Yi Ding

Assistant Professor at UT Dallas

Course Info

Instructor: Yi Ding

Office: ECSS 4.703

Office hours: by appointment

Email: yi.ding@utdallas.edu

Lecture: 8:30 pm - 9:45 pm, Monday/Wednesday

Location: JSOM 2.714

Syllabus

Project.

Assignment.

Course Description

Machine learning is transforming the way mobile and embedded systems perceive and interact with the world. Empowered by rich data from sensors embedded in our phones, wearables, vehicles, and infrastructure, mobile computing is becoming increasingly intelligent, context-aware, and human-centric.

In this course, we explore how sensing technologies, machine learning techniques, and mobile systems jointly enable applications in wireless sensing, multimodal fusion, on-device learning, and adaptive edge intelligence. Topics include RF-based sensing (e.g., Wi-Fi, Bluetooth, GPS, satellite), acoustic and visual sensing, inertial and environmental sensing, signal tokenization and feature modeling, mobile system optimization, privacy-preserving learning, and the use of foundation models in mobile and sensing scenarios.

Students are expected to:

(i) read and present research papers from top-tier conferences (e.g., MobiCom, SenSys, UbiComp, NeurIPS),
(ii) participate actively in in-class discussions and invited talks from academia and industry, and
(iii) design, implement, and present a final project that explores new ideas in mobile sensing and machine learning.

Course Learning Objectives

By the end of this course, you will be able to

  1. Understand the core principles of applying machine learning techniques to mobile and embedded systems, including sensing modalities, signal processing, and on-device learning.
  2. Explain state-of-the-art research and system designs in mobile sensing, multimodal data fusion, edge intelligence, and federated learning.
  3. Evaluate the trade-offs and constraints in mobile and resource-constrained environments (e.g., latency, energy, privacy), and how they affect the deployment of machine learning models.
  4. Design and propose intelligent mobile sensing systems that integrate machine learning, signal modeling, and system-level optimization.
  5. Implement prototypes or simulations using real-world or simulated sensor data, employing tools such as Python, PyTorch/TensorFlow, and edge deployment toolkits.
  6. Communicate technical insights effectively through paper presentations, invited talk discussions, and final project demos.

Required Texts

No books are required. All the materials will be online.

Course Schedule (Tentative)

W1 Course Introduction & Motivation (08/24, 08/26, 08/31)
  • Lecture: Course Introduction
  • Lecture: Paper Reading and Presentation
  • Lecture: ML in Mobile Computing - Background
W2 Sensing Modalities I: GPS and Satellite (09/02, 09/09)
W3 Sensing Modalities II: Wi-Fi and Bluetooth (09/14, 09/16)
W5 Sensing Modalities III: IMU and Environmental Sensors (09/21, 09/23)
W4 Sensing Modalities IV: Acoustic and Visual (09/28, 09/30)
W6 Sensing Modalities V: UWB and mmWave (10/05, 10/07)
W7 Sensing Modalities VI: Multi-Modality (10/12, 10/14)
W8 Project Proposal Presentation (10/19, 10,21)
W9 Foundation Models for Sensing (10/26, 10/28)
W10 Efficient Mobile AI (11/02, 11/04)
W11 Privacy, Security & Trust in Mobile Sensing (11/09, 11/11)
W12 System-Level Co-Design & Optimization (11/16, 11/18)
W13 Mobile AI Applications & Real-World Deployment (11/23, 11/25)
W14 Fall Break (11/30, 12/2)
W15 Final Project Presentation (12/7, 12/9)


Invited Talks