1st Open Call
- Correlation analysis. Techniques and algorithms will be developed to allow the correlation between accident data and road morphology to obtain the main KPIs identified.
- Simulation of road safety. It will be possible to carry out simulations, by means of modifications in the parameters of the road morphology, so that based on the analysis and correlations of historical data, possible accidents that can occur are predicted.
3. Awareness of the user. Through the correlation of data, alerts will be created to make the user aware of the risk on the road. A database of alerts will be created so that they can be displayed in a presentation layer in the RACC Infotransit APP.
Maybe to perform a correlation analysis it is necessary to previously carry out a process of data inference in order to establish links between the data sets. Likewise, and due to the previous analysis we have carried out, the identification of possible causes of accidents can be distorted due to lack of information such as the state of the road.
We will have other data sets in addition to those provided by the RACC to expand the information if necessary (providers: National Department of Traffic (DGT) and Government of Catalonia).
We’ll use a standard methodology already tested and widely used: Cross Industry Standard Process for Data Mining (CRISP-DM). Phases:
1) Business understanding: Understanding the project objectives and requirements from a business perspective, and then converting this knowledge into a big data problem definition.
2) Data understanding
Initial data collection and proceeds with activities in order to get familiar with the data, to identify data quality problems, to discover first insights into the data, or to detect interesting subsets to form hypotheses for hidden information. Also define the final metrics as KSI (Killed and Serious Injured), RI (Risk Index), AADT (Annual Average Daily Traffic Flow), high accident road sections (black spots) and other metrics obtained by correlation.
3) Data preparation
This phase covers all activities to construct the final dataset from the initial raw data. Also we include the data ETL process.
A modelling techniques is selected: Clustering, Classification, Regression, Association
Evaluate the model data quality.
The knowledge gained will need to be organized and presented in a way that is useful to the customer.
Solvent is an IT company that provides technological support and business development services, for companies in various sectors of activity, in the following areas:
- Consulting and Projects:
- Optimization of business processes.
- IT transformation plans.
- Strategic project consulting.
- Project Management Office (PMO).
- Project management for the implementation of business management systems (ERP, CRM, …).
- Development of customized software in desktop, web or mobility environments.
- Integration of applications and corporate management systems.
- Application maintenance.
- User support.
- Advanced Data Analytics:
- Complex data modeling.
- Business Intelligence Solutions.
- Big Data applied to the business.
- IoT, Industry 4.0.