Artificial Intelligence in Biomedical Engineering

Explore the basics of artificial intelligence for tracking health and emotions

The objective of the course is to provide the students with hands-on experience in artificial intelligence applications for developing biomedical instrumentation. We will study what artificial intelligence is, its current uses, potentialities, challenges, and risks, in a practical and simple way. We will explore some algorithms and mathematical models that help machines "learn" and make decisions, including decision trees, support vector machines, and neural networks. From deep learning models, which are multi-layered neural networks, we will explore the amazing applications, and how can be used for detecting diseases. The students will be able to build their own artificial intelligence models using available data and data that they will collect in a simple experiment.

Students will understand what exactly artificial intelligence is, and will be able to explain the functioning of widely used machine learning algorithms. Students will be able to identify the applications of machine learning in biomedical instrumentation and its future opportunities in this field all through hands-on experiences in training artificial intelligence models.

Sessions Offered

Session 3: July 9 – July 15


Residential, Non-Credit

This class is meant to be immersive and students will:

  • Learn the basics of artificial intelligence, including several machine learning algorithms
  • Understand the applications of artificial intelligence to biomedical instrumentation
  • Apply concepts of artificial intelligence in practical projects

Meet the Professor


Hugo F. Posada-Quintero,

Assistant Professor in the Department of Biomedical Engineering

My research includes the development of signal processing techniques, wearable instrumentation, and sensors for biomedical applications. Specifically, the aim of my research is to develop models and biomedical instrumentation for the detection and prediction of stress, fatigue, pain, emotional state, hydration status, wakefulness, cognitive performance, and heart failure, among others. We use modern mathematical tools to process bioelectrical signals obtained from different sites of the body, like the electrocardiogram, electromyogram, photoplethysmogram, and electrodermal activity, and explore the relationship between those signals and the biomedical variable being detected or predicted. Our mathematical processes are focused on the development of more sensitive biomarkers and features, and the development of multimodal algorithms (multiple signals combined). In addition, we use our novel features and train artificial intelligence tools (machine learning and deep learning algorithms) for the development of more accurate models. Furthermore, we develop novel sensors and electronic devices to better capture electrophysiological signals using portable and wearable devices.