Road accident investigation using an object-oriented database

The continuation of the downward trend in the number of injuries arising from road accidents in Britain and the effectiveness of casualty reduction targets are both dependent upon the availability of improved high-quality information. This paper describes the development of, and issues surrounding, an experimental road accident database within a geographical information system (GIS). It highlights ways in which the quality and completeness of road accident data may be improved by providing a separate definition of the road network and considers the benefits of using an object-oriented database system.

Reducing road accidents pose a significant threat to public safety. However, many studies in road accident investigation and forecasting have utilized limited input and small data sets, limiting their influence and usability; and available large data sets that are confidential, either are old or include significant details about nature like natural causes (weather, points of interest, etc.). We have used machine learning concepts to identify the various factors that influence the severity of road accidents using dates, weather, regions, countries, and other variables to assist the research community in addressing these issues. We present these figures. in this paper, as well as an exhaustive rundown of information, got, from this data set with respect to spatiotemporal gamble factors.

Integration of object-oriented programming languages and database systems in KOPERNIK

This research investigates the modal split of passengers’ transport in a new approach different from the dominant methodology of four-step demand model, using accidents data in calculation, assuming that the more accidents for a mode (cars, public transport, and bicycles), the more passengers who are using it. More than 100,000 road accidents are analyzed for consecutive four years in Hungary. Drivers, front-seat and rear-seat passengers are categorized through age intervals. Age distribution profiles for each mode of private cars, public transport, cycling, motors are developed after normalized the intervals with their corresponding population. Hypothesis of using the approach of finding passenger modal split through road accident data is tested as overall percentages in macro level as Hungary scale and selected cities in micro level for cities of Budapest, Miskolc, Pecs, and Szeged. Forecasting of the passenger cars split ratio is developed for four years ahead depending on time-series decomposition method. Results show that modes of passenger cars, and walking and cycling percentages are acceptable with limitations in reality, unlike public transport which is rejected at all times to be estimated through road accidents data, while forecasting passenger cars is convenient.KeywordsModal splitRoad accidentsPassengers transportPublic transportPassengers’ safetyForecasting

With increasing use of technologies, the amount of accident data has been growing at an ever-increasing rate in the last few years. Government entities and private sectors have been busy and involved in collecting accident data on daily bases. Data for accidents is often among the most valuable assets since it helps in budgeting and implementation of policies and also helps policymakers to make decisions pertaining to infrastructure planning and development. But, as the mount of this data is growing, there is high demand and a need of finding methods, technique and tools to analyse such large volumes of data and find a solution to understand t he cause of increasing accidents in different regions of the world. In this research, we propose and implement a data mining framework to identify, analyse and determine attributes contributing to road accidents. The main aim of this research project is to implement a data mining framework for analysing the relationship between accident attributes and make recommendations for preventing the high occurrence of these accidents. This framework is evaluated with road accidents data from Khomas region, Namibia. The results demonstrate that the use of such an analytical tool can help in creating a knowledge base. The results find out that male drivers have massively contributed to the higher risk of accidents, especially, at intersections and during daylight. It also observed that young drivers are often involved in road traffic accidents happening in clear areas. Proportionally, old aged drivers are most likely to be involved in fatal accidents than in non-fatal accidents.

Road accidents are becoming a global crisis which does not only cost human life but also affect the economic condition of a nation. Therefore it is gaining the interest of several researchers to analyze the influential factors behind road accidents and suggest the preventive measures. A large country like India is also suffering from a substantial amount of road accidents and try to incorporate improve road safety measures. In this paper, we evaluate the performances of different Indian states in road safety measures based on the recorded road accident data. The current analysis is based on a novel line encoding method which categorizes Indian states into three categories, i.e., best performer, average performer, and stragglers. Results have efficiently identified the states that reduce road accidents and the potential states which need to improve on road safety to a great extent. The outcome after ranking the states based on our approach shows there is a high linear correlation between accident rate with population and number of vehicles whereas accident and literacy rate shares an inverse correlation. The satisfactory results based on our approach definitely enlight the interdisciplinary research domains.

A study on road accident prediction and contributing factors using explainable machine learning models: analysis and performance

Analysis of road accidents in two mixed industrial urban zones, using nested Poisson and Negative Binomial models

This paper compares two approaches to meeting the data handling requirements of Intermedia, a hypermedia system developed at the Institute for Research in Information and Scholarship at Brown University. Intermedia, though written using an object-oriented programming language, relies on a traditional relational database management system for data storage and retrieval. We examine the ramifications of replacing the relational database with an object-oriented database. We begin by describing the important characteristics each database system. We then describe Intermedia and give an overview of its architecture and its data handling requirements. We explain why and how we used a relational database management system and the problems that we encountered with this system. We then present the design of an object-oriented database schema for Intermedia and compare the relational and object-oriented database management system approaches.

To enhance the safety and integration of vulnerable road users (pedestrians and cyclists) into the transportation system, a growing number of European cities, including Vilnius, are aligning their traffic management solutions with the concept of street humanisation. The Naujamiestis district is the first city district in Vilnius to undergo these changes. To assess the impact of street humanisation strategies on road safety, this preliminary paper analyses data from the road accident history database for the period 2018–2021 and results from instantaneous vehicle speed analysis. The results of the road accident database history are presented graphically and using heat maps. The data from the instantaneous speed analysis are analysed using the Kruskal- Wallis and Mann-Whitney-Wilcoxon non-parametric statistical criteria. The findings indicate that the concept of street humanisation is effective in enforcing 30 km/h speed limit. The analysis of road accident data history shows a decrease in the number of accidents and their consequences in the study area and the entire city of Vilnius between 2018 and 2022. However, it is currently challenging to determine whether street humanisation concept directly contributes to the decline in road accidents. Therefore, it is proposed to revisit the analysis in the future.

Genetic algorithms (GAs) are stochastic methods that are widely used in search and optimization.The breeding process is the main driving mechanism for GAs that leads the way to find the global optimum.And the initial phase of the breeding process starts with parent selection.The selection utilized in a GA is effective on the convergence speed of the algorithm.A GA can use different selection mechanisms for choosing parents from the population and in many applications the process generally depends on the fitness values of the individuals.Artificial neural networks (ANNs) are used to decide the appropriate parents by the new hybrid algorithm proposed in this study.And the use of neural networks aims to produce better offspring during the GA search.The neural network utilized in this algorithm tries to learn the structural patterns and correlations that enable two parents to produce high-fit offspring.In the breeding process, the first parent is selected based on the fitness value as usual.Then it is the neural network that decides the appropriate mate for the first parent chosen.Hence, the selection mechanism is not solely dependent on the fitness values in this study.The algorithm is tested with seven benchmark functions.It is observed from results of these tests that the new selection method leads genetic algorithm to converge faster.

Object-oriented databases (OODBs) have been used for many advanced applications requiring advanced modeling power. In this paper, a locking-based concurrency control scheme is presented for OODBs. The proposed scheme reduces locking overhead for class hierarchy which is an important property in OODBs. While existing schemes show good performance only for specific applications, the proposed scheme can incur less locking overhead for any applications. For the performance evaluation of the proposed scheme, simulation is conducted using 007 benchmark. Through the simulation, the proposed scheme is compared with the two existing techniques. The performance studies show that the proposed scheme is superior to existing works.

Domain-specific data service models can retrieve critical features from frequently occurring road accident patterns (RAPs). The aim of this research is to propose scan efficient association rules’ mining-based pattern analysis which provides more accurate RAP prediction in frequent accident locations with the fastest matching pattern search from a RAP database (RAP DB). Association rules’ mining technique derives a correlation between frequent RAP and association among various attributes of a road accident. While the clustering technique discriminates different RAPs, Naïve Bayes Classification classifies and then predicts the severity of accident using Fuzzy Inference Engine (FIE) interfaced with RAP Case Library (RAP CL) using hybrid intelligence. The results of the proposed road accident data service model prove a significant increase in the accuracy of accident prediction compared to the reported results. A novel hybrid learning algorithm, interfaced with Scan Efficient Apriori (SEA) algorithm implemented, leads the fast RAP search from the first scan through RAP CL and retain new RAP in the RAP CL using case-based reasoning (CBR) during subsequent scanning. Thus, the RAP miner built proves road accident prediction using SEA, FIE and CBR with the highest accuracy and fast RAP set processing.

Road accidents can have a profound and often life-altering impact on the victims involved. Reducing severity due to road accidents is crucial even when the absolute numbers are relatively low. The problem at hand revolves around the need to ascertain the degree of accident severity at locations identified as hotspots, thus requiring focused interventions to improve road safety. This study aims to identify road accidents hotspots of an inter-urban expressway in Malaysia, and to determine the level of accident severity at locations identified as hotspots. This involves visualizing and analyzing the spatial distribution of road accident data to identify the hotspot locations of road accidents along the expressway. The study employed ArcGIS as a platform for data visualization and analysis. The evaluation of accident hotspots by accident severity level was conducted using Kernel Density Estimation (KDE). Learning from each incident and implementing changes can help prevent future accidents. Targeted safety measures and interventions to mitigate the risks associated with specific locations is crucial in reducing the likelihood and severity of accidents.

Road accident analysis is a crucial technique for determining what elements contribute to collisions and can help lower the accident rate. The consideration of sight distance is a crucial component of highway geometric design in order to guarantee effective traffic operations with the highest level of safety at an affordable price. Road accidents frequently result from reduced visibility caused by foggy weather, hence there is increased interest in studying this issue. This study aims to determine and correlate sight distance, fog blockage, and their effects on traffic accidents at Jumja along Thimphu-Phuentsholing Highway (Asian Highway 48). Data gathering and prediction was aided by the usage of Geographic Information Systems and Artificial Neural Network technologies. Temperature, relative humidity and wind speed for seven years from 2017 to 2023 were considered for fog occurrence to train Artificial Neural Network. Visibility was trained and predicted for summer and winter seasons since the occurrence of fog is prevalent during these seasons. As a result, a correlation value R of 0.998 was found, proving the findings to be almost accurate. This study offers a thorough investigation of how sight distance contributes to traffic accidents at Jumja region. A conclusive finding addressing the significance of sight distance as a contributing factor to traffic accidents due to fog invisibility along Jumja region was made after completion of this study.