Fall’25: CS 6301 Special Topics in CS: Machine Learning in Mobile Computing

Course Info

Instructor: Yi Ding

Office: ECSS 4.703

Office hours: by appointment

Email: yi.ding@utdallas.edu

Lecture: 4:00 pm - 5:15 pm, Monday/Wednesday

Location: CR 1.202

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 & Guidance on Paper Reading and Presentation (08/25, 08/27)

• Lecture: Course Introduction & Logistics

Topic 1: Sensing: Wi-Fi & Bluetooth (9/22)

• Topic1-Paper1 Ding, Jian, et al. “Cost-effective soil carbon sensing with wi-fi and optical signals.” Proceedings of the 30th Annual International Conference on Mobile Computing and Networking. 2024.
• Topic1-Paper2 Li, Chenning, et al. “Wi-fi see it all: generative adversarial network-augmented versatile wi-fi imaging.” Proceedings of the 18th Conference on Embedded Networked Sensor Systems. 2020.
• Topic1-Paper3 Ni, Jiazhi, et al. “Experience: Pushing indoor localization from laboratory to the wild.” Proceedings of the 28th Annual International Conference on Mobile Computing And Networking. 2022.
• Topic1-Paper4 Li, Xin, et al. “Uwb-fi: Pushing wi-fi towards ultra-wideband for fine-granularity sensing.” Proceedings of the 22nd Annual International Conference on Mobile Systems, Applications and Services. 2024.
• Topic1-Paper5 Adib, Fadel, and Dina Katabi. “See through walls with WiFi!.” Proceedings of the ACM SIGCOMM 2013 conference on SIGCOMM. 2013.
• Topic1-Paper6 Wang, Yuxi, Kaishun Wu, and Lionel M. Ni. “Wifall: Device-free fall detection by wireless networks.” IEEE Transactions on Mobile Computing 16.2 (2016): 581-594.

Topic 2: Sensing: Motion & Environmental Sensors (IMU, Biochemical, etc.) (9/3, 9/10)

• Topic2-Paper1 Xu, Huatao, et al. “Practically adopting human activity recognition.” Proceedings of the 29th Annual International Conference on Mobile Computing and Networking. 2023.
• Topic2-Paper2 Brooks, Jas, and Pedro Lopes. “Smell & paste: Low-fidelity prototyping for olfactory experiences.” Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems. 2023.
• Topic2-Paper3 Yin, Xiangyu, et al. “PTEase: objective airway examination for pulmonary telemedicine using commodity smartphones.” Proceedings of the 21st Annual International Conference on Mobile Systems, Applications and Services. 2023.
• Topic2-Paper4 Zhou, Pengfei, et al. “Iodetector: A generic service for indoor outdoor detection.” Proceedings of the 10th acm conference on embedded network sensor systems. 2012.
• Topic2-Paper5 Xie, Zhiqing, et al. “TransFloor: Transparent floor localization for crowdsourcing instant delivery.” Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 6.4 (2023): 1-30.

Topic 3: Sensing: Acoustic & Vision (9/24, 10/1)

• Topic3-Paper1 Liang, Xiaoxuan, et al. “Sondar: Size and shape measurements using acoustic imaging.” Proceedings of the Twenty-fifth International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing. 2024.
• Topic3-Paper2 Cao, Shirui, et al. “Powerphone: Unleashing the acoustic sensing capability of smartphones.” Proceedings of the 29th Annual International Conference on Mobile Computing and Networking. 2023.
• Topic3-Paper3 Zhang, Yongzhao, et al. “Acoustic sensing and communication using metasurface.” 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI 23). 2023.
• Topic3-Paper4 Zhang, Yanbo, et al. “Face recognition in harsh conditions: An acoustic based approach.” Proceedings of the 22nd annual international conference on mobile systems, applications and services. 2024.
• Topic3-Paper5 Liu, Xuanyu, et al. “AcousAF: Acoustic Sensing-Based Atrial Fibrillation Detection System for Mobile Phones.” Companion of the 2024 on ACM International Joint Conference on Pervasive and Ubiquitous Computing. 2024.
• Topic3-Paper6 Li, Ke, et al. “Gazetrak: Exploring acoustic-based eye tracking on a glass frame.” Proceedings of the 30th Annual International Conference on Mobile Computing and Networking. 2024.

Topic 4: Sensing: GPS & Satellite (10/6, 10/8, 10/13)

• Topic4-Paper1 Rathi, Raghav, and Zhenghao Zhang. “StarAngle: User Orientation Sensing with Beacon Phase Measurements of Multiple Starlink Satellites.” Proceedings of the 22nd ACM Conference on Embedded Networked Sensor Systems. 2024.
• Topic4-Paper2 Wang, Yunfan, et al. “Global localization of energy-constrained miniature rf emitters using low earth orbit satellites.” Proceedings of the 21st ACM Conference on Embedded Networked Sensor Systems. 2023.
• Topic4-Paper3 Ecola, Geneva, et al. “SARLink: Satellite Backscatter Connectivity using Synthetic Aperture Radar.” Proceedings of the 23rd ACM Conference on Embedded Networked Sensor Systems. 2025.
• Topic4-Paper4 Li, Ruinan, et al. “Plug-and-play indoor GPS positioning system with the assistance of optically transparent metasurfaces.” Proceedings of the 30th Annual International Conference on Mobile Computing and Networking. 2024.
• Topic4-Paper5 Dong, Huixin, et al. “Gpsmirror: Expanding accurate gps positioning to shadowed and indoor regions with backscatter.” Proceedings of the 29th Annual International Conference on Mobile Computing and Networking. 2023.
• Topic4-Paper6 Hong, Zhiqing, et al. “Smallmap: Low-cost community road map sensing with uncertain delivery behavior.” Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 8.2 (2024): 1-26.

Topic 5: Sensing: Multi-Modality (10/15, 10/27)

• Topic5-Paper1 Liu, Yang, et al. “SPATIUM: A Context-Aware Machine Learning Framework for Immersive Spatiotemporal Health Understanding.” Proceedings of the 23rd Annual International Conference on Mobile Systems, Applications and Services. 2025.
• Topic5-Paper2 Dai, Shenghong, et al. “Babel: A scalable pre-trained model for multi-modal sensing via expandable modality alignment.” Proceedings of the 23rd ACM Conference on Embedded Networked Sensor Systems. 2025.
• Topic5-Paper3 Liu, Kaiwei, et al. “TaskSense: A Translation-like Approach for Tasking Heterogeneous Sensor Systems with LLMs.” Proceedings of the 23rd ACM Conference on Embedded Networked Sensor Systems. 2025.
• Topic-Paper4 Post, Kevin, et al. “Contextllm: Meaningful context reasoning from multi-sensor and multi-device data using llms.” Proceedings of the 26th International Workshop on Mobile Computing Systems and Applications. 2025.
• Topic-Paper5 Liu, Yimeng, et al. “Hydra: Accurate multi-modal leaf wetness sensing with mm-wave and camera fusion.” Proceedings of the 30th Annual International Conference on Mobile Computing and Networking. 2024.
• Topic-Paper6 Ouyang, Xiaomin, et al. “ADMarker: A Multi-Modal Federated Learning System for Monitoring Digital Biomarkers of Alzheimer’s Disease.” Proceedings of the 30th Annual International Conference on Mobile Computing and Networking. 2024.

Topic 6: Learning: Mobile AI Efficiency (10/29, 11/5)

• Topic6-Paper1 Team, Gemma, et al. “Gemma 2: Improving open language models at a practical size.” arXiv preprint arXiv:2408.00118 (2024).
• Topic6-Paper2 Gu, Yuxian, et al. “MiniLLM: Knowledge Distillation of Large Language Models.” ICLR. 2024.
• Topic6-Paper3 Lin, Ji, et al. “AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration.” MLSys. 2024.
• Topic6-Paper4 Arora, Daman, and Andrea Zanette. “Training language models to reason efficiently.” arXiv preprint arXiv:2502.04463 (2025).
• Topic6-Paper5 Rastikerdar, Mohammad Mehdi, et al. “Cactus: Dynamically switchable context-aware micro-classifiers for efficient iot inference.” Proceedings of the 22nd Annual International Conference on Mobile Systems, Applications and Services. 2024.
• Topic6-Paper6 Hojjat, Ali, et al. “Limitnet: Progressive, content-aware image offloading for extremely weak devices & networks.” Proceedings of the 22nd Annual International Conference on Mobile Systems, Applications and Services. 2024.
• Topic6-Paper7 Frantar, Elias, et al. “Gptq: Accurate post-training quantization for generative pre-trained transformers.” arXiv preprint arXiv:2210.17323 (2022).

Topic 7: Learning: On-Device Learning & Model Compression (11/10, 11/12)

• Topic7-Paper1 Jabbour, Jason, et al. “Don’t Run with Scissors: Pruning Breaks VLA Models but They Can Be Recovered.” arXiv preprint arXiv:2510.08464 (2025).
• Topic7-Paper2 Chen, Junyu, et al. “Deep compression autoencoder for efficient high-resolution diffusion models.” arXiv preprint arXiv:2410.10733 (2024).
• Topic7-Paper3 Wang, Lehao, et al. “AdaEvo: Edge-assisted continuous and timely DNN model evolution for mobile devices.” IEEE Transactions on Mobile Computing (2023).
• Topic7-Paper4 Famá, Fernanda, et al. “Contrastive Self-Supervised Learning at the Edge: An Energy Perspective.” arXiv preprint arXiv:2510.08374 (2025).
• Topic7-Paper5 Liu, Renyuan, et al. “DAF: An Efficient End-to-End Dynamic Activation Framework for on-Device DNN Training.” Proceedings of the 23rd Annual International Conference on Mobile Systems, Applications and Services. 2025.
• Topic7-Paper6 Misra, Ashitabh, Nurani Saoda, and Tarek Abdelzaher. “Latency-constrained input-aware quantization of time series inference workflows at the edge.” IEEE INFOCOM 2025-IEEE Conference on Computer Communications. IEEE, 2025.

Topic 8: Learning: Federated Learning & Mobile Systems (11/12, 11/17)

• Topic8-Paper1 Chen, Rui, et al. “EEFL: High-speed wireless communications inspired energy efficient federated learning over mobile devices.” Proceedings of the 21st Annual International Conference on Mobile Systems, Applications and Services. 2023.
• Topic8-Paper2 Ouyang, Xiaomin, et al. “Harmony: Heterogeneous multi-modal federated learning through disentangled model training.” Proceedings of the 21st Annual International Conference on Mobile Systems, Applications and Services. 2023.
• Topic8-Paper3 Tabatabaie, Mahan, and Suining He. “Naturalistic e-scooter maneuver recognition with federated contrastive rider interaction learning.” Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 6.4 (2023): 1-27.
• Topic8-Paper4 TBistritz, Ilai, Ariana Mann, and Nicholas Bambos. “Distributed distillation for on-device learning.” Advances in Neural Information Processing Systems 33 (2020): 22593-22604.
• Topic8-Paper5 Shin, Jaemin, et al. “Fedbalancer: Data and pace control for efficient federated learning on heterogeneous clients.” Proceedings of the 20th Annual International Conference on Mobile Systems, Applications and Services. 2022.
• Topic8-Paper6 Lin, Shouxu, et al. “FLAMMABLE: A Multi-Model Federated Learning Framework with Multi-Model Engagement and Adaptive Batch Sizes.” arXiv preprint arXiv:2510.10380(2025).
• Topic8-Paper7 Zhang, Yuwei, Tong Xia, and Cecilia Mascolo. “FedEE: Uncertainty-Aware Personalized Federated Learning for Realistic Healthcare Applications.” (2024).

Topic 9: Learning: Foundation Models for Sensing & Mobile AI (11/17, 11/19)

• Topic9-Paper1 Xu, Huatao, et al. “Penetrative ai: Making llms comprehend the physical world.” Proceedings of the 25th International Workshop on Mobile Computing Systems and Applications. 2024.
• Topic9-Paper2 Imran, Sheikh Asif, et al. “Llasa: Large multimodal agent for human activity analysis through wearable sensors.” arXiv preprint arXiv:2406.14498 3.4 (2024).
• Topic9-Paper3 Narayanswamy, Girish, et al. “Scaling wearable foundation models.” arXiv preprint arXiv:2410.13638 (2024).
• Topic9-Paper4 Quan, Pengrui, et al. “Sensorbench: Benchmarking llms in coding-based sensor processing.” Proceedings of the 26th International Workshop on Mobile Computing Systems and Applications. 2025.
• Topic9-Paper5 Dong, Qifei, Xiangliang Chen, and Mahadev Satyanarayanan. “Creating edge ai from cloud-based llms.” Proceedings of the 25th International Workshop on Mobile Computing Systems and Applications. 2024.
• Topic9-Paper6 Lloyd, Catherine, et al. “Stress-GPT: Stress detection with an EEG-based foundation model.” Proceedings of the 30th Annual International Conference on Mobile Computing and Networking. 2024.
• Topic9-Paper7 Yang, Bufang, et al. “Edgefm: Leveraging foundation model for open-set learning on the edge.” Proceedings of the 21st ACM Conference on Embedded Networked Sensor Systems. 2023
• Topic9-Paper8 Sayyid-Ali, Abdur-rahman Ibrahim, et al. “CheckMate: LLM-Powered Approximate Intermittent Computing.” Proceedings of the 23rd ACM Conference on Embedded Networked Sensor Systems. 2025.

Topic 10: Mobile AI Applications (11/19, 12/1)

• Topic10-Paper1 Yuan, Jinliang, et al. “Mobile foundation model as firmware.” Proceedings of the 30th Annual International Conference on Mobile Computing and Networking. 2024.
• Topic10-Paper2 Wen, Hao, et al. “Autodroid: Llm-powered task automation in android.” Proceedings of the 30th Annual International Conference on Mobile Computing and Networking. 2024.
• Topic10-Paper3 Chen, Kaixin, et al. “Lit: Fine-grained toothbrushing monitoring with commercial led toothbrush.” Proceedings of the 29th annual international conference on mobile computing and networking. 2023.
• Topic10-Paper4 Jiao, Wenli, et al. “Bioscatter: Low-power sweat sensing with backscatter.” Proceedings of the 21st Annual International Conference on Mobile Systems, Applications and Services. 2023.
• Topic10-Paper5 Zhang, Xi, et al. “mmfer: Millimetre-wave radar based facial expression recognition for multimedia iot applications.” Proceedings of the 29th annual international conference on mobile computing and networking. 2023.
• Topic10-Paper6 Wang, Zheng, et al. “HearFire: Indoor fire detection via inaudible acoustic sensing.” Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies 6.4 (2023): 1-25.
• Topic10-Paper7 Cai, Chao, et al. “AcuTe: Acoustic thermometer empowered by a single smartphone.” Proceedings of the 18th conference on embedded networked sensor systems. 2020.
• Topic10-Paper8 Sun, Zehua, et al. “Rf-egg: An rf solution for fine-grained multi-target and multi-task egg incubation sensing.” Proceedings of the 30th Annual International Conference on Mobile Computing and Networking. 2024.

Invited Talks

• Sep. 8, 2025, Zhiqing Hong (Rutgers, UB Berkeley): Understanding Human Behavior with IMU Sensing & Wearable AI

• Sep. 29, 2025, Anlan Yu (Peking University): FineSat: Enhancing GNSS Signals for High-precision Sensing

• Oct. 15, 2025, Jing Yang (KTH): Literature Survey of Mobile AI Efficiency

• Nov. 10, 2025, Tong Liu (Central South Univeristy): Advancing FL in Mobile Computing - From Foundations to Our Recent Work