Fuzzy Matching
programmes; or, the implementation of
automated identification systems for
trusted travellers.
Existing Challenges
Another issue in passenger screening
is that those entrusted with the task
are frequently poorly educated and
lowly paid. Accordingly, we cannot
have high expectations of the
motivation level and accuracy of the
screening staff. Security test results
indicate that screening processes are
certainly not foolproof; there is always
a percentage of tests that fail,
highlighting the vulnerabilities of the
system. And, it shouldn’t be forgotten
that personnel integrity seems to be a
problem in many locations.
So, how can we ensure that the “bad”
guys and girls are actually caught in the The Google search engine uses a form of ‘fuzzy searching’: even if you make a typo,
screening process? How can we be sure to it presents documents that may still match your needs
filter the needles from the haystack?
Remember, we are not only looking for is collected. works: even if you make a typo,
(potential) terrorists, but also for The good news is that most processes are Google presents you documents that
scam artists, illegal trespassers, and digital nowadays. The bad news is that most may still match your needs.
regular criminals. information is not centrally stored. Even “Fuzzy logic” is an instrument in
Adding more screening staff and better within one airline there are multiple differentiating passengers based on
scanning technology, whilst providing systems dealing with the different characteristics that may be imprecise,
improved training and better quality control processes, which is historically grown. absent, or wrong, let alone process valid
processes will probably help decrease the Although the information flows swiftly from data. Fuzzy logic is applied in matching
percentage of “false negatives” (letting one system to another, it does not mean (known) passenger data with risk profiles.
through passengers that should have been that all information is structured in the Matching with fuzzy logic is
caught), but it is unrealistic to think we will same way, or even has the same definition. particularly useful for finding
ever be watertight. Let alone the fact that the positive information that best fits multiple,
All the trends point in the direction of identification of passengers is hard to complex conditions. Unlike regular
rising costs, an increasing number of achieve, especially remotely. It is only database searches, which offer
passengers, lack of sufficient space for recently that passport number recording limited results when there are too
requisite security processes, and has become part of the check-in process. many criteria and too many results
increasing security requirements. Aviation when there are not enough criteria,
and border security agencies face some The Case for Fuzzy match technology thrives in complex
serious challenges. Along with this, the Searching
cost related to security will increase year These issues pose serious challenges
after year tremendously, especially if for traditional databases and queries
screening processes are not conducted in thereof, a problem exacerbated by the
“…fuzzy searching
a smarter way. vast amount of data that is turned
around in a daily airport operation.
means searching
Differentiation Given that data may well be wrong
Part of the “smarter way” is to use (eg. name typos or self-supplied
according to fuzzy logic
available information on air travellers for data), imprecise (eg. how many
differentiation. This will enable a different industry names exist for
rules, which is based on
differentiated approach to screening ‘business class’), or absent (what is
different groups of people. required in one country may not be
the principle that there is
Differentiating passengers based on the required in another), the application
available information at a certain point in of “fuzzy” searching is necessary.
not only an exact match
time is not an easy task. In the world of Fuzzy searching means searching
aviation, information is collected at many according to fuzzy logic rules, which is
with the search criteria,
different times in the process, by a variety based on the principle that there is
of parties: at the time of booking, time of not only an exact match with the
but also a degree of
payment, ticketing, check-in, arrival at the search criteria, but also a degree of
airport, and luggage drop off, information approximation. Much like Google
approximation…”
Aviationsecurityinternational April 2008 www.asi-mag.com 23
Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44