Courses at the Department of Intelligent Systems Engineering
Our courses in Intelligent Systems Engineering will help you build the world of tomorrow. Learn about the cyber-physical systems that form the bedrock of our growing "smart" world or how bioengineering can lead to better healthcare and fight disease. Discover how machine learning can improve signal processing to create more effective wearable technologies, or use information visualization and advanced robotics to solve real-world problems.
Software Systems Engineering
Critical engineering in areas such as high performance computing, robotics, real-time (eg. collision avoidance) or embedded (eg., medical implantation control, internet of things, etc) systems requires a low-overhead language that allows you to directly interact with, understand, and control hardware. The two main languages enabling this type of detailed hardware control are low-overhead C/C++ and assembly, and Software Systems Engineering teaches the applied software skills students need to work in such environments.
Systems, Signals, and Control
Signals are all around us, both in the natural world and in our engineered systems: the sequence of tones that make up your favorite song, the ebb and flow of traffic, the rise and fall of the stock market, the temperature over the course of a day, a week, or years. This course introduces students to fundamental principles of signals, and how they are represented, analyzed, and transformed. This course lays the foundation for students interested in telecommunication, signal processing, or control theory.
Nanoscale Simulation and Engineering Applications
This course will introduce students to the basics and applications of computational modeling and simulation in the sciences and engineering. Deterministic methods including particle dynamics simulations are covered in detail. Students will apply modeling and simulation to design and analyze properties of material systems at the nanoscale, becoming familiar with current research in nanoengineering.
Graduate and Undergraduate Cross-listed Courses
Robots are becoming an everyday part of our lives, and this course introduces foundational concepts for physical robotics, and how we model and control the motion of actual robotic devices from vehicles to smart prostheses. Students will learn tools for describing, analyzing, simulating, and controlling robots while applying theory both to simulated and physical robotic systems.
Simulating Cancer as an Intelligent System
Cancer can be viewed as an adaptive intelligent system, where renegade cells break the rules, reuse the body’s natural processes to re-engineer their environments, and evade treatments. Using computational models, we explore this perspective and the potential for future clinicians to plan treatments with data-driven models.
This course teaches the basic principles of human cognition and perception, as well as techniques and algorithms for designing and critiquing scientific visualizations in different domains (neuro, nano, bio-medicine, IoT, smart cities). Students earn hands-on experience using modern tools for designing scientific visualizations that provide novel and/or actionable insights and work with 3D printing and augmented reality deployment while gaining teamwork/project management expertise.
Introduction to Cyber-Physical Systems
Cyber-Physical Systems (CPS) integrate computation, networking, and physical processes. The CPS involve transdisciplinary technologies and are typically regarded as "smart" systems. This course covers a broad range of CPS with both uses and component technologies. Computational algorithms, dynamical systems, control, formal analysis, sensor networks, and mechanical construction issues will be included. Particularly, topics related to real-world applications such as autonomous systems will be discussed. Lab sessions and hand-on experience are essential aspects of the course.
Introduction to Bioengineering
Introduction to Bioengineering provides the fundamental biological concepts governing the organization of living organisms, key concepts and definitions in cell, molecular, and microbiology, cell division, and cell differentiation into tissues and organs. Each topic is presented with a bioengineering application to provide a merger of the disciplines of engineering and biology.
Machine Learning for Signal Processing
The intersection of machine learning and signal processing is the focus of Machine Learning for Signal Processing, providing an insight into basic and advanced machine learning models, as well as various hands-on experiences in broadly defined signal processing systems. Examples of the intelligent systems related but not limited to the course include: image segmentation, speech/music processing, human activity detection from smartphone sensors, sentiment analysis on the Internet text streams, and more.
Deep Learning Systems
This course teaches the pipeline for building state-of-the-art, deep learning-based intelligent systems. It covers basic neural network theories as well as general training mechanisms in the context of Python GPU computing libraries, such as Tensorflow and PyTorch. The course also aims to cover various application areas of deep learning.
Image Processing for Medical Applications
Learn how to develop intelligent algorithms and software for medical imaging that can improve patient care while helping researchers understand how the body functions. Students will be familiarized with algorithms for registration, tracking, de-noising, warping, segmentation, model fitting, and interactive visualization of medical datasets. Techniques such as Fourier analysis and unsupervised, supervised and reinforcement learning will be used to build these applications. We also will use datasets from different medical domains, including advanced MRI images of the brain and images from optical tomography and histology.
Information Visualization provides an overview of the state-o-of-the-art and teaches visualization theory and the process of producing effective and actionable visualizations that take the needs of users into account. Students apply the visualization knowledge and skills that they gain in the course by working in teams on real-world client projects.
This graduate level course covers a selected set of important and popular robotics planning and learning topics. Specifically, the course teaches robotic motion control and planning, decision-making, state estimate—such as the simultaneous localization and mapping (SLAM) —reinforcement learning, and networked multi-robot coordination. Students develop projects using the Robot Operating System (ROS) in Linux environment.
What is possible in biomedical engineering today, and what are the future challenges? Learn about the current research front in tissue engineering and regenerative medicine, neuroengineering, synthetic biology and computational synthetic biology.