IET Intelligent Transport Systems
Volume 8, Issue 1, February 2014
Volumes & issues:
Volume 8, Issue 1
February 2014
On-line passenger estimation in a metro system using particle filter
- Author(s): Francisco Reyes and Aldo Cipriano
- Source: IET Intelligent Transport Systems, Volume 8, Issue 1, p. 1 –8
- DOI: 10.1049/iet-its.2012.0057
- Type: Article
- + Show details - Hide details
-
p.
1
–8
(8)
Urban metro rail systems are subject to high and growing demand as the populations of major cities increase. A point may be reached where improving system management using advanced control is more attractive than expanding the network. Control schemes for strengthening system performance and therefore user satisfaction typically involve measuring certain system state variables such as the numbers of passengers aboard trains and waiting at stations. Given the high cost of installing the necessary sensors, an alternative methodology is proposed for online estimation of the two variables using a particle filter. Experiments performed on a dynamic simulator show that the variable values can be inferred by measuring only train dwell-times and passengers entering stations, data on which are generally accessible without major investment. The level of accuracy of the estimates generated by the methodology is high enough to enable a model-based controller implemented in a real metro system to achieve significant performance improvements.
Reliability of an in-vehicle warning system for railway level crossings – a user-oriented analysis
- Author(s): Risto Öörni
- Source: IET Intelligent Transport Systems, Volume 8, Issue 1, p. 9 –20
- DOI: 10.1049/iet-its.2012.0129
- Type: Article
- + Show details - Hide details
-
p.
9
–20
(12)
This study analyses the reliability of an in-vehicle warning system developed in Finland during 2008–2010. The system is based on the positioning of trains using GPS, calculation of the states of level crossings on a server and in-vehicle equipment that retrieves information about the states of level crossings from the server. Information about the reliability of the system is very relevant for accurate estimation of the impacts of the system and for estimating the potential for improvements to it. The study starts with a description of the system under analysis, continues by defining the concept of reliability and provides an estimate for the reliability of the system from the user point of view. To achieve this objective, the study defines the relevant concepts and describes a methodology for analysis of the reliability of the system. The main input to the analysis of reliability includes a brief overview of existing concepts related to the reliability of in-vehicle ITS systems and empirical data obtained in a field test carried out in southern Finland. The analysis shows that the expected functionality has been achieved, but the reliability level of the pilot system needs improvement, especially reduction in the share of missed alarms.
Acoustic signal-based approach for fault detection in motorcycles using chaincode of the pseudospectrum and dynamic time warping classifier
- Author(s): Basavaraj S. Anami and Veerappa B. Pagi
- Source: IET Intelligent Transport Systems, Volume 8, Issue 1, p. 21 –27
- DOI: 10.1049/iet-its.2012.0086
- Type: Article
- + Show details - Hide details
-
p.
21
–27
(7)
The sound of a moving vehicle gives a clue of the fault. This study investigates fault detection of motorcycles using chaincode of the pseudospectrum. The motorcycle sound signals are analysed for spectral variations and these variations are traced by a chaincode. The chaincode features are used to classify the sample into healthy or faulty using dynamic time warping technique. MATLAB version 7.8.0.347 (R2009a) is used for effective implementation. The classification results obtained are over 91% and 93%, respectively, for faulty and healthy motorcycles. The results are comparable with the reported works based on wavelets. The proposed work finds applications in traffic census, traffic rule enforcement, machine fault discovery, automatic surveillance and the like.
Principal component analysis-based learning for preceding vehicle classification
- Author(s): Muthulingam Alarmel Mangai and Nanjappagounder Ammasai Gounden
- Source: IET Intelligent Transport Systems, Volume 8, Issue 1, p. 28 –35
- DOI: 10.1049/iet-its.2012.0118
- Type: Article
- + Show details - Hide details
-
p.
28
–35
(8)
This study presents a new scheme for cluster generation and classification of preceding vehicles from images. The proposed clustering algorithm models the distribution of vehicle images using ‘vehicle’ clusters. ‘Non-vehicle’ clusters are generated by modelling the distribution of non-vehicle images. The clusters are created using K-means clustering algorithm. Hierarchically related nested eigenspaces are acquired to reassign the patterns of each cluster. An appropriate classifier is obtained to classify the vehicles based on the ‘distance-from-feature-space’ measurement. The eigenspaces of vehicle clusters together with non-vehicle clusters are used for classification. The approach of modelling the distribution of vehicle and non-vehicle images and the choice of the classifier used are investigated through experiments thoroughly. Comparison on the performance of the proposed scheme is made with that of MultiClustered Modified Quadratic Discriminant Function approach of categorising the preceding vehicles. The superior performance of the proposed scheme is clearly illustrated through the classification results.
How does the use of a continuously updating database allow for the analysis of a user's changing behaviour in electric vehicles?
- Author(s): Graeme A. Hill ; Phil T. Blythe ; Visalakshmi Suresh
- Source: IET Intelligent Transport Systems, Volume 8, Issue 1, p. 36 –42
- DOI: 10.1049/iet-its.2012.0059
- Type: Article
- + Show details - Hide details
-
p.
36
–42
(7)
Environmental considerations mean that continuing to use internal combustion is, in the long term, unviable because of availability and cost of the fuel and the environmental effects of their emissions. If full electric vehicles (EVs) are to be a more sustainable method of transport then some of the perceived problems of EVs must be addressed, such as ‘range anxiety’ and ‘technical performance’. To do this it is necessary to understand how drivers behave in EVs, both through their overall trip statistics and their driving behaviour within trips. This has been achieved in this project through instrumenting the EVs with a direct link to the vehicle's controller area network bus, a global positioning system and a networked link to an always on database. Through analysis of the vehicle data, it has been possible to build up a quantitative picture of how the vehicles are typically used. Quantitative examples include trip lengths, trip efficiency correlated to the braking techniques and general driving behaviour changes such as improved efficiency at low battery levels. From this study it can be shown that it is possible to monitor EVs and selectively produce derived statistics which can be used to analyse the behaviour of drivers.
Driver fatigue and drowsiness monitoring system with embedded electrocardiogram sensor on steering wheel
- Author(s): Sang-Joong Jung ; Heung-Sub Shin ; Wan-Young Chung
- Source: IET Intelligent Transport Systems, Volume 8, Issue 1, p. 43 –50
- DOI: 10.1049/iet-its.2012.0032
- Type: Article
- + Show details - Hide details
-
p.
43
–50
(8)
Real time driver health condition monitoring system with drowsiness alertness was proposed. A new embedded electrocardiogram (ECG) sensor with electrically conductive fabric electrodes on the steering wheel of a car was designed to monitor the driver's health condition. The ECG signals were measured at a sampling rate of 100 Hz from the driver's palms as they stay on a pair of conductive fabric electrodes located on the steering wheel. Practical tests were conducted using an embedded ECG sensor with a wireless sensor node, and their performance was assessed under non-stop 2 h driving test. The ECG signals were measured and transmitted wirelessly to a base station connected to a server PC in personal area network environment. The driver's health condition such as the normal, fatigued and drowsy states was analysed by evaluating the heart rate variability in the time and frequency domains.
Missing traffic data: comparison of imputation methods
- Author(s): Yuebiao Li ; Zhiheng Li ; Li Li
- Source: IET Intelligent Transport Systems, Volume 8, Issue 1, p. 51 –57
- DOI: 10.1049/iet-its.2013.0052
- Type: Article
- + Show details - Hide details
-
p.
51
–57
(7)
Many traffic management and control applications require highly complete and accurate data of traffic flow. However, because of various reasons such as sensor failure or transmission error, it is common that some traffic flow data are lost. As a result, various methods were proposed by using a wide spectrum of techniques to estimate missing traffic data in the last two decades. Generally, these missing data imputation methods can be categorised into three kinds: prediction methods, interpolation methods and statistical learning methods. To assess their performance, these methods are compared from different aspects in this paper, including reconstruction errors, statistical behaviours and running speeds. Results show that statistical learning methods are more effective than the other two kinds of imputation methods when data of a single detector is utilised. Among various methods, the probabilistic principal component analysis (PPCA) yields best performance in all aspects. Numerical tests demonstrate that PPCA can be used to impute data online before making further analysis (e.g. make traffic prediction) and is robust to weather changes.
Exploring the influence of traveller information on macroscopic fundamental diagrams
- Author(s): Ting-ting Zhao ; Zhi-heng Li ; Bing-yan Huang ; Bei-peng Mu ; Yi Zhang
- Source: IET Intelligent Transport Systems, Volume 8, Issue 1, p. 58 –67
- DOI: 10.1049/iet-its.2011.0234
- Type: Article
- + Show details - Hide details
-
p.
58
–67
(10)
Macroscopic fundamental diagrams (MFD), proposed by Geroliminis and Daganzo, describe the network-wide average relation between the number of vehicles in the network and the output flow of the network. As pointed out by Geroliminis and Daganzo, several factors may influence MFD. The authors study the influence of traveller information on MFDs. The authors use microscopic simulation software TransModeler to model and simulate the dissemination of traveller information as well as the drivers’ route choice behaviours that had been affected by the information. The influences of several model parameters, including the informed percentage, the reroute time interval and the acceptable delay level, are also examined. To help preliminarily understand the information's influence, the homogeneity of road sections’ density distribution under different model parameters is also investigated. To further understand information's influence, incident information dissemination is investigated as a special case. An iterative model is proposed to depict traffic information's influence on incident-induced congestion propagation. The analysis results are compared with simulation results to validate this model's effectiveness.
Methodology for quantification of fuel reduction potential for adaptive cruise control relevant driving strategies
- Author(s): Adrian Zlocki and Philipp Themann
- Source: IET Intelligent Transport Systems, Volume 8, Issue 1, p. 68 –75
- DOI: 10.1049/iet-its.2012.0095
- Type: Article
- + Show details - Hide details
-
p.
68
–75
(8)
Driving strategies in terms of acceleration or deceleration determine fuel consumption and energy recuperation (regeneration), especially for hybrid vehicles. Drivers, who do not always adapt optimal driving strategies, can be supported by technical systems that either recommend optimal strategies or provide an optimised longitudinal vehicle control, which is the focus of adaptive cruise control (ACC) systems. Within this paper, a methodology on how to quantify the fuel reduction potential for different driving strategies in ACC relevant driving scenarios is described. This methodology can be applied for different drive train concepts – hybrid vehicles as well as conventional drive train vehicles. Reference measurements of different drivers are recorded in order to determine the baseline for the quantification of probable fuel reduction potential against a realistic reference. The representative average driver for the relevant scenario is derived from these measurements. The reference profiles are examined with respect to different driver types and the velocity profiles are used as an input for the simulation of different driving strategies. A vehicle simulation model allows the calculation of fuel consumption as well as the determination of the state of charge of the hybrid battery, if applicable. The methodology is verified by means of driving tests with a test vehicle.
Most viewed content
Most cited content for this Journal
-
LSTM network: a deep learning approach for short-term traffic forecast
- Author(s): Zheng Zhao ; Weihai Chen ; Xingming Wu ; Peter C. Y. Chen ; Jingmeng Liu
- Type: Article
-
Survey of smartphone-based sensing in vehicles for intelligent transportation system applications
- Author(s): Jarret Engelbrecht ; Marthinus Johannes Booysen ; Gert-Jan van Rooyen ; Frederick Johannes Bruwer
- Type: Article
-
Robust control of heterogeneous vehicular platoon with uncertain dynamics and communication delay
- Author(s): Feng Gao ; Shengbo Eben Li ; Yang Zheng ; Dongsuk Kum
- Type: Article
-
Modelling the driving behaviour at a signalised intersection with the information of remaining green time
- Author(s): Tie-Qiao Tang ; Zhi-Yan Yi ; Jian Zhang ; Nan Zheng
- Type: Article
-
Comprehensive survey on security services in vehicular ad-hoc networks
- Author(s): Maria Azees ; Pandi Vijayakumar ; Lazarus Jegatha Deborah
- Type: Article