A Multi-Scale Attributes Attention Model for Transport Mode Identification

Jiang, Guiyuan; Lam, Siew-Kei; He, Peilan; Ou, Changhai; Ai, Dihao

doi:10.1109/tits.2020.3008469

Cited by 13 publications

(5 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, their extracted features are highly abstract and nonintuitive, making interpretation challenging. Recently, DL with image-based features emerged in TMD, aiding the capture of spatial information, local patterns, and global context [27][28][29][30][31], but entailing temporal information loss, increased computational requirements, and more data preprocessing complexity. Therefore, we aim for a method that achieves high detection results using minimal features and computational resources, striking a balance between effectiveness and practicality.…”

Section: Related Workmentioning

confidence: 99%

POPAyI: Muscling Ordinal Patterns for Low-Complex and Usability-Aware Transportation Mode Detection

Cardoso-Pereira,

Borges,

Viana

et al. 2024

IEEE Internet Things J.

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

POPAyI: Muscling Ordinal Patterns for Low-Complex and Usability-Aware Transportation Mode Detection

Cardoso-Pereira,

Borges,

Viana

et al. 2024

IEEE Internet Things J.

View full text Add to dashboard Cite

“…As deep learning techniques have developed, researchers have begun applying deep learning methods to various motion or global positioning system (GPS) sensors. Studies have applied convolutional neural networks (CNNs), ensemble CNNs, convolutional long shortterm memory (convolutional LSTM), or other self-designed architectures to the features extracted from GPS sensors, and they achieved up to 92.7% accuracy [9], [10], [20], [23]. In contrast, studies using motion sensors have applied neural networks (NNs), deep neural networks (DNNs), CNNs, recurrent neural networks (RNNs), or other self-designed architectures, resulting in accuracies up to 98.4% [3], [4], [6], [8], [10], [24], [26].…”

Section: Related Studies a Tmd For People With And Without Mobility D...mentioning

confidence: 99%

“…TMD technology has significant social benefits and real-life applications, such as urban planning, traffic control, controlling potential hazards, health monitoring, localization and positioning, and journey planning [2], [4]. To exploit such advantages, researchers have extensively studied TMD based on smartphone sensor data, which include motion and location sensors [3], [9], [10]. TMD can be more valuable for people with mobility disabilities because it aids in improving their mobility and accessibility, and such improvement is essential as they are important factors for their quality of life and social inclusion [11], [12].…”

Section: Introductionmentioning

confidence: 99%

User and Period Independent Transportation Mode Detection for Wheelchair Users

et al. 2023

View full text Add to dashboard Cite

Transportation mode detection (TMD) is an important research area in human activity recognition. It can improve the mobility and accessibility of people by providing a better understanding of their mobility patterns, thereby enhancing their quality of life and social inclusion. Although previous studies of TMD for people without mobility disabilities exhibited, the performance of TMD models on new users and periods was limited. This issue would be more important for people with mobility disabilities. This study investigated the negative impact of user and period differences on the performance of TMD for wheelchair users (wTMD) and suggested a method to address these challenges. Our main findings are (1) user and period differences degraded the wTMD performance from 94.28% to 59.32%; (2) the multi-DenseNet with a soft voting ensemble provided a 76.49% accuracy to data from different users and periods. We expect that our understanding of wTMD will aid in the design of more generalized wTMD models.

show abstract

“…Holidays can also lead to traffic congestion around specific areas (like temples or churches). Incorporating these factors can enhance the capability of our model to distinguish such traffic situations [19]. We construct X t e ∈ R N ×de to encode external factors, which include one-hot encoded weather conditions, concatenate it with a binary variable to indicate whether the day is a holiday or not.…”

Section: External Factorsmentioning

confidence: 99%

Learning Congestion Propagation Behaviors for Traffic Prediction

Sun

Jiang

et al. 2021

2021 IEEE International Intelligent Transportation Systems Conference (ITSC)

Self Cite

View full text Add to dashboard Cite

Traffic prediction is a challenging task as the traffic flow is influenced by many seasonal, stochastic, and structural factors. In addition, the spatial and temporal distribution of traffic flow can induce direct and indirect congestion propagation patterns. While existing works have attempted to model spatial-temporal graphs to capture the spatial correlations and temporal dependencies, they fail to consider congestion propagation behavior among road segments. In this paper, we propose a novel traffic prediction model that takes into account the congestion propagation tendencies to improve prediction accuracy. A novel diffusion graph convolution network model is developed to capture the spatial traffic correlations while considering the congestion propagation behavior. Our model also jointly learns the importance of seasonal traffic speed correlations, road contextual information (structural information), and stochastic factors (external factors) through an attention layer. Experimental results on real-world data-set demonstrate the superiority of our method over state-of-theart traffic prediction techniques, and confirm the significance of congestion propagation behavior in traffic prediction.

show abstract

A Multi-Scale Attributes Attention Model for Transport Mode Identification

Cited by 13 publications

References 46 publications

POPAyI: Muscling Ordinal Patterns for Low-Complex and Usability-Aware Transportation Mode Detection

POPAyI: Muscling Ordinal Patterns for Low-Complex and Usability-Aware Transportation Mode Detection

User and Period Independent Transportation Mode Detection for Wheelchair Users

Learning Congestion Propagation Behaviors for Traffic Prediction

Contact Info

Product

Resources

About