Congestion Recognition Research Articles

MobileNetV2 with Spatial Attention module for traffic congestion recognition in surveillance images

Traffic congestion recognition is essential for road traffic condition monitoring and improving transportation operation efficiency. Recent works have proposed using computer vision to develop cost-effective traffic congestion detection systems. This paper proposed a custom framework for recognizing traffic congestion using a trained advanced CNNs model on highway surveillance images. The proposed CNNs model uses an attention mechanism that significantly helps the network performing better. Specifically, a spatial attention module is proposed to aggregate model features and increase representational power. Exploring the optimal model choice for edge device deployment: MobileNetV2 is considered the best model choice for this task due to its lowest FLOPs and params. Furthermore, the accuracy of MobileNetV2 with attention module on the test set exceeds that of several advanced CNNs models such as VGG16, GoogLeNet, ResNet50, Efficientnetb0, DenseNet121. For a selected dataset of real-world traffic congestion images, test accuracy of 98.58% strongly supports the model’s efficiency in recognizing traffic congestion rendering image samples. In addition, proposed model also achieves 98.82% on the UCSD dataset, which as same as sort-of-the-art method. In summary, we have developed a congestion detection framework equipped with spatial attention module. Extensive experimental validation has demonstrated that using MobileNetV2 as the backbone network achieves state-of-the-art performance. The framework also uses the Grad-CAM approach for visual interpretability and localization of traffic congestion in surveillance images. Judging from the results of Grad-CAM, attention-integrated models can localize traffic congestion in surveillance images better. Our model is developed under the Pytorch framework using python3.8.

Integrating AI-Technology with Unmanned Aerial Vehicles for Traffic Congestion Recognition

This article explores the integration of unmanned aerial vehicles (UAVs) and artificial intelligence (AI) technology to address traffic congestion. By leveraging UAVs equipped with route-planning capabilities, aerial images of traffic scenes are captured and analyzed using convolutional neural networks (CNNs). The processed data is then transmitted to a traffic management center, enabling timely recognition and response to congestion. This framework offers a practical approach to alleviate traffic delays, reduce fuel consumption, mitigate pollution, and enhance overall road safety

Correlation between non-invasive measurements and intracardiac pressures using machine learning techniques

Abstract Background Solutions targeting early recognition of congestion in heart failure (HF) patients have the potential to prevent readmissions and can thus significantly reduce the burden on HF care. A gold standard measure of congestion is the invasively measured pulmonary capillary wedge pressure (PCWP). However, the invasive nature and accessibility of this measurement limits its clinical use. Non-invasive approximation of the PCWP using biosensing wearables could be a promising replacement for HF monitoring. Purpose The primary aim of this retrospective study was to create a model that estimates the PCWP based on non-invasive measurements of vital signs using both traditional statistics and machine learning (ML) techniques. Methods The study cohort consisted of right-sided heart catheterizations between 23/6/2017 and 19/8/2022. The following models were used: linear regression or classification, k-nearest neighbors, random forest, gradient boosting and multilayer perceptron. The outcome measure for the regression models was the continuous PCWP as measured during the catheterization. The two outcome classes for the classification models were low (<12 mmHg) and high (≥12 mmHg) PCWP. Non-invasive mean arterial blood pressure (MAP), saturation, heart rate, weight and temperature measured at most 72 hours before or after the catheterization were collected as the features for the models. Additionally, ECG-signals acquired during the catheterization were used to calculate the heart rate variability (HRV). The data was split in a validation (20%) and training (80%) data set. The models were built based on the training set and then applied on the validation set to determine the coefficient of determination (R2) for the regression models and the AUC of the ROC for the classification models. Results A total of 859 catheterizations were included of which 31.2% had HF as primary diagnosis. Average age of the cohort was 59 ± 14 years and 52.2% were male. In the HF group, the features with the highest correlation with the PCWP were the HRV and gender (Table 1). All the used regression techniques resulted in low R2 values of up to 0.10 and the classification techniques in AUC of the ROC values of up to 0.61 (Table 2). Conclusion In the current study, PCWP could not be approximated with non-invasive measurements using traditional statistics and ML techniques. These findings support the notion that traditional measures for monitoring HF are poorly correlated with hemodynamic parameters. Perhaps repeated measurements over time could overcome the shortcomings of a single vital signs measurement for congestion evaluation. Future prospective research is needed to evaluate the potential of wearable devices measuring trends over a longer period and their potential in predicting hemodynamics.

Acute heart failure: differential diagnosis and treatment.

Acute heart failure is a heterogeneous clinical syndrome and is the first cause of unplanned hospitalization in people >65 years. Patients with heart failure may have different clinical presentations according to clinical history, pre-existing heart disease, and pattern of intravascular congestion. A comprehensive assessment of clinical, echocardiographic, and laboratory data should aid in clinical decision-making and treatment. In some cases, a more accurate evaluation of patient haemodynamics via a pulmonary artery catheter may be necessary to undertake and guide escalation and de-escalation of therapy, especially when clinical, echo, and laboratory data are inconclusive or in the presence of right ventricular dysfunction. Similarly, a pulmonary artery catheter may be useful in patients with cardiogenic shock undergoing mechanical circulatory support. With the subsequent de-escalation of therapy and haemodynamic stabilization, the implementation of guideline-directed medical therapy should be pursued to reduce the risk of subsequent heart failure hospitalization and death, paying particular attention to the recognition and treatment of residual congestion.

Congestion and Use of Diuretics in Heart Failure and Cardiomyopathies: a Practical Guide.

Heart failure is a highly prevalent condition caused by many different aetiologies and characterised by cardiac dysfunction and congestion. Once developed, congestion leads to signs (peripheral oedema) and symptoms (breathlessness on exertion), adverse cardiac remodelling, and an increased risk of hospitalisation and premature death. This review summarises strategies that could enable early identification and a more objective management of congestion in patients with heart failure. For patients with suspected or diagnosed heart failure, combining an echocardiogram with assessment of great veins, lungs, and kidneys by ultrasound might facilitate recognition and quantification of congestion, the management of which is still difficult and highly subjective. Congestion is a one of the key drivers of morbidity and mortality in patients with heart failure and is often under-recognised. The use of ultrasound allows for a timely, simultaneous identification of cardiac dysfunction and multiorgan congestion; ongoing and future studies will clarify how to tailor diuretic treatments in those with or at risk of heart failure.

Aviation and Airspace Management under Rough Set Theory

With the development of aviation industry, a series of problems have appeared in aviation and airspace, among which the most prominent problem is the congestion of aviation and airspace. Airspace congestion has become a major problem in the development of civil aviation in China. Especially in the central and eastern regions of China, airspace congestion is becoming more and more serious. To better solve the problem of airspace congestion, rough set theory and the Fuzzy C-means (FCM) model are first analyzed. By analyzing the temporal and spatial characteristics of traffic congestion in the control sector, a multisector traffic congestion identification model is established based on radar track data. Four multisector congestion characteristics including equivalent traffic volume, proximity, saturation, and traffic density are established. FCM and rough set theory are used to classify and identify sector congestion. Finally, the model based on FCM-rough set theory is compared with other methods based on the data of the regional control sector in northwest China. The experimental results show that the congestion recognition rate of the model is 92.6%, 93.5%, and 94.2%, and the congestion misjudgment rate is 1.5%, 1.2%, and 1.3%, respectively. Hence, the multisector congestion recognition model has a high recognition rate and a low misjudgment rate, and the overall discrimination result is relatively stable. By comparing the proposed method with other methods, it is concluded that the recognition accuracy of the model based on FCM theory is superior to other methods. In summary, the congestion situation of the sector is affected by a variety of macro- and micro-characteristics of the sector, and the congestion identification model is feasible and efficient. Multisector traffic congestion identification has certain application value for airspace planning, air traffic control-assisted decision making, and air traffic flow management. This work can optimize the aviation and airspace management system and provide relevant suggestions for the study of aviation and airspace congestion.

An Attention-Based Digraph Convolution Network Enabled Framework for Congestion Recognition in Three-Dimensional Road Networks

Congestion recognition is necessary for vehicle routing, traffic control, and many other applications in intelligent transportation systems. Besides, traffic facilities in the three-dimensional road network, which contains the fundamental spatiotemporal features for congestion recognition, provides multi-source traffic information. To exploit these traffic big data, in this paper, we propose an attention mechanism-based digraph convolution network (ADGCN) enabled framework to tackle the congestion recognition problem. It can be divided into two parts, spatial relevance modeling and temporal relevance modeling. At first, the representation incorporates spatiotemporal traffic information with the three-dimensional urban network, and partially decouples the global network topology to a single-knot digraph. Then a digraph-based convolution network is used to capture high-order spatial features. Finally, to proceed with time-series features, the multi-modal attention mechanism is introduced to catch the long-range temporal dependence and the congestion classifier is defined accordingly. This distinguishes the proposed model from the conventional congestion recognition methods. Comprehensive experiments are conducted based on real traffic data. The results demonstrate the advantages of the proposed framework over the existing spatiotemporal analysis methods.

Congestion Recognition of the Air Traffic Control Sector Based on Deep Active Learning

The air traffic control sector (ATCS) is the basic unit of the airspace system. If we can identify the congestion of an ATCS, it will help provide decision support for planning and daily operations. However, current methods mainly characterize congestion from the static structure and the dynamic operational features, resulting in poor generalization and operability. To this end, we propose a deep learning method from the perspective of complex networks. It takes aircraft as nodes to construct an aircraft network and utilizes the complexity indices to characterize it. So, the problem of identifying congestion becomes the complexity of the aircraft network. Inspired by active learning methods, we construct a deep active learning (DAL) model for congestion recognition. It adopts an iterative semi-supervised approach to reduce the number of labeled samples while ensuring recognition performance. To make full use of a large number of unlabeled samples, the sparse autoencoder is employed to characterize all labeled samples and unlabeled samples. The hidden layer of the deep neural network is constructed by stacking. In the process of active learning iteration, minimum confidence, marginal sampling, and information entropy are introduced as measures to select samples from the unlabeled sample set with significantly different features from the labeled sample set. The model is applied to three representative sectors in China’s airspace as cases. Results suggest that DAL can reduce the labeled sample set’s redundancy and achieve the desired performance with the smallest number of samples. Additionally, DAL is superior to the existing mainstream methods in the four objective evaluation indices.

Robust Traffic Congestion Recognition in Videos Based on Deep Multi-Stream LSTM

Robust Traffic Congestion Recognition in Videos Based on Deep Multi-Stream LSTM

Congestion recognition for hybrid urban road systems via digraph convolutional network

Congestion recognition is the prerequisite for traffic control and management, vehicle routing, and many other applications in intelligent transportation systems. Different types of roads with traffic facilities provide multi-source heterogeneous field traffic data, which contain the fundamental information and distinct features for congestion recognition. To exploit these traffic big data, in this paper, we propose a machine learning-based framework to tackle the congestion recognition problem. It can be divided in two parts, a digraph-based representation for hybrid urban traffic network and a Dirgraph Convolutional Neural Network (DGCN)-based learning model. At first, the representation incorporates the fundamental traffic variables with the correlation of different traffic flows, and partially decouples the global network topology from local traffic information. And then, to proceed with digraph-based samples, a new type of graph feature extraction method is introduced and the graph Fourier transform is defined accordingly. This distinguishes the proposed model from the conventional graph convolutional networks. Comprehensive experiments are conducted based on real traffic data. The results demonstrate the advantages of the proposed framework over the existing congestion recognition methods.

Design of affinity-aware encoding by embedding graph centrality for graph classification

Deep learning methods for graph classification are critical for graph data mining. Recently, graph convolutional networks (GCNs) have been able to achieve state-of-the-art node classification. A typical process for GCNs includes two iterative steps: node feature encoding and message passing. While the former encodes each graph node independently via the uniform encoding function, the latter updates the features of each node by weighted aggregation of the features of neighboring nodes, where the weights are generated by predefined or learned graph Laplacian. However, their accuracy deteriorates for graph classification tasks because the uniform encoding function encodes all the node features involved. In this study, we propose a novel affinity-aware encoding for graph classification. In our model, we implement a separate encoding function for the neighboring nodes of each node for updating the node features, where the nodes are arranged in the order of affinity values, such as graph centrality, in order to determine the correspondence between an encoding function and a specific neighboring node. Our separate encoding function performs non-Euclidean neighboring encoding for each node by weight sharing, which enables message passing. We also develop two variants based on our separate encoding function: the graph centrality-convolutional neural network (C-CNN) and the graph centrality-graph convolutional network (C-GCN). The former performs the separate encoding function on graph data directly by the function of message passing. The latter combines the separate encoding function with the normalized graph Laplacian implemented on the graph data. Experiments demonstrate that the results obtained by our models are consistent with those obtained by classical convolutional neural networks (CNNs) on the MNIST dataset, and they outperform existing GCNs on the 20NEWS, Reuters8, and Reuters52 datasets. We also apply our two variants to online car-hailing service data for traffic congestion recognition. Our methods show state-of-the-art results compared with GCNs.

Spatiotemporal Congestion Recognition Index to Evaluate Performance under Oversaturated Conditions

We developed a congestion index for traffic management that uses link travel time based on global positioning system probe vehicle data. The congestion index can be used to evaluate the performance of an arterial network under oversaturated conditions. It considers congestion intensity and congestion duration, unlike existing congestion indices. After investigating current big traffic data, we selected the average link travel speed that could be collected at all times over a wide range to develop the congestion index. We used extra travel time as a new measure of effectiveness. The congestion criterion for monitoring oversaturated conditions was set as extra travel time with three congestion levels when traffic flow exceeded capacity. We devised the new congestion index by reflecting the three congestion levels to monitor oversaturated conditions macroscopically and to examine congestion characteristics microscopically. A spatiotemporal congestion recognition index (SCRIN) was defined based on congestion intensity and congestion duration. We analyzed SCRIN to monitor the traffic congestion of Seoul city using the data on travel speeds from the seoul transport operation and information service (TOPIS) for 2016.

Real-time congestion prediction for urban arterials using adaptive data-driven methods

Congestion prediction can support traffic departments to take effective traffic management measures, and it aids users to adopt smarter trip strategies, including route and departure time selection. This paper proposes an adaptive data-driven real-time congestion prediction method. The method framework includes a traffic pattern recognition algorithm based on the adaptive K-means clustering, a two-dimensional speed prediction model and an adaptive threshold calibration method. After the principal component analysis, the adaptive K-means cluster algorithm is conducted to obtain different traffic patterns. Congestion recognition is realized with an adaptive threshold calibration method and congestion prediction is then raised according to different traffic patterns. Parameter calibration and model evaluation are carried out on the proposed method using floating car travel speed data. The results show that the adaptive K-means cluster recognition algorithm can better recognize the traffic patterns than Gaussian Mixture model, and the proposed congestion prediction method has better real-time performance, accuracy and robustness than Autoregressive Integrated Moving Average model and Kalman Filtering method.

Urban Road Congestion Recognition Using Multi-Feature Fusion of Traffic Images

Traffic congestions happen more and more frequently on the current urban roads. Detecting the congestion rapidly and effectively can avoid the second damages. In this paper, we use the traffic images as data source instead of the videos to detect traffic congestions, which have the advantages of low cost and big probability to be applied widely. Firstly, the interest region of the traffic images are calibrated manually, and then the image features in the interest region are abstracted, including the sift corner, gray histogram variance, gray level co-occurrence matrix of energy and contrast. Finally, BP neural network is used to realize image multi-feature fusion, and to classify the traffic condition described by the traffic images. The simulation results show that the method can recognize the traffic condition with the accuracy of 95%.

Water and sodium in heart failure: a spotlight on congestion.

Despite all available therapies, the rates of hospitalization and death from heart failure (HF) remain unacceptably high. The most common reasons for hospital admission are symptoms related to congestion. During hospitalization, most patients respond well to standard therapy and are discharged with significantly improved symptoms. Post-discharge, many patients receive diligent and frequent follow-up. However, rehospitalization rates remain high. One potential explanation is a persistent failure by clinicians to adequately manage congestion in the outpatient setting. The failure to successfully manage these patients post-discharge may represent an unmet need to improve the way congestion is both recognized and treated. A primary aim of future HF management may be to improve clinical surveillance to prevent and manage chronic fluid overload while simultaneously maximizing the use of evidence-based therapies with proven long-term benefit. Improvement in cardiac function is the ultimate goal and maintenance of a "dry" clinical profile is important to prevent hospital admission and improve prognosis. This paper focuses on methods for monitoring congestion, and strategies for water and sodium management in the context of the complex interplay between the cardiac and renal systems. A rationale for improving recognition and treatment of congestion is also proposed.

Urban Transportation Crowded Recognition Technology and Application

The urban road traffic congestion has not only brought many inconvenient for people's routine work and life, but also will restrict the growth of the economical, to accelerate the urban environment worsening and serious influence the city sustainable development. This paper studies based on the dynamic detection of urban road traffic congestion condition recognition technology can fast and accurate discover in the road network which already had the traffic congestion or soon occurs, then estimated the crowded proliferation scope and duration, which are advantageous to carry on the transportation induction and the traffic control promptly. And according to the different target client to the different emphasis point to the distinguish algorithm, has designed the urban road traffic congestion recognition grading warning system.

The London Congestion Charge

By the 1990s, the average speed of trips across London was below that at the beginning of the twentieth century—before the car was introduced—and by the end of that decade, public concern over levels of traffic congestion was high. In early 2003, London imposed a congestion charge—a daily charge for driving or parking a vehicle on public roads within central London between the hours of 7:00 a.m. and 6:30 p.m. on workdays. Traffic congestion has declined substantially, and the program is largely popular. This article describes the origins of the London congestion charge, how it overcame practical and theoretical difficulties, and what effects it has had. The introduction of the London congestion charge is, in important respects, a triumph of economics. It represents a high-profile public and political recognition of congestion as a distorting externality and of road pricing as an appropriate policy response.

Reserch of Judging Congestion Considered Human Subjectivity

Traffic congestion is one of the major concerns of road users. But only few information is provided by the road administration. The performance measurement is thought to be important for road sectors to be accountable for policies and projects. In this relation, outcome index for the traffic congestion from the viewpoint of road users is also important. The purposes of this paper are, firstly to develop the recording system of the driver's judgment on congestion by using PC, secondly to find major factors affecting the congestion recognition of drivers as well as passengers, and lastly to develop congestion judgment model.