Road Traffic Accident Prediction is really widely necessary element that affects the premature death of lots of people and also have the losses of property which is either public or private. Traffic road safety basically is a word which is related to the proper planning and the executing the various approaches to reduce the cause of road traffic accidents. Road traffic accident survey is really most essential to pick out diverse elements connected with road accidents that can surely help in decreasing the accident rate. The homogeneity of road traffic accident data is major problem in traffic road safety survey. Primarily in this paper we are using decision tree, random forest classifier on a current traffic road accident data. Although, in these defined procedures they are efficiently fitted to pull out homogeneity of road traffic accident data. Several studies center on procedure of road accidents. Other elements put in weather and light conditions of the road. Road accident harshness keeps on changing over a period of time and also expand infinitely. Hence in this study we basically examined latest works, data mining methodologies and tools that were demonstrated better in accident factual data analysis and prediction. We also made a web app using flask to deploy our machine learning model and use this app to predict and send a message to alert the user.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Traffic improvisation by identifying the accident locations using ML/Data mining approaches


    Contributors:


    Publication date :

    2022-12-16


    Size :

    4640887 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Identifying Accident-Prone Locations Using Fuzzy Pattern Recognition

    Sayed, T. / Abdelwahab, W. / Navin, F. | British Library Online Contents | 1995



    Using Accident Correctability to Identify Accident-Prone Locations

    Sayed, T. / Navin, F. / Abdelwahab, W. et al. | British Library Conference Proceedings | 1995