Application of
data mining, real-time monitoring and visualisation techniques to allow prediction and mitigation of risks in
flights before safety events occur (proactive safety management).
This project focused on integration
of data from different sources (airport and airline data) and from different databases (safety-related data and
operational data) in order to identify robust predictors of outcome variables by applying advanced analytics and
visualisation techniques. The aim of the project is to contribute to stakeholders’ capacity to intervene
proactively on predicted risks by providing a technology solution that supports the identification and
implementation of automatic notification barriers to alert operators of impending safety threats.
We
delivered the pattern matching and performance management components of our state of the art safety
management system that provides functionality for data collection, real-time data processing, visualisation,
notification and alerting to inform crews, flight planners and other decision makers about increased levels
of risk before a flight takes off.
The solution included the following features:
- Integration of safety and operational data across different databases and
different stakeholders
- Application of advanced data mining techniques to detect
-
- patterns of variables (risk patterns)
- combinations of values that affect the likelihood or severity of
safety events
- Continuous monitoring of safety and operational performance indicators
- Matching of performance indicators to risk patterns identified from historical
data
- Automatic notification module informs relevant stakeholders of any patterns or
alarms that were raised by the risk pattern matching function
- Completely customisable dashboards with charts, gauges, counters and data
lists
- Multiple dashboards: private or shared dashboards
- Flexible searching and filtering
- Sophisticated data cube techniques to explore, drill-down or roll up data
(similar to pivot tables in spreadsheet products)
- Limitless scalability without impacting on performance
2019-12-20
Safety performance management – Eurocontrol
You are here:
Home
/
Portfolio / Safety performance management – Eurocontrol
Safety performance management – Eurocontrol
Development,
deployment and support of a safety risk monitoring solution for European regulatory bodies and for state air
navigation service providers.
Traditionally, safety performance is
measured by the use of reported accidents and incidents that compromise certain specified safety criteria in a
number of operational areas. A drawback with such measurements is that they can distort the subsequent
mitigation efforts by focusing on the performance of a particular local safety measure, rather than considering
an integrated system-wide measure. A system-wide indicator is required from which long term trends can be
identified for better risk management. In collaboration with EUROCONTROL and Aloft Aviation Consulting,
Corballis has participated in the development of a performance monitoring tool that combines multiple KPIs
through an innovative process of aggregating data based on data relationships and assessments of influence of
KPIs within the operational system.
The application imports mandatory
safety incident data and aggregates it to represent a single view of air traffic safety across Europe. This
is achieved by aggregating multiple operational safety risks, expressed as the sum of reported incidents, in
a weighted manner, into one value that can vary over time. It was designed to support European and national
safety policy changes across Europe.
The performance monitoring tool includes:
- easily definable performance objectives and goals
- implementation of the EUROCONTROL APF methodology
- interactive dashboard with charts, gauges, counters and data lists
- sophisticated visual data cube techniques (similar to pivot tables in
spreadsheet products) to explore, drill-down or roll up data
- KPI data importer for easy connection to existing data sources or uploading of
files (Excel, CVS)
- innovative definition of the KPI hierarchy using mindmaps
- export support to a wide range of file formats and APIs
2019-12-20
Border security passenger screening
You are here:
Home
/
Portfolio / Border security passenger screening
Border security passenger screening
Development of
a border security passenger screening application for an international client and border security agency.
Passenger screening and risk
profiling can be unpredictable by nature and require fast response times. This information is not always
accurate. Data sources are diverse e.g. immigration systems, national watchlists, traveller records/history,
visas as well as external sources such as Interpol’s lost and stolen records. Corballis’ client requested us to
implement a real-time and scalable passenger screening system that can be integrated with various data sources
and provides response times in the milliseconds range.
We delivered a custom analytic
tool which aids border security agents to analyse connections between passengers and targets in near
real-time. The implemented system architecture allows border security agencies to handle hundreds of
millions of passenger records each year without any impact on the system’s performance. The solution
leveraged Corballis’ innovative graph visualisation library, which supported the graphical representation of
people and the connections between them in the form of a graph that can be used to execute complex search
queries, revealing hidden patterns and linkages. This tool allows users to search and view visualisation
networks in near real-time.
Analytics services included:
- Advanced passenger screening module based on a distributed NoSQL and graph
database
- roles and responsibilities
- Integration with third party data sources (watch lists, lost and stolen
records, immigration systems, etc.)
- Automatic data quality management (data cleansing, de-duplication, auto
correction of mistakes, validation, etc.)
- Advanced searching capabilities (fuzzy matching, “more like this” querying,
etc.)
- Target profile management
- Scalable architecture
The Corballis visualisation library supported the following functions:
- Accessing of huge amounts of data in easily digestible visuals
- Interactive visualisations make it easy to explore and analyse large
quantities of passenger data
- Highlighting of exceptions and outliers
- Customisable flight and passenger network visualisation
- Intelligent layout mechanisms to make sense of data easily
- Rich set of interactive controls
- Zooming, panning, drag & drop support
- Dynamic filtering of the visualisation to allow drill-down and roll up
operations
- Export the visualisations to a wide range of formats (images, JSON, PDF,
etc.)