@Gerafftes

Hi, long time no see.

Over the past few weeks, I have been developing two new approaches for presence detection. The main issue was that the system could not reliably distinguish between an empty room and a room with me standing inside :( .
To solve this, I first developed D5 and then D6. D5 is already available on GitHub. D6 is not available yet because it is still under development and has not been fully validated with real measurements and blind tests.
D5 Presence Detection:
D5 was designed to determine whether a room is empty or occupied. It compares the current CSI measurements with a previously recorded empty-room reference. However, D5 mainly evaluated changes in one direction. In practice, a person’s presence can cause CSI values to either increase or decrease, depending on the receiver and the propagation path. As a result, D5 behaved more like a motion detector and could miss a person who remained still. While it significantly improved presence detection, it was not yet robust enough for reliable real-world use.
D6 – Presence Detection and Position Classification:
D6 builds on D5 by evaluating deviations from the empty-room reference in both directions, making it much more effective at detecting people who remain stationary. Once a person has been detected, D6 attempts to classify their position. Instead of calculating arbitrary coordinates, it identifies one of nine predefined locations (P01–P09) that were previously trained using CSI recordings.
A position is only reported if:

• the hardware setup is valid and sealed,
• all receivers provide fresh and valid CSI data,
• the correct transmitter has been verified,
• a person has been detected,
• a valid position index is available, and the classification result is sufficiently confident.

If any of these conditions are not met, D6 deliberately reports no position instead of inventing one.
The software pipeline is largely complete, but the system still needs to be validated using a new sealed setup, fresh training recordings, and independent blind tests before D6 can be released on GitHub.

I also redesigned the UI from the standard RuView interface to a clean white Samaritan-inspired design, based on the AI system from the TV series Person of Interest.

I’ve completed the DigiKey tutorial and searched for the Receptacle USB-C Connector. I’ll use the DX07B024ZJ1C1088. Now, I’ll create the custom ESP32 board ;)

Started learning KiCad with DigiKey. The annoying part was Hackatime/WakaTime. The timer kept tracking the wrong project and KiCad was not sending progress correctly, even though it was listed as a monitored app. After about an hour of debugging, I found an old .wakatime-project file causing the wrong name and set up a manual KiCad heartbeat command for the correct StarDance project. Not much visible hardware progress today, but the tracking problem is finally understood and mostly fixed :))))