Team E7: The Wand Makers

Carnegie Mellon ECE Capstone, Spring 2025 — Sharon Lai, Olina Zhang, Nadia Palar

Tag: status report

Sharon’s Status Report for 3/29/2025
Posted by : hsuanjul Sharon's Status Reports

Accomplishments

  • Assisted Olina on CNN model: tested with various waving approaches of the gestures
  • Successfully flashed firmware to new PCB: resolved version conflicts and weird errors across different laptops.
  • Integrated new model: Confirmed that it is safe to reduce buffer size to 7K (7*1024), given that the model size was reduced by a noticeable amount
  • Adjusted the printed wand model: fixed the button problem of easily being jammed and false long press

Schedule Update

I remain on track. Will be able to showcase at least one type of IR transforming with the wand fully assembled during the interim design review.

Plans For Next Week

Perform minor updates to our design and focus on the interim review. Print new wand case for final review if needed. Update and place the receiver PCB if needed.

Team Status Report for 3/22/2025
Posted by : yunjiaz Team Status Reports

Risks and Contingency Plans
We completed fine-tuning the firmware this week and began integration testing. So far, the system appears to be functioning as expected. Firmware remains the most critical component, but with the recent fine-tuning, we are more confident in its stability.

Design Changes
There are no changes to the design at this stage.

Schedule
We remain on schedule.

Team Status Report for 3/15/2025
Posted by : hsuanjul Team Status Reports

Risks and Contingency Plans

Although there haven’t been a lot of major changes to the updated PCB, we might still encounter bugs when integrating it with the new PCB. At this point the most vulnerable part of the project is the firmware, and Nadia and Sharon are devoting most of the time to it. The old version of firmware is rather stable, so in the worst case where we are not able to completely debug the new firmware, we would make minor modifications on the old firmware.

Design Changes

No changes to our design at this point.

Schedule

We remain on schedule.

Sharon’s Status Report for 3/15/2025
Posted by : hsuanjul Sharon's Status Reports

Accomplishments

  • Received manufactured PCB: did basic power testings on the board to make sure there is no short circuit on the board and all pins are soldered on the correct pads. Pulled test points to high and verified basic function of the MCU.
  • Started testing the firmware: flashed the updated firmware to the board. Assisted Nadia with debugging the firmware.

Schedule Update

I will spend most of my time assisting Nadia with the firmware for the rest of the semester.

Plans for Next Week

Assist Nadia with firmware testing.

Olina’s Status Report for 3/15/2025
Posted by : yunjiaz Olina's Status Reports

This week, I spent time refining and testing the CNN model. I employed a series of Conv1D layers with LeakyReLU activations and a final Dense layer for classification. I spent time adjusting the hyperparameters and experimented with various learning rates for the Adam optimizer. Through experimentation, the optimal balance between convergence rate and stability was achieved with the learning rate of 0.001. Also, I experimented with different combinations of columns as input features and decide on a better choice for the combination.

There is a trade-off when we need to balance model complexity and overfitting. I found that larger batch sizes have better training stability, but they require more memory in order to cache intermediate results during training.

Next week, I will perform the final fine-tuning of our model.

Sharon’s Status Report for 3/8/2025
Posted by : hsuanjul Sharon's Status Reports

Accomplishments

  • Last week was midterm week and everyone on the team were extremely busy. Therefore, we decided to take a break from the project.

Schedule Update

PCB verification part is a bit off track since we are still waiting for it to be manufactured. I will work on verification as soon as the board arrives after spring break.

Plans for Next Week

Assist Nadia with firmware testing. PCB verificationb

Olina’s Status Report for 3/7/2025
Posted by : yunjiaz Olina's Status Reports

These 2 weeks, I compared the CNN, RNN, and LSFM models. While all three models performed well in training, CNN demonstrated the best generalization with minimal overfitting, the fastest training time, and high robustness to noise. In addition to the comparison, I worked on fine-tuning the models to improve their performance and reduce overfitting, focusing on optimizing hyperparameters and refining preprocessing techniques.

During fine-tuning, I encountered difficulties in balancing model performance and overfitting. Additionally, optimizing computational efficiency while maintaining accuracy was challenging.

Next week, I will complete the fine-tuning process and finalize model evaluations. Additionally, I will analyze the impact of fine-tuning adjustments and document findings to guide further improvements.

Sharon’s Status Report for 2/22/2025
Posted by : hsuanjul Sharon's Status Reports

Accomplishments

  • Wrapped up my part for a firmware update and handed it over to Nadia.
  • Made final adjustments on BOM and layout for PCB, and ordered through JLC. It is expected to ship next week. We are looking to receive it by the end of next week or at the start of the week after next.
  • Made adjustments on 3D-Model: put an additional hole for an LED signal on the wand body to align with the updated PCB for better usability.

Please check the project GitHub for updated details.

Schedule Update

PCB verification part is a bit off track since we are still waiting for it to be manufactured. As we wait for the PCB, we will focus more on the firmware side so that we will be able to have a working firmware once we get the customized PCB.

Plans for Next Week

Assist Nadia with firmware testing.