Traffic Database Research Articles

Fuzzy Petri Nets for Traffic Node Reliability.

Self-driving cars are one of the main areas of research today, but it has to be acknowledged that the information from the sensors (the perceptron) is a huge amount of data, which is now unmanageable even when projected onto a single traffic junction. In the case of self-driving, the nodes have to be sequenced and organized according to the planned route. A self-driving car in Hungary would have to be able to interpret more than 70,000 traffic junctions to be able to drive all over the country. Besides the huge amount of data, another problem is the issue of validation and verification. For self-driving cars, this implies a level of complexity using traditional methods that calls into question the economics of the already existing system. Fuzzy Petri nets provide an alternative solution to both problems. They allow us to obtain a model that accurately describes the reliability of a node through its dynamics, which is essential in perception since the more reliable a node is, the smaller the deep learning mesh required. In this paper, we outline the analysis of a traffic node's safety using Petri nets and fuzzy analysis to gain information on the reliability of the node, which is essential for the modeling of self-driving cars, due to the deep learning model of perception. The reliability of the dynamics of the node is determined by using the modified fuzzy Petri net procedure. The need for a fuzzy extension of the Petri net was developed by knowledge of real traffic databases.

Biogeographic variation in environmental and biotic resistance modifies predicted risk of marine invasions by ships

IntroductionGlobal shipping has accelerated the spread of non-native species. Factors such as environmental filtering and interactions with local biota can affect invasion likelihood, yet their relative contribution to predicting invasion risk remains unresolved. To test how abiotic filters and an experimentally-derived measure of biotic resistance interact with propagule pressure, we developed an integrated model to evaluate their relative effects on invasion risk of marine biofouling organisms to different focal port regions. We predicted that environmental filtering impacts invasion risk when fewer but stronger connections are part of the network. Further, predation is a mechanism of biotic resistance, which can reduce invasion risk, with most pronounced effects predicted in the tropics that decline at higher latitudes.MethodsWe examined shipping traffic and predation impact at three coastal bioregions spanning 47-degrees of latitude al range in the Northeast Pacific (Alaska, California, and Panama). We used vessel traffic databases to characterize propagule pressure and construct a worldwide port network of marine shipping routes and ports. Environmental resistance was estimated using temperature and salinity data from donor and recipient regions. We further used standardized predator exposure experiments to quantify predation impact on fouling community biomass as an estimate of potential for biotic resistance. We then expanded on existing models of relative invasion risk to incorporate the probability that propagules will survive predation by local predators and overcome environmental filtering to generate a predicted invasion risk for each port.ResultsEnvironmental filtering in all regions and predation pressure in the tropics worked to reduce the invasion risk, resulting in markedly different cumulative risk profiles over time among regions.DiscussionIn an increasingly connected world with more vessel traffic, our results highlight that while the number and distribution of shipping routes are important to understand risk, abiotic and biotic filters can modify model predictions.

Analysis of Road Traffic Accidents in Dense Cities: Geotech Transport and ArcGIS

Road Traffic Accidents (RTAs) provide a substantial risk to both public safety and infrastructure within severe earthquake zones. This research aims to provide a thorough analysis of the many elements that contribute to RTAs in the area. Although research on RTAs has been conducted in numerous settings, there is a lack of localized research specifically focused on developing countries. Therefore, this study is necessary to address this gap in literature. Our study focuses on examining the distinct issues and elements that are particular to this specific location. The objective is to provide customized solutions that effectively reduce the occurrence of accidents. The objective of this study is to examine the status of RTAs, ascertain the main factors contributing to RTAs, and provide viable approaches to improve road safety. A comprehensive study of data was undertaken, which included the examination of key highways, accident-prone areas, and causes contributing to accidents. Insights were derived by the use of statistical analysis, hotspot mapping, and the categorization of incidents. The results revealed a distressing roadway are afflicted by a significant frequency of accidents, even those occurring on prominent thoroughfares. Excessive speed has been revealed as the primary contributing factor, closely followed by negligence and recklessness. The common factor seen in these events was the insufficient enforcement of traffic regulations. The research highlights several practical consequences. Firstly, it is advised to implement urgent actions such as the upgrading of the traffic database, the adoption of contemporary traffic management software, and the enforcement of rigorous traffic laws. The establishment of a comprehensive centralized database system is crucial in order to enhance the documenting and management of accidents. Furthermore, the use of cost-benefit analysis provides justification for the adoption of traffic calming measures in locations with a high incidence of accidents. Furthermore, the implementation of continuous road safety awareness efforts and the establishment of clear legislative guidelines pertaining to fatal accidents are imperative measures in promoting enhanced road safety.

Pattern recognition of urban traffic accidents: Application of cluster analysis and support vector machine in accident pattern recognition

Urban traffic accidents impose a significant threat to public safety because of its frequent occurrence and potential for severe injuries and fatalities. Hence, an effective analysis of accident patterns is crucial for designing accident prevention strategies. Recent advancement in data analytics have provided opportunities to improve the pattern of urban traffic accidents. However, the existing works face several challenges in adapting the complex dynamics, and heterogeneity of the accident data. To overcome these challenges, we proposed an innovative solution by combining the K-means clustering and Support Vector Machine to precisely predict the traffic accident patterns. By leveraging the efficiencies of clustering technique and machine learning, this work intends to identify the intricate patterns within the traffic database. Initially, a traffic accident database was collected and fed into the system. The collected database was pre-processed to improve and standardize the raw dataset. Further, cluster analysis is employed to identify distinct patterns within the dataset and group similar accidents into clusters. This clustering enables the system to recognize common accident scenarios and identify recent accident trends. Subsequently, a Support Vector Machine is deployed to classify accidents into distinct categories through intensive training with identified clusters. The combination enables the system to understand the complex relationships among diverse accident variables, making it an effective framework for real-time pattern recognition. The proposed strategy is implemented in Python and validated using the publicly available traffic accident database. The experimental results manifest that the proposed method achieved 99.65% accuracy, 99.53% precision, 99.62% recall, and 99.57% f-measure. Finally, the comparison with the existing techniques shows that the developed strategy offers improved accuracy, precision, recall, and f-measure compared to existing ones. shows that the developed strategy offers improved accuracy, precision, recall, and f-measure compared to existing ones.

Floating Ports as Support for Port Relocation Measures on Sea Level Rise

Ports are one of the structures where the effects of global warming are most severe and intense in atmospheric, oceanic, and geographical terms. According to the Intergovernmental Panel on Climate Change (IPCC)'s assessment reports, although it is possible to slow down global warming by reducing greenhouse gas (GHG) emissions, it is not foreseen to stop global warming and sea level rise (SLR) in any scenario. The rising sea level, an inevitable consequence of global warming, is a clear threat to conventional port facilities. In summary, SLR triggered by climate change, which is today's hot topic, may cause conventional port infrastructures to be flooded and lose their functionality. To cope with this threat, port facility planning, and design stages must be carried out by referring to the updated threshold values in Shared Socioeconomic Pathway (SSP) scenarios defined by the Working Groups of the IPCC. However, the uncertainty about the scale, timing, and location of SLR makes definitive solution-oriented approaches more prominent. One of these approaches is floating port structures. This study aims to reveal the role of floating port structures in the implementation of the relocation measure emphasized in the IPCC Sixth Assessment Report (AR6) for conventional ports under the threat of SLR. Initially, in this study, regions with higher SLR risk were identified by considering SSP scenarios contributed by Sixth Phase of the Coupled Model Intercomparison Project (CMIP6) data. Afterwards, the dynamic downscaling model was used to determine the regions with higher regional sea level rise (RSLR) risk and the Marine Traffic database was used to determine the ports in these regions. Thus, it is evaluated whether floating ports can be a suitable alternative in the relocation decision of ports under SLR risk. It is expected that maritime transport will be maintained at adequate security and operational levels by revealing the pros and cons of floating ports.

Modeled underwater sound levels in the Pan-Arctic due to increased shipping: Analysis from 2013 to 2019.

The loss of Arctic sea ice is one of the most visible signs of global climate change. As Arctic sea ice has retreated, Arctic marine shipping has increased. The Pan-Arctic's unique underwater acoustic properties mean that even small increases in ship traffic can have a significant effect on the ambient soundscape. This study presents the first long-term, basin-scale model of shipping noise in the Pan-Arctic with a focus on a few select sub-regions. The Arctic Ship Traffic Database from the Protection of the Arctic Marine Environment is used in this study to model the locations and source levels from ships operating in the Pan-Arctic between 2013 and 2019. The acoustic footprint of these ships is explored temporally for the entire basin as well as for the select large maritime ecosystems of the Barents Sea, the Northern Bering-Chukchi Sea, and Baffin Bay. From 2013 to 2019, modeled shipping noise propagating underwater broadly increased between 5-20 dB across the Pan-Arctic, but more specific results in sub-regions are presented and discussed.

Remote sensing traffic scene retrieval based on learning control algorithm for robot multimodal sensing information fusion and human-machine interaction and collaboration.

In light of advancing socio-economic development and urban infrastructure, urban traffic congestion and accidents have become pressing issues. High-resolution remote sensing images are crucial for supporting urban geographic information systems (GIS), road planning, and vehicle navigation. Additionally, the emergence of robotics presents new possibilities for traffic management and road safety. This study introduces an innovative approach that combines attention mechanisms and robotic multimodal information fusion for retrieving traffic scenes from remote sensing images. Attention mechanisms focus on specific road and traffic features, reducing computation and enhancing detail capture. Graph neural algorithms improve scene retrieval accuracy. To achieve efficient traffic scene retrieval, a robot equipped with advanced sensing technology autonomously navigates urban environments, capturing high-accuracy, wide-coverage images. This facilitates comprehensive traffic databases and real-time traffic information retrieval for precise traffic management. Extensive experiments on large-scale remote sensing datasets demonstrate the feasibility and effectiveness of this approach. The integration of attention mechanisms, graph neural algorithms, and robotic multimodal information fusion enhances traffic scene retrieval, promising improved information extraction accuracy for more effective traffic management, road safety, and intelligent transportation systems. In conclusion, this interdisciplinary approach, combining attention mechanisms, graph neural algorithms, and robotic technology, represents significant progress in traffic scene retrieval from remote sensing images, with potential applications in traffic management, road safety, and urban planning.

IoT-Based Smart Booking of Electric Vehicle Charging Station

The Immense growth in the implementation of electric vehicles (EVs), has established a path in the advancements of charging infrastructure. Interlinking and connecting the charging stations to a common server is essential for future EV adoption, and this can reduce the user's anxiety. The existing charging stations have not implemented charging slot availability and time scheduling management. The objective of this research is to enhance the current electric vehicle (EV) charging infrastructure by gathering and sharing real-time information about the availability of reserve slots at charging stations. This information is made available to users through an interactive application created with Android Studio, allowing them to locate the closest charging station for their EV. The application utilizes the State of Charge of the EV to assign available charging slots. The proposed real-time predictive charging server infrastructure avoids latency, effectively manages time scheduling, and avoids draining electric vehicle batteries. This proposed system uses the real-time traffic database to estimate the minimum distance path to reach the charging station.

Can AIS data improve the short-term forecast of weekly dry bulk cargo port throughput? - a machine-learning approach

ABSTRACT This study examines the development of a machine-learning model to forecast weekly throughputs of dry bulk cargo in the short term based on automatic identification system (AIS) data. Specifically, the weekly amounts of iron ore exported from several major ports in Australia and Brazil in the latter half of 2019 are forecasted three weeks in advance using a long short-term memory model. We examine many variables extracted from AIS data, including the vessel position, speed, draught, and destination, as the input features of the model. Consequently, we develop a highly accurate forecasting model that uses four influential variables derived from AIS data, namely, vessel traffic around the target port and in the region, vessel traffic at major partner import ports, and vessel traffic at the target port during the past year. Finally, by forecasting the weekly port cargo throughputs in the first half of 2020, which was affected by the COVID-19 pandemic, the applicability of the model is confirmed, even for ports where the throughput fluctuates significantly. In particular, this study demonstrates that AIS data are beneficial not only as a real-time traffic database but also as a database containing various related explanatory variables, including historical vessel traffic.

Load Models Representative of Brazilian Actual Traffic in Girder-Type Short-Span Highway Bridges

The Brazilian code NBR 7188 for highway bridge design prescribes a live load model consisting of a 3-axle vehicle plus a uniform load, which are both affected by an impact factor when considering dynamic effects. It does not play out actual traffic static effects and may be, in some cases, non-conservative. This work presents two load model configurations developed by gathering a real traffic database, traffic simulations, modeling of the dynamic interaction between vehicles and structure, and statistical extrapolations. Proposed load models comprise dynamic effects and were calibrated for two-lane single carriageway bridges with span lengths up to 40 m under free-flowing traffic. The target values of the effects were compared to those generated by the new proposed load models, as well as by the Brazilian design load model. Adequacy of the proposed models is demonstrated; results show that the effects generated by the Brazilian design load model are underestimated in many cases, particularly for negative moments in cantilevers.

CTTE: Customized Travel Time Estimation via Mobile Crowdsensing

Estimating the origin-destination travel time is a fundamental problem in many location-based services for vehicles, e.g., ride-hailing, vehicle dispatching, and route planning. Recent work has made significant progress to accuracy, but they largely rely on GPS trajectories which are too coarse to model many personalized driving behaviors, e.g., differentiating novice and veteran drivers. In this paper, we propose Customized Travel Time Estimation (CTTE) that fuses GPS trajectories, smartphone inertial data, and road network within a deep recurrent neural network. It constructs a road link traffic database with topology representation, speed statistics, and query distribution. It also calibrates inertial readings, estimates the arbitrary phone’s pose in car, and detects multiple aggressive driving events (e.g., bump judders, sharp turns, sharp slopes, frequent lane shifts, overspeeds, and sudden brakes). Finally, we demonstrate our solution on two typical transportation problems, i.e., predicting traffic speed at holistic level and estimating customized travel time at personal level, within a multi-task learning structure. Experiments on two large-scale real-world traffic datasets from DiDi platform show our effectiveness compared with the state-of-the-art.

Machine learning based real-time prediction of freeway crash risk using crowdsourced probe vehicle data

Real-time prediction of crash risk can support traffic incident management by generating critical information for practitioners to allocate resources for responding to anticipated traffic crashes proactively. Unlike previous studies using archived traffic data covering a limited highway environment such as a segment or corridor, this study uses a statewide live traffic database from HERE to develop real-time traffic crash prediction models. This database provides crowdsourced probe vehicle data that are high-resolution real-time traffic speed for the entire freeway network (nearly 2,000 miles) in Alabama. This study aims to use machine learning models to predict crash risk on freeways according to pre-crash traffic dynamics (e.g., mean speed, speed reduction) along with static freeway attributes. Traffic speed characteristics were extracted from the HERE database for both pre-crash and crash-free traffic conditions. Random Forest (RF), Support Vector Machine (SVM) and Extreme Gradient Boosting (XGBoost) were developed and compared. Separate models were estimated for three major crash types: single-vehicle, rear-end, and sideswipe crashes. The model prediction accuracy indicated that the RF models outperform other models. Models for rear-end crashes are found to have greater accuracy than other models, which implies that rear-end crashes have a significant relationship with pre-crash traffic dynamics and are more predictable. The traffic speed factors that are ranked high in terms of feature importance are the speed variance and speed reduction prior to crashes. According to partial dependence plots, the rear-end crash risk is positively related to the speed variance and speed reductions. More results are discussed in the paper.

PREDICTION STOCK PRICE BASED ON DATA SCIENCE TECHNIQUE

Predicting how the stock market will perform is one of the most difficult tasks. It can be described as one of the most important processes to predict. This is a difficult task with a lot of unknown things. To avoid this problem in one of the most interesting (or potentially profitable) time-series data sets, machine learning techniques have been used. As a result, stock price forecasts have emerged as an important research topic. The aim is to anticipate greater accuracy of stock price estimation systems based on machine learning. Suggest a method based on machine learning to accurately predict the value of a stock price index using the results of a stock price index or the highest accuracy scenario by comparing surveillance to differentiate machine learning algorithms. In addition, the effectiveness of a few machine learning methods from the departmental traffic database provided for testing will be compared and discussed. A set of data with a test breakdown report, identify the confusion matrix, and separate the data from the essentials, and the result shows that the efficiency of the proposed machine learning algorithm method can be compared with the best accuracy with precision, memory, and F1 Score. Keywords: - Data Editing, Upcoming Stock Returns, Machine Learning Tips.

Machine learning-based early detection of IoT botnets using network-edge traffic

In this work, we present an IoT botnet detection solution, EDIMA, consisting of a set of lightweight modules designed to be deployed at the edge gateway installed in home networks with the remaining modules expected to be implemented on cloud servers. EDIMA targets early detection of IoT botnets prior to the launch of an attack and includes a novel two-stage Machine Learning (ML)-based detector developed specifically for IoT bot detection at the edge gateway. The ML-based bot detector first employs supervised ML algorithms for aggregate traffic classification and subsequently Autocorrelation Function (ACF)-based tests to detect individual bots. The EDIMA architecture also comprises a malware traffic database, a policy engine, a feature extractor and a traffic parser. Performance evaluation results using our testbed setup with real-world IoT malware traffic as well as other public IoT datasets show that EDIMA achieves high bot scanning and bot-CnC traffic detection accuracies with very low false positive rates. The detection performance is also shown to be robust to an increase in the number of IoT devices connected to the edge gateway where EDIMA is deployed. Further, the runtime performance analysis of a Python implementation of EDIMA deployed on a Raspberry Pi reveals low bot detection delays and low RAM consumption. EDIMA is also shown to outperform existing detection techniques for bot scanning traffic and bot-CnC server communication.

A hierarchical RCNN for vehicle and vehicle license plate detection and recognition

<span>Vehicle and vehicle license detection obtained incredible achievements during recent years that are also popularly used in real traffic scenarios, such as intelligent traffic monitoring systems, auto parking systems, and vehicle services. Computer vision attracted much attention in vehicle and vehicle license detection, benefit from image processing and machine learning technologies. However, the existing methods still have some issues with vehicle and vehicle license plate recognition, especially in a complex environment. In this paper, we propose a multivehicle detection and license plate recognition system based on a hierarchical region convolutional neural network (RCNN). Firstly, a higher level of RCNN is employed to extract vehicles from the original images or video frames. Secondly, the regions of the detected vehicles are input to a lower level (smaller) RCNN to detect the license plate. Thirdly, the detected license plate is split into single numbers. Finally, the individual numbers are recognized by an even smaller RCNN. The experiments on the real traffic database validated the proposed method. Compared with the commonly used all-in-one deep learning structure, the proposed hierarchical method deals with the license plate recognition task in multiple levels for sub-tasks, which enables the modification of network size and structure according to the complexity of sub-tasks. Therefore, the computation load is reduced.</span>

Calibration of the empirical fundamental relationship using very large databases

This paper describes a procedure for fitting traffic stream models using very large traffic databases. The proposed approach consists of four steps: (1) an initial treatment to eliminate noisy, inaccurate data and to homogenize the information over the density range; (2) a first fitting of the model, based on the sum of squared orthogonal errors; (3) a second filter, to eliminate outliers that survived the initial data treatment; and (4) a second fitting of the model. The proposed approach was tested by fitting the Van Aerde traffic stream model to 104 thousand observations collected by a permanent traffic monitoring station on a freeway in the metropolitan region of São Paulo, Brazil. The model fitting used a genetic algorithm to search for the best values of the model parameters. The results demonstrate the effectiveness of the proposed approach.

Empirical approach for identifying potential rear-end collisions using trajectory data

This paper proposes a novel approach for examining rear-end collisions between successive vehicles in a traffic stream. In this approach, a new safety measure of the follower driver's attentiveness is proposed, referred to herein as instantaneous heeding time (IHT), reflecting the subject follower's heeding nature concerning its leader. A safety framework that integrates the IHT with the distance gap and the instantaneous follower's speed is presented. The applicability of the framework is demonstrated using an Indian-traffic trajectory database (developed in this study) and the homogeneous traffic database of the next generation simulation (NGSIM) project developed in the United States (U.S.). Five study sections in India and two study sections in the U.S. are analyzed for three traffic-flow levels. For Indian traffic, the results show that motorized two-wheelers (MTW) have degraded road safety due to the unrestrained lateral crisscross movements. Due to the presence of MTW, the Indian-traffic stream operates in a disorderly fashion, thereby increasing the probability of rear-end collisions with other vehicle classes. Further, the importance of implementing cautioning measures for drivers that reduce the probability of collisions is demonstrated. Besides, the NGSIM application results confirmed the proposed framework's applicability to both Indian and homogeneous traffic conditions. In practice, the proposed framework can be used in real-time to monitor the driver's aggressive instincts.

Spatial Analysis for the Classification of Prone Roads Traffic Accidents: A Systematic Literature Review

Identifying prone road traffic accidents (PRTA) has been based on the total number of accidents data. Determining road names that have not been appropriately approved makes the data biased. Many researchers have reviewed many factors, spatial methods of analysis, and ways to improve past traffic strategies. The searching method with a systematic literature review (SLR) was conducted on seven publishers of the traffic accident classification database. They are ACM Digital Library, IEEE e-Xplore, ScienceDirect, Springer, Sage, Taylor & Francis, and Wiley, then produced 189 major relevant studies to the findings of this study. SLR is used to find the most relevant journals, research topics, trends in the field, multi-criteria spatial dataset parameters, estimation methods, trends, the best methods currently, proposed improvement methods, and the most commonly used efforts to determine in a collection of road traffic accidents. The study results obtained that multi-criteria spatial data were developed in different spatial analyses. The SLR mapping results found gaps for hybrid two types of classification methods on multi-criteria decision making (MCDM) and Spatial Multi-level Classification. The consistency test of many methods is done by the Consistency Test Method (MCT), the value of Precision-Recall Accuracy (ARC), and Site Consistency Test (SCT).

Algorithm of automated annotation of areas of roads with increased accidents

The paper describes the methodology of annotating of road accidents centres of interactive accidents map. Based on the statistical analysis of the traffic accidents database the range of accident risk zones of a roadmap of the city are allocated as well as cause of accidents. These information in the form of text messages is applied to a vector map of a geographical area, in this paper – the map of Nizhny Novgorod. The annotation algorithm also takes into account the data of the road infrastructure, the weather, the driver (the user of the interactive crash map). The method was tested during the creation of e-cards of Nizhny Novgorod.

Transatlantic and Ancestral Routes and the Pharmacological and Biological Potential of Ocimum basilicum L.: A Review

Basil (Ocimum basilicum L.) is not endemic in Brazil; however, it is a symbolic plant for traditional peoples and was present in ancestral cultural resistance. Several species were introduced to Brazil through the slave trade on the Africa-Brazil transatlantic route. In addition, the active constituents of basil are of great pharmaceutical and biological importance, and the plant has been used for therapeutic purposes by a wide variety of people, from quilombola communities to the pharmaceutical industry. Thus, based on African ethnobotany and modern science, this review article aimed to contextualize the endemic and epistemic importance of the origin, traditional, ancestral, medicinal and therapeutic uses of basil, consumed en masse in Brazil (during and after) the slavery period. The bibliographic review was carried out by consulting historical books and Scopus scientific databases. Scielo, transatlantic slave traffic database and Web of Science. The results showed that traditional communities, quilombos and terreiros, already made medicinal and liturgical uses of basil, before its use by the pharmaceutical industry. And that after the period of slavery, several studies carried out by researchers with basil proved that this species has several therapeutic properties, already reported by traditional communities. Thus, it is concluded that O. basilicum L. is an endemic species of the African continent, introduced in Brazil on the transatlantic route and that the traditional and ancestral knowledge for therapeutic use and application was already present in the territory, before the studies of proof of activity, post slavery period. Currently, the species is widely applied in the pharmaceutical and biological industry. However, there is a need for strategies that recognize, value and integrate the knowledge of the traditional peoples of the African diaspora, scientific productions.