Infrastructures

24 pages, 1941 KiB

Open AccessArticle

Handling Imbalanced Data in Road Crash Severity Prediction by Machine Learning Algorithms

by Nicholas Fiorentini and Massimo Losa

Infrastructures 2020, 5(7), 61; https://doi.org/10.3390/infrastructures5070061 - 20 Jul 2020

Cited by 88 | Viewed by 9098

Crash severity is undoubtedly a fundamental aspect of a crash event. Although machine learning algorithms for predicting crash severity have recently gained interest by the academic community, there is a significant trend towards neglecting the fact that crash datasets are acutely imbalanced. Overlooking [...] Read more.

Crash severity is undoubtedly a fundamental aspect of a crash event. Although machine learning algorithms for predicting crash severity have recently gained interest by the academic community, there is a significant trend towards neglecting the fact that crash datasets are acutely imbalanced. Overlooking this fact generally leads to weak classifiers for predicting the minority class (crashes with higher severity). In this paper, in order to handle imbalanced accident datasets and provide a better prediction for the minority class, the random undersampling the majority class (RUMC) technique is used. By employing an imbalanced and a RUMC-based balanced training set, we propose the calibration, validation, and evaluation of four different crash severity predictive models, including random tree, k-nearest neighbor, logistic regression, and random forest. Accuracy, true positive rate (recall), false positive rate, true negative rate, precision, F₁-score, and the confusion matrix have been calculated to assess the performance. Outcomes show that RUMC-based models provide an enhancement in the reliability of the classifiers for detecting fatal crashes and those causing injury. Indeed, in imbalanced models, the true positive rate for predicting fatal crashes and those causing injury spans from 0% (logistic regression) to 18.3% (k-nearest neighbor), while for the RUMC-based models, it spans from 52.5% (RUMC-based logistic regression) to 57.2% (RUMC-based k-nearest neighbor). Organizations and decision-makers could make use of RUMC and machine learning algorithms in predicting the severity of a crash occurrence, managing the present, and planning the future of their works. Full article

► Show Figures

Figure 1

18 pages, 3688 KiB

Open AccessArticle

Aeroelastic Response of Suspended Pedestrian Bridges Made of Laminated Wood and Hemp

by Fabio Rizzo

Infrastructures 2020, 5(7), 60; https://doi.org/10.3390/infrastructures5070060 - 20 Jul 2020

Cited by 2 | Viewed by 2856

Abstract

The work described in this paper investigated, by calculating critical flutter speed, the aeroelastic response of suspended pedestrian bridges made of a laminated wood structure and hemp cables and compared them to bridges with a steel structure and harmonic steel cables. Critical flutter [...] Read more.

The work described in this paper investigated, by calculating critical flutter speed, the aeroelastic response of suspended pedestrian bridges made of a laminated wood structure and hemp cables and compared them to bridges with a steel structure and harmonic steel cables. Critical flutter speed was estimated using a numerical two degree of freedom (2-DOF) generalized deck model based on finite-element modal analysis. The critical flutter speeds of two sets of 25 different structural configurations, obtained by varying the deck chord and the permanent deck loads, made of steel and of laminated wood respectively, were estimated using experimental flutter derivatives obtained from 30 wind tunnel experiments. One of the most significant results was that pedestrian bridges made of laminated wood and hemp have a higher torsional frequency than those made of steel and that this affects critical flutter speed. A case study was performed and discussed by analyzing the structural and aeroelastic response of a 250 m pedestrian bridge with a 12 m deck chord and two approximately 32 m tall towers. Full article

(This article belongs to the Special Issue Innovative Materials and Sustainable Infrastructure Construction)

► Show Figures

Figure 1

18 pages, 4138 KiB

Open AccessArticle

BIM-Based Design for Road Infrastructure: A Critical Focus on Modeling Guardrails and Retaining Walls

by Salvatore Antonio Biancardo, Nunzio Viscione, Antonio Cerbone and Enzo Dessì, Jr.

Infrastructures 2020, 5(7), 59; https://doi.org/10.3390/infrastructures5070059 - 13 Jul 2020

Cited by 40 | Viewed by 8207

Abstract

Although building information modeling (BIM) has been widely adopted in the building industry for several decades, the use of BIM in the context of transportation infrastructure has been slow in terms of both adoption and application. Industry and academia are increasingly making efforts [...] Read more.

Although building information modeling (BIM) has been widely adopted in the building industry for several decades, the use of BIM in the context of transportation infrastructure has been slow in terms of both adoption and application. Industry and academia are increasingly making efforts to adopt BIM for other non-building civil infrastructure but, so far, there has not been a comprehensive review of these efforts specifically regarding transportation. This paper explores BIM implementation in an infrastructure design project. An Autodesk ^® BIM-based tool, Civil 3D, is proposed as a potential BIM tool platform. This paper also focuses on modeling specific road elements not editable from the standard library, such as guardrails and retaining walls, as well as proposing different solutions using Revit and Subassembly Composer and analyzing the interoperability among BIM-based tools. Full article

(This article belongs to the Special Issue Road and Rail Infrastructures)

► Show Figures

Graphical abstract

14 pages, 2619 KiB

Open AccessArticle

Analyzing Transportation Sustainability in the Canary Islands Archipelago

by Rui Alexandre Castanho, Arian Behradfar, Ana Vulevic and José Manuel Naranjo Gómez

Infrastructures 2020, 5(7), 58; https://doi.org/10.3390/infrastructures5070058 - 6 Jul 2020

Cited by 27 | Viewed by 4493

Abstract

The scarcity of resources, the limited land, and the overstressing of tourism, as well as the estrangements of movement, make the insular territories relevant case studies in terms of their regional management and governance and, consequently, sustainable development. Thereby, Transportation and Infrastructures’ Sustainability [...] Read more.

The scarcity of resources, the limited land, and the overstressing of tourism, as well as the estrangements of movement, make the insular territories relevant case studies in terms of their regional management and governance and, consequently, sustainable development. Thereby, Transportation and Infrastructures’ Sustainability in these territories is not an exception. In this regard, the present study, through exploratory tools, expects to analyze, using accessibility and connectivity indicators, the impacts over the social-economic sphere that the local Transportation and Infrastructures may deliver to the populations of the Canary Islands Archipelago. The study enables us to identify the islands of La Palma, El Hierro, Fuerteventura, and La Gomera as those with better accessibility patterns. Full article

► Show Figures

Graphical abstract

16 pages, 5401 KiB

Open AccessArticle

Effect of Limestone Powder and Fine Gypsum on the Cracking Tendency of Blast-Furnace Slag Cement Concrete Subjected to Accelerated Curing

by Bernard A. Zulu, Shingo Miyazawa and Nobukazu Nito

Infrastructures 2020, 5(7), 57; https://doi.org/10.3390/infrastructures5070057 - 3 Jul 2020

Viewed by 3045

Abstract

Thermal stresses are generated in concrete during the accelerated curing process in precast concrete. These stresses may cause concrete to crack, which would have a negative effect on the general concrete performance. This paper provides the results of the thermal stress analysis of [...] Read more.

Thermal stresses are generated in concrete during the accelerated curing process in precast concrete. These stresses may cause concrete to crack, which would have a negative effect on the general concrete performance. This paper provides the results of the thermal stress analysis of concrete containing 25% replacement of ordinary Portland cement (OPC) by ground granulated blast-furnace slag cement (GGBFS) with 3000 cm²/g fineness. A total of 2.5% of limestone powder and 1.75% of fine gypsum by mass of OPC were incorporated in the other concrete mix proportion to check their effect on the cracking tendency of concrete. The concrete was subjected to heat curing. JCMAC, a 3D finite element analysis software developed in Japan, was used in this study for the thermal stress analysis. The heat curing period of one day, similar to generally used in the precast concrete industry for civil engineering products consisting of 3 h preheating period, heating to a peak temperature of 65 °C and this temperature was kept for 3 h, and lastly cooling was used in the study. A standard precast box culvert model member together with some experimental results obtained in the laboratory were used in the analysis. Lower cracking resistance at 1 day was observed in both mix proportions that would lead to cracking at demolding time. Curing sheets were then introduced in the analysis to cover the precast mold during accelerated curing and this showed improvement in cracking resistance of concrete containing limestone powder and fine gypsum. Full article

(This article belongs to the Section Infrastructures Materials and Constructions)

► Show Figures

Graphical abstract

13 pages, 5964 KiB

Open AccessArticle

Development of Smart Pavement Design Sensitivity Analysis Software for Asset Management System

by Byungkyu Moon, Jungyong “Joe” Kim and Hosin “David” Lee

Infrastructures 2020, 5(7), 56; https://doi.org/10.3390/infrastructures5070056 - 2 Jul 2020

Viewed by 4624

Abstract

There are a number of pavement management systems, but most of them are limited in providing pavement design and pavement design sensitivity information. This paper presents efforts towards the integrated pavement design and management system, by developing smart pavement design sensitivity analysis software. [...] Read more.

There are a number of pavement management systems, but most of them are limited in providing pavement design and pavement design sensitivity information. This paper presents efforts towards the integrated pavement design and management system, by developing smart pavement design sensitivity analysis software. In this paper, the sensitivity analyses of critical design input parameters have been performed to identify input parameters which have the most significant impacts on the pavement thickness. Based on the existing pavement design procedures and their sensitivity analysis results, a smart pavement design sensitivity analysis (PDSA) software package was developed, to allow a user to retrieve the most appropriate pavement thickness and immediately perform pavement design sensitivity analysis. The PDSA software is a useful tool for managing pavements, by allowing a user to instantaneously retrieve a pavement design for a given condition from the database and perform a design sensitivity analysis without running actual pavement design programs. The proposed smart PDSA software would result in the most efficient pavement management system, by incorporating the optimum pavement thickness as part of the pavement management process. Full article

(This article belongs to the Special Issue Smart Cities and Infrastructures)

► Show Figures

Graphical abstract

28 pages, 7085 KiB

Open AccessArticle

Roads Detection and Parametrization in Integrated BIM-GIS Using LiDAR

by Luigi Barazzetti, Mattia Previtali and Marco Scaioni

Infrastructures 2020, 5(7), 55; https://doi.org/10.3390/infrastructures5070055 - 1 Jul 2020

Cited by 38 | Viewed by 7203

Abstract

Building Information Modeling (BIM) has a crucial role in smart road applications, not only limited to the design and construction stages, but also to traffic monitoring, autonomous vehicle navigation, road condition assessment, and real-time data delivery to drivers, among others. Point clouds collected [...] Read more.

Building Information Modeling (BIM) has a crucial role in smart road applications, not only limited to the design and construction stages, but also to traffic monitoring, autonomous vehicle navigation, road condition assessment, and real-time data delivery to drivers, among others. Point clouds collected through LiDAR are a powerful solution to capture as-built conditions, notwithstanding the lack of commercial tools able to automatically reconstruct road geometry in a BIM environment. This paper illustrates a two-step procedure in which roads are automatically detected and classified, providing GIS layers with basic road geometry that are turned into parametric BIM objects. The proposed system is an integrated BIM-GIS with a structure based on multiple proposals, in which a single project file can handle different versions of the model using a variable level of detail. The model is also refined by adding parametric elements for buildings and vegetation. Input data for the integrated BIM-GIS can also be existing cartographic layers or outputs generated with algorithms able to handle LiDAR data. This makes the generation of the BIM-GIS more flexible and not limited to the use of specific algorithms for point cloud processing. Full article

(This article belongs to the Section Smart Infrastructures)

► Show Figures

Graphical abstract

12 pages, 896 KiB

Open AccessTechnical Note

Improving Safety of Transportation of Dangerous Goods by Railway Transport

by Nijolė Batarlienė

Infrastructures 2020, 5(7), 54; https://doi.org/10.3390/infrastructures5070054 - 1 Jul 2020

Cited by 13 | Viewed by 6882

Abstract

The transport of dangerous goods by rail carries a high risk of accident and every effort should be made to ensure that such transport is carried out under the best possible safety conditions. The research objective was to analyze and identify the main [...] Read more.

The transport of dangerous goods by rail carries a high risk of accident and every effort should be made to ensure that such transport is carried out under the best possible safety conditions. The research objective was to analyze and identify the main risks associated with the transport of dangerous goods by rail as well as to identify and assess the main factors of safe transport in order to reduce the risk of accident. For this purpose, analysis of the literature, systematization, generalization, and evaluation by experts was applied. The article states that in order to ensure the safe transport of dangerous goods by rail, it is necessary to comply with the rules for loading and unloading dangerous goods, the established requirements and instructions, and technical conditions of wagons and their labelling as well as preventive measures to reduce the risk. Recommendations are provided on how to reduce accidents and incidents in the transport of dangerous goods by rail. Full article

► Show Figures

Figure 1

16 pages, 368 KiB

Open AccessReview

An Overview on the Current Status and Future Perspectives of Smart Cars

by Fabio Arena, Giovanni Pau and Alessandro Severino

Infrastructures 2020, 5(7), 53; https://doi.org/10.3390/infrastructures5070053 - 30 Jun 2020

Cited by 54 | Viewed by 14059

Abstract

In recent years, the smart car sector has been increasing enormously in the Internet of Things (IoT) market. Furthermore, the number of smart cars seems set to increase over the next few years. This goal will be achieved because the application of recent [...] Read more.

In recent years, the smart car sector has been increasing enormously in the Internet of Things (IoT) market. Furthermore, the number of smart cars seems set to increase over the next few years. This goal will be achieved because the application of recent IoT technologies to the automotive sector opens up innovative opportunities for the mobility of the future, in which connected cars will be more and more prominent in smart cities. This paper aims to provide an overview of the current status and future perspectives of smart cars, taking into account technological, transport, and social features. An analysis concerning the approaches to making smart a generic car, the possible evolutions that could occur in the coming decades, the characteristics of 5G, ADAS (advanced driver assistance systems), and the power sources is carried out in this paper. Full article

(This article belongs to the Special Issue Resilient and Smart Transport Infrastructure for Connected and Autonomous Vehicles)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Infrastructures, Volume 5, Issue 7 (July 2020) – 9 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI