Showing papers in "International Journal of Intelligent Transportation Systems Research in 2016"

A Multi-Modal Driver Fatigue and Distraction Assessment System

Abstract: In this paper, we present a multi-modal approach for driver fatigue and distraction detection. Based on a driving simulator platform equipped with several sensors, we have designed a framework to acquire sensor data, process and extract features related to fatigue and distraction. Ultimately the features from the different sources are fused to infer the driver’s state of inattention. In our work, we extract audio, color video, depth map, heart rate, and steering wheel and pedals positions. We then process the signals according to three modules, namely the vision module, audio module, and other signals module. The modules are independent from each other and can be enabled or disabled at any time. Each module extracts relevant features and, based on hidden Markov models, produces its own estimation of driver fatigue and distraction. Lastly, fusion is done using the output of each module, contextual information, and a Bayesian network. A dedicated Bayesian network was designed for both fatigue and distraction. The complementary information extracted from all the mod- ules allows a reliable estimation of driver inattention. Our experimental results show that we are able to detect fatigue with 98.4 % accuracy and distraction with 90.5 %.

Analysis of Large-Scale Traffic Dynamics in an Urban Transportation Network Using Non-Negative Tensor Factorization

Abstract: In this paper, we present our work on clustering and prediction of temporal evolution of global congestion configurations in a large-scale urban transportation network. Instead of looking into temporal variations of traffic flow states of individual links, we focus on temporal evolution of the complete spatial configuration of congestions over the network. In our work, we pursue to describe the typical temporal patterns of the global traffic states and achieve long-term prediction of the large-scale traffic evolution in a unified data-mining framework. To this end, we formulate this joint task using regularized Non-negative Tensor Factorization, which has been shown to be a useful analysis tool for spatio-temporal data sequences. Clustering and prediction are performed based on the compact tensor factorization results. The validity of the proposed spatio-temporal traffic data analysis method is shown on experiments using simulated realistic traffic data.

Recent Advances on Context-Awareness and Data/Information Fusion in ITS

Abstract: Intelligent transportation systems (ITS) involve various emerging technologies and applications. This paper presents a comprehensive review of recent advances on data/information fusion and context-awareness referring to ITS. Data/Information fusion is necessary to fuse the data from different sensors and thereby extract relevant information on the target sources. On the other hand, context-aware information processing provides awareness of the driving environments by deploying intelligent query processing and smart information dissemination. The fusion and context-awareness should help in improving ITS operations with better road-awareness service, traffic monitoring, vehicle detection as well as development of new methods. This paper is centered on data fusion and context aware methodologies developed recently in the areas of ITS rather than on their ITS applications. We found that the recent progresses in ITS fusion are devoted to the potential cooperative approaches providing real-time/dynamic vehicle sensing technologies, whereas the recent context awareness techniques are deploying service concepts (e.g. location aware service) and frameworks. It is believed that the newly developed advanced fusion/context-aware techniques are becoming more effective to tackle complex traffic scenarios (e.g. traffic intersection) as well as complex urban environments.

Blended Power Management Strategy Using Pattern Recognition for a Plug-in Hybrid Electric Vehicle

Abstract: The dual power source of a plug-in hybrid electric vehicle (PHEV) requires a high level control strategy in order to establish a power split decision that will minimize fuel consumption while taking full advantage of the embedded source of electrical energy. Literature shows that the optimal control of the power split is greatly influenced by the future trip to be made and that blended strategies are more appropriate regarding battery usage throughout a trip. This paper proposes a blended strategy for a PHEV which uses a driving pattern recognition scheme that allows control adaptation in real-time regarding current driving conditions.

Modeling Traffic at Sags

Abstract: Freeway capacity decreases at sags due to local changes in car-following behavior. Consequently, sags are often bottlenecks in freeway networks. This article presents a microscopic traffic model that reproduces traffic flow dynamics at sags. The traffic model includes a new car-following model that takes into account the influence of freeway gradient on vehicle acceleration. The face-validity of the traffic model is tested by means of a simulation study. The study site is a sag of a Japanese freeway. The simulation results are compared to empirical traffic data presented in previous studies. We show that the model is capable of reproducing the key traffic phenomena that cause the formation of congestion at sags, including the lower capacity compared to normal sections, the location of the bottleneck around the end of the vertical curve, and the capacity drop induced by congestion. Furthermore, a sensitivity analysis indicates that the traffic model is robust enough to reproduce those phenomena even if some inputs are modified to some extent. The sensitivity analysis also shows what parameters need to be calibrated more accurately for real world applications of the model.

VANET IR-CAS for Safety ACN: Information Retrieval Context Aware System for VANET Automatic Crash Notification Safety Application

Abstract: We propose IR-CAS ACN, a fully Automated Crash Notification safety application that enhances accuracy and efficiency with its precise notifications and increased decentralization. It can be considered as an improvement to the BMW Advanced ACN (AACN): It decentralizes the severity calculation by introducing in-vehicle severity estimation. It fully automates the solution and disseminates more informative messages with partial rather than graded relevance that is insensitive to differences in severity within grades. Different IR models are compared using binary and partial effectiveness measures; estimating severity by calculating the Manhattan distance between the crash and severest crash context vectors outperforms tried models.

Semantically Enriched Multi-Modal Routing

Abstract: We present an innovative extension to routing: intention-oriented routing which is a direct result of combining classical routing-services with Semantic Web technologies. Thereby, the intention of a user can be easily incorporated into route planning. We highlight two use cases where this hybridization is of great significance: neighborhood routing, where a neighborhood can be explored (e.g. searching for events around your place) and via routing, where errands should be run along a route (e.g. buying the ingredients for dinner on your way home). We outline the combination of different methods to achieve these services, and demonstrate the emerging framework on two case studies, with a prototype extending in-use routing services.

Risk of Traffic Incident Delay in Routing and Scheduling of Hazardous Materials

Abstract: Unlike normal traffic incidents, incidents involving hazardous material are associated with significant traffic delays. The model of the hazardous material routing and scheduling problem presented in this paper considers such potential effect of a hazardous material incident, in addition to the traditionally considered risk to exposed population. Probable loss due to congestion created by the probable incident is used as its measure. The objective is to minimize sum of the population-based and congestion-based risk cost. The model was used to explore routing and scheduling in an ITS data-based hazardous material logistics instance derived from the road network of Osaka City, Japan. Comparison of the results showed that the model provides a better alternative to the conventional population-based model as it gives balanced optimal solution avoiding paths that causes large increase of the congestion-based cost.

Estimation of Pedestrian Pose and Orientation Using on-Board Camera with Histograms of Oriented Gradients Features

Abstract: Understanding pedestrian behavior, including head and body orientation, is important for a pedestrian safety system. In this paper, we propose an approach that estimates head pose and body orientation by considering two constraints, the pedestrian model constraint between head and body directions and the temporal constraint. In our approach, given an image of pedestrian, image features are extracted and estimates are made of the probabilities of the head position, size and orientation, and the body orientation; these are obtained using a multi-class classifier and tracked by particle filter. We applied two constraints to the particle filter to achieve more accurate estimate. Experiments using real videos from an on-board monocular camera show the effectiveness of our approach.

Traffic Congestion Forecasting Based on Possibility Theory

Abstract: Traffic congestion state identification is one of the most important tasks of ITS. Traffic flow is a nonlinear complicated system. Traffic congestion state is affected by many factors, such as road channelization, weather condition, drivers’ different driving behavior and so on. It is difficult to collect all necessary traffic information. Traffic congestion auto identification result based on incomplete traffic information exists uncertain. Little work has been done to analyze the uncertainty. Possibility theory introduced by Zadeh is an efficient means to present incomplete knowledge. Possibility distribution determination is an important task of possibility theory. In this paper, possibility theory is used to describe the uncertainty of traffic state. The possibility distribution of traffic state is determined according to the probability distribution of traffic flow parameters, such as volume, speed and occupancy and so on. The multi-variable distribution of traffic flow parameters is determined with large-scale traffic flow data. Large-scale traffic congestion samples are generated with parallel k-mean clustering method. Traffic congestion forecasting is based on the forecasting of traffic flow parameters with SVM (Support Vector Machines). At last, a practical example is analyzed with the proposed method.

An Evaluation Analysis on Three-Wheeled Personal Mobility Vehicles

Abstract: Personal mobility vehicles are proposed as a new category of transportation device that offers several potential benefits to solve the current problems, such as mobility issues of the elderly, downtown area revitalization, and development of low-carbon transport. This paper aims to explore basic attitude of the general public to understand how people think about three-wheeled personal mobility vehicles. Using the surveys data on i-REAL conducted in Toyota, a discussion is made by employing Quantification Theory and Semantic Differential Method. Moreover, textual data derived from the survey are classified by applying Text Mining. Furthermore, conclusions are drawn and suggestions for further work are made. As a conclusion from the comparative analysis between the unexperienced and experienced groups, the experience brings people to make different evaluations so that the test rides are very important to know the true answers. The analysis on the experienced people shows that the elderly highly evaluated the hobby factors, the male highly evaluated the practice factors and the weather condition seems being a key factor for the current model.

Analysis of Dead Zone in Wireless Power Transfer via Magnetic Resonant Coupling for Charging Moving Electric Vehicles

Abstract: Wireless power transfer via magnetic resonant coupling is widely researched for various applications especially for charging electric vehicles. In order to reduce the dependency on battery capacity, charging while the vehicle is moving may be a solution. Wireless power transfer lane is constructed by embedding the coils beneath the road to provide charging coverage to certain distance. The actual system will consists of arbitrary number of coils and therefore conventional equivalent circuit analysis will be complex. In this paper, a new and simplified analysis method using impedance inverter representation and power division principle is proposed to investigate the feasibility of charging lane.

A Cluster Management System for VANETs

Abstract: Vehicular ad-hoc networks (VANETs) are a key solution for communication in intelligent transportation systems (ITS). However, high mobility of vehicles on roads may cause varying delays and message losses which can limit the use of VANETs in some ITS scenarios. This paper proposes and evaluates a cluster management system for VANETs (CMS) that makes communication in VANETs more robust and efficient, enabling the collection of data of individual vehicles that travel on roads at any time. Simulated experiments show that the proposed system achieves improved communication in VANETs enabling their use in ITS applications such as the real-time road traffic management and control.

Assessment of the Contribution of Time Reversal on a UWB Localization System for Railway Applications

Abstract: UWB radio has the potential to offer good performance in terms of localization precision. Time Reversal channel pre-filtering facilitates signal detection and also helps to increase the received energy in a targeted area. This paper assesses the quantitative and qualitative contributions of the Time Reversal (TR) technique associated with an Ultra Wideband (UWB) localization system applied to a railway odometry problem. The analytical and simulation results for Power Delay Profile, equivalent channel model and focusing gain of the TR-UWB are given. The contribution of the TR technique associated with UWB radio to enhance the localization resolution is analysed. To perform these studies, and to be representative of the proposed railway application, a deterministic channel model is used. The analytical simulation and experimental results show that time reversal has very promising characteristics regarding its association with the UWB in terms of localization error. These results also indicate that the TR-UWB technique delivers improved performance over UWB only localization approach, that could benefit the development of the proposed railway application.

Evaluation of Fuzzy Inference-based Self-tuning of Steering Control Gains for Heavy-duty Trucks

Abstract: As the number of automobiles in worldwide increases, the number of associated serious environmental and safety problems also increases. A solution to these problems is an autonomous platooning system for trucks, which is expected to have various effects such as reduction in carbon dioxide emissions and increase in traffic capacity. Although various control laws have been proposed for automated driving, control gains are typically tuned manually. The optimal values change owing to the freight or over a period of several years. Therefore, when the control performance decreases, gain tuning is again required. In this study, as additional evaluations of the proposed self-tuning method, we newly examine if the method can adjust gain to the change of a freight weight by simulation and evaluate the convergence property of the method experimentally.

Automated Courier Transport on the Rail Network: Concept and its Feasibility

Abstract: A concept for an automated rail-road intermodal courier service system is proposed. While rail transport suffers a number of difficulties, such as long exchange time, large container size and slow speed, the proposed system aims to solve them using ITS-aided transfer robots and an ICT-based routing system. The system is based on a loosely coupled design by which the flexibility of rail networks can be utilized. We investigated the feasibility of the proposed system in economical, physical and technological aspects and obtained positive results. This system copes with aging society, and future industry needs for automation and just-in-time delivery of small packets.