Depression is one of the most common mood disorders and the number of patients increases significantly in recent years. Due to the lack of biomarkers, conversation between patients and psychiatrists is still the main clinical diagnostic method which is easily influenced by subjectivity of both patients and psychiatrists. Synthetic House-tree-person test (S-HTP), a convenient and efficient mental assessment tool, minimizes subjective influences from patients, while its effectiveness is limited by the professional ability of analyst. Here we introduce a deep learning model DeHTP, a flexible and convenient depression detection method based on S-HTP without interaction between people. Experimental results demonstrate that DeHTP achieves 0.963 AUC and 0.9 accuracy, and outperforms the conventional manual analysis of S-HTP, which is conducted on the guideline of 50 conclusions from previous study related to depression. In addition, it reveals 22 depression-correlated drawing features aligned with conclusions above from the perspective of our proposed model. Leveraging the advantages of deep learning and S-HTP, this approach has the potential for widespread promotion and adoption as the available tool for daily self-mental monitoring, as well as the promising auxiliary diagnostic method in clinical.

This paper presents a traffic oscillation mitigation-oriented optimal control framework for connected and automated vehicles (CAVs) in a mixed traffic environment where the behavior of human-driven vehicles (HVs) is unknown. The primary objective of this framework is to alleviate traffic oscillations, thereby improving overall traffic flow. To achieve this, we introduce a novel total equilibrium spacing estimation method, incorporating stochastic parameters into a car-following model and quantifying the deviation between the mean and equilibrium spacing. This estimation, integrated with a jam-absorption driving strategy, is embedded into a Model Predictive Control (MPC) model for the objective of mitigating traffic oscillations. The efficacy of the proposed control method is evaluated through two experiments utilizing real vehicle trajectory datasets. The first experiment focuses on a single CAV, exploring the impact of key controller parameters on oscillation mitigation. Results demonstrate the optimal performance of the proposed Oscillation Mitigation-based Model Predictive Control (OM-MPC) model, even with a shorter CAV distance (e.g., 100 m), revealing a positive correlation between CAV distance and suitable preset oscillation duration. The second experiment extends the investigation to multiple stop-and-go shockwaves and varying CAV penetration rates. A comparative analysis of control models, including OM-MPC, regular MPC, and proportional-integral with saturation, is conducted based on velocity mean (VM), road segment congestion index (RI), and vehicle stop times (VST). The findings underscore the effectiveness of the proposed control method in mitigating traffic oscillations and enhancing overall traffic efficiency, establishing it as the optimal choice among the three approaches.

We consider the role of non-localities in speed-density data used to fit fundamental diagrams from vehicle trajectories. We demonstrate that the use of anticipated densities results in a clear classification of speed-density data into stationary and non-stationary points, namely, acceleration and deceleration regimes and their separating boundary. The separating boundary represents a locus of stationary traffic states, i.e., the fundamental diagram. To fit fundamental diagrams, we develop an enhanced cross entropy minimization method that honors equilibrium traffic physics. We illustrate the effectiveness of our proposed approach by comparing it with the traditional approach that uses local speed-density states and least squares estimation. Our experiments show that the separating boundary in our approach is invariant to varying trajectory samples within the same spatio-temporal region, providing further evidence that the separating boundary is indeed a locus of stationary traffic states.

This paper presents a hierarchical tactical merging optimization (HTMO) approach for connected and automated vehicles (CAV) at freeway merging segments. The proposed approach comprises two layers: a merging sequencing layer and a trajectory optimization layer, which are coupled by a hierarchical model that utilizes sequence set and vehicle state variables. In the merging sequencing layer, a sequence set variable is introduced to simplify the sequence space and identify the optimal merging sequence using a customized tabu search algorithm. In the trajectory planning layer, we formulate a two-point-boundary optimal control model for CAV trajectory planning, incorporating a platoon formation strategy to further enhance travel efficiency. To handle outliers caused by variations in the preceding vehicle’s trajectory, we have developed a heuristic trajectory optimization algorithm to ensure the generation of feasible trajectories with predetermined optimal acceleration values as proposed. Numerical experiments conducted demonstrate the robust convergence performance and computational efficiency of the HTMO approach across different arrival flow scenarios and parameters setting, thanks to its utilization of a rolling horizon strategy. Additionally, when combined with the platoon formation strategy, the schedule produced by HTMO significantly reduces total travel time and delay, as evidenced by our findings.

This paper proposes a hierarchical model for cooperative on-ramp merging control (CORMC) in mixed traffic with both connected automated vehicles (CAVs) and connected human-driven vehicles (CHVs). The upper-layer of the CORMC model employs an anticipatory position searching (APS) algorithm to determine the anticipatory positions at which merging vehicles (MVs) should merge from the on-ramp lane to the adjacent mainline lane, and to assign cooperative vehicles (CVs) for each MV. A collaborative utility choice (CUC) model is presented to determine the optimal maneuver of CVs to create proper gaps for MVs. The driver compliance rate is introduced to account for CHVs’ unwillingness to follow the instructions given by the CUC model. The lower-layer comprises a cooperative merging control (CMC) model that ensures safe and smooth merging execution for MVs. Longitudinal and lane changing models are developed for mainline vehicles to facilitate an efficient and safe merging process. Simulation results show that the performance benefits of the CUC model are marginal when the CHV compliance rate is relatively low. However, the performance improvement is significant at higher compliance rates ($>$50%). Furthermore, the CORMC model has the potential to increase merging and mainline throughput by over 75% at sufficiently high CAV penetration rates. Comparison of three control strategies shows that the APS algorithm plays an important role in the CORMC model. A comparison with the Simulation of Urban Mobility (SUMO) indicates that the CORMC model significantly mitigates the propagation of congestion waves across varying levels of CAV penetration and on-ramp flow rates.

In the foreseeable future, a coexistence of human-driven vehicles (HVs) and connected automated vehicles (CAVs) is expected in traffic flow systems. Effectively controlling CAVs to improve overall traffic performance and stability is a crucial yet challenging issue, especially when considering the uncertain behavior of HVs. This study proposes an optimal CAV controller for mixed connected traffic based on the adaptive model predictive control (AMPC) method. To mitigate the instability of the mixed platoon, the concept of loose disturbance string stability (LDSS) is introduced and integrated into the controller. Instead of using a fixed platoon size, a platoon formation criterion is established to dynamically calculate the number of vehicles in a platoon, taking into account the uncertain behavior of HVs, such as sudden deceleration and lane changes. An adaptive parameter tuning approach is incorporated into the MPC-based control framework to enhance the control performance in terms of stability, accuracy and disturbance recovery ability. The effects of the proposed CAV controller on overall traffic performance are investigated through two simulation experiments. In the first experiment, the performance of the proposed controller and LDSS are verified under three scenarios: sudden deceleration, vehicle leaving, and vehicle cut-in. In the second experiment, the proposed AMPC method is compared with two existing models: the linear quadratic regulation -based and acceleration-based connected cruise control models. The comparison results demonstrate that the proposed control model ensures LDSS and outperforms the other two approaches in terms of disturbance mitigation, albeit with a slight sacrifice of traffic efficiency.

The rapid development of self-driving cars and breakthroughs in key technologies have made the truck platoon possible. In addition to reducing truck fuel consumption and air pollution by reducing air resistance, effective platoon strategies can also maximize highway throughput while improving driving safety. However, the truck platoon strategy’s current resource allocation model is still in the preliminary research stage. Therefore, inspired by the successful experience of deep reinforcement learning (DRL) in solving resource allocation problems, this article proposes a dynamic resource allocation model for the truck platoon based on the semi-Markov decision process (SMDP) and DRL, which is used to maximize system revenue when considering the resource cost and income balance of the transportation system. Precisely, the proposed method first models the process of controlling the dynamic in and out of the truck platoon as SMDP. The action value in a specific state obtained by the planning algorithm is used as a DRL sample for model training. Finally, the SMDP is optimized through the trained model to obtain a truck platoon resource that approximates the optimal strategy distribution plan. The experimental results show that compared with the traditional greedy algorithm, value iteration, and${Q}$-learning scheme concerning solving the dynamic resource allocation model of the truck platoon, the Deep${Q}$-Network (DQN) used in this article can reduce the probability of request processing delay while causing the system to obtain higher rewards.

It is widely accepted that travelers value both the reliability of travel time and its mean or expected value. Strategies for traffic signal control typically seek to optimize average travel times, although reliability is in general not explicitly taken into account. In this paper, we propose a new framework for evaluating the consequences of signal-control tactics on both reliability and expected values of travel time, based on an analytic model of travel time distribution. A genetic-algorithm-based approach is then employed to identify optimal multicriteria signal control strategies, including sensitivity analysis, to the relative weighting between reliability and expected value. We expose the properties of the proposed framework via an empirical case study of four alternative optimization approaches (the signal setting optimized with the traditional Webster's method, TRANSYT model, and the newly proposed model) under various traffic conditions. Results indicate that the newly proposed framework outperforms the alternative signal control strategies in terms of both travel-time variability and expected travel time.