Road Classification Research Articles

Optimization of Urban Road Green Belts under the Background of Carbon Peak Policy

To explore the reasonable width of urban road green belts under the background of carbon peak policy and provide quantitative design guidance for urban green-belt planning, a closed-loop design that integrates urban traffic, carbon emissions, urban greening, and carbon absorption was established at the road network level. First, the factors affecting urban transport carbon emissions were analyzed from the aspects of environment, economy, population, and technology. A carbon emission prediction model was constructed based on the STIRPAT (stochastic impacts by regression on population, affluence, and technology) model. The path of the carbon peak in the transportation sector was simulated. A scenario under the carbon peak target was designed to determine the development trend of each factor. The layout forms and design requirements of urban road greening were then summarized. The annual carbon sequestration amounts of different plant types were calculated. An objective optimization model was constructed with the lowest cost of greening as the objective function. The constraint conditions specify that the carbon absorption be greater than the carbon emissions, in addition to specifying the basic greening design requirements. Finally, an empirical study was conducted on a road network area in Xi’an. According to the results, the traffic carbon emissions of Xi’an City will be 2.71 Mt in 2025, with road traffic accounting for 1.94 Mt. Without considering the road-measurement green-width constraint, the proportions of the road green belt for six road classes and the red-line width under the carbon peak target are 0.31, 0.33, 0.40, 0.22, 0.21, and 0.23. These research results provide a quantitative and reliable basis for designing the width of an urban green belt under the background of carbon peak policy. Under proportion restrictions, road greening yields better performance by considering both aesthetics and road characteristics.

Determining safety aspects of Differential Speed Limit on Indian Expressway

Optimization of operating speed limit on any class of road is the biggest task faced by the transportation experts. A variety of speed control or management techniques are available all around the globe to minimize the frequency of over-speeding or for increasing the acceptability of the posted speed limit. In this study, a comparison is carried out between Uniform Speed Limit (USL) and Differential speed Limit (DSL) on an Expressway in India, using microsimulation package PTV VISSIM. In USL, a single speed limit is implemented for all class of vehicles whereas DSL strategy have two distinct speed limit for two different class of vehicles i.e., passenger carrying vehicles and goods carrying vehicles. Multiple Key Performance Indicators (KPIs) were considered. Results suggested that DSL seems to be the better strategy on the roads accommodating high speeds like Expressways under heterogenous conditions. Four out of five KPIs were showing the results in favor of DSL strategy in comparison to USL strategy. KPIs like speed variance, Road Safety Index (RSI), no. of vehicles having Deceleration-Rate-to-Avoid-Collision (DRAC) > 3.35 m/sec2 and no. of lane changes were showcasing better results in case of DSL strategy in comparison to USL strategy.

The impact of traffic mobility measures on vehicle emissions for heterogeneous traffic in Lagos City

Emissions from vehicular traffic are one of the key drivers of urban environmental air pollution, degrading the ambient air quality in many African cities and across the globe. This study sought to assess the impact of traffic mobility measures on the emission levels of air pollutants from vehicle exhaust in Lagos, Nigeria. Traffic flow and vehicle mix were collected daily during morning, afternoon, and evening peak periods along selected arterial and two-lane collector roadways. Simultaneously, five (5) air pollutants from vehicular traffic emissions were observed at distinct monitoring stations along the roadways using portable gas detectors. The traffic flow and mobility measures were inputted into a multiple exponential model to estimate the concentration of each pollutant. The result of the vehicle fleet composition revealed 3.5%, 4.5%, 57%, 32%, 1.5%, and 2% for motorcycles, tricycles, personal cars, minibuses, large buses, and heavy goods vehicles, respectively, on the two-lane road and 10%, 35%, 27%, 10%, and 18% for motorcycles, personal cars, minibuses, large buses, and heavy goods vehicles, respectively, on the arterial. The results of a multiple exponential regression model (MER) showed significant contributions from traffic flow, speed, vehicle fleet proportion, and pollutant concentration (p <0.05). However, the impact on ambient air quality revealed severe pollution levels for CO and PM2.5, while SO2, NO2, and PM10 showed moderate, poor, and poor pollution levels. This study has provided evidence on how pollutant emissions increase rapidly during peak traffic conditions in heterogeneous traffic on different classes of roads and recommended policies for managing vehicle fleets and traffic congestion with the aim of reducing the impact on the ambient air quality and health of the public on heavily trafficked roadways in sub-Saharan African cities.

The Advantages on Using GGBS and ACBFS Aggregate to Obtain an Ecological Road Concrete

This work aims to show the advantages of using GGBS (Ground Granulated Blast Furnace Slag) and ACBFS aggregate (Air-Cooled Blast Furnace Slag) on the tensile strength and durability properties of infrastructure concrete at the reference age of 28 days. Three concrete mixes were prepared: the first one was a control sample; the second one had 15% GGBS (instead of Portland cement) and 25% ACBFS (instead of natural sand); and the third had 15% GGBS (instead of Portland cement) and 50% ACBFS (instead of natural sand). The studies on mortars focused on the ratio of compressive strength (CS) in correlation with the specific surface area (obtained by the Blain method). The microstructure of the prepared mortars was examined at the age of 28 days by X-ray diffraction, SEM electron microscopy with an energy-dispersive EDX spectrometer, and NMR nuclear magnetic resonance relaxometry. The results of the tests carried out afterwards on the concretes containing slag (15% GGBS and 25% or 50% ACBFS) showed values that met high-quality criteria for exfoliation (S56 &lt; 0.1 kg/m2), carbonation, and gelling G100 (with a loss of resistance to compression η &lt; 25%). The slag concretes showed a degree of gelation of G100 (with a loss of compressive strength below 25%), low volume losses below 18,000 mm3/5000 mm2 (corresponding to wear class 4, grade I), and moderate penetration of chlorine ions (according to the RCPT test). All of these allow the concrete with slag (GGBS/ACBFS) to be recommended as an ecological road concrete. Our study proved that a high-class road concrete of BcR 5.0 can be obtained, with tensile strengths of a minimum 5 MPa at 28 days (the higher road concrete class in Romania, according to national standards).

Investigating two-wheelers risk factors for severe crashes using an interpretable machine learning approach and SHAP analysis

The use of two-wheelers (TWs) has gained popularity as an alternative to personal vehicles due to their flexibility, fuel economy, ease of parking, and size, especially in congested cities. However, TWs are considered vulnerable road users due to their higher riding risk compared to other modes. This study proposes a novel framework to extract latent and dependent heterogeneous risk factors that affect the crash severity of TWs. By combining eXtreme Gradient Boosting (XGBoost) and SHapley Additive exPlanation (SHAP) analysis, this study investigates the factors affecting TW crash severity, providing both local and global interpretability. The XGBoost method is employed to model crash severity, while SHAP analysis facilitates the derivation of explanations from the model, enhancing our understanding of the contributing factors. The French crash dataset for TWs between 2014 and 2017 is utilized for this analysis. The findings highlight that the department of the crash, road category, urbanization level, TW category, and age of the user significantly influence TW crash severity. Furthermore, severe injuries are more likely to occur in TW crashes associated with rural areas, older riders, riders not wearing helmets, run-off-road crashes, and crossing roads. The insights derived from this study can be leveraged to develop targeted interventions that address the identified risk factors and promote the safety of TW riders. By focusing on these key factors, policymakers and stakeholders can implement effective measures to reduce the severity of TW crashes and enhance the overall safety of TW users.

Evaluating the effectiveness of machine learning techniques in forecasting the severity of traffic accidents

Traffic accidents pose a significant public safety concern, leading to numerous injuries and fatalities worldwide. Predicting the severity of these accidents is crucial for developing effective road safety measures and reducing casualties. This paper proposes an analytic framework that utilizes machine learning models, including Naive Bayes, Random Forest, Logistic Regression, and Artificial Neural Networks, to predict the severity of traffic accidents based on contributing factors. This study analyzed ten years of UK traffic accident data (2005–2014, N = 2,047,256) to develop and compare different ML models. Results show that the proposed Random Forest and Logistic Regression models achieved an 87% overall prediction accuracy, outperforming Naive Bayes (80%) and Artificial Neural Networks (80%). By employing Random Forest-based feature importance analysis, the study identified Engine Capacity, Age of the vehicle, make of vehicle, Age of the driver, vehicle manoeuvre, daytime, and 1st road class as the most sensitive variables influencing traffic accident severity prediction. Additionally, the suggested RF model outperformed most existing models, attaining a remarkable overall accuracy and superior predictive performance across various injury severity classes. The findings have significant implications for developing efficient road safety measures and enhancing the current traffic safety system. The proposed framework and models can be adapted to various datasets to achieve accurate and effective predictions of traffic accident severity, serving as a valuable reference for implementing traffic accident management and control measures. Future research could extend the proposed framework to datasets containing Casualty Accident information to further improve the accuracy of injury severity prediction.

Radar-Based Road Surface Classification System for Personal Mobility Devices

As personal mobility devices (PMDs) have been widely adopted, the accident rate also increased. For safe driving, the speed of the PMDs should be controlled by recognizing the condition of the road surface. In recent advances in artificial intelligence, various studies have been conducted to recognize the type of material based on radar sensors and machine learning. However, there are very limited studies addressing radar-based material recognition in noisy radar signal environments like PMDs. In this paper, we proposed a road surface classification scheme based on the 60 GHz pulsed radar, which has low cost and low power usage to be applied to various PMDs. We also developed a lightweight deep neural network model to recognize the type of road surface from the radar data after removing unnecessary features using principal component analysis (PCA). The proposed mechanism is robust against ambient noise and can recognize surface types on roads of variable shapes with high accuracy and low computational complexity. The results of experiments showed that the proposed lightweight surface classification system improved accuracy with only about 40% of the parameters used in the previous study.

Stability Analysis of a Vehicle–Cargo Securing System for Autonomous Trucks Based on 6-SPS-Type Parallel Mechanisms

Stability prediction of the securing system for autonomous trucks is an important prerequisite for achieving safety monitoring of large cargo transportation and improving logistics efficiency. Considering the side slide risk of large cargo and the inability to predict stability using the existing under-constrained friction securing model, this paper proposes a new vehicle–cargo securing model based on the 6-SPS parallel mechanism. By establishing an analytical 3-DOF model, the dynamics performance of the vehicle–cargo system is analyzed based on the response solution under sinusoidal excitations. To verify the correctness of the analytical model, a multi-body dynamics model of the whole vehicle–cargo system based on the three-dimensional geometric model and the 6-SPS parallel mechanism is established for simulation in ADAMS. According to road class, pavement roughness is modeled by a white noise power spectrum method as the excitation in the simulation. The results show that the dynamics response of the analytical model accords well with that of the simulation model, with relative errors of 8.34% and 0.036% in amplitude and frequency, respectively. The proposed method can provide theoretical support for accurate stability prediction and for achieving safety monitoring of large cargo transportation for autonomous trucks.

Clustering of Asphalt Pavement Maintenance Sections Based on 3D Ground-Penetrating Radar and Principal Component Techniques

Asphalt pavement maintenance section classification is an important prerequisite for accurately determining asphalt pavement maintenance needs and formulating accurate maintenance plans. This paper introduces the three-dimensional (3D) ground-penetrating radar (GPR) pavement internal crack rate index on the basis of an original road surface performance data matrix, and the dimensionality of the road section classification data matrix was reduced through the principal component technique. An analysis of variance was used to compare the significance of the differences in the results for road section classification using different clustering methods and different clustering data and to investigate the influence of the clustering method, principal component technique and crack rate index on the maintenance road section classification results. The results showed that the principal component technique could reduce the dimensionality of the data matrix by 33% and retain more than 84% of the information. There was a genetic relationship between the clustering data and the technical characteristics of the classified sub-sections, and the internal crack rate was important for the characterisation of internal defects in asphalt pavement sub-sections and the determination of maintenance needs. The results of section classification varied considerably between clustering methods, and the choice of clustering method had a relationship to the pavement maintenance objectives. The dynamic clustering method combined with principal component analysis could significantly improve the significance of the differences in the clustering results, effectively improving the division of maintenance sections.

Analyzing the Effectiveness of Imbalanced Data Handling Techniques in Predicting Driver Phone Use

Distracted driving leads to a significant number of road crashes worldwide. Smartphone use is one of the most common causes of cognitive distraction among drivers. Available data on drivers’ phone use presents an invaluable opportunity to identify the main factors behind this behavior. Machine learning (ML) techniques are among the most effective techniques for this purpose. However, the potential and usefulness of these techniques are limited, due to the imbalance of available data. The majority class of instances collected is for drivers who do not use their phones, while the minority class is for those who do use their phones. This paper evaluates two main approaches for handling imbalanced datasets on driver phone use. These methods include oversampling and undersampling. The effectiveness of each method was evaluated using six ML techniques: Multilayer Perceptron (MLP), Support Vector Machine (SVM), Naive Bayes (NB), Bayesian Network (BayesNet), J48, and ID3. The proposed methods were also evaluated on three Deep Learning (DL) models: Arch1 (5 hidden layers), Arch2 (10 hidden layers), and Arch3 (15 hidden layers). The data used in this document were collected through a direct observation study to explore a set of human, vehicle, and road surface characteristics. The results showed that all ML methods, as well as DL methods, achieved balanced accuracy values for both classes. ID3, J48, and MLP methods outperformed the rest of the ML methods in all scenarios, with ID3 achieving slightly better accuracy. The DL methods also provided good performances, especially for the undersampling data. The results also showed that the classification methods performed best on the undersampled data. It was concluded that road classification has the highest impact on cell phone use, followed by driver age group, driver gender, vehicle type, and, finally, driver seatbelt usage.

FOXS-GSC—Fast Offset Xpath Service with HexagonS Communication

Congestion in large cities is widely recognized as a problem that impacts various aspects of society, including the economy and public health. To support the urban traffic system and to mitigate traffic congestion and the damage it causes, in this article we propose an assistant Intelligent Transport Systems (ITS) service for traffic management in Vehicular Networks (VANET), which we name FOXS-GSC, for Fast Offset Xpath Service with hexaGonS Communication. FOXS-GSC uses a VANET communication and fog computing paradigm to detect and recommend an alternative vehicle route to avoid traffic jams. Unlike the previous solutions in the literature, the proposed service offers a versatile approach in which traffic road classification and route suggestions can be made by infrastructure or by the vehicle itself without compromising the quality of the route service. To achieve this, the service operates in a decentralized way, and the components of the service (vehicles/infrastructure) exchange messages containing vehicle information and regional traffic information. For communication, the proposed approach uses a new dedicated multi-hop protocol that has been specifically designed based on the characteristics and requirements of a vehicle routing service. Therefore, by adapting to the inherent characteristics of a vehicle routing service, such as the density of regions, the proposed communication protocol both enhances reliability and improves the overall efficiency of the vehicle routing service. Simulation results comparing FOXS-GSC with baseline solutions and other proposals from the literature demonstrate its significant impact, reducing network congestion by up to 95% while maintaining a coverage of 97% across various scenery characteristics. Concerning road traffic efficiency, the traffic quality is increasing by 29%, for a reduction in carbon emissions of 10%.

Optimization land use based on multi-scenario simulation of ecosystem service for sustainable landscape planning in a mixed urban - Forest watershed

Integrating ecosystem services (ESs) into land development strategies can provide a new perspective in order to make more informed land use (LULC) decisions. In this sense, a specific framework is provided to use ESs in land allocation in Ilam urban watershed, Western Iran. This region is experiencing unsustainable development and destruction of natural ecosystems and as a result, these conditions have affected ecological characteristics, and ESs. Therefore, characterizing the LULC of this watershed and its impact on ESs is significant to comprehensively understanding the influences of human activities on ecosystems. Hence, the simulated annealing-genetic hybrid algorithm was assessed to optimize LULC using Six types of ESs; including, food provisioning (FP), water yield (WY), sediment retention (SR), recreation quality (RQ), aesthetic quality (AQ) and habitat quality (HQ). Regarding optimization approach, FP, WY, SR, RQ, AQ, HQ and land integration (LI) scenarios were designed based on LULC types and ESs. Considering the land allocation, the results indicated that most changes are related to the northwest, southeast, southwest and middle parts of the region. Moreover, an increasing trend was observed regarding dense forest and low-dense forest, according to the following scenarios: FP, RQ, LI, AQ, WY, SR and HQ. In contrast, a decreasing trend was obtained for cropland in the same order of scenarios. Additionally, the highest areas of garden, grassland, park, river, urban land, and road classes were observed in scenarios HQ, LI, SR, WY and FP, respectively. The results also revealed that the SDR scenario can be regarded as the best one having the lowest LULC fragmentation. Our study indicated that using ESs to optimize LULC allocation is a useful and an important strategy due to the fact that one can consider both the function and the structure of ecosystems in LULC planning and management decisions. Thus, the results of this research can help land managers in order to develop LULC, based on ESs and ecological conditions, which would finally lead to maintain the ESs and achieve sustainable development.

Landslide risk of regional roads: Consider the road mileage of expected losses

Considering the road disruption caused by landslides, this study develops a quantitative method to evaluate the landslide risk encountered by regional roads. First, a logistic regression model was performed to evaluate the landslide possibility with nine landslide factors and 359 landslide samples. Subsequently, network self-adjustment and three vulnerable factors were integrated to depict road vulnerability. After determining the cost of different road sections, the landslide risk of roads was calculated and expressed as a potentially expected loss. Results show that the study area highlights the road segments with low landslide risk, focusing on the expected loss of 0.0–0.1 million CNY; while lines of Tahe-Great Khingan-Mohe and Mohe-Huma maintain the highest risk, and the expected loss exceeds 0.8 million CNY. Furthermore, the lower the road class, not only the greater the expected loss, but the higher the road mileage exposed to landslides, which facilitates the mitigation strategy for different types of roads in response to landslides.

INFLUENCE OF SHOCK ABSORBER PROPERTIES ON TIRE LATERAL FORCE

The article examines how the damping properties of the suspension system of a vehicle affect the process of forming a lateral reaction in the contact patch of a tire and the supporting surface. A mathematical model of a car quarter, a tire stretched string model, and a road surface microprofile generator were used in the study. The dependences of normal and lateral reactions along the distance traveled for three classes of roads were obtained with a change in the parameter characterizing the damping properties of the vehicle suspension. Mathematical statistics methods were used to analyze the dependences. It was found that the average value of the normal load changes little with a decrease in the damping properties of the suspension, while the standard deviation increases. The average value of the lateral force is reduced by 22%, with the standard deviation increasing by 1.6 times. The use of the Kolmogorov-Smirnov criterion for the analysis of implementations of lateral forces makes it possible to determine the permissible range of nominal values of the parameters of the technical condition of vehicle suspension shock absorbers.&#x0D; Purpose. Obtaining and analyzing patterns that describe the change in the lateral reaction of a car tire when it moves under the action of a lateral force and suspension vibrations, as well as when changing the damping properties of a shock absorber.&#x0D; Methodology. In the article were used the methods of mathematical modeling and also statistical methods of the analysis.&#x0D; Results. Dependences have been obtained that characterize the influence of the damping properties of the suspension on the magnitude of the lateral reaction when the wheel moves along a road with bumps and under the action of a lateral force.&#x0D; Practical implications. It is expedient to apply the received results by the organizations and institutions involved in the development of methods and means of diagnosing vehicles.

Multilevel Analysis of Road Accident Frequency: The Impact of the Road Category

Multilevel Analysis of Road Accident Frequency: The Impact of the Road Category

Determining Free-Flow Speed on Different Classes of Rural Two-Lane Highways

Current analytical free-flow speed models consider all rural two-lane highways as the same road type despite their different functional significance in the network. The aim of this paper is to develop a prediction model for free-flow speed as a function of speed limit and road geometric characteristics for different classes of rural two-lane highways. The research was conducted on 50 representative sections of the two rural classes of two-lane highways equipped with automatic traffic counters in Serbia. In order to develop the appropriate models, it was necessary to determine the threshold values of vehicle time headway in the free-flow for both classes of rural two-lane highways, based on the total number of 191,720 vehicles. The obtained results show that there are differences in the threshold values of free-flow time headway for different road classes. Namely, it was determined that the values of free-flow time headway for Class I amounted to 6.3 s, and for Class II to 8.4 s. The free-flow speed prediction model for different road classes showed that speed limit had the highest impact on free-flow speed for Class I and II highways, followed by horizontal curve radius and shoulder width.

Kajian Teknisi Penerapan Jalan Umum di Jalan Akses Bandara Juanda

Juanda Airport Access Road, Sidoarjo Regency, East Java has a length of 3.15km with a width of 6m and there are 73 lighting points with a pole height of 12m and a distance between poles of 44m with a total of 8 single-arm poles and 65 double-arm poles. In addition, the street lighting lamps installed are 72 150 watt LED lamps and 66 250 watt SON-T type lamps. The measurement results are 26.37 lux for a 150 watt LED type lamp and 10.27 lux for a 250 watt SON-T lamp. However, from the many lights that have been installed, the lighting on the access road to Juanda Airport is still not optimal and many blackspots are found in certain areas. Therefore, it is necessary to do a re-analysis so that the road lighting for the Juanda Airport access road can meet the standards. The results of the analysis concluded that by carrying out a simulation on the dialux application according to the conditions in the field, 73 points of lighting poles were needed, the handlebar angle of the ornament was 14.06o with a total of 138 196 watt LED lights with an intensity of 15 lux which was in accordance with the standards of the Indonesian National Standards Agency 7391 : 2008 regarding the specifications for street lighting in urban areas and the Ministry of Energy and Mineral Resources 2014 for collector road classes for national road status, namely 15 - 20lux.

Wildlife mortality on roads crossing a protected area: The case of Dadia-Lefkimi-Soufli National Park in north-eastern Greece

Wildlife-vehicle collisions have been identified as an important ecological problem in most countries around the world, during the last decades. In the present work we examined the impacts on wildlife arising from two road categories crossing and adjoining the Dadia-Lefkimi-Soufli National Park (DLS NP), in north-eastern Greece. The study area is consisted of one of the most diverse fauna in Europe, with 202 bird species including 36 out of 38 European diurnal raptors, 60–65 mammal species, 29 reptiles and 13 amphibians. Vehicle collisions was the highest mortality factor in the study (83.9%) among five recorded categories, poison, electrocution, drowning, vehicle collisions and unidentified causes. 204 vehicle casualties were recorded out of 243 in total. Mammals (90.7%) were the vertebrates that mainly suffered from road mortality, including 11 species. The stone marten Martes foina contributed with the highest numbers, followed by the red fox Vulpes vulpes, the hedgehog Erinaceus roumanicus and the wild cat Felis silvestris. Although the contribution of birds on the road casualties was low, nine species were identified, including five diurnal and four nocturnal species, with raptors predominating. Most road casualties were observed in the national road network (71.6%), mainly during holidays (58.3%). Traffic volume, road category, season and blind bend were all dominant factors with different effects determining high wildlife-vehicle collision values. Mitigation measures that can reduce the harmful effects of roads on wildlife in the DLS NP are also discussed.

Measuring disparities in access to district and referral hospitals in the city of Kigali, Rwanda

The study focused on the identification of theoretical and methodological constructs that can be used to analyse and improve the spatial performance of public health service delivery systems and the development of a corresponding spatial-analysis and GIS-based planning approach using the city of Kigali as a case study. Access to health care as a multi-tiered system was measured by using five dimensions of access, namely geographic accessibility, availability, affordability, acceptability and accommodation. Geo-statistical analysis was performed to measure and evaluate access to the district and referral health care. For geographic access, the travel time for every trip is approximated for the two main modes of transport (walking and public transport). To realistically represent the friction of distance, the street network was categorised into several road classes for which different travel speeds are estimated for each transport mode on the basis of local knowledge. A factor analysis model was used for availability, affordability, acceptability, and accommodation dimensions. Different indicators were evaluated in various units and scales and standardized to see how satisfaction levels varied with each dimension. Based on the type of indicator, for the cost or benefit, the score was zero (0) or one (1). One (1) was considered a positive impact, while zero (0) was considered a negative impact. Summary scores were developed for all indicators by combining more than one indicator into a single value. The created summary score also ranges from 0 to 1, and the higher the score, the better the access attainment. To find areas that need intervention, the comparison of all five indicators and the scores of access for each indicator was made. The dimensions of geographic accessibility and availability appeared to be the most problematic. The district health care dimensions have revealed a low performance level in geographic accessibility (0.64) and a high-performance level in affordability (0.94). The referral health care dimensions have revealed a low performance level of geographic accessibility (0.17) and a high-performance level of acceptability (0.92). Health planners and policy makers will commonly require such a planning method, particularly in the developing world where spatial contexts are highly dynamic as a result of rapid urbanisation.

Machine learning-based soft-sensor development for road quality classification

Vibrations in road vehicles cause several harmful effects, health problems can occur for the passengers, and mechanical damage can occur to the vehicle components. Given the health, safety, and financial issues that arise, keeping the road network in good condition and detecting road defects as early as possible requires an extensive monitoring system. Related to this, our study presents the development of hardware and software for a low-cost, multi-sensor road quality monitoring system for passenger vehicles. The developed monitoring system can classify road sections according to their quality parameters into four classes. In order to detect vibrations in the vehicle, accelerometers and gyroscope sensors are installed at several points. Then, a machine learning-based soft-sensor development is introduced. Besides noise filtering, each data point is resampled by spatial frequency to reduce the velocity dependence. Subsequently, a decision tree-based classification model is trained using features from the power spectrum and principal component analysis. The classification algorithm is validated and tested with measurement data in a real-world environment. In addition to reviewing the accuracy of the model, we examine the correlation of the data measured in the cabin and on the suspension to see how much additional information is provided by the sensor on the axle.