Page 32 - ITU-T Focus Group on Aviation Applications of Cloud Computing for Flight Data Monitoring - Key findings, recommendations for next steps and future work

ITU-T Focus Group on Aviation Applications of Cloud Computing for Flight Data Monitoring
Key findings, recommendations for next steps and future work

connections and/or the use of standard flash memory cards. The data from QAR is used for flight operational
quality assurance (FOQA), which is quality assurance process in the airline and often required by the authorities.

1.57 reinforcement learning (Deliverable 1): Concerned with how an agent ought to take actions in an
environment so as to maximize some notion of long-term reward.

1.58 representation learning (Deliverable 1): Representation learning algorithms often attempt to preserve
the information in their input but transform it in a way that makes it useful, often as a pre-processing step
before performing classification or predictions, allowing to reconstruct the inputs coming from the unknown
data generating distribution, while not being necessarily faithful for configurations that are implausible under
that distribution.

1.59 safety service (Deliverable 4): Any radio communication service used permanently or temporarily for the
safeguarding of human life and property.
1.60 similarity and metric learning (Deliverable 1): Learning machine is given pairs of examples that are
considered similar and pairs of less similar objects. It then needs to learn a similarity function (or a distance
metric function) that can predict if new objects are similar. It is sometimes used in Recommendation systems.
1.61 software as a service (SaaS) (Deliverable 1): Provides on top of an infrastructure as a service (IaaS)
or a platform as a service (PaaS) a specific application over the Internet, such as a Customer Relationship
Management (CRM) application.
1.62 sparse dictionary learning (Deliverable 1): A datum is represented as a linear combination of basic
functions, and the coefficients are assumed to be sparse. Sparse dictionary learning has been applied in several
contexts. In classification, the problem is to determine which classes a previously unseen datum belongs to.
Suppose a dictionary for each class has already been built, then a new datum is associated with the class such
that it is best sparsely represented by the corresponding dictionary.
1.63 support vector machines (SVMs) (Deliverable 1): A set of related supervised learning methods used
for classification and regression. Given a set of training examples, each marked as belonging to one of two
categories, an SVM training algorithm builds a model that predicts whether a new example falls into one
category or the other.

1.64 topological quantum computer (Deliverable 1): Computation decomposed into the braiding of anions
in a 2D lattice.

1.65 transmitting portable electronic device (T-PED) (Deliverable 2&3): Electronic devices, typically but not
limited to consumer electronics, brought on board the aircraft by crew members, passengers, or as part of
the cargo. T-PEDs radiate transmissions on specific frequencies as part of their intended function. T-PEDs
include two-way radios, mobile phones of any type, satellite phones, and computers with mobile phone data
connection, wireless local area network (WLAN) or Bluetooth capability.
1.66 video analytics (Deliverable 1): Collection and detection of abnormal behaviour, movement or events
via video streaming.

24