Applicazione car pooling, condivisione dei posti auto attraverso i social network

L'obiettivo di questa tesi consiste nello sviluppare un'applicazione su piattaforma Android che permetta di organizzare il car pooling attraverso i social network.

Foreword

Foreword for the book, "INTERCHANGING: Future designs for responsive transport environments"

A method for systematically pooling data in very early stage construction price forecasting

Client owners usually need an estimate or forecast of their likely building costs in advance of detailed design in order to confirm the financial feasibility of their projects. Because of their timing in the project life cycle, these early stage forecasts are characterized by the minimal amount of information available concerning the new (target) project to the point that often only its size and type are known. One approach is to use the mean contract sum of a sample, or base group, of previous projects of a similar type and size to the project for which the estimate is needed. Bernoulli’s law of large numbers implies that this base group should be as large as possible. However, increasing the size of the base group inevitably involves including projects that are less and less similar to the target project. Deciding on the optimal number of base group projects is known as the homogeneity or pooling problem. A method of solving the homogeneity problem is described involving the use of closed form equations to compare three different sampling arrangements of previous projects for their simulated forecasting ability by a cross-validation method, where a series of targets are extracted, with replacement, from the groups and compared with the mean value of the projects in the base groups. The procedure is then demonstrated with 450 Hong Kong projects (with different project types: Residential, Commercial centre, Car parking, Social community centre, School, Office, Hotel, Industrial, University and Hospital) clustered into base groups according to their type and size.

Likelihood-maximising frameworks for enhanced in-car speech recognition

Speech recognition in car environments has been identified as a valuable means for reducing driver distraction when operating non-critical in-car systems. Likelihood-maximising (LIMA) frameworks optimise speech enhancement algorithms based on recognised state sequences rather than traditional signal-level criteria such as maximising signal-to-noise ratio. Previously presented LIMA frameworks require calibration utterances to generate optimised enhancement parameters which are used for all subsequent utterances. Sub-optimal recognition performance occurs in noise conditions which are significantly different from that present during the calibration session - a serious problem in rapidly changing noise environments. We propose a dialog-based design which allows regular optimisation iterations in order to track the changing noise conditions. Experiments using Mel-filterbank spectral subtraction are performed to determine the optimisation requirements for vehicular environments and show that minimal optimisation assists real-time operation with improved speech recognition accuracy. It is also shown that the proposed design is able to provide improved recognition performance over frameworks incorporating a calibration session.

Virtual design process : design validation tool schematic approach in car carrier

An important aspect of designing any product is validation. Virtual design process (VDP) is an alternative to hardware prototyping in which analysis of designs can be done without manufacturing physical samples. In recent years, VDP have been generated either for animation or filming applications. This paper proposes a virtual reality design process model on one of the applications when used as a validation tool. This technique is used to generate a complete design guideline and validation tool of product design. To support the design process of a product, a virtual environment and VDP method were developed that supports validation and an initial design cycle performed by a designer. The product model car carrier is used as illustration for which virtual design was generated. The loading and unloading sequence of the model for the prototype was generated using automated reasoning techniques and was completed by interactively animating the product in the virtual environment before complete design was built. By using the VDP process critical issues like loading, unloading, Australian Design rules (ADR) and clearance analysis were done. The process would save time, money in physical sampling and to large extent in complete math generation. Since only schematic models are required, it saves time in math modelling and handling of bigger size assemblies due to complexity of the models. This extension of VDP process for design evaluation is unique and was developed, implemented successfully. In this paper a Toll logistics and J Smith and Sons car carrier which is developed under author’s responsibility has been used to illustrate our approach of generating design validation via VDP.

Speeding in Australia and China : a comparison of the influence of legal sanctions and enforcement practices on car drivers

Despite increasingly sophisticated speed management strategies, speeding remains a significant contributing factor in 25% of Australia’s fatal crashes. Excessive speed is also a recognised contributor to road trauma in rapidly motorising countries such as China, where increases in vehicle ownership and new drivers, and a high proportion of vulnerable road users all contribute to a high road trauma rate. Speed choice is a voluntary behaviour. Therefore, driver perceptions are important to our understanding of the nature of speeding. This paper reports preliminary qualitative (focus groups) and quantitative (survey) investigations of the perceptions of drivers in Queensland and Beijing. Drivers’ definitions of speeding as well as their perceptions of the influence of legal factors on their reported speeds were explored. Survey participants were recruited from petrol stations (Queensland, n=833) and car washes (Beijing, n=299). Similarities were evident in justifications for exceeding speed limits across samples. Excessive speeds were not deemed as ‘speeding’ when drivers considered that they were safe and under their control, or when speed limits were seen as unreasonably low. This appears linked to perceptions of enforcement tolerances in some instances with higher perceived enforcement thresholds noted in China. Encouragingly, drivers in both countries reported a high perceived risk of apprehension if speeding. However, a substantial proportion of both samples also indicated perceptions of low certainty of receiving penalties when apprehended. Chinese drivers considered sanctions less severe than did Australian drivers. In addition, strategies to avoid detection and penalties were evident in both samples, with Chinese drivers reporting a broader range of avoidant techniques. Implications of the findings for future directions in speed management in both countries are discussed.

Facial feature detection for in-car environment

Acoustically, vehicles are extremely noisy environments and as a consequence audio-only in-car voice recognition systems perform very poorly. Seeing that the visual modality is immune to acoustic noise, using the visual lip information from the driver is seen as a viable strategy in circumventing this problem. However, implementing such an approach requires a system being able to accurately locate and track the driver’s face and facial features in real-time. In this paper we present such an approach using the Viola-Jones algorithm. Using this system, we present our results which show that using the Viola-Jones approach is a suitable method of locating and tracking the driver’s lips despite the visual variability of illumination and head pose.

The call of the road : factors predicting students' car travelling intentions and behaviour

The most common daily trip for employed persons and students is the commute to and from work and/or place of study. Though there are clear environmental, health and safety benefits from using public transport instead of private vehicles for these trips, a high proportion of commuters still choose private vehicles to get to work or study. This study reports an investigation of psychological factors influencing students’ travel choices from the perspective of the Theory of Planned Behaviour (TPB). Students from 3 different university campuses (n= 186) completed a cross-sectional survey on their car commuting behaviour. Particular focus was given to whether car commuting habits could add to understanding of commuting behaviour over and above behavioural intentions. Results indicated that, as expected, behavioural intention to travel by car was the strongest TPB predictor of car commuting behaviour. Further, general car commuting habits explained additional variance over and above TPB constructs, though the contribution was modest. No relationship between habit and intentions was found. Overall results suggest that, although student car commuting behaviour is habitual in nature, it is predominantly guided by reasoned action. Implications of these findings are that in order to alter the use of private vehicles, the factors influencing commuters’ intentions to travel by car must be addressed. Specifically, interventions should target the perceived high levels of both the acceptability of commuting by car and the perceived control over the choice to commute by car.

FPGA implementation of dual-microphone delay-and-sum beamforming for in-car speech enhancement and recognition

In an automotive environment, the performance of a speech recognition system is affected by environmental noise if the speech signal is acquired directly from a microphone. Speech enhancement techniques are therefore necessary to improve the speech recognition performance. In this paper, a field-programmable gate array (FPGA) implementation of dual-microphone delay-and-sum beamforming (DASB) for speech enhancement is presented. As the first step towards a cost-effective solution, the implementation described in this paper uses a relatively high-end FPGA device to facilitate the verification of various design strategies and parameters. Experimental results show that the proposed design can produce output waveforms close to those generated by a theoretical (floating-point) model with modest usage of FPGA resources. Speech recognition experiments are also conducted on enhanced in-car speech waveforms produced by the FPGA in order to compare recognition performance with the floating-point representation running on a PC.

Direct and indirect effects on households’ intentions to replace the old car

With the purpose of testing the hypothesis that households’ intentions to replace their old car have a direct negative relationship to its perceived quality (‘current level’) and a direct positive relationship to their aspirations for a new car (‘aspiration level’), a rotating panel of car owners were interviewed every fourth month during 2 years. In this data set the hypothesis received support. In addition the results showed that the age of the car, the total number of miles driven, and the number of anticipated repairs affected the current level, whereas marital status, the number of children, consumer confidence, and environmental concern affected the aspiration level.

Lip detection for audio-visual speech recognition in-car environment

Acoustically, car cabins are extremely noisy and as a consequence audio-only, in-car voice recognition systems perform poorly. As the visual modality is immune to acoustic noise, using the visual lip information from the driver is seen as a viable strategy in circumventing this problem by using audio visual automatic speech recognition (AVASR). However, implementing AVASR requires a system being able to accurately locate and track the drivers face and lip area in real-time. In this paper we present such an approach using the Viola-Jones algorithm. Using the AVICAR [1] in-car database, we show that the Viola- Jones approach is a suitable method of locating and tracking the driver’s lips despite the visual variability of illumination and head pose for audio-visual speech recognition system.

Vision-based navigational competencies for a car-like vehicle

If mobile robots are to perform useful tasks in the real-world they will require a catalog of fundamental navigation competencies and a means to select between them. In this paper we describe our work on strongly vision-based competencies: road-following, person or vehicle following, pose and position stabilization. Results from experiments on an outdoor autonomous tractor, a car-like vehicle, are presented.