Microscopic vehicle emissions models have been well developed in the past decades. Those models require second-by-second vehicle trajectory data as a key input to perform vehicle energy/emissions estimation. Due to the omnipresence of mobile sensors such as floating cars, real-world vehicle trajectory data can be collected in a large scale. However, most large-scaled mobile sensor data in practice are sparse in terms of sampling rate due to the consideration in implementation cost. In this paper, a new modal activity framework for vehicle energy/emissions estimation using sparse mobile sensor data is presented. The valid vehicle dynamic states are identified including four driving modes, named acceleration, deceleration, cruising, and idling. The best valid vehicle dynamic state with the largest probabilities is selected to reconstruct the second-by-second vehicle trajectory between consecutive sampling times. Then vehicle energy/emissions factors are estimated based on operating mode distributions. The proposed model is calibrated and validated using the Next Generation Simulation's dataset, and shows better performance in vehicle energy/emissions estimation compared with the linear interpolation model. Sensitivity analysis is performed to show the model accuracy with different time intervals. This paper provides a new methodology for vehicle energy/emissions estimation and extends the application area of sparse mobile sensor data.

Bus emissions have become one of the important contributing factors in urban environmental pollution due to the frequent use of heavy-duty diesel engines in the day-time. Local bus driving cycles have a significant influence on bus emissions under the different traffic conditions. This study investigated the operation mode distributions and emission characteristics for urban buses based on localized MOtor Vehicle Emission Simulator (MOVES) using sparse Global Position System (GPS) data in Shanghai, China. Sparse GPS data from forty-three buses were prepared, and then bus trajectories were reconstructed to calculate local bus driving cycles, including model description, model calibration, and trajectory reconstruction. MOVES localization was conducted for emission estimation mainly focusing on the bus emission inventory comparison between US and China. Bus emission factors were estimated based on the localized MOVES from the aspect of different driving conditions. Results show that with the increase in average traveling speed, the proportion of idling operation mode showed a decreasing trend. Four typical vehicle operation mode distributions were identified with different average speeds to show the impact of traffic conditions. Bus emission factors first rapidly decreased and then slowly declined towards some minimum values. Bus lanes exhibited emission reduction benefits under serious traffic congestion. The findings of this study have great importance for transportation operation management and policy-making to reduce bus emissions, as well as improving air quality.

Exclusive bus lane strategy is widely adopted in many cities to improve bus operation efficiency and reliability. With the development of connected vehicle technologies, the dynamic bus lane (DBL) strategy was proposed, with allowing general vehicles to share use of the bus lane to improve traffic efficiency in general purpose lanes (GPLs). Previous studies have rarely considered the eco-driving strategy of connected and automated vehicles/buses (CAVs/CABs) in GPLs under the mixed traffic conditions, and how to ensure bus priority with DBL control. In this study, a novel DBL control strategy was developed under the partially connected vehicle environment. A trajectory planning method while considering the joint effects of bus stop and signal phase for CAB was adopted, an eco-driving strategy for CAVs in GPL was proposed using a trigonometry trajectory planning method. And a novel DBL control method was established by integrated trajectory planning for both the CAVs and CABs to ensure bus operation priority. Numerical experiments were conducted to evaluate performance of the proposed novel DBL control in terms of travel time and energy consumption of general vehicles at the different levels of CAV market penetration rates (MPRs). Results indicated that about 16%-42% energy savings can be achieved with MPR varying from 20% to 100%, and the travel time can be improved by about 4%-10%. Meanwhile, sensitivity analysis was conducted to quantify the impacts of key parameters, including vehicle target speeds, heterogeneous traffic flow, random arrival interval of cars, position of bus stop, traffic volume in GPLs and buffer length at the stop line of signalized intersections.

With the rapid development of the cooperative vehicle infrastructure system, eco‐approach and departure has been attracting increasing attention for mitigating the impact of signalized intersections, which helps improve the energy efficiency of equipped vehicles. However, existing studies have rarely considered the balance of electric bus energy consumption and traveling time. Meanwhile, the joint effect of bus stops and signalized intersections, and their interactions were not discussed widely with connected and automated electric buses (CAEBs). In this study, an integrated CAEB trajectory planning methodology with the balance of traveling time and energy consumption is proposed. A bi‐level programming model is developed to obtain the optimal trajectories of CAEBs. Numerical experiments are conducted to analyse and compare the model with two baseline models. The results demonstrate the optimal performance of the derived scheme in terms of bus energy consumption, with approximately 30–50% energy savings. Furthermore, model sensitivity analysis is conducted to quantify the impacts of the related system parameters. The findings also reveal that the entry time, conversion coefficient, and final speed have significant impacts on electric bus energy consumption along signalized arterials with bus stops.

The occurrence of flight risks and accidents is closely related to pilot workload. Effective detection of pilot workload has been a key research area in the aviation industry. However, traditional methods for detecting pilot workload have several shortcomings: firstly, the collection of metrics via contact-based devices can interfere with pilots; secondly, real-time detection of pilot workload is challenging, making it difficult to capture sudden increases in workload; thirdly, the detection accuracy of these models is limited; fourthly, the models lack cross-pilot generalization. To address these challenges, this study proposes a large language model, WorkloadGPT, which utilizes low-interference indicators: eye movement and seat pressure. Specifically, features are extracted in 10 s time windows and input into WorkloadGPT for classification into low, medium, and high workload categories. Additionally, this article presents the design of an appropriate text template to serialize the tabular feature dataset into natural language, incorporating individual difference prompts during instance construction to enhance cross-pilot generalization. Finally, the LoRA algorithm was used to fine-tune the pre-trained large language model ChatGLM3-6B, resulting in WorkloadGPT. During the training process of WorkloadGPT, the GAN-Ensemble algorithm was employed to augment the experimental raw data, constructing a realistic and robust extended dataset for model training. The results show that WorkloadGPT achieved a classification accuracy of 87.3%, with a cross-pilot standard deviation of only 2.1% and a response time of just 1.76 s, overall outperforming existing studies in terms of accuracy, real-time performance, and cross-pilot generalization capability, thereby providing a solid foundation for enhancing flight safety.