CPS CASE STUDIES ECPS 209, Course Code: 15220 Quarter: Winter Quarter 2020

Course Description

ECPS 209: Cyber-Physical Systems Case Studies (4)
Covers CPS case studies in applications such as (but not limited to): automotive and transportation, manufacturing, power distribution grid, medical and healthcare, robotics, civil infrastructure, avionics.
Restriction: Graduate students only.

Course Resources

• Course web site at
  http://newport.eecs.uci.edu/~doemer/w20_ecps209/

Course Contents

Module	Topics
1	Artificial Intelligence (AI) and Machine Learning (ML) AI/ML: The Same Difference? This module will introduce the basic concepts and definitions of AI/ML. In addition, we will demystify the technology and highlight the capabilities this toolset provides. We will dive into actual examples in healthcare, finance, and art. Machines Think Differently To truly unlock the value from AI/ML, this module will cover the need to think beyond automation and how to find true innovation. To accomplish, we will explore how machines think, and more importantly think differently than humans. From self-driving cars to original food recipes, machines have great strengths and limitations that we will learn how to exploit or avoid. The Data Challenge Data is the fuel for AI/ML. How much is enough? Which data is truly meaningful? What happens if we don't have (enough) data? This module will dive into the data challenges, and what options we have to deal with them. The Power & Peril of Training AI/ML requires training to do anything. We will learn the different training strategies, when to apply them, and how to curate content continually. More importantly, we define how to establish the key element of AI/ML training: The Ground Truth. Building Responsible AI Google Vision initially couldn't recognize women or non-Caucasian nationalities as people. Amazon created an AI recruitment tool that was sexist. How did these things happen? This module will dive into the new type team needed to develop AI/ML solutions. More importantly, we will discuss the need for diversity and inclusion in teaching the machine to reduce the amount of implicit bias in our solutions. AI/ML: The Platform for Emerging Tech AI/ML is already going beyond a toolset to a foundational platform technology. Other emerging technologies like VR and Blockchain are integrating AI/ML technology to build more robust solutions. For example, imagine an astronomy VR educational module augmented by AI to create an interactive, personalized experience for a 6th grader. This module will dive into how these technologies are being integrated, and how to identify opportunities by combining technology.
2	Smart Home: Applied Residential Systems Motivation: The number of 'smart' devices in a home is increasing dramatically. Understanding the numbers and types of devices, communication methods and protocols, physical challenges via layout and building materials, typical use cases, protocol conversions and connectivity to the IP world are all building blocks to developing next generation devices. A review of the strengths and weaknesses of the various devices and means will help prepare the student for developing future systems. Overview: The proposed course will provide an applied understanding of the various protocols (and why there are so many), transmission methods and signaling propagation through a compare and contrast perspective. At the end of the course, the student will be able to select and implement a home automation solution based on a specific use case. Prerequisites: Undergraduate courses in device communications theory. Tentative Topics: Common signaling methods, Physical propagation challenges, Device message propagation, Common communication languages, Device performance and scalability, Data privacy in-home and out. Alternative Topics: Energy consumption vs device responsiveness, Cloud infrastructures and back end data flow, Use case explorations and evolutions, Effects of Silicon Development on device size and power consumption, Challenges of device interaction and compatibility, Challenges of device interactive logic and the consumer ("programming" a home), Challenges of device physical installations. Assessment Method: Module Paper due at end of module.
3	Smart and Connected Health Overview and Goals: Cyber-Physical Systems (CPS) and Internet-of-Things (IoT) technologies are remodeling the healthcare sector in terms of social benefits and penetration as well as economics. Enabled by ubiquitous computing, all the healthcare system entities can be monitored and managed continuously. These technologies allow remote monitoring and tracking of patients living alone at home or treated in hospitals. Data generated from sensors attached to patients is made available to doctors, family and interested parties giving them the ability to check the subject's vital signs and contextual information from anywhere at any time as well as performing intelligent decision making to assist healthcare workers. However, remote healthcare minoring systems necessitate a higher degree of dependability, accessibility, efficiency, and robustness, compared to the IoT applications in other sectors. In this module, state-of-the-art will be presented in detail including background from the recent years. The module aims at covering different key aspects of general-purpose IoT technologies as well as the recent achievements in the context of e-health systems including low-latency and real-time application requirements, interoperability, reliability, federation, energy efficiency, mobility, hierarchical Fog-assisted computing and data analytics, geo-distribution and context awareness, and the notion of Internet-of-Cognitive-Things (IoCT). Moreover, several case studies on remote health monitoring solutions (e.g., smart pain assessment, remote maternity care, and early warning for cardiovascular diseases) will be covered in the course to better demonstrate the real-world challenges in realizing these solutions. It will also provide a basic understanding of vital signs and bio-signal processing as a new skill set for students.



• Note that contents are tentative and may change!
• Please see the Schedule page for up-to-date scheduling information.

Course Policies

• Instruction:

  This course is coordinated by the instructor of record who covers 1 week of instruction and is responsible for the overall grade assignment.
  Three modules are delivered by dedicated instructors with expertise in their respective CPS areas.

• Attendance Policy:

  Attendance and active participation is required. It is the student's responsibility to make up for any missed instruction or assignments. Substitute assignments or exams will only be arranged for absence due to documented medical (or similar) reasons. Proper documentation is required.

• Exams:

  Each module ends with an exam that is graded by the module instructor. The instructor of record collects the scores, determines the final letter grade, and submits that to the registrar.

• Grading Policy:

  The final grade for the course will be determined based on participation and the scores achieved in the modules, as follows:
  • 10% Participation and attendance
  • 30% Module 1 exam (and assignments)
  • 30% Module 2 exam (and assignments)
  • 30% Module 3 exam (and assignments)

• Academic Honesty:

  Academic honesty is a requirement for passing this class. Any student who compromises the academic integrity of this course is subject to a failing grade. Academic dishonesty includes, but is not limited to copying answers from another student, allowing another student to copy your answers, communicating exam answers to other students during an exam, attempting to use notes or other aids during an exam, or tampering with an exam after it has been corrected and then returning it for more credit. If you do so, you will be in violation of the UCI Policies on Academic Honesty (see Academic Integrity). It is your responsibility to read and understand these policies. Note that any instance of academic dishonesty will be reported to the Academic Integrity Administrative Office for disciplinary action and is cause for a failing grade in the course.