Tagged signal-processing
5 pieces
- · 7 min read
The Physical Ceiling: What No Model Can Recover From Your Sensor
Whatever your sensor and that first little circuit throw away is gone. You cannot get it back later with software. A photo that comes out blurry does not become sharp with editing, and the fancy tools that appear to sharpen it are inventing plausible detail rather than recovering real detail, which is exactly the distinction that matters when the output drives a decision about a person.
- · 8 min read
The Driven Reference Electrode: Your Front End's Hero and Its Hidden Risk
The third electrode is a feedback loop wrapped around a person. It senses the body's common mode and drives against it, which is what turns a hope about electrode symmetry into an actively regulated quantity and gives you rejection figures worth quoting. It is also a deliberately low-impedance connection between your circuit and the body, which makes it a stability problem, a safety-limited path, and the exact node any injected current will come home through.
- · 7 min read
Common Mode Rejection: How a Biosignal Front End Hears a Whisper at a Concert
When you measure off a body you are not measuring your signal. You are measuring your signal plus the person plus the room, all summed at the amplifier, and the thing you want is microvolts while the mains hum coupling into the person can be a thousand times larger. The entire job of the front end is pulling the small thing out from under the large thing, by throwing away everything that appears equally on both inputs.
- · 18 min read
Sensor Placement Is an Algorithm Decision
On a wearable device, where the sensor physically sits is not a comfort decision, it is the decision that determines whether you need an AI model at all, and whether you ship in 6 months or 18. It is usually made in month 2 by someone who does not work on signals, and by month 9 it has quietly become a year-long AI project nobody planned.
- · 9 min read
Cleaning Your Input Can Make Your AI Worse
A model does not read your input, it reads a compressed representation of it, keeping only the features it found useful and throwing the rest away. So cleaning up a messy input with a denoiser polishes exactly the information the model already discarded, and moves the features it actually reads in a direction you cannot see, which is why input quality can go up while accuracy goes down.