Automatic construction of concept hierarchies: The case of foliage-dwelling spiders

In this paper, we present the hierarchical variable dependencies that were obtained from raw data with the use of two machine learning techniques on an ecological data set. The data set contains features of field margins and the corresponding number of spider species inhabiting them. This data set was used before by domain experts to construct a fuzzy qualitative model with hierarchical variable dependencies, which we use for comparison with our results. One of the machine learning methods constructs a hierarchical structure similar to the one in the experts’ model, while revealing some additional interesting relations of environmental features with respect to the number of spider species. The other method constructs a different hierarchy from the one proposed by the experts, which, according to our classification performance experiments, might be even more appropriate.     

Application of machine learning methods to palaeoecological data

A palaeoecological study was conducted to investigate past environmental conditions and vegetation dynamics around the southwestern Ljubljana Moor. In order to find potential regularities and/or dependencies among co-existent plant species through time, different machine learning methods were applied to pollen records from the cores taken at Bistra and Ho?evarica. The data comprised relative pollen frequencies of the most common plant genera/families at particular core depths that correspond to particular ages in the Early and Mid Holocene periods. The applied methods include equation discovery and hierarchical clustering. Both methods have found plausible and explainable relationships among identified plant genera/families.     

Multicriteria ranking of workplaces regarding working conditions in a mining company

Ranking of workplaces with respect to working conditions is very significant for each company. It indicates the positions where employees are most exposed to adverse effects resulting from the working environment, which endangers their health. This article presents the results obtained for 12 different production workplaces in the copper mining and smelting complex RTB Bor – ‘Veliki Krivelj’ open pit, based on six parameters measured regularly which defined the following working environment conditions: air temperature, light, noise, dustiness, chemical hazards and vibrations. The ranking of workplaces has been performed by PROMETHEE/GAIA. Additional optimization of workplaces is done by PROMETHEE V with the given limits related to maximum permitted values for working environment parameters. The obtained results indicate that the most difficult workplace is on the excavation location (excavator operator). This method can be successfully used for solving similar kinds of problems, in order to improve working conditions.     

The analysis of influence of individual and environmental factors on 2-wheeled users’ injuries

Objective: Powered 2-wheeled motor vehicles (PTWs) are one of the most vulnerable categories of road users. Bearing that fact in mind, we have researched the effects of individual and environmental factors on the severity and type of injuries of PTW users. The aim was to recognize the circumstances that cause these accidents and take some preventive actions that would improve the level of road safety for PTWs.

Methods: In the period from 2001 to 2010, an analysis of 139 road accidents involving PTWs was made by the Faculty of Transport and Traffic Engineering in Belgrade. The effects of both individual (age, gender, etc.) and environmental factors (place of an accident, time of day, etc.) on the cause of accidents and severity and type of injuries of PTWs are reported in this article. Analyses of these effects were conducted using logistic regression, chi-square tests, and Pearson's correlation.

Results: Factors such as categories of road users, pavement conditions, place of accident, age, and time of day have a statistically significant effect on PTW injuries, whereas other factors (gender, road type; that is, straight or curvy) do not. The article also defines the interdependence of the occurrence of particular injuries at certain speeds. The results show that if PTW users died of a head injury, these were usually concurrent with chest injuries, injuries to internal organs, and limb injuries.

Conclusions: It has been shown that there is a high degree of influence of individual factors on the occurrence of accidents involving 2-wheelers (PTWs/bicycles) but with no statistically significant relation. Establishing the existence of such conditionalities enables identifying and defining factors that have an impact on the occurrence of traffic accidents involving bicyclists or PTWs. Such a link between individual factors and the occurrence of accidents makes it possible for system managers to take appropriate actions aimed at certain categories of 2-wheelers in order to reduce casualties in a particular area. The analysis showed that most of the road factors do not have a statistically significant effect on either category of 2-wheeler. Namely, the logistic regression analysis showed that there is a statistically significant effect of the place of accident on the occurrence of accidents involving bicyclists.     

The influence of alcohol on pedestrians: A different approach to the effectiveness of the new traffic safety law

Objective: The aim of this study was to explore the effects of the new traffic safety law on pedestrian mortality by exploring hazardous behaviors of pedestrians in terms of alcohol use and blood alcohol concentration (BAC).

Methods: A retrospective autopsy study was performed, covering a 7-year period (from 2006 to 2012), including cases of fatally injured pedestrians who died at the scene of the incident. Blood samples obtained from the femoral vein during autopsy were analyzed for BAC. The entire sample was divided into 2 groups. The first included cases from 2006 to 2009, at which time the old traffic safety law was in force, and the second included cases from 2010 to 2012, under the new traffic safety law.

Results: A total of 247 cases were examined, covering a 7-year period. The average age was 57.5 ± 19.7 years (median 61.0 years) with a significant male predominance of 147 men to 100 women. This predominance also applied to alcohol use (54 vs. 13). The results show a significant decrease in the total annual number of fatally injured pedestrians, starting from 2009, compared to previous years, reaching a low in 2010, one year after implementation of the new traffic safety law. In contrast, the proportion of alcohol-intoxicated pedestrians showed no significant difference in the years preceding and following the new traffic safety law, nor did the annual distribution of BAC or mean BAC before and after application of the new law.

Conclusion: The present study indicates that the new traffic safety law has been quite effective in reducing pedestrian mortality. However, alcohol consumption and intoxication in pedestrians remains a fairly important factor in motor vehicle accidents involving pedestrians, because the proportion of pedestrians positive for alcohol, the proportion of severely intoxicated pedestrians with BAC > 1 g/L, and annual mean BAC have remained unchanged.     

Controlling factors of phytoplankton seasonal succession in oligotrophic Mali Ston Bay (south-eastern Adriatic)

Fine spatial and temporal phytoplankton variability in Mali Ston Bay has been observed for the first time based on physicochemical properties and small herbivorous zooplankton. Extensive year-through research was conducted during 2002 at Usko station which is traditionally an area of intensive shellfish farming. The Neretva River inflow, submarine springs (“vruljas”) and precipitation are additional sources of nutrients in the bay. Temperature and salinity, combined with total inorganic nitrogen (TIN) were observed to be the most important environmental factors driving the succession of phytoplankton communities. Orthophosphate was a potential limiting factor for phytoplankton development. The nanophytoplankton abundances, as well as the microphytoplankton diatoms are controlled by herbivorous zooplankton grazing (‘top-down’ control) more than other groups of microphytoplankton. Nanophytoplankton dominated phytoplankton abundance and its most intensive development was recorded in winter and spring, while increase in microphytoplankton abundance occurred in spring and autumn. Diatoms dominated microphytoplankton abundance mostly in winter and autumn, while dinoflagellates dominated in spring and summer. Considering the number of taxa and abundance, dinoflagellates were the dominant microphytoplankton group during the year and were the main component of the spring blooms. At that time, in conditions of elevated temperature (>16 °C), decreased salinity (34–36) and increased concentrations of TIN, blooms of harmful dinoflagellate Prorocentrum minimum were recorded for the first time in the bay. The results showed a significant difference in environmental conditions, as well as in the annual phytoplankton succession and community structure, as compared with studies carried out more than 20 years ago in this area.     

A decision support system for assessing landfill performance

Designing environmentally sound landfills is a challenging engineering task due to complex interactions of numerous design variables; such as landfill size, waste characteristics, and site hydrogeology. Decision support systems (DSS) can be utilized to handle these complex interactions and to aid in a performance-based landfill design by coupling system simulation models (SSM). The aim of this paper is to present a decision support system developed for a performance-based landfill design. The developed DSS is called Landfill Design Decision Support System – LFDSS. A two-step DSS framework, composed of preliminary design and detailed design phases, is set to effectively couple and run the SSMs and calculation modules. In preliminary design phase, preliminary design alternatives are proposed using general site data. In detailed design phase, proposed design alternatives are further simulated under site-specific data using SSMs for performance evaluation. LFDSS calculates the required landfill volume, performs landfill base contour design, proposes preliminary design alternatives based on general site conditions, evaluates the performance of the proposed designs, calculates the factor of safety values for slope stability analyses, and performs major cost calculations. The DSS evaluates the results of all landfill design alternatives, and determines whether the design satisfies the predefined performance criteria. The DSS ultimately enables comparisons among different landfill designs based on their performances (i.e. leachate head stability, and groundwater contamination), constructional stability and costs. The developed DSS was applied to a real site, and the results demonstrated the strengths of the developed system on designing environmentally sound and feasible landfills.