Project

# Title Team Members TA Documents Sponsor
7 Adaptive Light-Filtering Glasses
Jahnavi Thejo Prakash
Kewal Ghosalkar
Lukas Dumasius design_document1.pdf
proposal1.pdf
# Team Members:
- Kewal Ghosalkar (kewalkg2)
- Jahnavi Thejo Prakash (jahnavi7)

# Problem

People around the world struggle with photosensitive epilepsy, migraines, TBI, and other such photosensitive medical conditions that increase sensitivity to light. Intense flickering lights can worsen sensitivity and in some cases also lead to convulsions and seizures. Current solutions include remedies like avoiding triggers, or using tinted glasses. In unfamiliar situations, these passive solutions can prove to be unreliable since they cannot update dynamically.

# Solution

We propose adaptive smart glasses that can detect lighting conditions that may trigger such photosensitive conditions and adapt the tint on the lenses accordingly. The glasses can also provide warnings and possibly contain a system to detect seizures.

# Solution Components
## Optical Attenuation Subsystem
- LCD light valve attached to the lenses of the glasses. These can darken proportionally to the perceived level of risk.

## Sensor Subsystem
- Set of 3 photodiodes for detecting the intensity of incoming light.
- Wide FOV photodiode placed in the front for measuring ambient light brightness
- Narrow FOV photodiode placed in front to measure light incident on the users eyes
- Feedback photodiode placed behind the lenses to measure the actual light exposure on the user's eye. This provides feedback for a closed feedback loop to make adjustments based on the attenuation of the LCD light valve on the lenses.
- Transimpedance amplifiers for each of the 3 photodiodes in the sensor subsystem to utilize the full range of the ADC

## Processing Subsystem
- STM32L series microcontroller, with an internal ADC sampling rate of 1000 Hz, which is large enough to avoid aliasing within the Epilepsy ranges of 3-60Hz
- Signal processing will first estimate and remove average brightness or DC component from each signal in the amplifier results. A band-pass filter will remove slower flicker changes caused by movements and noise. An FFT & modulation depth measurements will determine the frequency and strength of the dominating flicker.
- Similarity flicker frequency checks will run for the two forward facing photodiodes over several sampling windows. If risk is detected, the lens will become more attenuated and adjustments will be made based off of the flicker magnitude on the behind-lens sensor with a close loop feedback system.

## Power Subsystem
- Single LiPo to power the entire system.
- Boost converter to step up 3.7V of the LiPo to 5V for the Light valve.
- 3.3V LDO for the STM32, photodiodes and amplifiers.
- USB C charging.
- The Power subsystem will live on a separate hip mounted pack out of concerns for weight, space and safety.

# Criterion For Success
- Our solution can be considered successful if the glasses can:
- Accurately detect epilepsy triggering frequencies around 3 to 60Hz with an accuracy of at least 80%
- Accurately reject non-hazardous changes in light caused my sudden movements or environment changes with a false positive rate of less than 10%
- Assign a replicable risk score to each situation and activate the optical attenuation system within 0.5s of hazardous inputs
- Have a reasonable battery life for daily use of around >8 hours on a single charge.

# Alternatives
A paper titled “EpilepSee” from 2024 attempts to build a device very similar to ours, however there are a few improvements we are trying to make:
- The sampling frequency in the paper was limited to 40Hz which can lead to aliasing at flicker frequencies above 20Hz leading to faults in signal processing. We plan on using a much higher sampling frequency at around 1 kHz to avoid aliasing.
- The paper is measuring light inputs using a single sensor, we want to use multiple sensors to provide more data for signal processing.
- The device in the paper is a prototype and is not very portable. We are attempting to make our design more portable, hence more comfortable for use.
- The paper uses an open loop design. We are going to use a closed loop design which should allow for more precise attenuation
The response time for the device in the paper is 1-1.5s, we plan on having a much faster response time of <0.5s
# Extensions
- The ability for the users to input the exact frequencies they are susceptible to. This can be done through Bluetooth or with an extra serial debugger module to input this data.
- An IMU can monitor for seizure-like body movements and trigger a safety response, alerting the user’s emergency contact.
- A display that provides a warning before any optical attenuation takes place and allows users the option for manual overriding.

# Links

- [EpilepSee Paper](https://ora.ox.ac.uk/objects/uuid%3Aabb3258d-264e-42e0-8967-40408397f96f/files/scj82k980j)
- [Small Liquid Crystal Light Valve – The Pi Hut](https://thepihut.com/products/small-liquid-crystal-light-valve-controllable-shutter-glass)

RFID Automatic Self Checkout Basket

Jada-Marie Griggs, Oscar Kaplon, Jacob Slabosz

Featured Project

Team Members:

- Jacob Slabosz (slabosz2)

- Oscar Kaplon (okaplon2)

- Jada-Marie Griggs (jgrig7)

# Problem

Checking out at a store can be a point of frustration for many shoppers. With long lines, clients may wait for long lengths of time until it is their turn at the register, where they then still have to scan each item one by one, either on their own at a self checkout or with a cashier. Checkouts can also be troublesome for business owners, as they have to pay multiple employees to man the registers. Existing mobile self checkout options aim to fix this, though they still rely on customers being truthful and scanning all of their items.

# Solution

We propose a smart shopping basket equipped with UHF RFID that automatically detects and tracks items placed inside without immediately charging the customer. As items are added or removed, the system updates a live item list and running total that the shopper can view through a connected web application. When finished shopping, the user explicitly chooses how to complete checkout — either by paying digitally online (e.g., Apple Pay) or by proceeding to a traditional register for cash payment — ensuring transparency and user control. An integrated load cell cross-verifies item additions by detecting weight changes, allowing the system to flag errors when an item is placed in the basket but no RFID tag is detected. By shifting item identification earlier in the shopping process while preserving flexible payment options, the system reduces checkout congestion and operational overhead.

# Solution Components

## Subsystem 1: NFC/RFid Sensing System

We will make use of UHF (Ultra High Frequency) RFID due to the fact that it is able to detect multiple tags “piled” on top of one another and has an increased range over standard RFID. Using a M5Stack UHF RFID Unit (JRD-4035) as the reader module, we will access the data via the UART connection. Each individual item will have a unique RFID tag (1568-27180-ND or similar part number). We will also tune the power (attenuation) of the RFID reader such that it only detects items inside of the basket.

## Subsystem 2: Status Indicator (LED)

The basket will be equipped with RGB LED lights (WS2812B) that can be set to multiple colors. This will be able to display different colors in different patterns (strobing, pulsing, etc.) based on different statuses of the basket: solid white to indicate the basket is ready, pulsing red to indicate there was an error with the item, or a green pulse to indicate a successful reading of an item. The LED will be controlled by the microcontroller.

## Subsystem 3: Brain

The microcontroller (ESP32-C3-DEVKITM-1-N4X) will use input from the RFID subsystem to keep track of every items’ unique tag and determine which are in the basket. With WiFi and bluetooth connectivity, it will communicate with the store’s infrastructure (or in our case an emulation on a laptop computer).

## Subsystem 4: Load Cell

A load cell (1528-4543-ND) which supports 20kg and an amplifier (1568-13879-ND) will be used to ensure the signals can be picked up by the microcontroller. The load cell will be placed at the bottom of the basket underneath a plate so that all the weight of all items will be registered.

## Subsystem 5: Power Regulator

Given that the RFID module requires a stable 5V supply and draws a significant inrush current during startup while the microcontroller and LEDs operate at 3.3V, we propose the system to be powered via a USB-C input using a breakout board with proper CC termination (Adafruit USB-C Breakout or something similar). This board exposes the 5 V and GND pins for the circuit while automatically handling the USB-C configuration pins, ensuring that the source delivers a stable 5 V at sufficient current. The 5V bus directly powers the RFID module and LEDs, with a 470 µF bulk capacitor and 0.1 µF decoupling capacitors placed nearby to absorb startup current spikes and prevent voltage dips. A buck converter (MP1584EN module or something similar) steps down 5V to 3.3V to supply the microcontroller, sensors, and LEDs reliably. This arrangement ensures stable operation during RFID power-up events, isolates the microcontroller from voltage fluctuations caused by high-current devices, and provides a simple USB-powered system suitable for our project’s purposes.

Additionally, we will include a PTC (MF-MSMF050-2-ND) to prevent large amounts of current to go through the 5V bus via temperature detection

USB breakout board 1568-23055-ND. (Digikey)

Or cheaper option - Adafruit USB Type C Breakout Board - Downstream Connection Product ID: 4090

## Subsystem 6: Web Application

A web application (running via smartphone emulator on a laptop) will connect to the device via the “store’s” infrastructure (WiFi), allowing a shopper to see a live list of the items in their basket and a running total. The web application will connect to a centralized server (emulated on a computer) and access the information via API, meaning that shoppers do not need to use a bluetooth connection which poses security risks.

# Criterion For Success

- Shall successfully identify the unique ID of an item placed in the basket within 5 seconds with 95% accuracy

- Shall successfully identify the unique IDs of 10 different items placed in the basket at the same time within 10 seconds with 95% accuracy

- Shall not detect items placed further than 12 inches from the bowl with 95% accuracy.

- LED ring shall change color within 5 seconds of an item being placed in the basket and successfully detected.

- LED ring shall change color within 5 seconds of an item with no tag being placed in the basket.

- The web application shall display all items in the basket with 100% accuracy within 10 seconds of an item being added.

Project Videos