Service recommendations help travelers locate en route traffic information service of interest in a timely manner. However, recommendations based on simple traffic information, such as the number of requests for the location of a facility, fail to consider an individual's preferences. Most existing work on improving service recommendations has continued to utilize the same ratings and rankings of services without consideration of diverse users' demands. The challenge remains to push forward the modeling of spatiotemporal trajectories to improve service recommendations. In this research, we proposed a new method to address the above challenge. We developed a personalized service-trajectory correlation that could recommend the most appropriate services to users. In addition, we proposed the use of ''congeniality'' probability to measure the service demand similarity of two travelers based on their service-visiting behaviors and preferences. We employed a clustering-based scheme, taking into account the spatiotemporal dimensions to refine the trajectories at each spot where travelers stayed at a certain point in time. Experiments were conducted employing a real global positioning system-based dataset. The test results demonstrated that our proposed approach could reduce the deviation of the trajectory measurement to 10% and enhance the success rates of the service recommendations to 60%.

The prebraking-related actions typically studied are the main maneuvers carried out to avoid collision. Especially for those braking actions taken when turning or parking, accidents often occur because of human errors such as the incorrect choice of pedal. However, regarding these daily braking-related driving behaviors, the effects of the driver characteristics, such as driving experience and gender, on the prebraking behaviors remain unknown. Therefore, defining prebraking behaviors as the movements of a driver's body before his or her foot touches the brake pedal, this paper identifies the details of drivers' driving behaviors while prebraking by analyzing the data collected from a wearable high-precision 23-joint motion capture device and further confirms the effects of driver experience, gender and stature on these behaviors. According to two-way analyses of variance (ANOVAs) that were performed on 100 sets of motion data collected from a set of driving experiments involving two different tasks, drivers perform similar prebraking body actions even under different braking scenarios. Moreover, the results of an interaction effects analysis confirmed the impact of drivers' experiences, gender and stature on their prebraking actions. The results of this study can serve as guidelines for future self-driving and advanced driver assistance system (ADAS) development and provide useful insights for the identification and training of new drivers.

One of the challenges posed by the study of vehicular ad hoc networks (VANETs) is the transmission of data issued by valued traffic information services under incomplete link conditions. Many dissemination protocols have been developed by the community to solve the issue. In this survey, the authors explore the service discovery where data dissemination should serve as a foundation. Then, they propose an overview and taxonomy of a large range of data dissemination available for VANETs. Finally, they illustrate the simulation infrastructure by collaborating two independent simulators. The objective is to provide guidelines to easily understand and extend the capabilities of protocols according to the users' needs.

In this paper, we aim to provide an optimal passenger matching solution by recommending ridesharing groups of passengers from GPS trajectories. Existing algorithms for rider grouping usually rely on matching pre-selected origin-destination coordinates. Unfortunately, the semantics in the spatial layout (e.g., social interactions and properties of the locations) are ignored, leading to inaccuracies in discovering the ridesharing groups. Meanwhile, the destinations manually entered by users impact the accuracy of matching, as these addresses are usually not available in a road network or are not optimal for passenger pickup. This is particularly true when a passenger travels in a less familiar place. Given a set of passengers and the distribution of their destination, our approach is to compute the ridesharing matching between passengers. The raw GPS trajectories can be characterized by a combination of time constraints, traffic environments, and social activities. We first developed a PrefixSpan-prediction using a partial matching (P-PPM) destination-prediction algorithm to mine the frequent movement patterns from the trajectory data and determine the confidence of the movement rules. Our method uses the total travel time as the matching objective. Our approach is superior to the baseline methods in terms of accuracy (increased from 46% to 80%). We have also achieved significant improvements on other metrics, such as users' saved travel distance. We demonstrated that using our proposed method, a group of passengers could save over 19% of total travel miles, which shows that the ridesharing scheme could be effective.

No abstract