Short-Range Sensing and Applications Using Communication Signals
Project Description
Short-range wireless communication systems—such as Wi-Fi, Bluetooth, and related technologies—offer more than just data transmission capabilities. By leveraging the physical-layer characteristics of these signals, it is possible to extract information about the surrounding environment and the activities of people within it. Such capabilities open the door to a wide range of sensing applications, including indoor positioning, human activity recognition, and physiological signal monitoring (e.g., respiration rate).
In this project, we will explore the use of short-range wireless communication signals for sensing purposes. Students will design and implement systems that utilize a network of heterogeneous short-range devices—such as Wi-Fi access points, Raspberry Pi boards, Arduino microcontrollers, Bluetooth gateways, Bluetooth beacons, and Android smartphones—configured in mesh or cooperative topologies to collect and process communication signal data.
By applying signal processing and machine learning (including neural networks) techniques to these signals, the project aims to build prototypes that demonstrate robust sensing capabilities under realistic conditions. Potential application scenarios include smart home systems, indoor navigation aids, elderly care monitoring, and activity-based human–machine interaction.
This UROP project will provide practical experience in hardware configuration, wireless networking, data capture, signal analysis, and prototype system development, bridging theory with hands-on skills.
In this project, we will explore the use of short-range wireless communication signals for sensing purposes. Students will design and implement systems that utilize a network of heterogeneous short-range devices—such as Wi-Fi access points, Raspberry Pi boards, Arduino microcontrollers, Bluetooth gateways, Bluetooth beacons, and Android smartphones—configured in mesh or cooperative topologies to collect and process communication signal data.
By applying signal processing and machine learning (including neural networks) techniques to these signals, the project aims to build prototypes that demonstrate robust sensing capabilities under realistic conditions. Potential application scenarios include smart home systems, indoor navigation aids, elderly care monitoring, and activity-based human–machine interaction.
This UROP project will provide practical experience in hardware configuration, wireless networking, data capture, signal analysis, and prototype system development, bridging theory with hands-on skills.
Supervisor
LI, Mo
Quota
2
Course type
UROP1100
Applicant's Roles
• Prior exposure to wireless communication/networking is preferred (e.g., having taken courses in networking or wireless systems).
• Practical experience with embedded systems and device programming (e.g., Raspberry Pi, Arduino) is strongly preferred.
• Familiarity with signal processing concepts and tools (e.g., MATLAB, Python libraries such as NumPy/SciPy).
• Basic skills in machine learning and neural networks (e.g., PyTorch, TensorFlow) for data modeling and classification tasks.
• Interest in interdisciplinary projects involving both hardware and software.
• Practical experience with embedded systems and device programming (e.g., Raspberry Pi, Arduino) is strongly preferred.
• Familiarity with signal processing concepts and tools (e.g., MATLAB, Python libraries such as NumPy/SciPy).
• Basic skills in machine learning and neural networks (e.g., PyTorch, TensorFlow) for data modeling and classification tasks.
• Interest in interdisciplinary projects involving both hardware and software.
Applicant's Learning Objectives
• Develop an understanding of short-range wireless communication technologies (e.g., Wi-Fi, Bluetooth) and their physical-layer characteristics.
• Gain practical skills in configuring and programming multiple device types for cooperative or mesh networking.
• Learn how to preprocess and analyze wireless signal data for sensing purposes.
• Acquire experience in implementing machine learning/data-driven approaches to build sensing applications (including neural network design, training, and evaluation).
• Apply engineering knowledge to develop complete sensing prototypes from hardware setup to software deployment.
• Gain practical skills in configuring and programming multiple device types for cooperative or mesh networking.
• Learn how to preprocess and analyze wireless signal data for sensing purposes.
• Acquire experience in implementing machine learning/data-driven approaches to build sensing applications (including neural network design, training, and evaluation).
• Apply engineering knowledge to develop complete sensing prototypes from hardware setup to software deployment.
Complexity of the project
Moderate