International Journal of Vehicle Safety (5 papers in press)
Novel robust real-time driver drowsiness detection based on image processing and feature extraction methods
by Maryam Keyvanara, Nasrin Salehi, Amirhassan Monadjemi
Abstract: Recently, the human lifestyle has strongly been affected by the novel technological equipment. The applications of artificial intelligence are widely being used to improve the performance and quality of modern life. One of the important applications of these techniques is to seek to improve public safety, including the safety of driving. The statistics indicate that the mortality in car accidents yearly constitutes a significant proportion of the overall deaths. A number of strategies have been studied to materialise driver drowsiness detection systems. One of the best strategies relies on image processing and computer vision methods. In this paper, a novel real-time method for driver drowsiness detection is presented. This method uses Haar wavelet-based features for face detection. The eye state determination has been performed using PCA feature extraction along with an SVM classifier. The proposed method has been implemented and tested on a real-time ARM based embedded system, with a camera installed in front of the driver. Results show that the presented intelligent system has a high detection accuracy, compared to the methods presented thus far, on the standard datasets such as BioID and RS-DMV.
Keywords: driver drowsiness detection; Haar cascade classifier; SVM; face and eye detection; real-time tracking; PCA.
Crashworthiness optimal design of a new extruded octagonal multi-cell tube under dynamic axial impact
by Zhonghao Bai, Kai Sun, Feng Zhu, Libo Cao, Jun Hu, Clifford C. Chou, Binhui Jiang
Abstract: A new extruded octagonal multi-cell tubular energy absorber is developed for improving and enhancing the vehicle crashworthiness. A combined experimental and numerical study is conducted to further assess its performance. In this study, a sled impact test is first performed to investigate the structural response of an octagonal multi-cell tube, and the test data are then used to validate the FE tube model. Using this FE tube model, the effect of key geometric parameters on the structural crashworthiness is analyzed in detail. It is found that the number of webs along the circumferential direction, the size of inner tube and wall thicknesses of outer tube, web and inner tube have significant effect on crashworthiness of the energy absorber mentioned above. Based on the parametric study, multi-objective optimization is subsequently performed to further improve its energy absorption efficiency. These findings can provide valuable guidelines for designing such new types of energy absorbers under dynamic axial impact.
Keywords: octagonal multi-cell tube; energy absorption efficiency; energy absorber; sled impact test; structural crashworthiness; multi-objective optimization; dynamic axial impact.
Understanding the spatial patterns of tanker accidents in Nigeria using geographically weighted regression
by Moses Olaniran Olawole, Olabisi Michael Olapoju
Abstract: Tanker accidents are an important cause of death and injury in Nigeria, yet the spatial patterns and determinants of these events are not well known. This study examines the spatial patterns of reported tanker accidents cases between 2007 and 2010, and models the spatial patterns of some factors associated with the occurrence of tanker accidents. Data on tanker accidents was extracted from published records of accidents by the Federal Road Safety Commissions of Nigeria (FRSC), while determinants of accidents were extracted from the Annual Abstract of Statistics of Nigeria. The spatial pattern of tankers was mapped using Arc GIS 10 software. Global and local Morans I statistics were used to examine the spatial and cluster patterns of tanker accidents, respectively. The spatial relationships were modelled through ordinary least square (OLS) and geographically weighted regression (GWR) techniques. Findings indicated that tanker accidents vary by state and also revealed an upward trend in the occurrence of tanker accidents between 2007 and 2010. Morans I demonstrated that the pattern of tanker accidents was spatially autocorrelated across the study period. The local Morans I indicates persistent clustering of tanker accidents in Ogun and Oyo states throughout the study period. Distance to FCT (Abuja) from state capital, length of federal roads, number of tanker parks, total drivers licences issued and household size were revealed to contribute to the occurrence of tanker accidents in the country. The results of this study help to identify factors influencing occurrences and spatial pattern of tanker accidents in the country, and also to give valuable contributions to prevention measures to future occurrence of tanker accidents in Nigeria.
Keywords: accidents; spatial pattern; tanker; OLS; GWR; Nigeria.
Special Issue on: Vehicle Active Safety for Intelligent Transportation Systems
Fuzzy fractional PID gain controller for antilock braking system using an electronic wedge brake mechanism
by Fauzi Ahmad, Saiful Amri Mazlan, Khisbullah Hudha, Hairi Zamzuri, Hishammudin Jamaluddin
Abstract: This paper focuses on the design of a adaptive fuzzy Proportional-Integral-Derivative (PID) with fractional gain controller. The controller, which is based on the conventional PID controller, is modified to be P1-α I1-β D1-γ; with the objective to make the controller more flexible and elastic to the changes in input and the system parameter. In this control structure, the fuzzy logic controller acts as the tuner for the parameter of α, β and γ, so that the overall controller parameter can be varied to adapt to the changes in a system. The designed controller is applied to a validated antilock braking system model. Numerous numerical simulations and comparisons with other PID with fractional gain and conventional PID controllers show that the fuzzy fractional PID controller not only ensures good control performance with respect to reference input but also improves the system effectiveness with respect to model uncertainties.
Keywords: fuzzy logic controller, fractional PID controller, fuzzy fractional PID controller, antilock braking system, electronic wedge brake
A preliminary study to optimise safety conditions on a freight urban robotic vehicle
by Giovanni Gerardo Muscolo, Giorgio Moregola, Rezia Molfino
Abstract: The authors are developing a new concept architecture of a light duty full electric vehicle for efficient sustainable urban freight transport that allows the movement of two Euro Pallets 800 x 1200 mm (or boxes with similar bottom part). Active suspensions of the vehicle have been designed in order to adapt their stiffness to the payload on board and to modify the chassis height during loading and unloading tasks. In this paper, a preliminary study to optimise safety conditions of goods on board the vehicle, and of people near the vehicle is presented. In order to guarantee safety conditions at the vehicles driver and city areas where the vehicle should be moved, design optimisations on the chassis have been developed. These optimisations have been compared using computational analysis. Two alternative solutions have been proposed and one of the presented results has been included on the real vehicle.
Keywords: safety; freight transport; robotic vehicle; computational analysis.