The dynamic modulus (E*) of hot-mix asphalt mixtures is one of the most laborious and time-consuming material parameters to measure in the laboratory. It involves expensive, specialized equipment and expertize that are not readily available in most laboratories. Consequently, several efforts have been devoted to E* prediction models. Unfortunately, developing these prediction models is complex because of the numerous contributory factors and their non-linear influence on E* values. Moreover, such models are not able to prioritize or screen the major factors influencing the E* values. This study presents a new framework for analyzing the dynamic modulus influencing factors by adopting two modeling approaches. First, deep residual neural networks (DRNNs) for non-parametric approaches are used to improve the E* prediction capabilities and derive deep insight into the contributory parameters' effect on the E* value. Second, the well-known Witczak 1–40D prediction equation is used as a representative of the classical statistical modeling approach. In the validation of the models, a comprehensive laboratory database is utilized to account for all significant contributory parameters, such as binder characteristics, volumetric properties, mixture gradation, and testing circumstances parameters. Then, the performance is assessed using typical performance metrics. Lastly, intensive global sensitivity analysis (GSA) is undertaken with the assistance of Latin Hypercube Simulation. Three distinct GSA methods are used to emphasize the influence of each contributory factor on the value of E* in actual practice while reducing the possibility for result distortion owing to correlations between contributory variables. Performance metrics of the DRNNs and the Witczak 1–40D prediction models give the GSA conclusions high credibility. The GSA reveals that, among all possible inputs, the binder content, shear modulus, voids in the mineral aggregates, and temperature are the most significant factors in determining the E* value.

One of the most difficult issues in the design of power ankle-foot prosthetics is to create a control
system that can simulate biological ankle-foot behavior in various operating conditions. The
powered semi-active ankle-foot prosthetic is a complex nonlinear system with high coupling. This
work presents the dynamic model of powered ankle prosthetics. For powered ankle prostheses, a
fuzzy logic- proportional-integral (FL-PI) controller is presented. In the initial stage of control,
two proportional-integral (PI) controllers are designed to regulate motor speed and current,
respectively. In the next stage of control, two FL-PI controllers are designed. The Fuzzy logic
controller is designed to tune online the gains of the PI controller. During a normal walking gait
cycle, FL-PI controllers are used to regulate the specified model under these external disturbances.
The performance of PI controllers and FL-PI controllers are compared during the walking gait
cycle. The results reveal that a powered semi-active ankle-foot prosthetic with a fuzzy logic-PI
controller method outperforms a PI controller alone.

Understanding blood transport in cardiovascular flows is important for managing patients with cardiovascular disease. In this study, three-dimensional Lagrangian coherent structures have been extracted for the first time in both healthy patients and patients with aortic regurgitation. To achieve this, a computationally efficient approach based on Lagrangian descriptors was employed with four-dimensional (4D) magnetic resonance imaging velocity fields. In healthy subjects, Lagrangian coherent structures analysis revealed well-defined mitral jet structures during early filling, directing flow toward ejection during systole. For patients with aortic regurgitation, complex flow structures included interactions between the mitral and regurgitant jets, indicating altered blood transport mechanisms. This study highlights the ability of Lagrangian descriptors to extract coherent structures from patient-specific 4D flow MRI data in a computationally efficient way. It also underscores the importance of extracting three-dimensional Lagrangian coherent structures to gain a better understanding of the complex interaction between the mitral inflow and the regurgitant jet.

In junction traffic operations, vehicle delay is one of the most essential performance measures of effectiveness. It allows traffic engineers to assess the performance of a traffic system component or the efficacy of a system-wide control plan. Real-time applications such as adaptive signal control, congestion management, and dynamic traffic assignment often use this technology. Obtaining real-time data on intersection performance, such as control delay, may be time-consuming and labor-intensive. This study presents a new approach for estimating network-level real-time delay from passive traffic counting. Total Travel Delay Estimation Technique (TTD) is proposed for signalized intersection delays that can be computed by examining real-time data from arrival and departure detectors upstream and downstream of a junction. The proposed estimation method mathematically manipulated equations that relate the input-output model and vehicle O–D data acquired from the Automatic Turning Movement Identification System (ATMIS). The developed methods utilize the obtained real-time traffic detection system as input data. The proposed methods are applied for three cases: simple, semi-generalized, and generalized networks, where any of them can be used as a building TTD estimation block for the whole actual network. Results from the TTD were compared to VISSIM output, and a statistical test was conducted under varying traffic conditions (low, medium, high, and saturated). The findings show that the proposed methodology can yield stable and reliable results in various traffic volumes and turning movement conditions. Future field implementation studies for the suggested methods are recommended to evaluate the model’s reliability and efficacy in real-time traffic scenarios.

Traffic control and management applications require the full realization of traffic flow data. Frequently, such data are acquired by traffic sensors with two issues: it is not practicable or even possible to place traffic sensors on every link in a network; sensors do not provide direct information about origin–destination (O–D) demand flows. Therefore, it is imperative to locate the best places to deploy traffic sensors and then augment the knowledge obtained from this link flow sample to predict the entire traffic flow of the network. This article provides a resilient deep learning (DL) architecture combined with a global sensitivity analysis tool to solve O–D estimation and sensor location problems simultaneously. The proposed DL architecture is based on the stacked sparse autoencoder (SAE) model for accurately estimating the entire O–D flows of the network using link flows, thus reversing the conventional traffic assignment problem. The SAE model extracts traffic flow characteristics and derives a meaningful relationship between traffic flow data and network topology. To train the proposed DL architecture, synthetic link flow data were created randomly from the historical demand data of the network. Finally, a global sensitivity analysis was implemented to prioritize the importance of each link in the O–D estimation step to solve the sensor location problem. Two networks of different sizes were used to validate the performance of the model. The efficiency of the proposed method for solving the combination of traffic flow estimation and sensor location problems was confirmed from a low root-mean-square error with a reduction in the number of link flows required.

In the context of critical energy infrastructures (e.g., hydrogen infrastructure) that extensively utilize power converters, the need for reliable and accurate monitoring is of paramount importance. Addressing this necessity, this paper presents a novel GPU-based multivariate approach to Insulated Gate Bipolar Transistor (IGBT) lifetime prediction. Despite the substantial technological advances in the field, accurately predicting the lifetime of IGBTs remains a significant challenge. Current methods often rely on single precursor variable models, which can lack the precision required in demanding power electronic applications. In contrast, this study utilizes multiple precursor variables (V _CE(ON) and case temperature) to achieve more accurate results. Initial results using NASA's open-source dataset, and Gaussian Process Regression (GPR) reveal that our multivariate model outperforms its single-variable counterparts in …