Vehicle Classification Research Articles

Real-Time Vehicle Classification Using LSTM Optimized by Oppositional-Based Wild Horse Optimization

Real-Time Vehicle Classification Using LSTM Optimized by Oppositional-Based Wild Horse Optimization

Comfort in Automated Driving: A Literature Survey and a High-Level Integrative Framework

The advancement of automated vehicle technology and the resulting shift from active driver control to a more passive role introduce previously unexplored factors that influence drivers' comfort. Examples include the vehicle's level of automation and the driver's preferred driving style, trust in the vehicle, and situation awareness. To structure these as a resource that can support future research, we conducted a comprehensive literature review, identifying 51 works that directly or peripherally address comfort in an automated driving context. Most of these works focus on the physical component of comfort, rooted in vehicle dynamics, while only a few consider a broader concept of comfort necessary to encompass a more expansive set of factors. Based on this review, we propose an integrative framework of 27 comfort influencing factors and their interrelationships. We categorize factors into six groups, encompassing the driving environment, vehicle physical features and automation system, and the user's activity, individual characteristics, and understanding of the automated system. These six groups are organized into the three larger categories of environment, vehicle, and user-related considerations. Patterns that emerge from the framework include that: a) some factors primarily influence physical well-being (such as motion forces), b) some contribute to discomfort (automation failures) while others contribute to comfort (secondary activities), c) some are stable and known before the trip (individual characteristics) while others change over time (environment), and d) comfort or discomfort can lead users to change either the relevant factors (level of automation) or their own behavior (secondary activities).

Proposed Index for Assigning an Environmental Label to Passenger Cars

At present, the classification of vehicles by means of the environmental label aims to positively distinguish the most environmentally friendly vehicles and to be an effective instrument at the service of municipal policies, both to restrict traffic during high pollution periods and to promote new technologies through tax benefits and other incentives related to mobility and the environment. However, there is a great deal of controversy about the awarding of this environmental label, since it is basically based only on the year of manufacture of the vehicle and the type of fuel it uses, without taking into account many other factors that influence the environmental characterization of a vehicle. This paper presents a proposal for an index to characterize passenger cars from an environmental point of view, considering other additional factors, such as tire wear and particulate emissions during braking. The proposed index is applied to a series of passenger cars representative of the segments currently present in the Spanish market. The index considers seven vehicle parameters. Up to three cases with different parameter weights are analyzed. This index provides greater discrimination of the environmental performance of vehicles than the current eco-labeling system, in each of the three cases studied.

Classification, military applications, and opportunities of unmanned aerial vehicles

Unmanned aerial vehicles (UAVs) are cutting-edge technologies used for military purposes world-wide at tactical, operational, and strategic levels. This study provides an overview of the history and current state of military drones, considering a global and Ecuadorian background. Then, a classification of the UAVs developed and built in Ecuador is conducted based on their endurance, altitude, and wing span to understand the national context and progress. The research also delves into the applications of UAVs in several military operations and missions, aiming to create a framework that aligns UAV capabilities with specific operational needs; this permits the identification of the challenges and opportunities the country faces. Unmanned aerial systems have changed the battlefield, and the government needs to adapt to a national strategy that incorporates this technology; this research analyzes and provides insights to improve military capabilities such as exploring modern UAV military applications, technical updates in communication, navigation, and data acquisition systems; and the integration of emerging technologies like smart materials, artificial intelligence, and electric propulsion systems. This study provides valuable insights into the Ecuadorian UAVs that enhance the country’s military operations and offer some applications and uses of this technology for national security.

LiVeR: Lightweight Vehicle Detection and Classification in Real-Time

Detection of vehicles and their classification is a significant component of wide-area monitoring and surveillance, as well as intelligent- transportation . Existing solutions tend to employ heavy-weight infrastructure and costly equipment, as well as largely depend on constant support from the cloud through round-the-clock internet connectivity and uninterrupted power supply. Moreover, existing works mainly concentrate on localized measurement and do not discuss their efficient integration to address the problem over a wide area. For practical use in an outdoor environment, apart from being technically sound and accurate, a solution also needs to be cost-effective , lightweight , easy to install , flexible , low overhead , and easily maintainable , as well as self-sufficient as much as possible. However, fulfilling all these goals together is a challenging task. In this work, we propose an IoT-assisted strategy, LiVeR , to accomplish it. For self-sufficient on-the-fly classification in resource-constrained low-power IoT devices, LiVeR minimizes not only the computational requirements but also the energy consumption, which enables sustained operation in a hostile outdoor environment for a considerably long time solely based on battery power. Through extensive studies based on outdoor measurement and trace-based simulation on empirical data, we demonstrate that LiVeR classifies vehicles of small, medium, and large size with an accuracy of 91.3% up to 98.8%, 92.3% up to 98.5%, and 93.8% up to 98.8%, respectively, for single-lane traffic. We also demonstrate that LiVeR spends only about one-third of the number of RF packets to achieve vehicle detection and classification compared to the state-of-the-art RF-based solution, considerably extending the lifetime of the system.

Analisis Pengaruh Beban Berlebih terhadap Sisa Umur Perkerasan Lentur pada Jalan Kawasan Industri Driyorejo dengan Metode MDPJ 2017

Flexible pavement is designed with regard to the load that will be received in order to achieve optimal performance throughout its service life. However, conditions in the road reveal indications of overloading by each category of vehicles, especially overload vehicles. Driyorejo industrial area road is a provincial road that connects the main industrial areas in Gresik Regency. With traffic dominated by overload vehicles, especially large trucks carrying a lot of goods, indications of damage to the pavement are becoming increasingly clear and obvious. This research aims to assess the impact of traffic load on the remaining life expectancy of flexible pavement, focusing on the load of vehicles crossing the road in the Driyorejo industrial area as the study variable. The calculation method used is the Bina Marga 2017 Method. The data used are Average Daily Traffic (LHR) data and vehicle load data. From the calculation results, the actual traffic growth (i) value is 32.7%. Vehicle overloading causes a decrease in the planned life of the road as indicated by the truck factor value of 1.06. The Remaining Life (RL) calculation represents a 14% decrease from the standard RL value of 69.3% to 55.3% under overload conditions, so it can be concluded that the overload significantly reduces the life of the road which was originally designed for 10 years to only 7 years.

Fatigue assessment of bridges using interacting filtering approach with sub-structured predictor model based on current health

Fatigue estimation for critical structures necessitates comprehensive monitoring, which, in turn, requires dense instrumentation and models that heavily rely on computational resource models that heavily rely on computational resources. However, the fatigue vulnerability of different segments within the infrastructure can be considered to adopt a cost-effective substructure-based monitoring approach, minimizing the need for extensive instrumentation or complex models. However, estimating or instrumenting the substructure boundary adds to the complexity. In addition, conventional fatigue estimation approaches often assume constant structural health, disregarding the unknown current health status of aging structures. To overcome this limitation, a novel substructure-based fatigue life estimation approach is developed, incorporating an interacting ensemble-particle filter that considers the current health status while remaining robust against boundary forces. Numerical experiments validate the proposed approach on a simulated reinforced concrete box girder bridge, utilizing a 3D beam model that accounts for dynamic interaction with vehicles. A parametric analysis investigates the relationships between fatigue damage and factors such as surface roughness, vehicle speed, vehicle weight, and vehicle category, aiming to identify dominant stimuli. The results demonstrate an accurate estimation of health parameters and remaining useful life (RUL). Furthermore, a novel decomposed approach for RUL estimation is developed, enabling the mapping of traffic information to fatigue damage without requiring costly simulations. A case study highlights the practical applicability of the approach, focusing on a reinforced concrete box girder bridge in Himachal Pradesh, India.

Service time thresholds at barrier-operated freeway exit toll booths

This paper discusses service times based on vehicle class at barrier-operated toll booths. Service times were measured using four vehicle classifications: car (C), medium goods vehicle (MGV), trucks & bus (TB), and articulated truck (AT) with two payment options: electronic (ETC) and manual toll collection (MTC). Each toll booth has both payment systems and resulting in mixed toll booth utilization in terms of payment and vehicles. The collected data was utilized to estimate logistic regression, and non-parametric statistical tests were performed. Findings indicate, when vehicle size increases, so does service time for even ETC. Furthermore, logistic regression used to compute threshold service times shifting from ETC to MTC for C, MGV, TB, and AT, which were 5.92, 7.51, 10.00, and 12.80 s, respectively. The transition time for a vehicle switch from ETC to MTC based on the logistic curve is denoted by threshold service time. Below the threshold, ETC is more favorable option and affected by barrier and vehicle class. Overall, the results indicate that operators can benefit from more dynamic operational conditions facilitated by threshold service times, enabling adaptive and efficient toll booth operations. Additionally, these thresholds can serve as valuable measure of service quality for managing freeway exits.

Simulation and Evaluating of Traffic Flow for Hillah City Using VISSIM and GIS Programs

Abstract The transportation network is crucial for modern society, with roads being essential for passenger and goods transportation. Al-Hillah, a highly congested center in Babylon province, experiences congestion due to its strategic location as a major transit route and the presence of vitality centers like education, commerce, and government. The main goals of this study are to evaluate the service level of the current traffic situation on the road network using the VISSIM software and to know the extent of the network’s connectivity using the GIS program. The whole length of the Hillah Road network as well as the number of nodes and linkages are among the data collected. These links represent major and minor arterials and vehicle movement surveys, both external and internal, from the center city for peak periods, vehicle classification, and geometric characteristics for each link and node in the network. Then a collection of parameters was computed for assessing the road network, which is considered one of the quantitative indicators used to measure network connectivity, such as β the index, α the index, γ the index and η the index. The results showed that the study sites operate with a high level of service LOS (F), and on the basis of this, some improvements were suggested to improve the level of service and reduce congestion.

Deep multi-metric training: the need of multi-metric curve evaluation to avoid weak learning

The development and application of artificial intelligence-based computer vision systems in medicine, environment, and industry are playing an increasingly prominent role. Hence, the need for optimal and efficient hyperparameter tuning strategies is more than crucial to deliver the highest performance of the deep learning networks in large and demanding datasets. In our study, we have developed and evaluated a new training methodology named deep multi-metric training (DMMT) for enhanced training performance. The DMMT delivers a state of robust learning for deep networks using a new important criterion of multi-metric performance evaluation. We have tested the DMMT methodology in multi-class (three, four, and ten), multi-vendors (different X-ray imaging devices), and multi-size (large, medium, and small) datasets. The validity of the DMMT methodology has been tested in three different classification problems: (i) medical disease classification, (ii) environmental classification, and (iii) ecological classification. For disease classification, we have used two large COVID-19 chest X-rays datasets, namely the BIMCV COVID-19+ and Sheffield hospital datasets. The environmental application is related to the classification of weather images in cloudy, rainy, shine or sunrise conditions. The ecological classification task involves a classification of three animal species (cat, dog, wild) and a classification of ten animals and transportation vehicles categories (CIFAR-10). We have used state-of-the-art networks of DenseNet-121, ResNet-50, VGG-16, VGG-19, and DenResCov-19 (DenRes-131) to verify that our novel methodology is applicable in a variety of different deep learning networks. To the best of our knowledge, this is the first work that proposes a training methodology to deliver robust learning, over a variety of deep learning networks and multi-field classification problems.

Genetic Diversity in Salmonella enterica in Outbreaks of Foodborne and Zoonotic Origin in the USA in 2006-2017.

Whole genome sequencing is replacing traditional laboratory surveillance methods as the primary tool to track and characterize clusters and outbreaks of the foodborne and zoonotic pathogen Salmonella enterica (S. enterica). In this study, 438 S. enterica isolates representing 35 serovars and 13 broad vehicle categories from one hundred epidemiologically confirmed outbreaks were evaluated for genetic variation to develop epidemiologically relevant interpretation guidelines for Salmonella disease cluster detection. The Illumina sequences were analyzed by core genome multi-locus sequence typing (cgMLST) and screened for antimicrobial resistance (AR) determinants and plasmids. Ninety-three of the one hundred outbreaks exhibited a close allele range (less than 10 allele differences with a subset closer than 5). The remaining seven outbreaks showed increased variation, of which three were considered polyclonal. A total of 16 and 28 outbreaks, respectively, showed variations in the AR and plasmid profiles. The serovars Newport and I 4,[5],12:i:-, as well as the zoonotic and poultry product vehicles, were overrepresented among the outbreaks, showing increased variation. A close allele range in cgMLST profiles can be considered a reliable proxy for epidemiological relatedness for the vast majority of S. enterica outbreak investigations. Variations associated with mobile elements happen relatively frequently during outbreaks and could be reflective of changing selective pressures.

Vehicle Classification Algorithm Based on Improved Vision Transformer

Vehicle classification technology is one of the foundations in the field of automatic driving. With the development of deep learning technology, visual transformer structures based on attention mechanisms can represent global information quickly and effectively. However, due to direct image segmentation, local feature details and information will be lost. To solve this problem, we propose an improved vision transformer vehicle classification network (IND-ViT). Specifically, we first design a CNN-In D branch module to extract local features before image segmentation to make up for the loss of detail information in the vision transformer. Then, in order to solve the problem of misdetection caused by the large similarity of some vehicles, we propose a sparse attention module, which can screen out the discernible regions in the image and further improve the detailed feature representation ability of the model. Finally, this paper uses the contrast loss function to further increase the intra-class consistency and inter-class difference of classification features and improve the accuracy of vehicle classification recognition. Experimental results show that the accuracy of the proposed model on the datasets of vehicle classification BIT-Vehicles, CIFAR-10, Oxford Flower-102, and Caltech-101 is higher than that of the original vision transformer model. Respectively, it increased by 1.3%, 1.21%, 7.54%, and 3.60%; at the same time, it also met a certain real-time requirement to achieve a balance of accuracy and real time.

Temperature Behavior in Headlights: A Comparative Analysis between Battery Electric Vehicles and Internal Combustion Engine Vehicles

In the context of a global shift towards renewable energies and climate change mitigation, the market for electric vehicles has experienced a remarkable upswing, with battery electric vehicles (BEVs) leading this transformative wave. The appeal of BEVs lies in their ability to significantly curtail CO2 emissions by supplanting the traditional internal combustion engine (ICE) with an electric motor. This pivotal change in vehicular technology extends its influence to various subsystems, including automotive lighting. Headlights are particularly sensitive to the thermal environment they operate in, which can profoundly affect their functionality and durability. The removal of an ICE in BEVs typically results in a reduction in heat exposure to headlight components, prompting a potential reevaluation of their design. This article presents a comprehensive analysis of temperature distributions within headlight units, comparing BEVs and ICE vehicles. The study encompasses a robust dataset of nearly 30,000 vehicles from around the globe, taking into account the impact of ambient temperature on headlight operation. The investigation delineates the distinct thermal behaviors of the two vehicle categories and offers strategic recommendations for conceptual modifications of headlights in BEVs. These adjustments are aimed at enhancing headlight efficacy, prolonging lifespan, and furthering the sustainability objectives of electric mobility.

Automatic toll collection system using RFID with vehicle classification using convolutional neural network

Automatic toll collection system using RFID with vehicle classification using convolutional neural network

Improved time series models for the prediction of lane-change intention

ABSTRACT To improve the accuracy of lane-change intention prediction and analyze the influence of driving styles on prediction outcomes, the T-Encoder-Sequence model is proposed in this paper. It integrates the Transformer’s encoder module with various recurrent neural network (RNN) models and introduces a multimodal fusion input structure. Building on this, a risk indicator model, capable of reflecting driver stress, is established to calculate the model’s input parameters. Consequently, the model can simultaneously capture global information and consider the impact of vehicle classes on drivers. Furthermore, the k-means++ algorithm is employed to categorize vehicle trajectories into conservative, conventional, and aggressive types for further analysis. The results demonstrate that training the model with risk indicator parameters markedly enhances prediction performance. Under identical input parameters, the T-Encoder-Sequence model exhibits notably superior prediction efficacy compared to the original model. The T-Encoder-Sequence model, trained with risk indicator parameters, demonstrates substantial advantages compared to other studies.

Gelatin and lipidoid integrate to create gelasomes to enhance siRNA delivery with low toxicity

RNAi therapeutics possess the potential to cure many uncurable human diseases. For instance, RNAi therapeutics using liposomes showed remarkable survival benefits in patients with liver diseases. However, the extension of liposomes to deliver RNA to cure other ailments has largely been unsuccessful. Therefore, researchers are focusing on designing and testing different combinations of materials for versatile RNA delivery applications. Yet, an efficient and safe RNA delivery platform has not been identified. In this work, we have developed a new class of RNA-delivery vehicle called “Gelasomes,” using an incongruous combination of gelatin and lipidoid to exploit each material's unique properties while overcoming their inherent limitations. The low in vivo toxicity of Gelasomes is attributed to the exterior gelatin layers that shield the exposure of cationic lipidoid-siRNA clusters and yet present a biocompatible surface. Indeed, toxicity studies in mice indicate that repeated administration of Gelasomes (up to 48 mg/kg BW) is well-tolerated with no notable changes in body weight, hematology, or serum chemistry. Interestingly, the gelatin outer layer efficiently protects siRNA from serum degradation (48 h), preserving its functionality beyond two months of storage. Notably, Gelasomes possess dual siRNA conjugation modes, i.e., electrostatic binding with lipidoid core and covalent attachment to gelatin surface. The bivalency coupled with lipidoids' high transfection efficiency rendered Gelasomes with remarkably high gene silencing efficiency (>90 %) at very low treatment doses in vitro (40 μg/mL). In vivo studies further confirmed the high gene silencing ability of Gelasomes in non-small cell lung tumor mouse models. This new platform is tunable on all fronts: size, degree of surface coating, and biomolecule functionalization. Truncating the lipidoid C14-tail to a C8-tail yielded Gelasomes of reduced size. As lipidoids with different carbon lengths are synthesizable, we can develop a library of Gelasomes with different sizes. The surface coating with less gelatin resulted in high transfection efficiency at low doses of Gelasomes. The structure of Gelasomes offers chemical handles to couple target-specific molecules like antibodies to tune their properties for efficient biological application.

Assessing Survey Data to Study Traffic Flow Characteristics: An in-depth analysis of King Fahad Road, Al-Ahsa, Saudi Arabia

Traffic volume studies are crucial for understanding vehicle quantity, movements, and classifications at specific sites. This study aims to establish a correlation between flow rate and density, providing in-sights into traffic flow characteristics such as density, velocity, and flow, essential for effective road design. The proposed method combines automated (mobile phones and cars) and manual counts on separate sheets, offering a compelling alternative to traditional traffic study methods. The collected da-ta can be utilized for various purposes including estimating fuel consumption, road pricing, road user cost, and planning road network improvements. Acquiring precise traffic data using cost-effective, low-tech solutions is vital for comprehending urban traffic dynamics. Evaluating collected data, which encompasses traffic parameters like flow, density, and speed, is crucial for informing urban road de-sign and planning. For instance, traffic flow indicates throughput, density reflects traffic conditions, and speed is essential for calculating travel times. This investigation focused on King Fahad Road in Al-Ahsa, Saudi Arabia, chosen among three alternative urban roads based on varying traffic condi-tions. Smartphones and cars were used to collect traffic data during weekday evening peak hours, ana-lyzing the interrelation between traffic flow, density, and vehicle speed. Manual traffic counts were conducted to determine measured density and speed, which were then used to estimate calculated den-sity. Additionally, a statistical t-test was performed to validate measured density against calculated den-sity at a 5% significance level. The data collection systems utilized in this research provide a cost-effective solution, considering capital, operational, and maintenance expenses, while remaining por-table and non-intrusive to road users during surveys. These characteristics make the system a practical choice for implementation in developing nations where resources are constrained, rendering costlier al-ternatives economically unfeasible.

Calibrating Car-Following Models Using SUMO-in-the-Loop and Vehicle Trajectories From Roadside Radar

This paper presents an innovative calibration method for car-following (CF) models in the Simulation of Urban MObility (SUMO) using real-world trajectory data from a 1.5 km signalized urban corridor, captured by roadside radars. By applying a sophisticated track-level association and fusion methodology, the study extends trajectory analysis beyond individual radar fields of view. The enhanced data is then utilized to refine the Krauss, IDM, and W99 CF models within SUMO, addressing the literature gap by integrating SUMO into the calibration loop, thereby accommodating the simulator's integration scheme and any model adaptations. The research identifies that default SUMO models tend to exhibit shorter time headways compared to real-world data, with calibration effectively reducing this discrepancy. Moreover, the W99 model, despite its unrealistic acceleration profiles when calibrated without considering acceleration, most accurately captures the higher-end energy consumption distribution. Conversely, the IDM model, with its default parameters, provides the closest approximation to observed acceleration behaviors, highlighting the nuanced performance of CF models in traffic simulation and their implications for energy consumption estimation. Detailed results of optimized parameters for each CF model are provided in appendix in addition to distribution information that may be useful for other modelers to use directly or other datasets to be compared in the future (including expansion of the work to include vehicle classification).

Comparing and Parameterizing the Electrical Energy Consumption Models in SUMO

This paper examined the performances of the current four battery models in SUMO. The possibility of expanding the model parameterization was also investigated and the corresponding extension was carried out for PHEMlight. Accordingly, the models can be compared more fairly. Three scenarios were used, namely the Worldwide harmonized Light vehicles Test Cycle, a constant high-speed highway scenario and an area scenario with a relatively complex traffic situation. The results show that all models can address recuperation and propulsion, and deliver the similar result at very low acceleration. The models based on average vehicle data generally tend to deliver higher battery consumption than the models with individual vehicle type-specific parameterization, especially PHEMlight5, while HBEFA4 only has one electric vehicle class and is therefore not sensitive to various vehicle characteristics. Moreover, the model by Kurczveil and López (EVM) seems to tend to have the lowest consumption of all models.

A holistic approach for efficient greener in-space propulsion

This paper presents a comprehensive framework for designing in-space propulsion systems, integrating four criteria: global propulsive performance, environmental impact, cost efficiency, and architectural reliability. The study focuses on the emerging class of Orbital Transfer Vehicles to illustrate the application of this method. By examining the synergistic potential of OTVs and greener propellants, the paper addresses different mission scenarios, including LEO, GEO, and lunar missions, with both scientific and commercial objectives. The proposed framework aims to go beyond traditional cost-centric approaches, offering a more complete evaluation method for early design phases. A case study comparing three liquid bipropellant options, pressure-fed MON-3/MMH, 98%-HTP/RP-1, and self-pressurizing N2O/Ethane, demonstrates the utility of the tool. Findings suggest that scientific missions benefit most from 98%-HTP/RP-1, while traditional propellants remain preferable for cost-driven commercial missions to GEO and the Moon, though greener alternatives are competitive for less demanding LEO missions. This innovative framework aims to guide the selection of propulsion systems to achieve greener space missions, aligning traditional performance figures with environmental responsibility.