

show abstract

“…The data with consecutive zeros in most cases obstruct the model's learning, inducing close-to-zero results in prediction. This problem can be mitigated by transforming the data into latent feature space representation (14,15). In this research, an autoencoder based on the convolutional neural network was used to efficiently extract the latent feature of the data and alleviate the problem caused by sparse data representation (16).…”

mentioning

confidence: 99%

Spatiotemporal Demand Prediction Model for E-Scooter Sharing Services with Latent Feature and Deep Learning

Ham

Cho

Park³

et al. 2021

Transportation Research Record

View full text Add to dashboard Cite

The electric scooter (e-scooter) sharing service has attracted significant attention because of its extensive usage and eco-friendliness. Since e-scooters are mostly accessed by foot, the presence of e-scooters within walking distance has a crucial effect on the service quality. Therefore, to maintain appropriate service quality, relocation strategies are often used to properly distribute e-scooters within service areas. There are extensive literatures on demand forecasting for an efficient relocation. However, the study of the relocation of small-scale spatial units within walking distance level is still inadequate because of the sparsity of demand data. This research aims to establish an effective methodology for predicting the demand for e-scooters in high spatial resolution. A new grid-based spatial setting was created with the usage data. The model in the methodology predicts not only the identified demand but also the unmet demand to increase practicality. A convolutional autoencoder is used to obtain the latent feature that can reduce the problem of representing sparse data. An encoder–recurrent neural network–decoder (ERD) framework with a convolutional autoencoder resulted in a huge improvement in predicting spatiotemporal events. This new ERD framework shows enhanced prediction performance, reducing the mean squared error loss to 0.00036 from 0.00679 compared with the baseline long short-term memory model. This methodological strategy has its significance in that it can solve any prediction issue with spatiotemporal data, even those with sparse data problems.

show abstract

Learning Heterogeneous Spatial-Temporal Representation for Bike-Sharing Demand Prediction

Cited by 68 publications

References 16 publications

Pay attention to doctor–patient dialogues: Multi-modal knowledge graph attention image-text embedding for COVID-19 diagnosis

Pay attention to doctor–patient dialogues: Multi-modal knowledge graph attention image-text embedding for COVID-19 diagnosis

A Road Network Enhanced Gate Recurrent Unit Model for Gather Prediction in Smart Cities

Spatiotemporal Demand Prediction Model for E-Scooter Sharing Services with Latent Feature and Deep Learning

Contact Info

Product

Resources

About