In recent years, the importance of user information has increased rapidly for context-aware applications. This paper proposes a deep learning mechanism to identify the transportation modes of ...smartphone users. The proposed mechanism is evaluated on a database that contains more than 1000 h of accelerometer, magnetometer, and gyroscope measurements from five transportation modes, including still, walk, run, bike, and vehicle. Experimental results confirm the effectiveness of the proposed mechanism, which achieves approximately 95% classification accuracy and outperforms four well-known machine learning methods. Meanwhile, we investigated the model size and execution time of different algorithms to address practical issues.
Transportation mode recognition (TMR) is a common but critical task in the human behavior research field, which provides decision support for urban traffic planning, public facility arrangement, ...travel route recommendations, etc. The rapid development of urban information technology, mobile sensors and artificial intelligence has generated solutions for TMR; however, they rely on extra sensors and Geographic Information System (GIS) information, which are not always available. Recognition is usually simplified by disregarding the trajectories among transportation mode change points. In this paper, we proposed an ensemble learning-based approach to automatically recognize transportation modes (including a hybrid mode) using only Global Positioning System (GPS) data. A total of 72 features were extracted to better distinguish different transportation modes. Furthermore, we exploited a deep forest to combine various types of classification models, which facilitates robust learning with different trajectory samples and modes. The experimental results for the Geolife dataset show the efficiency of our approach, and the improved deep forest model achieved the best performance among all experiments that we conducted with 88.6% accuracy.
•Segmentation based classification is robust enough for today's passive tracking.•Improper training and testing split can significantly distort reported accuracies.•Point-based (online) ...classification underperforms segment based classification.•Recurrent Neural Networks yield better label accuracies but worse label sequences.
GPS based campaigns have been hailed as an alternative to transportation surveys that promise relatively high accuracy at a relatively low burden on the participants and fewer forgotten trips. However they still necessitate the recruitment of participants and are thus potentially biased and certainly not encompassing significant parts of the population. Given the high penetration of mobile phones, passive tracking by telephone providers would alleviate those two shortcomings at the cost of reduced sampling frequency and positional accuracy. The trade-off in quality has not yet been quantified and therefore recommendations on sensible thresholds are not yet available. In this study therefore, instead of presenting yet another method for mode of transport classification, we therefore compare the performance of existing mode detection schemes under deteriorating sampling rates and positional accuracies. As a possibility to compensate for the deteriorating signal we also calculate features from users’ positional histories that could be beneficial if their behaviour is repetitive. The evaluation is not only based on pointwise accuracy, but includes quality measures that pertain to trips as a whole. We find that the necessary accuracy and sampling rate for applications will depend on whether the information of whole trajectories can be used, or whether only the current information is available. The former being relevant to ex-post analyses while the latter situation appears more frequently in near-time analyses. For segmentwise classification, there is no major impact on the quality of the classification by the tested levels of spatial accuracies as long as the sampling intervals can be kept at or below a minute, whereas for point based classification the sampling interval should be between 30 s and a minute and increasing spatial accuracy always improves the classification.
•We investigated the merits of accelerometer data in detecting transportation modes.•We examined three approaches: GPS only, accelerometer only and both accelerometer and GPS data.•We used the ...Bayesian Belief Network method.•Accelerometer data made a substantial contribution to recognize transportation modes.•The combination of GPS and accelerometer data performs best.
Potential advantages of global positioning systems (GPS) in collecting travel behavior data have been discussed in several publications and evidenced in many recent studies. Most applications depend on GPS information only. However, transportation mode detection that relies only on GPS information may be erroneous due to variance in device performance and settings, and the environment in which measurements are made. Accelerometers, being used mainly for identifying peoples’ physical activities, may offer new opportunities as these devices record data independent of exterior contexts. The purpose of this paper is therefore to examine the merits of employing accelerometer data in combination with GPS data in transportation mode identification. Three approaches (GPS data only, accelerometer data only and a combination of both accelerometer and GPS data) are examined. A Bayesian Belief Network model is used to infer transportation modes and activity episodes simultaneously. Results show that the use of accelerometer data can make a substantial contribution to successful imputation of transportation mode. The accelerometer only approach outperforms the GPS only approach in terms of the predictive accuracy. The approach which combines GPS and accelerometer data yields the best performance.
The smartphone-based sensors (including accelero-meter, proximity, and gyroscope sensors) are ubiquitous and emerging mobility data sources that could be used for transportation modes (i.e. bus, ...train, car, walking, and stationary) detection. One of the important challenges in transportation modes detection is to build an appropriate model that can extract useful data from the sensor outputs and that can reduce misclassifications. Several factors make the feature modeling difficult including inappropriate sampling frequency of input signals, wavering behavior of devices (e.g. the changing orientation of a device relative to the human body), and continuous base vibration causing similar sensor outputs for both stationary and non-stationary states and related threshold values of velocity. This paper proposes novel approaches to address these challenges by developing a robust transportation mode detector based on a convolution neural network (CNN). The proposed robust detector develops a feature modeling technique by novel feature fusion and cloning techniques. Pre-trained features are constructed using a separate vanilla neural network (VNN) framework to extract the distinguishing components from the original features that are combined with the original and cloned features. The proposed feature fusion technique is successfully able to overcome the noise from the base vibration and the minimal informative outputs from the lower sampling frequency. This enables the CNN to be trained with more efficient and discriminative features that result in a better classification model. The proposed approaches have been validated using a large volume of mobile sensor data based on the movements of travelers. Different types of mobile sensors have been used to collect data including accelerometer, proximity, and gyroscope. Experimental results demonstrate that the proposed approaches can improve the performance of the detection engine significantly over conventional techniques and reduces the misclassification rate.
Monitoring the daily transportation modes of an individual provides useful information in many application domains, such as urban design, real-time journey recommendation, and providing ...location-based services. In existing systems, accelerometer and GPS are the dominantly used signal sources for transportation context monitoring which drain out the limited battery life of the wearable devices very quickly. To resolve the high energy consumption issue, in this paper, we present EnTrans, which enables transportation mode detection by using only the kinetic energy harvester as an energy-efficient signal source. The proposed idea is based on the intuition that the vibrations experienced by the passenger during traveling with different transportation modes are distinctive. Thus, voltage signal generated by the energy harvesting devices should contain sufficient features to distinguish different transportation modes. We evaluate our system using over 28 h of data, which is collected by eight individuals using a practical energy harvesting prototype. The evaluation results demonstrate that EnTrans is able to achieve an overall accuracy over 92% in classifying five different modes while saving more than 34% of the system power compared to conventional accelerometer-based approaches.
The rise of technology-enabled ride-hailing services has affected individuals’ transportation-related decisions. The impact of these ride-hailing services likely varies across traveler segments that ...differ in their usage of various modes of transportation. In this paper, we develop and leverage a framework that allows us to examine the impact of ride-hailing services on the transportation mode choice for three traveler segments: drivers (who primarily use a personal automobile to travel), riders (who primarily use public transit to travel), and walkers (who primarily use non-motorized modes of transport). We first develop a framework outlining how the behavior of different traveler segments would be impacted by the introduction of ride-hailing services and show how this affects traffic congestion and public transportation ridership. To test the framework, we compiled a rich dataset, combining data on public transportation ridership, traffic congestion, and individual transportation mode choice. Employing a difference-in-differences methodology, we show that the Uber entry in a market enabled those who were walkers and riders prior to the entry of Uber to travel more conveniently, leading to an increase in traffic congestion, and induced those who were drivers to substitute their use of private automobiles with a combination of Uber and public transit. We introduced urban compactness to assess the heterogeneous impact of ride-hailing services for cities that differ in their distribution of traveler segments. We found that Uber entry increases traffic congestion and reduces public transit demand more in cities with higher levels of urban compactness, i.e., where the proportion of riders and walkers is higher than that of drivers. This work provides a holistic framework to understand the mechanism underlying the impact of ride-hailing services on public transit and traffic congestion. Urban planners and policy makers can leverage our framework, methodology, and empirical results to guide city planning decisions that have implications for sustainability.