Hybrid PCA-Based and Machine Learning Approaches for Signal-Based Interference Detection and Anomaly Classification Under Synthetic Data Conditions
Sebastián Čikovský, Patrik Šváb, Peter Hanák · 2025
Read Hybrid PCA-Based and Machine Learning Approaches for Signal-Based Interference Detection and Anomaly Classification Under Synthetic Data Conditions by Sebastián Čikovský, Patrik Šváb, Peter Hanák (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12736517.txt.
Description
Sebastián Čikovský, Patrik Šváb, and Peter Hanák present a 2025 paper on spotting interference in sensor signals while keeping false alarms near one percent. Safety systems cannot cry wolf, yet they run on multichannel data that shift over time and place. The authors built a light pipeline with no deep learning, using only standard Python libraries.
Three signals are fused: how badly a principal component model rebuilds the data, how locally odd the leftovers look, and how unsure a Monte Carlo check is. A learned combiner, tuned under a strict false-alarm rule, merges them. On synthetic tests with heavy noise shifts, fusion lifted detection from about 0.60 to 0.74 at the one percent alarm rate, and held up far better as signals degraded.
Catalog record
| CREATOR | Sebastián Čikovský, Patrik Šváb, Peter Hanák |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 66 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |