AI Use Cases
Identify performance and risk for pilots through flying patterns and other data
Identify performance and risk for pilots through flying patterns and other data. Similar analysis can be done on road drivers although the data is inevitably more likely to be complicated by ground-level interactions that would be more traceable in the air (e.g. other vehicular movement).
Identify performance and risk for employee drivers through driving patterns and other data
Identify performance and risk for drivers through driving patterns and other data. This can be used for a variety of drivers including those of taxis, HGV or delivery vehicle operators.
Search for and challenge inbuilt bias in algorithms
Search for inbuilt bias in algorithms will be a growing field. This will be driven by growing regulatory, press interest, consumer unease, potential legal challenge and a need to avoid black box AI. Management teams will also want to understand algorithm outcomes to ensure that the business is being optimised appropriately.
Monitor vital signs through CCTV to detect abnormalities
Whether babies in cots, horses in stables or indviduals in hospital beds CCTV can be used to monitor behaviour, stance and audio to predict potential issues or healthcare related abnormalities. Predictive messages can then be sent to trigger human intervention. CCTV reduces some of the issues associated with wearables although clearly only works in defined spaces.
Detect suspicious nautical vessel activity indicating overfishing or smuggling
Using image and location tracking data to identify suspicious behaviour patterns by nautical vessels that might indicate, for example, over-fishing. This would also include multi-vessel activity to predict load transfer. Similar technological approaches might be used to identify other nautical malfeasance such as smuggling.
Monitor transport fleet networks in real time to ensure safety of passengers and drivers
The roll out of peer to peer transport apps creates potential security risks, particularly in markets where personal checks on users and drivers are less developed. Automated systems will highlight beahvioural anomalies that may indicate a developing security or health situation and trigger both back-up enquiries and potentially further action.
Detect fake biometric credentials
The rise of biometric-based security systems poses risks that fake credentials - photographs, scans, copies or even post-mortem presentation - may be offered to fool security systems. Image recognition is used to scan for and observe minute differences that may suggest the credentials are invalid.
Predict hazardous locations and establishments based on open source data
Location and establishments hazardous to consumers and individuals might include restaurants, illegal businesses, areas prone to crime and violence and others. Hazards may be medical, environmental, human-caused or other natural phenomena.
Identify individual's activity likely to result in accidents
Typically using video or camera technology to spot individuals whose activity is at risk of causing accidents or other problems. Relevant images will be flagged for potential further intervention.
Identify items of concern in the mail
Volumes of mail are such that it is almost impossible to consistently check for items of concern - whether smuggled drugs or packages of suspicious substances likes anthrax. Using X-rays or similar sensor technology large volumes of images can be processed to indicate which items of mail should be properly investigated.
Confirm animal identity through eye scans
HIgh value animals can need identifying at critical moments - for example to ensure that the right horse has been entered in a race or has been provided to stud. Individual eye scans are kept on record and then a portable scanner can be used to ensure that the right aninal is present.
Stress test biometric seurity systems
The proliferation of security systems reliant on biometric sensors creates a need for these to be stress-tested. One way of doing this is the creation of faked credentials to fool the system. Clearly there is also a potentially criminal aspect to this work.