Educational objectives General Objectives:
The objectives of this course are to present a wide spectrum of Machine
Learning methods and algorithms, discuss their properties, convergence
criteria and applicability. The course will also present examples of
successful application of Machine Learning algorithms in different
application scenarios.
The main outcome of the course is the capability of the students of
solving learning problems, by a proper formulation of the problem, a
proper choice of the algorithm suitable to solve the problem and the
execution of experimental analysis to evaluate the results obtained.
Specific Objectives:
Knowledge and understanding:
Providing a wide overview of the main machine learning methods and
algorithms
for the classification, regression, unsupervised learning and
reinforcement learning problems. All the problems are formally defined
and theoretical basis as well as technical and implementation details
are provided in order to understand the proposed solutions.
Applying knowledge and understanding:
Solving specific machine learning problems starting from training data,
through a proper application of the studied methods and algorithms. The
development of two homeworks (small projects to be developed at home)
allows the students to apply the acquired knowledge.
Making judgements:
Ability of evaluating performance of a machine learning system using
proper metrics and evaluation methodologies.
Communication skills:
Ability of writing a technical report describing the results of the
homeworks, thus showing abilities in communicating results obtained from
the application of the acquired knowledge in solving a specific problem.
Being exposed to examples of communication of results obtained in
practical cases given by experts within seminars offered during the course.
Learning skills:
Self-study of specific application domains, problems and solutions
during the homeworks, with possible application of teamwork for the
solution of specific problems.
|
Educational objectives One course of the student's choice
|
Educational objectives The course aims to provide the analytical bases functional to the evaluation models and design methods
related to the "planning and verification of Critical Infrastructures (CIs)", understood as a service referable
primarily to mobility infrastructures, more generally, to complex systems where risk analysis is required to
verify safety conditions (general target). The main topics are:
Asset System Definition and Characterization (knowledge and understanding)
The definition of data collection for Critical Infrastructures (CIs, i.e. roads and railways) and their functional
classification is based on fixed target set (i.e. public transport, cargo and dangerous goods transport,
mobility) and on operational continuity (internal and external interdependencies) both in ordinary
conditions and in emergency. The resulting operational classification of critical points, according to the
guidelines on CIs monitoring and maintainability in order to operational classify in warning classes, is the
actual proposal compliant with critical component classification to define durability (Assets’ Age) and
vulnerability to hazards. Consequently impact analysis of functional unavailability on services continuity
(evaluation of interconnections and alternative paths) is derived to investigate redundancy and verify
alternative paths to guarantee services continuity. Results imply the definition of critical points ranking. In
addition, the scenarios analysis, based on Initiating Events (i.e. seismic event, fire event, both natural and
anthropic hazards), is proposed to quantify the hazard flow versus exposed people, services and assets. The
hazard identification for critical points allows mapping of hazard indicators.
Learning achievements (applying knowledge and understanding):
1: CIs: data collection and their functional classification based on target set (i.e, public transport, cargo and
dangerous goods) and operational continuity (internal and external interdependencies) both in ordinary
conditions and in emergency.
2: CIs: analysis of critical points according to the guidelines on CIs monitoring and maintainability in order
to operational classify in warning classes.
3: CIs: Impact analysis of functional unavailability on service continuity (evaluation of interconnections and
alternative paths).
4: CIs: Ranking of critical points. Scenarios analysis based on Initiating Events (i.e. seismic event, fire event)
to quantify hazard flow versus exposed people, services and assets.
5: CIs: hazard identification for critical points (Hazard Indicators mapping).
Multi-hazard risk assessment of infrastructure networks and assets (knowledge and understanding)
Main knowledge derives from a comprehensive multi-hazard risk assessment framework to be used for
linear critical infrastructures (i.e., road and railway networks, oil and gas pipelines, distribution networks
for energetic purpose, hydraulic networks for civil purposes, as well as point-like infrastructures). The
reliability analysis results by scenario simulations referred to multiple hazards, analysis of the interactions
between different hazard sources, domino effects and interdependencies between CIs component.
Risk Evaluation: Quantitative Probabilistic Risk evaluation is directed towards the question of acceptability
and the explicit discussion of safety criteria. For a systemic and operable risk evaluation one has to define
safety criteria and to determine whether a given risk level is acceptable or not. In other words risk
evaluation has to give an answer to the question “Is the estimated risk acceptable?”
Risk and Safety Management: If the estimated risk is considered as not acceptable, additional safety
measures have to be proposed. Therefore the effectiveness and also cost-effectiveness of different safety
measures can be determined by using the initial frequency and consequence analysis of the scenarios
which will be positively or negatively affected under the assumption that the investigated safety measure
has been implemented.
Learning achievements (applying knowledge and understanding):
1: Development of multi-hazard risk assessment for road and railway networks, including main types of
consequences that can be analyzed in a critical infrastructure risk assessment.
2: Quantitative probabilistic risk assessment: fault tree and event tree analysis, multi-hazard scenarios
analysis, fire and evacuation simulation for road and railway tunnels
3: General model for interactions and interdependencies among components of the same critical
infrastructure as well as with components of other types of critical infrastructures is defined. Consequently
integrated framework for the multi-hazard risk assessment of CIs will be set up accounting also for
interactions and interdependencies.
Integrated Technologies and Solutions for Holistic Risk Reduction & Resilience Enhancement (knowledge
and understanding)
Main knowledge derives from holistic integrated solutions addressing an overall protection of roads and
railways. Safety is investigated at different levels: starting from single asset (road or rail and their critical
points) to global network (interconnections and alternative paths), with focus on interdependencies and
domino effects, considering multi-risks natural or accidental and will be addressed through development of
open knowledge-sharing tool.
|
Educational objectives
Apprenticeship
|
Educational objectives Final dissertation
|
