Speed prediction for triggering vehicle activated signs

Accurate speed prediction is a crucial step in the development of a dynamic vehcile activated sign (VAS). A previous study showed that the optimal trigger speed of such signs will need to be pre-determined according to the nature of the site and to the traffic conditions. The objective of this paper is to find an accurate predictive model based on historical traffic speed data to derive the optimal trigger speed for such signs. Adaptive neuro fuzzy (ANFIS), classification and regression tree (CART) and random forest (RF) were developed to predict one step ahead speed during all times of the day. The developed models were evaluated and compared to the results obtained from artificial neural network (ANN), multiple linear regression (MLR) and naïve prediction using traffic speed data collected at four sites located in Sweden. The data were aggregated into two periods, a short term period (5-min) and a long term period (1-hour). The results of this study showed that using RF is a promising method for predicting mean speed in the two proposed periods.. It is concluded that in terms of performance and computational complexity, a simplistic input features to the predicitive model gave a marked increase in the response time of the model whilse still delivering a low prediction error.

Regionalekonomisk betydelse av travsporten : exemplet Dalatravet Rättvik

Tidigare studier har visat att hästnäringen inklusive spridningseffekter årligen omsätter ca 46 miljarder kronor och bidrar till sysselsättning för ca 30 000 helårsverken. Motsvarande beräkningar för travsportens del av hästnäringen eller för en mindre region finns däremot inte. Denna rapport syftar till att uppskatta regionalekonomisk betydelse av travsport i Sverige med utgångspunkt i en mindre travbanas verksamhet. Dalatravet Rättvik (DT Rättvik) används som en fallstudie. Resultaten baseras dels på registerdata över faktiskt registrerade hästar med koppling till DT Rättvik dels på enkätmaterial insamlat från ett urval av besökare vid tävlingar under sommaren 2014. Totalt används svar från 444 besökare i analysen. Resultaten från beräkningarna visar att den direkta ekonomiska effekten av DT Rättviks 333 travhästar i amatör- eller proffsträning genererar 20 miljoner i travhästtrelaterad konsumtion. DT Rättviks travsportevenemang uppskattas generera ca 29 miljoner varav 11,1 miljoner ärett tillskott till den regionala ekonomin i form av turistekonomisk omsättning. Travsportens sammanlagda regionalekonomiska effekt beräknas således uppgå till minst 31,1 miljonerkronor. Inkluderas även utbildning, avel och uppfödning samt sysselsättning vid ATG-ombudså uppskattas travsporten generera ca 40 helårsverken inom DT Rättviksregionen.  

Benchmark Evaluation of HOG Descriptors as Features for Classification of Traffic Signs

The purpose of this paper is to analyze the performance of the Histograms of Oriented Gradients (HOG) as descriptors for traffic signs recognition. The test dataset consists of speed limit traffic signs because of their high inter-class similarities.   HOG features of speed limit signs, which were extracted from different traffic scenes, were computed and a Gentle AdaBoost classifier was invoked to evaluate the different features. The performance of HOG was tested with a dataset consisting of 1727 Swedish speed signs images. Different numbers of HOG features per descriptor, ranging from 36 features up 396 features, were computed for each traffic sign in the benchmark testing. The results show that HOG features perform high classification rate as the Gentle AdaBoost classification rate was 99.42%, and they are suitable to real time traffic sign recognition. However, it is found that changing the number of orientation bins has insignificant effect on the classification rate. In addition to this, HOG descriptors are not robust with respect to sign orientation.

To what extent are CO2 emissions from intra-urban shopping trips by cars affected by drivers’ travel behaviour and store location?

Transportation is seen as one of the major sources of CO2 pollutants nowadays. The impact of increased transport in retailing should not be underestimated. Most previous studies have focused on transportation and underlying trips, in general, while very few studies have addressed the specific affects that, for instance, intra-city shopping trips generate. Furthermore, most of the existing methods used to estimate emission are based on macro-data designed to generate national or regional inventory projections. There is a lack of studies using micro-data based methods that are able to distinguish between driver behaviour and the locational effects induced by shopping trips, which is an important precondition for energy efficient urban planning. The aim of this study is to implement a micro-data method to estimate and compare CO2 emission induced by intra-urban car travelling to a retail destination of durable goods (DG), and non-durable goods (NDG). We estimate the emissions from aspects of travel behaviour and store location. The study is conducted by means of a case study in the city of Borlänge, where GPS tracking data on intra-urban car travel is collected from 250 households. We find that a behavioural change during a trip towards a CO2 optimal travelling by car has the potential to decrease emission to 36% (DG), and to 25% (NDG) of the emissions induced by car-travelling shopping trips today. There is also a potential of reducing CO2 emissions induced by intra-urban shopping trips due to poor location by 54%, and if the consumer selected the closest of 8 existing stores, the CO2 emissions would be reduced by 37% of the current emission induced by NDG shopping trips.

Young peoples’ entrance to the workplace : Introduction to occupational health and safety

Negative outcomes of a poor work environment are more frequent among young workers. The aim of the current study was to study former pupils’ conditions concerning occupational health and safety by investigating the workplaces’, safety climate, the degree of implementation of SWEM and the their introduction programs. Four branches were included in the study: Industrial, Restaurant, Transport and Handicraft, specialising in wood. Semi-structured dialogues were undertaken with 15 employers at companies in which former pupils were employed. They also answered a questionnaire about SWEM. Former pupils and experienced employees were upon the same occasion asked to fill in a questionnaire about safety climate at the workplace. Workplace introduction programs varied and were strongly linked to company size. Most of the former pupils and experienced employees rated the safety climate at their company as high, or good. Employers in three of the branches rated the SWEM implemented at their workplaces to be effective. The Industry companies, which had the largest workplaces, gave the most systematic and workplace introduction for new employees. There are no results from this study explaining the fact that young workers have a higher risk for workplace accidents.

On processing GPS tracking data of spatiotemporal car movements : a case study

The advancement of GPS technology has made it possible to use GPS devices as orientation and navigation tools, but also as tools to track spatiotemporal information. GPS tracking data can be broadly applied in location-based services, such as spatial distribution of the economy, transportation routing and planning, traffic management and environmental control. Therefore, knowledge of how to process the data from a standard GPS device is crucial for further use. Previous studies have considered various issues of the data processing at the time. This paper, however, aims to outline a general procedure for processing GPS tracking data. The procedure is illustrated step-by-step by the processing of real-world GPS data of car movements in Borlänge in the centre of Sweden.

GRASP and statistical bounds for heuristic solutions to combinatorial problems

The quality of a heuristic solution to a NP-hard combinatorial problem is hard to assess. A few studies have advocated and tested statistical bounds as a method for assessment. These studies indicate that statistical bounds are superior to the more widely known and used deterministic bounds. However, the previous studies have been limited to a few metaheuristics and combinatorial problems and, hence, the general performance of statistical bounds in combinatorial optimization remains an open question. This work complements the existing literature on statistical bounds by testing them on the metaheuristic Greedy Randomized Adaptive Search Procedures (GRASP) and four combinatorial problems. Our findings confirm previous results that statistical bounds are reliable for the p-median problem, while we note that they also seem reliable for the set covering problem. For the quadratic assignment problem, the statistical bounds has previously been found reliable when obtained from the Genetic algorithm whereas in this work they found less reliable. Finally, we provide statistical bounds to four 2-path network design problem instances for which the optimum is currently unknown.

Residential planning, driver mobility and CO2 emission

The literature on residences and citizens’ transports has focused on either reforming traffic managing in response to residential relocation or post-evaluation of urban planning policies or the evolution of the urban spatial form. In a city there are hotspots that attract the citizens and most of the transportation in the city arises as the citizens’ movement between their residence and the hotspots. Little scholarly attention has been devoted to the possibility to minimize citizens’ transportation in the city by the urban planning of residential areas. In this paper we propose a method to evaluate the environmental impact (in terms of CO2-emissions) of urban plans of residential areas. The method is illustrated in a Swedish case of a midsize city which is presently preoccupied with urban planning of new residential areas in response to substantial population growth due to immigration. The residential plans aims to increase the compactness and residential density in the current center and sub centers leads to less CO2 emissions compare to urban expansion to the edge of the city. The plans of concentrated apartment buildings are more effective in meeting residential needs and mitigating CO2 emissions than dispersed single-family houses.

The Power of the Synthetic Control Method

The synthetic control method (SCM) is a new, popular method developed for the purpose of estimating the effect of an intervention when only one single unit has been exposed. Other similar, unexposed units are combined into a synthetic control unit intended to mimic the evolution in the exposed unit, had it not been subject to exposure. As the inference relies on only a single observational unit, the statistical inferential issue is a challenge. In this paper, we examine the statistical properties of the estimator, study a number of features potentially yielding uncertainty in the estimator, discuss the rationale for statistical inference in relation to SCM, and provide a Web-app for researchers to aid in their decision of whether SCM is powerful for a specific case study. We conclude that SCM is powerful with a limited number of controls in the donor pool and a fairly short pre-intervention time period. This holds as long as the parameter of interest is a parametric specification of the intervention effect, and the duration of post-intervention period is reasonably long, and the fit of the synthetic control unit to the exposed unit in the pre-intervention period is good.