Vehicles with adaptive cruise control, i.e., SAE Levels 1 and 2 automated vehicles (AVs), have been operating on roads with a significant and rapidly growing penetration rate. Identifying these AVs ...is critical to understanding near-future mixed traffic characteristics and managing highway mobility and safety. This study identifies adaptive cruise control-equipped vehicles from human-driven vehicles (HVs) by constructing a set of learning-based models using car-following trajectories in a short time window. It is extendible to Level 3 and + AV identification when data is available. To compare model performance and draw physical insights, two physics-based models are proposed based on the premise that, in general, the car-following behavior of an AV is less volatile than an HV. Four car-following datasets, including AV makes from different manufacturers, are mixed to build a comprehensive identification model. Results show that physics-based approaches identify more than 80% AVs and 70% HVs. The identification accuracy of learning-based models is even higher. For example, the cluster-aware long short-term memory network identifies 98.79% of AVs and 95.45% of HVs. Learning-based identification models developed by this study can be integrated with the existing infrastructure (e.g., surveillance cameras), which have been used to extract car-following trajectories, to detect AVs in mixed traffic streams. This opens unparalleled data-driven opportunities to analyze and control mixed traffic to enhance safety (e.g., notifying surrounding traffic of the presence of AVs) and mobility (e.g., opening AV dedicated lanes when the percentage is great enough).
•E. coli, S. aureus, and S. typhimurium were detected by the universal aptasensor.•UiO-66/MB/aptamer was applied as a signal amplification and recognition probe.•The membrane filtration and ...homogeneous strategy were effectively combined.•The sensor exhibited adaptability in humidity and salt environments.•The detection time was 30 min, and the lower detection limit was 3 CFU⋅mL−1.
Rapid and sensitive detection of foodborne pathogens in complex environments is essential for food protection. A universal electrochemical aptasensor was fabricated for the detection of three common foodborne pathogens, including Escherichia coli (E. coli), Staphylococcus aureus (S. aureus), and Salmonella typhimurium (S. typhimurium). The aptasensor was developed based on the homogeneous and membrane filtration strategy. Zirconium-based metal–organic framework (UiO-66)/methylene blue (MB)/aptamer composite was designed as a signal amplification and recognition probe. Bacteria were quantitatively detected by the current changes of MB. By simply changing the aptamer, different bacteria could be detected. The detection limits of E. coli, S. aureus and S. typhimurium were 5, 4 and 3 CFU·mL−1, respectively. In humidity and salt environments, the stability of the aptasensor was satisfactory. The aptasensor exhibited satisfactory detection performance in different real samples. This aptasensor has excellent potential for rapid detection of foodborne pathogens in complex environments.
Aflatoxin (AFs) contamination is one of the serious food safety issues. Aflatoxin B1 (AFB1) is the most common and toxic aflatoxin, which has been classified as a class 1 carcinogen by the ...International Agency for Research on Cancer (IARC). It is extremely destructive to liver tissue. Developing a convenient and sensitive detection technique is essential. In this paper, we developed a homogeneous dual recognition strategy based electrochemical aptasensor for accurate and sensitive detection of aflatoxin B1 (AFB1) based on the magnetic graphene oxide (MGO) and UiO-66. The MGO was synthesized for the recognition and magnetic separation of AFB1 from complex samples. UiO-66/ferrocenecarboxylic acid (Fc)/aptamer composites were constructed as both recognition and signal probes. The probes would specifically capture AFB1 enriched by MGO, which enables dual recognition in homogeneous solution, thus further improving the accuracy of AFB1 detection. The electrochemical aptasensor for AFB1 had a linear range from 0.005 to 500 ng mL−1. Additionally, the limit of detection was 1 pg mL−1. It shows a favorable potential for both sensitive and accurate detection of AFB1 in real samples.
Display omitted
•A homogeneous and dual recognition electrochemical aptasensor for the detection of aflatoxin B1 was developed.•The UiO-66/ferrocene/aptamer composites were designed as signal and identification probes.•Dual recognition strategy overcomes the non-specificity and improves the accuracy of detection.•The limit of detection was 1 pg mL−1 within 40 min without complex operation.
The connected automated vehicle (AV) technologies provide unprecedented opportunities for precisely controlling and optimising vehicle trajectories to improve traffic performance from the aspects of ...travel time reduction, driving comfort improvement, fuel consumption and emission savings and safety enhancement. Recently, connected and automated vehicle (CAV) trajectory optimisation research has become a hot topic. This study provides an overview of studies on CAV trajectory optimisation in the road traffic context, with a focus on the literature in the past decade. Rather than exhausting all related studies, this review focuses on categorising representative studies with several relevant criteria. On the basis of the review outcomes, research gaps and needs are discussed to facilitate future research.
•Propose the system of Individual Variable Speed Limits with Location Optimization (IVSL-LC).•Consider regulation of vehicle trajectory shapes associated fuel consumption and traffic ...throughput.•Determine not only configurations but also locations of individual advisory speeds.•Focus on near-future connected vehicle technologies without automation capabilities.•Consider compliance rates of human drivers.
Traffic signals on urban highways force vehicles to stop frequently and thus causes excessive travel delay, extra fuel consumption and emissions, and increased safety hazards. To address these issues, this paper proposes a trajectory smoothing method based on Individual Variable Speed Limits with Location Optimization (IVSL-LC) in coordination with pre-fixed traffic signals. This method dynamically imposes speed limits on some identified Target Controlled Vehicles (TCVs) with Vehicle to Infrastructures (V2I) communication ability at two IVSL points along an approaching lane. According to real-time traffic demand and signal timing information, the trajectories of each approaching vehicle are made to run smoothly without any full stop. Essentially, only TCVs’ trajectories need to be controlled and the other vehicles just follow TCVs with Gipps’ car-following model. The Dividing RECTangles (DIRECT) algorithm is used to optimize the locations of the IVSLs. Numerical simulation is conducted to compare the benchmark case without vehicle control, the individual advisory speed limits (IASL) and the proposed IVSL-LC. The result shows that compared with the benchmark, the IVSL-LC method can greatly increase traffic efficiency and reduce fuel consumption. Compared with IASL, IVSL-LC has better performance across all traffic demand levels, and the improvements are the most under high traffic demand. Finally, the results of compliance analysis show that the effect of IVSL-LC improves as the compliance rate increases.
•Collect field trajectory data with periodic oscillation settings.•Propose a new time-domain method to estimate oscillation features.•Quantitatively reveal the relationships between traffic ...oscillation features.•Estimate a time gap function to improve the performance of car following models.
Despite numerous theoretical models, only limited field experiments have been conducted to investigate traffic oscillation propagation, and the relationships between traffic oscillation features (e.g., period, speed variation, spacing and headway) have not received quantitative analysis. This study conducts a set of field experiments designed to inspect such relationships. In these experiments, 12 vehicles equipped with high-resolution global positioning system (GPS) devices following one another on public roads, and the lead vehicle was asked to move with designed trajectory profiles incorporating various parameters. Measurements of five features are extracted from processing the field vehicle trajectory data with a time-domain method. Frequency analysis is also proposed with the Fourier transform method to verify the effectiveness of the features measured by the time-domain method. Compared to the frequency-domain method, the time-domain method yields more measurements with comparable quality and is more robust on trajectories with a small number of oscillation cycles. Then, a series of linear regression analyses reveal a number of new findings on the relationships between these features. For example, the time gap between two consecutive vehicles is negatively correlated with the speed standard deviation of the preceding vehicle and the initial speed of the following vehicle. It is also positively correlated with the average speed of the preceding vehicle and the initial spacing. The findings are helpful in constructing new microscopic traffic models better describing traffic oscillation dynamics. To illustrate this benefit, revised car following models are proposed to capture the relationship between time gap and other features. The simulation results show that the revised models yield better prediction accuracy (in range of 18% to 40% with the oscillation experiment dataset and in range of 30–63% with the stationary experiment dataset) than the classical models on reproducing real-world trajectories.
As the aging population grows, particularly for the baby boomer generation, the United States is witnessing a significant increase in the elderly population experiencing multifunctional disabilities. ...These disabilities, stemming from a variety of chronic diseases, injuries, and impairments, present a complex challenge due to their multidimensional nature, encompassing both physical and cognitive aspects. Traditional methods often use univariate regression-based methods to model and predict single degradation conditions and assume population homogeneity, which is inadequate to address the complexity and diversity of aging-related degradation. This study introduces a novel framework for multi-functional degradation modeling that captures the multidimensional (e.g., physical and cognitive) and heterogeneous nature of elderly disabilities. Utilizing deep learning, our approach predicts health degradation scores and uncovers latent heterogeneity from elderly health histories, offering both efficient estimation and explainable insights into the diverse effects and causes of aging-related degradation. A real-case study demonstrates the effectiveness and marks a pivotal contribution to accurately modeling the intricate dynamics of elderly degradation, and addresses the healthcare challenges in the aging population.
Representation learning stands as one of the critical machine learning techniques across various domains. Through the acquisition of high-quality features, pre-trained embeddings significantly reduce ...input space redundancy, benefiting downstream pattern recognition tasks such as classification, regression, or detection. Nonetheless, in the domain of tabular data, feature engineering and selection still heavily rely on manual intervention, leading to time-consuming processes and necessitating domain expertise. In response to this challenge, we introduce ReConTab, a deep automatic representation learning framework with regularized contrastive learning. Agnostic to any type of modeling task, ReConTab constructs an asymmetric autoencoder based on the same raw features from model inputs, producing low-dimensional representative embeddings. Specifically, regularization techniques are applied for raw feature selection. Meanwhile, ReConTab leverages contrastive learning to distill the most pertinent information for downstream tasks. Experiments conducted on extensive real-world datasets substantiate the framework's capacity to yield substantial and robust performance improvements. Furthermore, we empirically demonstrate that pre-trained embeddings can seamlessly integrate as easily adaptable features, enhancing the performance of various traditional methods such as XGBoost and Random Forest.
Automated Vehicle Identification in Mixed Traffic Li, Qianwen; Li, Xiaopeng; Yao, Handong ...
2021 IEEE International Intelligent Transportation Systems Conference (ITSC),
2021-Sept.-19
Conference Proceeding
Identifying autonomous vehicles (AVs) (e.g., those with adaptive cruise control) from traffic stream benefits enhancing traffic safety, elevating roadway capacity, and assisting autonomous vehicle ...management. This study tests the feasibility of identifying AVs using externally observed vehicle trajectory information. Two learning-based models are utilized to conduct the identification with car-following trajectory information in a short time window as the input. Four car-following trajectory datasets involving AVs makes from different manufacturers are mixed to build a comprehensive identification model. Results show that AVs and human-driven vehicles (HVs) can be successfully identified with a very high accuracy, i.e., the long short-term memory network can correctly identify 98.17% of AVs and 94.14% of HVs. This verifies the feasibility of using existing infrastructure and economic technologies to identify AVs from HVs, which opens unprecedented data-driven opportunities to study and manage near-future mixed traffic.