Traffic state estimation (TSE) bifurcates into two main categories, model-driven and data-driven (e.g., machine learning, ML) approaches, while each suffers from either deficient physics or small data. To mitigate these limitations, recent studies introduced hybrid methods, such as physics-informed deep learning (PIDL), which contains both model-driven and data-driven components. This paper contributes an improved paradigm, called physics-informed deep learning with a fundamental diagram learner (PIDL + FDL), which integrates ML terms into the model-driven component to learn a functional form of a fundamental diagram (FD), i.e., a mapping from traffic density to flow or velocity. The proposed PIDL + FDL has the advantages of performing the TSE learning, model parameter identification, and FD estimation simultaneously. This paper focuses on highway TSE with observed data from loop detectors, using traffic density or velocity as traffic variables. We demonstrate the use of PIDL + FDL to solve popular first-order and second-order traffic flow models and reconstruct the FD relation as well as model parameters that are outside the FD term. We then evaluate the PIDL + FDL-based TSE using the Next Generation SIMulation (NGSIM) dataset. The experimental results show the superiority of the PIDL + FDL in terms of improved estimation accuracy and data efficiency over advanced baseline TSE methods, and additionally, the capacity to properly learn the unknown underlying FD relation.

For its robust predictive power (compared to pure physics-based models) and sample-efficient training (compared to pure deep learning models), physics-informed deep learning (PIDL), a paradigm hybridizing physics-based models and deep neural networks (DNNs), has been booming in science and engineering fields. One key challenge of applying PIDL to various domains and problems lies in the design of a computational graph that integrates physics and DNNs. In other words, how the physics is encoded into DNNs and how the physics and data components are represented. In this paper, we offer an overview of a variety of architecture designs of PIDL computational graphs and how these structures are customized to traffic state estimation (TSE), a central problem in transportation engineering. When observation data, problem type, and goal vary, we demonstrate potential architectures of PIDL computational graphs and compare these variants using the same real-world dataset.

The Waymo Open Dataset has been released recently, providing a platform to crowdsource some fundamental challenges for automated vehicles (AVs), such as 3D detection and tracking. While the dataset provides a large amount of high-quality and multi-source driving information, people in academia are more interested in the underlying driving policy programmed in Waymo self-driving cars, which is inaccessible due to AV manufacturers’ proprietary protection. Accordingly, academic researchers have to make various assumptions to implement AV components in their models or simulations, which may not represent the realistic interactions in real-world traffic. Thus, this paper introduces an approach to learn a long short-term memory (LSTM)-based model for imitating the behavior of Waymo’s self-driving model. The proposed model has been evaluated based on Mean Absolute Error (MAE). The experimental results show that our model outperforms several baseline models in driving action prediction. In addition, a visualization tool is presented for verifying the performance of the model.

Emerging evidence suggests that atypical changes in driving behaviors may be early signals of mild cognitive impairment (MCI) and dementia. This study aims to assess the utility of naturalistic driving data and machine learning techniques in predicting incident MCI and dementia in older adults. Monthly driving data captured by in-vehicle recording devices for up to 45 months from 2977 participants of the Longitudinal Research on Aging Drivers study were processed to generate 29 variables measuring driving behaviors, space and performance. Incident MCI and dementia cases (n = 64) were ascertained from medical record reviews and annual interviews. Random forests were used to classify the participant MCI/dementia status during the follow-up. The F₁ score of random forests in discriminating MCI/dementia status was 29% based on demographic characteristics (age, sex, race/ethnicity and education) only, 66% based on driving variables only, and 88% based on demographic characteristics and driving variables. Feature importance analysis revealed that age was most predictive of MCI and dementia, followed by the percentage of trips traveled within 15 miles of home, race/ethnicity, minutes per trip chain (i.e., length of trips starting and ending at home), minutes per trip, and number of hard braking events with deceleration rates ≥ 0.35 g. If validated, the algorithms developed in this study could provide a novel tool for early detection and management of MCI and dementia in older drivers.

Knowledge tracing models based on deep learning can achieve impressive predictive performance by leveraging attention mechanisms. However, there still exist two challenges in attentive knowledge tracing (AKT): First, the mechanism of classical models of AKT demonstrates relatively low attention when processing exercise sequences with shifting knowledge concepts (KC), making it difficult to capture the comprehensive state of knowledge across sequences. Second, classical models do not consider stochastic behaviors, which negatively affects models of AKT in terms of capturing anomalous knowledge states. This article proposes a model of AKT, called Enhancing Locality for Attentive Knowledge Tracing (ELAKT), that is a variant of the deep KT model. The proposed model leverages the encoder module of the transformer to aggregate knowledge embedding generated by both exercises and responses over all timesteps. In addition, it uses causal convolutions to aggregate and smooth the states of local knowledge. The ELAKT model uses the states of comprehensive KCs to introduce a prediction correction module to forecast the future responses of students to deal with noise caused by stochastic behaviors. The results of experiments demonstrated that the ELAKT model consistently outperforms state-of-the-art baseline KT models.