Abstract:There has been globally continuous growth in passenger car sizes and types over the past few decades. To assess the development of vehicular specifications in this context and to evaluate changes in powertrain technologies depending on surrounding frame conditions, such as charging stations and vehicle taxation policy, we need a detailed understanding of the vehicle fleet composition. This paper aims therefore to introduce a novel mathematical approach to segment passenger vehicles based on dimensions features… Show more
“…Since the division of vehicles into segments by experts is not standardized and therefore not always uniform, and some vehicle models have recently positioned themselves as "crossovers" between established vehicle categories [7][8], it has become increasingly difficult and inaccurate to segment the vehicle population using conventional classification methods. Using mathematical approaches, vehicles can be uniformly divided into segments based on similarity features.…”
The overall level of emissions from the Swiss passenger cars is strongly dependent on the fleet composition. Despite technology improvements, the Swiss passenger cars fleet remains emissions intensive. To analyze the root of this problem and evaluate potential solutions, this paper applies deep learning techniques to evaluate the inter-class (namely micro, small, middle, upper middle, large and luxury class) and intra-class (namely sport utility vehicle and non-sport utility vehicle) differences in carbon dioxide (CO2) emissions. This paper takes full use of novel semi-supervised fuzzy C-means (SSFCM), random forest and AdaBoost models as well as model fusion to successfully classify passenger vehicles and enable segmentbased CO2 emission evaluations.
“…Since the division of vehicles into segments by experts is not standardized and therefore not always uniform, and some vehicle models have recently positioned themselves as "crossovers" between established vehicle categories [7][8], it has become increasingly difficult and inaccurate to segment the vehicle population using conventional classification methods. Using mathematical approaches, vehicles can be uniformly divided into segments based on similarity features.…”
The overall level of emissions from the Swiss passenger cars is strongly dependent on the fleet composition. Despite technology improvements, the Swiss passenger cars fleet remains emissions intensive. To analyze the root of this problem and evaluate potential solutions, this paper applies deep learning techniques to evaluate the inter-class (namely micro, small, middle, upper middle, large and luxury class) and intra-class (namely sport utility vehicle and non-sport utility vehicle) differences in carbon dioxide (CO2) emissions. This paper takes full use of novel semi-supervised fuzzy C-means (SSFCM), random forest and AdaBoost models as well as model fusion to successfully classify passenger vehicles and enable segmentbased CO2 emission evaluations.
“…The compilation of chosen attributes is detailed in Table 2. The selection of these features was informed by their significance as established in prior research 5,32,35 and based on the statistical evaluations presented in Additional Information 1. The selected attributes are the Maximum number of passengers, Power-to-mass ratio and Maximum cargo mass.…”
Section: Methodsmentioning
confidence: 99%
“…Some of them 6,[27][28][29] have investigated various schemes using statistical and exploratory data analysis, aiming to describe typical characteristics of each segment. However, due to the complexity of the classification problem, most of these studies 5,[30][31][32][33][34] have tackled the classification and dimensionality reduction task with advanced Machine Learning (ML) algorithms and principal component analysis techniques, respectively. These studies have demonstrated that ML techniques can successfully address the complex problem of cars classification.…”
Section: Introductionmentioning
confidence: 99%
“…These studies have demonstrated that ML techniques can successfully address the complex problem of cars classification. Among them, the series of works by Niroomand et al 5,32,35 proved able to reproduce the EU classification scheme with an accuracy of up to 85%. Nevertheless, ML models obscure the understanding of vehicles classification, so that the criteria behind the assignation of a vehicle to a certain segment remain opaque.…”
Proper categorisation of light vehicles is crucial for analysing and comprehending the developments taking place in the road transport sector, that impact the environment, road safety, transport operation, and urban planning. However, current vehicle classification methods in Europe are based on empirical or legacy approaches, sometimes founded on obsolete criteria, and do not fully reflect recent changes in the vehicle fleet and market. This paper aims to establish a scientific approach for the classification of light vehicles by introducing a Bayesian statistical method to define vehicle segments in an explicit and reproducible way. Contrarily to previous studies that mostly depend on machine learning techniques, which, despite their high accuracy typically lack explainability, the proposed approach prioritises the transparency of classification decisions. Through an in-depth examination of vehicle physical attributes, key variables were identified and utilised to determine clear boundaries between segments. These boundaries were articulated through simple linear relationships of the chosen variables, thus providing well-defined criteria open for interpretation and verification. The algorithm could assign up to 82\% of the vehicles to the original segments. The accuracy demonstrated is comparable to that of several unsupervised machine learning models and transparently reveals the boundaries among different segments. The findings can be used by researchers and modellers to update existing vehicle fleet models, particularly those treating environmental and energy consumption impacts, or used as a possible standard for multi-purpose vehicle classification.
“…A typical data clustering process starts with a group of information items and splits them into k clusters using Euclidean distance and other similarity distance metrics. Partition-based clusters could satisfy a few of following requirements: i) Each cluster should have at least one data item and ii) In non-fuzzy clustering algorithms, each object must only be present in one cluster [9].…”
<span lang="EN-US">Large datasets have become useful in data mining for processing, storing, and handling vast amounts of data. However, handling and processing large datasets is time-consuming and memory intensive. As a result, the researchers adopted a partitioning strategy to improve controllability and performance and reduce the time and memory required to handle large datasets. Unfortunately, the numerous clustering techniques available in the literature could confuse experts in choosing the best techniques for a given dataset. Furthermore, no clustering technique can tackle all problems, such as cluster structure, noise, or density. To manage large datasets, existing clustering techniques need scalable solutions. Therefore, this paper proposes an ensemble partition-based clustering with a majority voting technique for large dataset partitioning using the aggregation of k-means, k-medoids, fuzzy c-means, expectation-maximization (EM) and density-based spatial clustering of applications with noise (DBSCAN) techniques. These techniques cluster the large dataset individually in the first stage. The final clusters are discovered in the next stage through a majority voting technique among the five clustering algorithms. These five clustering algorithms assigned data instances to the cluster with the most votes. The experimental findings demonstrate that the ensemble partition-based clustering method surpasses the other five clustering algorithms in terms of execution time and accuracy.</span>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.