Hien Vu

We present MmCows, a multimodal dataset for dairy cattle monitoring. This dataset comprises a large amount of synchronized data on behavioral, physiological, and environmental factors. It includes two weeks of data collected using wearable and implantable sensors deployed on ten milking Holstein cows, such as ultra-wideband (UWB) sensors, inertial sensors, and body temperature sensors. Additionally, it features 4.8M frames of high-resolution image sequences from four isometric view cameras, as well as temperature and humidity data from environmental sensors. One full day’s worth of image data is annotated as ground truth, totaling 20,000 frames with 213,000 bounding boxes of 16 cows, along with their 3D locations and behavior labels.

We presents a smart ear tag, named eTag, and an associated system that can read a passive microchip temperature sensor subcutaneously injected into the animal with minimal discomfort. It features a lightweight design using a single coil shared for microchip scanning and wireless charging. eTag is autonomously recharged by a wireless charger over the head during daily milking sessions, enabling perpetual operation without battery replacement after deployment. Our real-world deployment demonstrated that eTag can reliably collect accurate body temperature in real time while maintaining a positive energy flow. eTag is designed to enable the timely detection of heat stress and facilitate precision control of barn cooling systems.

This project addresses the challenges of pre-heating for Li-ion batteries in sub-zero conditions. We divided the cells into different groups and strategically transferred electrical energy between these groups. As the cells heat up during this transfer process, their SOC levels are balanced by effectively controlling the electrical current direction using our proposed four-state control policy. This technique achieved both temperature and SOC uniformity throughout the process and even for an extended duration after preheating, while does not requiring precise characterization of the thermal-electrochemical properties of the cells.

We implemented Extended Kalman Filter on a RISC-V MCU that processes data from a 9-DOF Inertial Measurement Unit (IMU), which is combined with Parallel Tracking and Mapping (PTAM) for pose tracking in AR applications.

We developed a high-energy supercapacitor-based power device for military soldiers that has a flexible and portable form factor while being able to sustain 840 W of output power in multiple 5-s discharge sessions. An advanced control algorithm was also developed that allows the main buck converter to work as a bi-directional buck-boost converter, keeping the system running continuously without interruption during the operation.

We implemented a high-speed design for a customized storage device that consists of an FPGA as a controller and 512GB of 16 SLC-NAND flash ICs while ensuring signal integrity and propagation delay. We also developed a dynamic voltage-scaling power backup system to extend the lifespan of capacitors in SSDs.