Congestion Model Research Articles

The Road to Explainable Graph Neural Networks

GOAL: Graph Neural Networks (GNNs) are being increasingly adopted in various real-world applications, including drug and material discovery [16, 17, 27], recommendation engines [29], congestion modeling on road networks [5], and weather forecasting [11]. However, similar to other deeplearning models, GNNs are considered black boxes due to their limited capacity to provide explanations for their predictions. This lack of interpretability poses a significant barrier to their adoption in critical domains such as healthcare, finance, and law enforcement, where transparency and trustworthiness are essential for decision-making processes. In these pivotal domains, understanding the rationale behind model predictions is crucial not only for compliance with interpretability requirements but also for identifying potential vulnerabilities and gaining insights to refine the model further. How do we make GNNs interpretable? This is a central motivating question driving my research pursuits.

Enhancing Urban Mobility: Predicting Traffic Congestion with Optimized ML Model

Abstract Traffic congestion is a critical challenge in urban areas, leading to increased travel times, pollution, and a decreased quality of life. This study addresses this issue by developing a predictive model for traffic congestion using the eXtreme Gradient Boosting (XGBoost) machine learning model, enhanced with hyperparameter optimization and detrending techniques. Key traffic parameters, including waiting times, vehicle angles, latitude, longitude, and speeds, are incorporated to improve the model's accuracy. Compared to ARIMA and LSTM models, the proposed XGBoost model significantly outperforms these approaches. LSTM exhibits much higher prediction errors. The XGBoost model, with its lowest MAE (0.007), MSE (0.008), and an accuracy of 99.5%, demonstrates superior performance and efficiency. Implemented in Python using the SUMO simulator for real-time traffic data, the proposed model showcases robust predictive capabilities, contributing to smarter urban mobility solutions and improved transportation systems. These findings underscore the effectiveness of advanced machine learning techniques in predicting traffic congestion and provide valuable insights for developing smarter urban mobility solutions. The study’s contributions aim to enhance transportation systems and improve the overall quality of urban life.

TCT-467 Prolonged Occlusion of the Superior Vena Cava Using the PreCardia System Reduces Cardiac Filling and Renal Venous Pressures Without Causing Cerebral Injury in a Preclinical Model of Systemic Congestion

TCT-467 Prolonged Occlusion of the Superior Vena Cava Using the PreCardia System Reduces Cardiac Filling and Renal Venous Pressures Without Causing Cerebral Injury in a Preclinical Model of Systemic Congestion

Sublinear message bounds of authenticated implicit Byzantine agreement

This paper studies the message complexity of authenticated Byzantine agreement (BA) in synchronous, fully-connected distributed networks under an honest majority. We focus on the so-called implicit Byzantine agreement problem where each node starts with an input value and at the end a non-empty subset of the honest nodes should agree on a common input value by satisfying the BA properties (i.e., there can be undecided nodes)3. We show that a sublinear (in n, number of nodes) message complexity BA protocol under honest majority is possible in the standard PKI model when the nodes have access to an unbiased global coin and hash function. In particular, we present a randomized Byzantine agreement algorithm which, with high probability achieves implicit agreement, uses O˜(n) messages, and runs in O˜(1) rounds while tolerating (1/2−ϵ)n Byzantine nodes for any fixed ϵ>0, the notation O˜ hides a O(polylogn) factor4. The algorithm requires standard cryptographic setup PKI and hash function with a static Byzantine adversary. The algorithm works in the CONGEST model and each node does not need to know the identity of its neighbors, i.e., works in the KT0 model. The message complexity (and also the time complexity) of our algorithm is optimal up to a polylog n factor, as we show a Ω(n) lower bound on the message complexity. We further extend the result to Byzantine subset agreement, where a non-empty subset of nodes should agree on a common value. Lastly, we analyze several relevant results that follow from the construction of the main result.To the best of our knowledge, this is the first sublinear message complexity result of Byzantine agreement. A quadratic message lower bound is known for any deterministic BA protocol (due to Dolev-Reischuk [JACM 1985]). The existing randomized BA protocols have at least quadratic message complexity in the honest majority setting. Our result shows the power of a global coin in achieving significant improvement over the existing results. It can be viewed as a step towards understanding the message complexity of randomized Byzantine agreement in distributed networks with PKI.

Abstract Tu037: Unraveling the Cellular Mechanisms of Cardiogenic Liver Disease

Background: Right heart failure (RHF) is associated with chronically elevated central venous pressures which can lead to hepatic dysfunction, fibrosis, and ultimately cirrhosis. Despite the prognostic importance of liver disease in RHF little is understood about the cellular and molecular changes that define cardiogenic liver disease. Filling this knowledge gap has the potential to lead to better diagnostic and therapeutic approaches for patients with heart failure and liver dysfunction. Aims: 1) To evaluate the key clinical and pathologic features of cardiogenic liver disease in humans 2) To explore shifts in the cellular landscape in the congested liver using human samples and a mouse model congestive hepatopathy. Methods: We identified 34 patients with heart failure who underwent liver biopsy due to concern for cardiogenic liver disease. These biopsy samples were stained for numerous cellular markers (macrophage subsets, activated stellate cells, endothelial cells, biliary cells) and compared to normal controls. Clinical data was also collected for the included patients. To model cardiogenic liver disease in a mouse we performed partial IVC ligation (pIVCL) to induce liver congestion and then assessed the liver response using flow cytometry, tissue imaging and mRNA analysis. Results: Liver biopsies from patients with cardiogenic liver disease demonstrated increased liver fibrosis, macrophage aggregates, and biliary metaplasia. The severity of biliary metaplasia was closely associated with the extent of liver congestion. Using multi-marker staining the metaplastic cells were found to be of hepatocyte origin. Interestingly, the liver niche containing metaplastic biliary cells was also enriched for recruited macrophages and activated stellate cells. Similar pathologic features were observed in the mouse model of liver congestion. Conclusions: In this study we identified biliary metaplasia and macrophage recruitment as key pathologic features of cardiogenic liver disease. Ongoing investigation of the interplay between macrophages and metaplastic biliary in humans and animal models of congestive hepatopathy may lead to the discovery of novel disease mechanisms and biomarkers for liver dysfunction in heart failure.

Abstract Mo041: Bile Acid Dysregulation in Response to Right Heart Failure and Hepatic Congestion

Introduction: Right heart failure (RHF), the result of impaired RV contractility and/or severe right-sided valvulopathies, is a clinical syndrome that commonly results in chronically elevated central venous pressures and hepatic congestion. Hepatic dysfunction in patients with heart failure portends a poor prognosis. In part, this may be due to the liver’s pivotal role in bile acid synthesis and processing. In addition to the classic role of a digestive surfactant, bile acids serve as important and dynamic signaling molecule. The present study characterizes a unique bile acid profile found in patients with RHF. Research Question: We hypothesize that RHF and hepatic congestion results in a dysregulation of bile acids. These untoward changes in bile acids concentrations may provide both important prognostic value and novel mechanistic pathways in congestive liver disease. Aims: 1) To characterize systemic and hepatic vein bile acid concentrations in patients with right heart failure. 2) To phenotype a mouse model of hepatic congestion and understand the mechanistic effects of specific bile acids on liver biology Methods: We enrolled a total of 60 patients who were referred for right heart catheterization (RHC). Patient demographics, echocardiograms, and routine laboratory tests were captured at enrollment. Blood was sampled from the IVC and hepatic vein during RHC. Bile acids were quantified from serum using liquid chromatography-tandem mass spectrometry. To model hepatic congestion, mice underwent ligation of the IVC. Blood and tissue samples were harvested and underwent mass spectrometry evaluation for the bile acid composition and immunohistochemistry was performed to characterize the immune landscape, respectively. Results: We captured a total of 12 control samples from patients with normal filling pressures, 25 patients with left heart failure (LHF), and 23 patients with RF. Patients with RHF had poorer survival outcomes compared to control or LHF. Patients with RHF had significant increases in specific conjugated bile acids when compared to control or LHF (Figure 1). Conclusions: In this study, we identified several conjugated bile acids that are uniquely elevated in patients with RHF compared to LHF and control. Additionally, patients with RHF had poorer survival. Collectively, these data suggest bile acids may serve as important biomarkers and signaling molecules in the pathogenesis of cardiogenic liver disease.

Dual scale porous medium model of lung congestion caused by tuberculosis

Dual scale porous medium model of lung congestion caused by tuberculosis

Nonalternant B,N-Embedded Helical Nanographenes Containing Azepines: Programmable Synthesis, Responsive Chiroptical Properties and Spontaneous Resolution into a Single-Handed Helix.

Heteroatom-embedded helical nanographenes (NGs) constitute an important and appealing class of intrinsically chiral materials. In this work, a series of B,N-embedded helical NGs (BN-HNGs) bearing azepines was synthesized via stepwise regioselective cyclodehydrogenation. First, the phenyl- or nitrogen-bridged dimers were efficiently clipped into highly congested model compounds 1 and 2. Later, the controllable Scholl reactions of the tetraphenyl-tethered precursor generated 1, 7 or 8 new C-C bonds, thereby establishing a robust method for the preparation of nonalternant BN-HNGs with up to 31 fused rings. The helical bilayer nature was unambiguously verified by X-ray diffraction analysis. The helical chirality was transferred to the stereogenic boron centers upon fluoride coordination, with a concave-concave structure to comply with the bilayer skeleton. Notably, the largest nonalternant BN-HNG (6) spontaneously resolved into a homochiral 41 helix structure as a molecular spiral staircase during crystallization via conglomerate formation at the single-crystal scale. The large twisted C2-symmetric π-surface and the dynamic chiral skeleton induced by curved azepines might have synergistic effects on self-recognition of enantiomers of 6 to achieve the intriguing spontaneous resolution behavior. The chiroptical properties of the enantiomer of 6 were further investigated, revealing that 6 had a strong chiroptical response in the visible range (400-700 nm).

Skin Pigmentation Affects ViOptix T.Ox Performance in Variably Pigmented Preclinical Model of Flap Ischemia and Congestion.

Free flap monitoring is more difficult in patients with dark skin because ischemia and congestion can be masked by pigmentation. For this reason, adjunct methods such as cutaneous near-infrared spectroscopy are of elevated importance in patients with highly pigmented skin. The purpose of this experiment is to determine if ViOpitx T.Ox performance is affected by cutaneous pigmentation. Swine with naturally occurring areas of nonpigmented and pigmented skin were used. Pigmentation of each animal was assessed using spectrophotometry and histopathology. During normoxemia, tissue oxygenation (StO2) measurements were taken of nonpigmented and pigmented skin using the T.Ox device. A bicolor pedicled rectus abdominis myocutaneous flap was raised, and T.Ox probe was adhered to adjacent areas of opposite coloration on the same flap. StO2 was measured continuously during reversible episodes of flap ischemia and congestion (n = 4 swine, n = 6 flaps). There was not a significant difference between baseline StO2 values of nonpigmented (49% ± 7.9%) and pigmented skin (47% ± 6.2%). The absolute change in StO2 was significantly larger during both ischemia (6%) and congestion (16%) in nonpigmented skin compared with adjacent pigmented skin. T.Ox detects flap ischemia and congestion in both highly pigmented and nonpigmented skin. However, surgeons need to be aware that StO2 changes related to complete flap ischemia or congestion may be much more subtle than what is seen in nonpigmented skin. This study establishes a novel internally controlled porcine model that isolates the impact of skin pigmentation when assessing cutaneous devices measuring tissue oxygenation.

Biased motility-induced phase separation: from chemotaxis to traffic jams

We propose a one-dimensional model of active particles interpolating between quorum sensing models used in the study of motility-induced phase separation (MIPS) and models of congestion of traffic flow on a single-lane highway. Particles have a target velocity with a density-dependent magnitude and a direction that flips with a finite rate that is biased toward moving right. Two key parameters are the bias and the speed relaxation time. MIPS is known to occur in such models at zero bias and zero relaxation time (overdamped dynamics), while a fully biased motion with no velocity reversal models traffic flow on a highway. Using both numerical simulations and continuum equations derived from the microscopic dynamics, we show that a single phase-separated state extends from the usual MIPS to congested traffic flow in the phase diagram defined by the bias and the speed relaxation time. However, in the fully biased case, inertia is essential to observe phase separation, making MIPS and congested traffic flow seemingly different phenomena if not simultaneously considering inertia and tumbling. We characterize the velocity of the dense phase, which is static for usual MIPS and moves backward in traffic congestion. We also find that in presence of bias, the phase diagram becomes richer, with an additional transition between phase separation and a microphase separation that is seen above a threshold bias or relaxation rate.

Cerebral venous congestion alters CNS homeostatic plasticity, evoking tinnitus-like behavior

BackgroundBrain function and neuronal activity depend on a constant supply of blood from the cerebral circulation. The cerebral venous system (CVS) contains approximately 70% of the total cerebral blood volume; similar to the cerebral arterial system, the CVS plays a prominent role in the maintenance of central nervous system (CNS) homeostasis. Impaired venous autoregulation, which can appear in forms such as cerebral venous congestion, may lead to metabolic abnormalities in the brain, causing severe cerebral functional defects and even chronic tinnitus. However, the role of cerebral venous congestion in the progression of tinnitus is underrecognized, and its pathophysiology is still incompletely understood. This study elucidated the specific pathogenetic role of cerebral venous congestion in the onset and persistence of tinnitus and the possible neurophysiological mechanisms.ResultsWe found that a rat model of cerebral venous congestion exhibited tinnitus-like behavioral manifestations at 14 days postoperatively; from that point onward, they showed signs of persistent tinnitus without significant hearing impairment. Subsequent neuroimaging and neurochemical findings showed CNS homeostatic plasticity disturbance in rats with cerebral venous congestion, reflected in increased neural metabolic activity, ultrastructural synaptic changes, upregulated synaptic efficacy, reduced inhibitory synaptic transmission (due to GABA deficiency), and elevated expression of neuroplasticity-related proteins in central auditory and extra-auditory pathways.ConclusionCollectively, our data suggest that alternations in CNS homeostatic plasticity may play a vital role in tinnitus pathology caused by cerebral venous congestion. These findings provide a new perspective on tinnitus related to cerebral venous congestion and may facilitate the development of precise interventions to interrupt its pathogenesis.

(370) - Statins Reduce Inflammation, Oxidative Stress and Endothelial Cell Activation in a Model of Venous Congestion in Systolic Heart Failure Patients

(370) - Statins Reduce Inflammation, Oxidative Stress and Endothelial Cell Activation in a Model of Venous Congestion in Systolic Heart Failure Patients

On the power of threshold-based algorithms for detecting cycles in the CONGEST model

It is known that, for every k≥2, C2k-freeness can be decided by a generic Monte-Carlo algorithm running in n1−1/Θ(k2) rounds in the congest model. For 2≤k≤5, faster Monte-Carlo algorithms do exist, running in O(n1−1/k) rounds, based on upper bounding the number of messages to be forwarded, and aborting search sub-routines for which this number exceeds certain thresholds. We investigate the possible extension of these threshold-based algorithms, for the detection of larger cycles. We first show that, for every k≥6, there exists an infinite family of graphs containing a 2k-cycle for which any threshold-based algorithm fails to detect that cycle. Hence, in particular, neither C12-freeness nor C14-freeness can be decided by threshold-based algorithms. Nevertheless, we show that {C12,C14}-freeness can still be decided by a threshold-based algorithm, running in O(n1−1/7)=O(n0.857…) rounds, which is faster than using the generic algorithm, which would run in O(n1−1/22)≃O(n0.954…) rounds. Moreover, we exhibit an infinite collection of families of cycles such that threshold-based algorithms can decide F-freeness for every F in this collection.

INFRAMARGINAL TRAVELERS AND TRANSPORTATION POLICY

AbstractStructural models of traffic congestion, such as the bottleneck model, are used to answer important, policy‐relevant questions. However, existing models typically assume that no travelers are inframarginal regarding when to travel; that is, given equilibrium travel times, no travelers strictly prefer their ex ante departure time to all others. In this article, I address this shortcoming by incorporating inframarginal travelers into these models. This change significantly improves these models' ability to fit the data and changes policy prescriptions. In the case of congestion pricing, it typically changes the optimal toll by at least 25% and significantly worsens the distributional impacts.

Congestion effects of energy and its influencing factors: China's transportation sector

This paper constructs a two-stage undesirable and desirable congestion model, which distinguishes purely technical inefficiency from congestion, to study the energy congestion of 30 transportation sectors in China from 2011 to 2020. The Heckman model is used to analyze the influence mechanism of various factors on the undesirable congestion of energy, which avoids sample selection bias. The results show that: (1) The undesirable congestion of energy mainly exists in the transport sector of the western region, while the desirable congestion of energy only exists in the transport sectors of the eastern and central regions. (2) Purely technical inefficiency in the transportation sector does not usually occur in isolation. (3) Population density and the proportion of clean freight turnover have a negative impact on the undesirable congestion of energy.

Aquila Optimizer-Based Hybrid Predictive Model for Traffic Congestion in an IoT-Enabled Smart City

Effective traffic congestion prediction is need of the hour in a modern smart city to save time and improve the quality of life for citizens. In this study, AB_AO (ARIMA Bi-LSTM using Aquila optimizer), a hybrid predictive model, is proposed using the most effective time-series data prediction statistical model ARIMA (Autoregressive Integrated Moving Average) and sequential predictive Deep Learning (DL) technique LSTM (Long Short-Term Memory) which helps in traffic congestion prediction with a minimum error rate. Also, the Aquila optimizer (AO) is used to elevate the adequacy of the AB_AO model. Three road traffic datasets of different cities from the “CityPulse EU FP7 project” are used to implement the proposed hybrid model. In a time-series dataset, two components need to be handled with care, i.e., linear and nonlinear. In this study, the ARIMA model has been used to manage linear components and Bi-LSTM is used to handle nonlinear components of the time-series dataset. The Aquila Optimizer (AO) is used for hyperparametric tuning to enhance the performance of Bi-LSTM. Error measurement parameters like the Mean Absolute Error (MAE), Mean Squared Error (MSE), and Mean Absolute Percentage Error (MAPE) are used to validate the results. A detailed mathematical and empirical analysis is given to justify the performance of the AB_AO model using an ablation study and comparative analysis. The AB_AO model acquires more stable and precise results with MSE as 18.78, MAE as 3.18, and MAPE as 0.21 than other models. It may further help to predict the vehicle count on the road, which may be of great help in reducing wastage of time in traffic congestion.

Faster Convergence of Integrated Activity-Based Models in Dynamic Multimodal Transit Assignment Using Macroscopic Road Congestion Estimation

This paper proposes an integrated framework of an activity-based behavior model and a multimodal transit assignment-simulation tool that captures road network congestion dynamics. The framework has two levels: the upper level is the demand-side activity-based model that decides individual travelers’ behavioral choices based on up-to-date information from the lower level; the lower level consists of both transit and road network estimation models on the supply side, whose inputs are trips from the upper level. The objective of this framework is to assess impacts of transit service policies, so the transit network is simulated with an agent-based multimodal hyperpath assignment model in each iteration, while the road network is mainly estimated by a macroscopic model of congestion (metamodel) instead of a simulation-based assignment model to accelerate execution time toward an equilibrated solution. Convergence under this framework is also defined from two aspects: individual choice behaviors and transit hyperpath assignment. One contribution of this paper is to incorporate the exogenous effects of road network dynamics into the integrated demand and transit assignment model, and to reduce the time to reach convergence with macroscopic modeling. This paper uses mode choice behavior as an example to demonstrate mathematical formulations and implementation procedures to reach two-level convergence. The framework is tested with the large-scale regional network of the Greater Chicago metropolitan area. The results suggest that the major advantage of the macroscopic road model is to accelerate convergence toward equilibrium when it is used to capture the traffic network congestion effects in this integrated mode choice-transit assignment framework.

Contextual Bayesian optimization of congestion pricing with day-to-day dynamics

Congestion pricing is a common approach to alleviate urban traffic congestion. The design of second-best congestion pricing schemes is typically formulated as non-linear programming and bi-level optimization problems, where the lower-level problem involves either a static or dynamic network equilibrium model. The complexity of these bi-level toll optimization problems increases considerably when incorporating day-to-day dynamic models of travel behavior and dynamic models of network congestion. These models are often operationalized using simulation, and consequently, the toll design problem is a computationally challenging simulation-based optimization problem where the evaluation of a single candidate pricing scheme involves simulating the day-to-day model until convergence. In order to circumvent this issue, we propose a contextual Bayesian optimization (BO) framework, where the BO scheme is embedded within the day-to-day dynamic model by using temporal contextual information. The framework implicitly incorporates the relationship between the objective function across days and uses past days’ observations (function evaluations) as weak priors when constructing the Gaussian process underlying the BO algorithm for the current day’s toll optimization problem, resulting in gains in computational efficiency.The contextual BO approach is applied to the design of distance-based pricing schemes for the morning commute problem. We demonstrate numerically that the scheme converges to the system optimum, and moreover, utilizes a significantly smaller number of simulation evaluations (ten-fold reduction) than the standard approach wherein each function evaluation involves simulating the day-to-day model until convergence. From a policy perspective, we find that the distance-based schemes yield significant welfare gains relative to area-based schemes and show that the design of the distance-based tariff scheme can significantly affect distributional impacts. A suitably designed two-part tariff structure can partially offset the relatively large welfare losses of travelers with longer commute distances while maintaining overall welfare. The proposed contextual BO scheme is also extended to incorporate context specific demand and supply information, which can be of value to policy-makers when evaluating optimal toll design schemes under a wide range of scenarios in a computational tractable manner.

A deep marked graph process model for citywide traffic congestion forecasting

AbstractForecasting citywide traffic congestion on large road networks has long been a nontrivial research problem due to the challenge of modeling complex evolution patterns of congestion in highly stochastic traffic environments. Arguing that purely data‐driven methods may not perform well for congestion forecasting, we propose a deep marked graph process model for predicting the congestion indices and the occurrence time of traffic congestion events for complex signalized road networks. Traffic congestion is considered as a nonrigorous spatiotemporal extreme event. We extend the traditional point process model by integrating a specially designed spatiotemporal graph convolutional network. This hybrid strategy takes advantage of the simple form of the point process model as well as the ability of graph neural networks to emulate the evolution of congestion. Experiments on real‐world congestion data sets show that the proposed method outperforms state‐of‐the‐art baseline methods, yielding satisfactory prediction results on a large signalized road network with superior computational efficiency.

Guiding Evacuees to Improve Fire Building Evacuation Efficiency: Hazard and Congestion Models to Support Decision Making by a Context-Aware Recommender System

Fires in large buildings can have tragic consequences, including the loss of human lives. Despite the advancements in building construction and fire safety technologies, the unpredictable nature of fires, particularly in large buildings, remains an enormous challenge. Acknowledging the paramount importance of prioritising human safety, the academic community has been focusing consistently on enhancing the efficiency of building evacuation. While previous studies have integrated evacuation simulation models, aiding in aspects such as the design of evacuation routes and emergency signalling, modelling human behaviour during a fire emergency remains challenging due to cognitive complexities. Moreover, behavioural differences from country to country add another layer of complexity, hindering the creation of a universal behaviour model. Instead of centring on modelling the occupant behaviour, this paper proposes an innovative approach aimed at enhancing the occupants’ behaviour predictability by providing real-time information to the occupants regarding the most suitable evacuation routes. The proposed models use a building’s environmental conditions to generate contextual information, aiding in developing solutions to make the occupants’ behaviour more predictable by providing them with real-time information on the most appropriate and efficient evacuation routes at each moment, guiding the occupants to safety during a fire emergency. The models were incorporated into a context-aware recommender system for testing purposes. The simulation results indicate that such a system, coupled with hazard and congestion models, positively influences the occupants’ behaviour, fostering faster adaptation to the environmental conditions and ultimately enhancing the efficiency of building evacuations.