| Topic |
Sub-topic |
| 1. Intelligent Systems |
1.1. Definition of Intelligent System within the field of Artificial Intelligence.
1.2. Intelligent products and services in the biomedical sector.
1.3. Evolution of intelligent systems: from symbolic reasoning to statistical learning methods. |
| 2. Knowledge Representation |
2.1. Knowledge-based systems.
2.2. Logical representation of knowledge.
2.3. Principles of propositional and first-order logic.
2.4. Inference mechanisms.
2.5. Applications in products and services for biomedical engineering. |
| 3. Uncertainty and Risk |
3.1. Definition in the context of biomedical engineering of engineering decisions.
3.2. Classification and types of uncertainty.
3.3. Decisions with uncertainty.
3.4. Uncertainty management.
3.5. Empirical definition of risk associated with uncertainty.
3.6. Uncertainty and risk in the biomedical sector. |
| 4. Expert Systems |
4.1. Definition and theoretical contextualization.
4.2. Types and components of expert systems.
4.3. Development of expert systems.
4.4. Deterministic models and stochastic models.
4.5. Inferential approaches.
4.6. Applications in products and services for biomedical engineering. |
| 5. Machine Learning algorithms. Regression, classification, and clustering algorithms. |
5.1. Machine learning: Definition applied to non-connectionist approaches.
5.2. Regression models.
5.3. Classification models.
5.4. Clustering models.
5.5. Data pretreatment.
5.6. Training methods.
5.7. Controlled data augmentation techniques.
5.8. Applications in products and services for biomedical engineering.
|
| 6. Neural Networks |
6.1. Definition and theoretical contextualization.
6.2. The connectionist paradigm versus the symbolic one.
6.3. Usual types and architectures.
6.4. Training methods.
6.5. Types of learning: supervised, unsupervised, reinforced.
6.6. Applications in products and services for biomedical engineering.
|
| 7. Evolutionary Algorithms |
7.1. Definition and theoretical contextualization.
7.2. Programming and evolutionary strategies.
7.3. Programming and genetic algorithms.
7.4. Genetic algorithm operators.
7.5. Applications in products and services for biomedical engineering. |
| 8. Decision Support Systems |
8.1. Definition and theoretical contextualization.
8.2. Components and development.
8.3. Relationship with intelligent systems. Complementary operation.
8.4. Verification, validation and contrast of results.
8.5. Search for the best hypothesis.
8.6. Applications of biomedical decision systems. |
Assignments
Practical implementation of an intelligent system on products and services in the field of biomedical engineering.
Throughout the assignments, students will be required to design, develop, and conceptually test a new intelligent system that incorporates, at a minimum, a symbolic or statistical inference model. Afterwards, they must apply it as a tool to support clinical decision-making. |
1. Definition of the problem within the biomedical engineering sector.
2. Evaluation of its relevance and integration with an intelligent product or service.
3. Search for solutions in the field of artificial intelligence.
4. Identification of criteria, variables, descriptors and any other relevant information.
5. Proposal of conceptual diagram of solution and evaluation of data flow.
6. Implementation of the solution.
7. Validation of results.
8. Dissemination, communication and presentation of the proposed solution. |
