Seminar pattern recognition and machine learning for human activity
UE-SIN.07807
| Teacher(s): Abou Khaled Omar, Mugellini Elena |
| Level: Master |
| Type of lesson: Seminar |
| ECTS: 5 |
| Language(s): English |
| Semester(s): SA-2015 |
Developing autonomous systems that are able to assist us in everydays tasks is one of the grand challenges in modern computer science. In fact, the availability of a system capable of automatically classifying the activity performed by a human is extremely attractive for many applications in the field of healthcare monitoring, surveillance, advanced human-‐machine interfaces, etc.
The objective of this seminar is to study some of the latest advances in pattern recognition together with
the related machine learning algorithms. A particular emphasis this year will be given to advances in analysis of people, human actions and interactions. The seminar will have a strong practical component as the students will investigate the various steps and the different pattern recognition and machine learning techniques applied to different business domains (health, financial, biometrics, security and surveillance,
interactive applications and environments, etc.).
The objective of this seminar is to study some of the latest advances in pattern recognition together with
the related machine learning algorithms. A particular emphasis this year will be given to advances in analysis of people, human actions and interactions. The seminar will have a strong practical component as the students will investigate the various steps and the different pattern recognition and machine learning techniques applied to different business domains (health, financial, biometrics, security and surveillance,
interactive applications and environments, etc.).
Training aims
Identify and describe existing pattern recognition and machine learning approaches for different human interaction modalities (voice, gesture, etc.)
Discuss and compare different methods for activity recognition along with their strengths and weaknesses
Evaluate and select the best machine learning approach for the recognition of specific activity
Compare and identify the best technological solution for designing and implementing a complete activity recognition system based on machine learning approach
Identify a set of business use-‐cases using machine learning technology and discuss related advantage and drawbacks
Discuss and compare different methods for activity recognition along with their strengths and weaknesses
Evaluate and select the best machine learning approach for the recognition of specific activity
Compare and identify the best technological solution for designing and implementing a complete activity recognition system based on machine learning approach
Identify a set of business use-‐cases using machine learning technology and discuss related advantage and drawbacks