Semi-Supervised Deep Learning Approach for Transportation Mode Identification Using GPS Trajectory Data

Abstract

Identifying users' transportation modes (e.g., bike, bus, train, and car) is a key step towards many transportation related problems including (but not limited to) transport planning, transit demand analysis, auto ownership, and transportation emissions analysis. Traditionally, the information for analyzing travelers' behavior for choosing transport mode(s) was obtained through travel surveys. High cost, low-response rate, time-consuming manual data collection, and misreporting are the main demerits of the survey-based approaches. With the rapid growth of ubiquitous GPS-enabled devices (e.g., smartphones), a constant stream of users' trajectory data can be recorded. A user's GPS trajectory is a sequence of GPS points, recorded by means of a GPS-enabled device, in which a GPS point contains the information of the device geographic location at a particular moment. In this research, users' GPS trajectories, rather than traditional resources, are harnessed to predict their transportation mode by means of statistical models. With respect to the statistical models, a wide range of studies have developed travel mode detection models using on hand-designed attributes and classical learning techniques. Nonetheless, hand-crafted features cause some main shortcomings including vulnerability to traffic uncertainties and biased engineering justification in generating effective features. A potential solution to address these issues is by leveraging deep learning frameworks that are capable of capturing abstract features from the raw input in an automated fashion. Thus, in this thesis, deep learning architectures are exploited in order to identify transport modes based on only raw GPS tracks. It is worth noting that a significant portion of trajectories in GPS data might not be annotated by a transport mode and the acquisition of labeled data is a more expensive and labor-intensive task in comparison with collecting unlabeled data. Thus, utilizing the unlabeled GPS trajectory (i.e., the GPS trajectories that have not been annotated by a transport mode) is a cost-effective approach for improving the prediction quality of the travel mode detection model. Therefore, the unlabeled GPS data are also leveraged by developing a novel deep-learning architecture that is capable of extracting information from both labeled and unlabeled data. The experimental results demonstrate the superiority of the proposed models over the state-of-the-art methods in literature with respect to several performance metrics.

A Semi-Supervised Deep Residual Network for Mode Detection in Wi-Fi Signals

“…In short, semisupervised algorithms add unlabelled samples to the training data and the classifier is retrained on the new augmented training dataset. In one of the few studies in using semisupervised deep learning approaches for mode detection, Dabiri et al (2019) proposed a semi-supervised Convolutional Autoencoder architecture to predict transportation mode using GPS data. They achieved an accuracy of 76.8% with four convolutional layer, showing a decrease in accuracy in a higher number of layers.…”

Big Data Analysis of Beijing Urban Rail Transit Fares Based on Passenger Flow

“…Lu et al [21] identified the tourists of common diligence and a model that considered their travel preferences was established to learn and predict their next trip. In addition, some scholars also analyze the big data in the field of transportation to release the travel behavior of passengers [22]- [24]. Although the existing literature considers the travel characteristics of passengers, previous research rarely studies the relationship between the travel characteristics of passengers and the strategy of urban rail transit fare.…”

Passenger Travel Patterns and Behavior Analysis of Long-Term Staying in Subway System by Massive Smart Card Data

“…Silva et al [17] (2014) demonstrated that people's travel patterns are predominantly spatial-temporal and predictable. Dabiri et al [18] (2014) proposed a deep semi-supervised convolution auto encoder (SECA) architecture for travel pattern recognition, which not only automatically extracts relevant features from GPS segments but also utilizes unlabeled data. Tao et al [19] (2014) used smart card data and flow-comap to check the spatial-temporal dynamics of bus passenger travel behavior; their research results can provide information for local public transport policies.…”

“…Lu et al [23] (2019) proposed a graph-based iterative propagation learning algorithm to identify visitors from public commuters and then designed a tourism preference analysis model to learn and predict their next trip. The literature [3,[17][18][19][20][21][22][23] primarily analyzed the passenger's travel mode from a spatial and temporal perspective.…”