A classification tree based modeling approach for segment related crashes on multilane highways

Introduction

This study presents a classification tree based alternative to crash frequency analysis for analyzing crashes on mid-block segments of multilane arterials.

Method

The traditional approach of modeling counts of crashes that occur over a period of time works well for intersection crashes where each intersection itself provides a well-defined unit over which to aggregate the crash data. However, in the case of mid-block segments the crash frequency based approach requires segmentation of the arterial corridor into segments of arbitrary lengths. In this study we have used random samples of time, day of week, and location (i.e., milepost) combinations and compared them with the sample of crashes from the same arterial corridor. For crash and non-crash cases, geometric design/roadside and traffic characteristics were derived based on their milepost locations. The variables used in the analysis are non-event specific and therefore more relevant for roadway safety feature improvement programs. First classification tree model is a model comparing all crashes with the non-crash data and then four groups of crashes (rear-end, lane-change related, pedestrian, and single-vehicle/off-road crashes) are separately compared to the non-crash cases. The classification tree models provide a list of significant variables as well as a measure to classify crash from non-crash cases. ADT along with time of day/day of week are significantly related to all crash types with different groups of crashes being more likely to occur at different times.

Conclusions

From the classification performance of different models it was apparent that using non-event specific information may not be suitable for single vehicle/off-road crashes.

Impact on Industry

The study provides the safety analysis community an additional tool to assess safety without having to aggregate the corridor crash data over arbitrary segment lengths.     

Changes in spring activity: Experiences of Kumaun Himalaya,India

Summary In Kumaun Himalaya, India, 60 percent of the rural population is dependent on natural springs for water supply. The authors claim that substantial reductions in spring water discharges are due to losses in the indigenous oak forest coverage and its partial replacement by pine. Other factors, such as overall forest cover depletion and construction activities, combine to produce severe reductions in spring discharge rates.Drs Anil Singh and Ravindra Pande are members of academic staff at Kumaun University working in the Laboratory for Hydrological and Geomorphological Investigations in the Department of Geography.     

Laboratory and Field Assessment of Arsenic Testing Field Kits in Bangladesh and West Bengal, India

High concentrations of arsenic in ground waters in West Bengal and Bangladeshhave become a major cause for concern in recent years. Given the enormity and the severity of the problemof arsenic poisoning, a task of evaluating the commercially available arsenic detection field kits for their capabilities was undertaken. In the light of the findings, generic specificationswere recommended which could form the basis forindigenous manufacture of these kits in the arsenic affected countries. This article presents the results of the laboratory and fieldevaluation conducted in Bangladesh and West Bengalof five arsenic testing field kits. The salient features of the kits, their merits and limitationshave been brought out. Based on the criteria of kitdesign, quality of chemicals used, colourcomparator charts, detection range, time required for analysis, cost etc., a comparative ranking ofthe kits has been made to facilitate the choice of the kit to meet specific requirements.     

Market basket analysis of crash data from large jurisdictions and its potential as a decision support tool

Data mining applications are becoming increasingly popular for many applications across a set of very divergent fields. Analysis of crash data is no exception. There are many data mining methodologies that have been applied to crash data in the recent past. However, one particular application conspicuously missing from the traffic safety literature until recently is association analysis or market basket analysis. The methodology is used by retailers all over the world to determine which items are purchased together. In this study, crashes are analyzed as supermarket transactions to detect interdependence among crash characteristics. The results from the analysis include simple rules that indicate which crash characteristics are associated with each other. The application is demonstrated using non-intersection crash data from the state of Florida for the year 2004. In the proposed methodology no variable needs to be assigned as dependent variable. Hence, it is useful in identifying previously unknown patterns in the data obtained from large jurisdictions (such as the State of Florida) as opposed to the data from a single roadway or intersection. Based on the association rules discovered from the analysis, it was concluded that there is a significant correlation between lack of illumination and high severity of crashes. Furthermore, it was found that under rainy conditions straight sections with vertical curves are particularly crash prone. Results are consistent with the understanding of crash characteristics and point to the potential of this methodology for the analysis of crash data collected by the state and federal agencies. The potential of this technique may be realized in the form of a decision support tool for the traffic safety administrators.     

Characterization of atmospheric dust at Gurushikar,Mt. Abu,Rajasthan

The nature of atmospheric aerosols at Gurushikar, Mt. Abu, Rajasthan where a gamma ray telescope is to be installed, was investigated. Air particulate samples collected on filters were used to estimate the total suspended particulate matter (TSPM) and its elemental composition. The TSPM varied from 31 to 103 g/m³ during January to March 1994. The heighest loads were observed during the months of May and June (80–100 g/m³) and lowest during October (20–60 g/m³). The dust was also examined for size, shape and nature of the mineral matter. The particle sizes varied from 100 m to 5 m. The course particles (>50 m) are irregular shaped quartz grains. Some of the medium size (=50 m) particles were spherical and were highly conducting. These particles were rich in iron content. Correlation coefficients among various elements in the dust showed that it is made up of mainly two components-wind blown ground dust and particulate arising out of wood and coal burning.     

Thermo-physical modeling of die-sinking EDM process

This paper reports the development of a thermo-physical model for die-sinking electric discharge machining (EDM) process using finite element method (FEM). Numerical analysis of the single spark operation of EDM process has been carried out considering the two-dimensional axi-symmetric process continuum. The analysis is based on more realistic assumptions such as Gaussian distribution of heat flux, spark radius equation based on discharge current and discharge duration, latent heat of melting, etc., to predict the shape of crater cavity and the material removal rate (MRR). Using the developed model, parametric studies were carried out to study the effect of EDM process parameters such as discharge current, discharge duration, discharge voltage and duty cycle on the process performance. Experimental studies were carried out to study the MRR and crater shapes produced during actual machining. When compared with the reported analytical models, our model was found to predict results closer to the experimental results. The thermo-physical model developed can further be used to carry out exhaustive studies on the EDM process to obtain optimal process conditions.     

Sorghum development and sensitivity to SO2 and NO2 singly and in mixtures

The responses of Sorghum bicolor seedlings, ranging from 3 to 24 days old, to SO₂ and NO₂, singly and in mixtures, were measured. When applied singly at 100 p.p.b., the pollutants significantly decreased all aspects of growth of the youngest group; the older seedlings were more tolerant. In contrast, the oldest seedlings were the most sensitive to mixtures of SO₂ and NO₂. When assessing the effects of different concentrations of SO₂, it was found that growth was decreased by 45 p.p.b.     

Identifying crash propensity using specific traffic speed conditions

INTRODUCTION: In spite of recent advances in traffic surveillance technology and ever-growing concern over traffic safety, there have been very few research efforts establishing links between real-time traffic flow parameters and crash occurrence. This study aims at identifying patterns in the freeway loop detector data that potentially precede traffic crashes. METHOD: The proposed solution essentially involves classification of traffic speed patterns emerging from the loop detector data. Historical crash and loop detector data from the Interstate-4 corridor in the Orlando metropolitan area were used for this study. Traffic speed data from sensors embedded in the pavement (i.e., loop detector stations) to measure characteristics of the traffic flow were collected for both crash and non-crash conditions. Bayesian classifier based methodology, probabilistic neural network (PNN), was then used to classify these data as belonging to either crashes or non-crashes. PNN is a neural network implementation of well-known Bayesian-Parzen classifier. With its superb mathematical credentials, the PNN trains much faster than multilayer feed forward networks. The inputs to final classification model, selected from various candidate models, were logarithms of the coefficient of variation in speed obtained from three stations, namely, station of the crash (i.e., station nearest to the crash location) and two stations immediately preceding it in the upstream direction (measured in 5 minute time slices of 10-15 minutes prior to the crash time). RESULTS: The results showed that at least 70% of the crashes on the evaluation dataset could be identified using the classifiers developed in this paper.     

Selected landslide types in the Central Himalaya: their relation to geological structure and anthropogenic activities

In a region that is highly sensitive to tectonic instability, the fragile nature of the Himalayas becomes further adversely affected by anthropogenic intervention. In the present study observations indicate that the landsliding process occurs along various tectonic zones where it is assisted by human activities. Bedding and joint plane dip slopes, high joint and joint set frequencies, low vegetation cover, high monsoonal rainfall, thin soil cover and anthropogenic activities were found to be the main causative factors of the landslides. Anthropogenic activities include local path, canal and road construction, mining and quarrying, overgrazing, deforestation and unscientific agricultural practices, such as tilling steeper slopes (>30) without contour benches and without provision of drainage ditches, and overcropping without giving rest to the overtaxed soils. Where slope conditions are critical human activities should be controlled so as to minimise the slope failure processes. Various recommendations are proposed.