Applied Sciences

Research

18 pages, 12334 KiB

Open AccessArticle

A Deep Learning Method for the Prediction of Pollutant Emissions from Internal Combustion Engines

by Federico Ricci, Massimiliano Avana and Francesco Mariani

Appl. Sci. 2024, 14(21), 9707; https://doi.org/10.3390/app14219707 - 24 Oct 2024

Viewed by 830

The increasing demand for vehicles is leading to a rise in pollutant emissions across the world. This decline in air quality is significantly impacting public health, with internal combustion engines being a major contributor to this concerning trend. Ever-stringent regulations demand high engine [...] Read more.

The increasing demand for vehicles is leading to a rise in pollutant emissions across the world. This decline in air quality is significantly impacting public health, with internal combustion engines being a major contributor to this concerning trend. Ever-stringent regulations demand high engine efficiency and reduced pollutant emissions. Therefore, every automobile company requires rigorous methods for accurately estimating engine emissions. The implementation of advanced technologies, including machine learning methods, has proven to be a promising solution. The present work aims to develop an artificial intelligence-based model to estimate the pollutant emissions produced by an internal combustion engine under varying operating conditions. Experimental activities have been conducted on a single-cylinder spark ignition research engine with gasoline port fuel injection under both stationary and dynamic operating conditions. This work explores different artificial intelligence architectures and compares their performance in order to determine the best approach for the presented task. These structures have been trained and tested based on data obtained from the engine control unit and fast emission analyzer. The main target is to evaluate the possibility of applying the presented artificial intelligence predictive model as an on-board virtual tool in the estimation of emissions in real driving conditions. Full article

(This article belongs to the Special Issue Applications of Artificial Intelligence in Transportation Engineering)

► Show Figures

Figure 1

20 pages, 6767 KiB

Open AccessArticle

Highly Accurate Deep Learning Models for Estimating Traffic Characteristics from Video Data

by Bowen Cai, Yuxiang Feng, Xuesong Wang and Mohammed Quddus

Appl. Sci. 2024, 14(19), 8664; https://doi.org/10.3390/app14198664 - 26 Sep 2024

Viewed by 918

Abstract

Traditionally, traffic characteristics such as speed, volume, and travel time are obtained from a range of sensors and systems such as inductive loop detectors (ILDs), automatic number plate recognition cameras (ANPR), and GPS-equipped floating cars. However, many issues associated with these data have [...] Read more.

Traditionally, traffic characteristics such as speed, volume, and travel time are obtained from a range of sensors and systems such as inductive loop detectors (ILDs), automatic number plate recognition cameras (ANPR), and GPS-equipped floating cars. However, many issues associated with these data have been identified in the existing literature. Although roadside surveillance cameras cover most road segments, especially on freeways, existing techniques to extract traffic data (e.g., speed measurements of individual vehicles) from video are not accurate enough to be employed in a proactive traffic management system. Therefore, this paper aims to develop a technique for estimating traffic data from video captured by surveillance cameras. This paper then develops a deep learning-based video processing algorithm for detecting, tracking, and predicting highly disaggregated vehicle-based data, such as trajectories and speed, and transforms such data into aggregated traffic characteristics such as speed variance, average speed, and flow. By taking traffic observations from a high-quality LiDAR sensor as ‘ground truth’, the results indicate that the developed technique estimates lane-based traffic volume with an accuracy of 97%. With the application of the deep learning model, the computer vision technique can estimate individual vehicle-based speed calculations with an accuracy of 90–95% for different angles when the objects are within 50 m of the camera. The developed algorithm was then utilised to obtain dynamic traffic characteristics from a freeway in southern China and employed in a statistical model to predict monthly crashes. Full article

(This article belongs to the Special Issue Applications of Artificial Intelligence in Transportation Engineering)

► Show Figures

Figure 1

32 pages, 8870 KiB

Open AccessArticle

Analysing Urban Traffic Patterns with Neural Networks and COVID-19 Response Data

by Lucia Svabova, Kristian Culik, Karol Hrudkay and Marek Durica

Appl. Sci. 2024, 14(17), 7793; https://doi.org/10.3390/app14177793 - 3 Sep 2024

Viewed by 721

Abstract

Accurate traffic prediction is crucial for urban planning, especially in rapidly growing cities. Traditional models often struggle to account for sudden traffic pattern changes, such as those caused by the COVID-19 pandemic. Neural networks offer a powerful solution, capturing complex, non-linear relationships in [...] Read more.

Accurate traffic prediction is crucial for urban planning, especially in rapidly growing cities. Traditional models often struggle to account for sudden traffic pattern changes, such as those caused by the COVID-19 pandemic. Neural networks offer a powerful solution, capturing complex, non-linear relationships in traffic data for more precise prediction. This study aims to create a neural network model for predicting vehicle numbers at main intersections in the city. The model is created using real data from the sensors placed across the city of Zilina, Slovakia. By integrating pandemic-related variables, the model assesses the COVID-19 impact on traffic flow. The model was developed using neural networks, following the data-mining methodology CRISP-DM. Before the modelling, the data underwent thorough preparation, emphasising correcting sensor errors caused by communication failures. The model demonstrated high prediction accuracy, with correlations between predicted and actual values ranging from 0.70 to 0.95 for individual sensors and vehicle types. The results highlighted a significant pandemic impact on urban mobility. The model’s adaptability allows for easy retraining for different conditions or cities, making it a robust, adaptable tool for future urban planning and traffic management. It offers valuable insights into pandemic-induced traffic changes and can enhance post-pandemic urban mobility analysis. Full article

(This article belongs to the Special Issue Applications of Artificial Intelligence in Transportation Engineering)

► Show Figures

Figure 1

14 pages, 981 KiB

Open AccessArticle

Driving Style and Traffic Prediction with Artificial Neural Networks Using On-Board Diagnostics and Smartphone Sensors

by Ghaith Al-refai, Mohammed Al-refai and Ahmad Alzu’bi

Appl. Sci. 2024, 14(12), 5008; https://doi.org/10.3390/app14125008 - 8 Jun 2024

Viewed by 1180

Abstract

Driving style and road traffic play pivotal roles in the development of smart cities, influencing traffic flow, safety, and environmental sustainability. This study presents an innovative approach for detecting road traffic conditions and driving styles using On-Board Diagnostics (OBD) data and smartphone sensors. [...] Read more.

Driving style and road traffic play pivotal roles in the development of smart cities, influencing traffic flow, safety, and environmental sustainability. This study presents an innovative approach for detecting road traffic conditions and driving styles using On-Board Diagnostics (OBD) data and smartphone sensors. This approach offers an inexpensive implementation of prediction, as it utilizes existing vehicle data without requiring additional setups. Two Artificial Neural Network (ANN) models were employed: the first utilizes a forward neural network architecture, while the second leverages bootstrapping or bagging neural networks to enhance detection accuracy for low-labeled classes. Support Vector Machine (SVM) is implemented to serve as a baseline for comparison. Experimental results demonstrate that ANNs exhibit significant improvements in detection accuracy compared to SVM. Moreover, the neural network with bagging model showcases enhanced recall values and a substantial improvement in accurately detecting instances belonging to low-labeled classes in both driving style road traffic. Full article

(This article belongs to the Special Issue Applications of Artificial Intelligence in Transportation Engineering)

► Show Figures

Figure 1

18 pages, 3738 KiB

Open AccessArticle

Predictive Analyses of Traffic Level in the City of Barcelona: From ARIMA to eXtreme Gradient Boosting

by Eloi Garcia, Laura Calvet, Patricia Carracedo, Carles Serrat, Pau Miró and Mohammad Peyman

Appl. Sci. 2024, 14(11), 4432; https://doi.org/10.3390/app14114432 - 23 May 2024

Viewed by 1160

Abstract

This study delves into the intricate dynamics of urban mobility, a pivotal aspect for policymakers, businesses, and communities alike. By deciphering patterns of movement within a city, stakeholders can craft targeted interventions to mitigate traffic congestion peaks, optimizing both resource allocation and individual [...] Read more.

This study delves into the intricate dynamics of urban mobility, a pivotal aspect for policymakers, businesses, and communities alike. By deciphering patterns of movement within a city, stakeholders can craft targeted interventions to mitigate traffic congestion peaks, optimizing both resource allocation and individual travel routes. Focused on Barcelona, Spain, this paper draws on data sourced from the city council’s open data service. Through a blend of exploratory analysis, visualization techniques, and modeling methodologies—including time series analysis and the eXtreme Gradient Boosting (XGBoost) algorithm—the research endeavors to forecast traffic conditions. Additionally, a study of variable importance is carried out, and Shapley Additive Explanations are applied to enhance the interpretability of model outputs. Findings underscore the limitations of traditional forecasting methods in capturing the nuanced spatial and temporal dependencies present in traffic flows, particularly over medium- to long-term horizons. However, the XGBoost model demonstrates robust performance, with the area under ROC curves consistently exceeding 80%, indicating its efficacy in handling non-linear traffic data variables. Full article

(This article belongs to the Special Issue Applications of Artificial Intelligence in Transportation Engineering)

► Show Figures

Figure 1

17 pages, 3504 KiB

Open AccessArticle

ADDGCN: A Novel Approach with Down-Sampling Dynamic Graph Convolution and Multi-Head Attention for Traffic Flow Forecasting

by Zuhua Li, Siwei Wei, Haibo Wang and Chunzhi Wang

Appl. Sci. 2024, 14(10), 4130; https://doi.org/10.3390/app14104130 - 13 May 2024

Cited by 1 | Viewed by 911

Abstract

An essential component of autonomous transportation system management and decision-making is precise and real-time traffic flow forecast. Predicting future traffic conditionsis a difficult undertaking because of the intricate spatio-temporal relationships involved. Existing techniques often employ separate modules to model spatio-temporal features independently, thereby [...] Read more.

An essential component of autonomous transportation system management and decision-making is precise and real-time traffic flow forecast. Predicting future traffic conditionsis a difficult undertaking because of the intricate spatio-temporal relationships involved. Existing techniques often employ separate modules to model spatio-temporal features independently, thereby neglecting the temporally and spatially heterogeneous features among nodes. Simultaneously, many existing methods overlook the long-term relationships included in traffic data, subsequently impacting prediction accuracy. We introduce a novel method to traffic flow forecasting based on the combination of the feature-augmented down-sampling dynamic graph convolutional network and multi-head attention mechanism. Our method presents a feature augmentation mechanism to integrate traffic data features at different scales. The subsampled convolutional network enhances information interaction in spatio-temporal data, and the dynamic graph convolutional network utilizes the generated graph structure to better simulate the dynamic relationships between nodes, enhancing the model’s capacity for capturing spatial heterogeneity. Through the feature-enhanced subsampled dynamic graph convolutional network, the model can simultaneously capture spatio-temporal dependencies, and coupled with the process of multi-head temporal attention, it achieves long-term traffic flow forecasting. The findings demonstrate that the ADDGCN model demonstrates superior prediction capabilities on two real datasets (PEMS04 and PEMS08). Notably, for the PEMS04 dataset, compared to the best baseline, the performance of ADDGCN is improved by 2.46% in MAE and 2.90% in RMSE; for the PEMS08 dataset, compared to the best baseline, the ADDGCN performance is improved by 1.50% in RMSE, 3.46% in MAE, and 0.21% in MAPE, indicating our method’s superior performance. Full article

(This article belongs to the Special Issue Applications of Artificial Intelligence in Transportation Engineering)

► Show Figures

Figure 1

25 pages, 26268 KiB

Open AccessArticle

Robust Artificial Intelligence-Aided Multimodal Rail-Obstacle Detection Method by Rail Track Topology Reconstruction

by Jinghao Cao, Yang Li and Sidan Du

Appl. Sci. 2024, 14(7), 2795; https://doi.org/10.3390/app14072795 - 27 Mar 2024

Cited by 2 | Viewed by 1078

Abstract

Detecting obstacles in the rail track area is crucial for ensuring the safe operation of trains. However, this task presents numerous challenges, including the diverse nature of intrusions, and the complexity of the driving environment. This paper presents a multimodal fusion rail-obstacle detection [...] Read more.

Detecting obstacles in the rail track area is crucial for ensuring the safe operation of trains. However, this task presents numerous challenges, including the diverse nature of intrusions, and the complexity of the driving environment. This paper presents a multimodal fusion rail-obstacle detection approach by key points processing and rail track topology reconstruction. The core idea is to leverage the rich semantic information provided by images to design algorithms for reconstructing the topological structure of railway tracks. Additionally, it combines the effective geometric information provided by LiDAR to accurately locate the railway tracks in space and to filter out intrusions within the track area. Experimental results demonstrate that our method outperforms other approaches with a longer effective working distance and superior accuracy. Furthermore, our post-processing method exhibits robustness even under extreme weather conditions. Full article

(This article belongs to the Special Issue Applications of Artificial Intelligence in Transportation Engineering)

► Show Figures

Figure 1

18 pages, 16034 KiB

Open AccessArticle

Steady-Speed Traffic Capacity Analysis for Autonomous and Human-Driven Vehicles

by Dilshad Mohammed and Balázs Horváth

Appl. Sci. 2024, 14(1), 337; https://doi.org/10.3390/app14010337 - 29 Dec 2023

Cited by 2 | Viewed by 1406

Abstract

As the automotive industry transitions towards the era of autonomous vehicles, it is imperative to assess and compare the following distances maintained by vehicles equipped with adaptive cruise control (ACC) systems against those of traditional human-driven vehicles. This study aims to provide insights [...] Read more.

As the automotive industry transitions towards the era of autonomous vehicles, it is imperative to assess and compare the following distances maintained by vehicles equipped with adaptive cruise control (ACC) systems against those of traditional human-driven vehicles. This study aims to provide insights into the future use of autonomous vehicles by empirically examining the following distances achieved under different driving conditions. Controlled experiments were conducted using three vehicles equipped with various types of ACC sensors, and comparable scenarios were replicated with human drivers. The experiments involved driving at multiple constant speeds to evaluate the efficacy of ACC in maintaining safe following distances. Our findings indicate that ACC systems consistently converge on optimal following distances, demonstrating their ability to regulate spacing between vehicles effectively. However, a notable downside emerged in terms of their adverse impact on road capacities, where the results indicate a mitigation in capacity percentages of 7.6%, 9.3%, and 15.6% for the three types of ACC-equipped vehicles compared to human drivers. This study sheds light on the intricate interplay between ACC systems and human driving behaviors, emphasizing the need to consider both factors when envisioning the future of autonomous vehicles. While ACC systems provide a standardized and reliable approach to following distances, the shorter distances observed in human-driven scenarios suggest a potential trade-off between safety and traffic capacity. These insights contribute to a comprehensive understanding of the dynamics involved in autonomous driving, facilitating informed decision making for the integration of autonomous vehicles into future transportation systems. Full article

(This article belongs to the Special Issue Applications of Artificial Intelligence in Transportation Engineering)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Applications of Artificial Intelligence in Transportation Engineering

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (8 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI